diff --git a/backend/rag/dspy_heritage_rag.py b/backend/rag/dspy_heritage_rag.py index 3f4fa193a2..bf8b983d92 100644 --- a/backend/rag/dspy_heritage_rag.py +++ b/backend/rag/dspy_heritage_rag.py @@ -50,13 +50,14 @@ def is_rate_limit_error(error: Exception) -> bool: return True # Check nested exceptions in ExceptionGroup (from asyncio.TaskGroup) - if hasattr(error, 'exceptions'): + if isinstance(error, BaseExceptionGroup): for sub_exc in error.exceptions: - if is_rate_limit_error(sub_exc): + if isinstance(sub_exc, Exception) and is_rate_limit_error(sub_exc): return True # Check __cause__ chain - if error.__cause__ and is_rate_limit_error(error.__cause__): + cause = error.__cause__ + if cause is not None and isinstance(cause, Exception) and is_rate_limit_error(cause): return True return False @@ -64,8 +65,10 @@ def is_rate_limit_error(error: Exception) -> bool: def extract_actual_error(error: Exception) -> Exception: """Extract the actual error from an ExceptionGroup if present.""" - if hasattr(error, 'exceptions'): + if isinstance(error, BaseExceptionGroup): for sub_exc in error.exceptions: + if not isinstance(sub_exc, Exception): + continue # Return rate limit error if found if is_rate_limit_error(sub_exc): return sub_exc @@ -206,11 +209,20 @@ COST_TRACKER_AVAILABLE = False get_tracker: Optional[Callable[[], Any]] = None try: - from .cost_tracker import get_tracker as _get_tracker, CostTracker + # Try absolute import first (when run directly by uvicorn) + from cost_tracker import get_tracker as _get_tracker, CostTracker get_tracker = _get_tracker COST_TRACKER_AVAILABLE = True + logger.info("Cost tracker loaded via absolute import") except ImportError: - logger.info("Cost tracker not available - timing/cost tracking disabled") + try: + # Try relative import (when imported as package) + from .cost_tracker import get_tracker as _get_tracker, CostTracker + get_tracker = _get_tracker + COST_TRACKER_AVAILABLE = True + logger.info("Cost tracker loaded via relative import") + except ImportError: + logger.info("Cost tracker not available - timing/cost tracking disabled") # Ontology mapper imports (graceful degradation if not available) # Provides multilingual matching and heritage code lookups from LinkML schema @@ -1192,7 +1204,7 @@ class HeritageQueryRouter(dspy.Module): "exploration": ["qdrant", "sparql"], } - def forward(self, question: str, language: str = "nl", history: History = None) -> Prediction: + def forward(self, question: str, language: str = "nl", history: History | None = None) -> Prediction: """Classify query and determine routing. Args: @@ -2953,7 +2965,7 @@ class HeritageRAGPipeline(dspy.Module): self, question: str, language: str = "nl", - history: History = None, + history: History | None = None, include_viz: bool = True, use_agent: bool = False, skip_cache: bool = False, @@ -3044,6 +3056,19 @@ class HeritageRAGPipeline(dspy.Module): # Use resolved question for subsequent steps if available resolved_question = getattr(routing, 'resolved_question', question) + # DEFENSIVE FIX: Validate resolved_question is not a DSPy placeholder + # The optimized model demos may not include resolved_question, causing DSPy + # to use placeholder text like "Not supplied for this particular example..." + if (not resolved_question or + "not supplied" in resolved_question.lower() or + "this particular example" in resolved_question.lower() or + len(resolved_question.strip()) < 5): + logger.warning( + f"Invalid resolved_question detected: '{resolved_question[:80] if resolved_question else 'None'}...', " + f"falling back to original question: '{question[:80]}'" + ) + resolved_question = question + # Step 2: Extract entities (use resolved question for better extraction) # Use fast_lm for entity extraction if available (performance optimization) if tracker and pipeline_timing: @@ -3328,8 +3353,39 @@ class HeritageRAGPipeline(dspy.Module): context = "\n".join(context_parts) # Use quality_lm for answer generation if available (this is the critical user-facing output) - if self.quality_lm: - with dspy.settings.context(lm=self.quality_lm): + # Wrap with cost tracking to measure generation time + if tracker and pipeline_timing: + with tracker.track_stage("generation"): + with tracker.track_llm_call("gpt-4o-mini") as llm_usage: + if self.quality_lm: + with dspy.settings.context(lm=self.quality_lm): + answer_result = self.answer_gen( + question=resolved_question, + context=context, + history=history, # Pass conversation history for context + sources=routing.sources, + language=language, + ) + else: + answer_result = self.answer_gen( + question=resolved_question, + context=context, + history=history, # Pass conversation history for context + sources=routing.sources, + language=language, + ) + timing_breakdown["generation_ms"] = pipeline_timing.generation_ms + else: + if self.quality_lm: + with dspy.settings.context(lm=self.quality_lm): + answer_result = self.answer_gen( + question=resolved_question, + context=context, + history=history, # Pass conversation history for context + sources=routing.sources, + language=language, + ) + else: answer_result = self.answer_gen( question=resolved_question, context=context, @@ -3337,14 +3393,6 @@ class HeritageRAGPipeline(dspy.Module): sources=routing.sources, language=language, ) - else: - answer_result = self.answer_gen( - question=resolved_question, - context=context, - history=history, # Pass conversation history for context - sources=routing.sources, - language=language, - ) answer = answer_result.answer confidence = answer_result.confidence citations = answer_result.citations @@ -3429,7 +3477,7 @@ class HeritageRAGPipeline(dspy.Module): self, question: str, language: str = "nl", - history: History = None, + history: History | None = None, include_viz: bool = True, skip_cache: bool = False, embedding_model: str | None = None, @@ -3515,6 +3563,19 @@ class HeritageRAGPipeline(dspy.Module): raise resolved_question = getattr(routing, 'resolved_question', question) + # DEFENSIVE FIX: Validate resolved_question is not a DSPy placeholder or LLM garbage + if (not resolved_question or + "not supplied" in resolved_question.lower() or + "this particular example" in resolved_question.lower() or + "unable to" in resolved_question.lower() or + "cannot" in resolved_question.lower() or + len(resolved_question.strip()) < 5): + logger.warning( + f"Invalid resolved_question in streaming: '{resolved_question[:80] if resolved_question else 'None'}...', " + f"falling back to original question: '{question[:80]}'" + ) + resolved_question = question + # Small delay between LLM calls to reduce rate limit pressure await asyncio.sleep(0.5) diff --git a/backend/rag/main.py b/backend/rag/main.py index 512ffe8271..95fd25a519 100644 --- a/backend/rag/main.py +++ b/backend/rag/main.py @@ -95,6 +95,7 @@ try: HybridRetriever as _HybridRetriever, create_hybrid_retriever as _create_hybrid_retriever, get_province_code as _get_province_code, + PERSON_JSONLD_CONTEXT, ) from glam_extractor.api.qdrant_retriever import HeritageCustodianRetriever as _HeritageCustodianRetriever from glam_extractor.api.typedb_retriever import TypeDBRetriever as _TypeDBRetriever, create_typedb_retriever as _create_typedb_retriever @@ -416,13 +417,21 @@ class PersonSearchRequest(BaseModel): class PersonSearchResponse(BaseModel): - """Person/staff search response.""" + """Person/staff search response with JSON-LD linked data.""" + + context: dict[str, Any] | None = Field( + default=None, + alias="@context", + description="JSON-LD context for linked data semantic interoperability" + ) query: str results: list[dict[str, Any]] result_count: int query_time_ms: float collection_stats: dict[str, Any] | None = None embedding_model_used: str | None = None + + model_config = {"populate_by_name": True} class DSPyQueryRequest(BaseModel): @@ -836,6 +845,18 @@ class ValkeyClient: # Build CachedResponse schema matching the Valkey API # Maps DSPyQueryResponse fields to CachedResponse expected fields + # + # IMPORTANT: Include llm_response metadata (GLM 4.7 reasoning_content) in cache + # so that cached responses also return the chain-of-thought reasoning. + llm_response_data = None + if response.get("llm_response"): + llm_resp = response["llm_response"] + # Handle both dict and LLMResponseMetadata object + if hasattr(llm_resp, "model_dump"): + llm_response_data = llm_resp.model_dump() + elif isinstance(llm_resp, dict): + llm_response_data = llm_resp + cached_response = { "answer": response.get("answer", ""), "sparql_query": None, # DSPy doesn't generate SPARQL @@ -851,6 +872,7 @@ class ValkeyClient: "embedding_model": response.get("embedding_model_used"), "llm_model": response.get("llm_model_used"), "original_context": context, + "llm_response": llm_response_data, # GLM 4.7 reasoning_content }, } @@ -1476,17 +1498,19 @@ async def lifespan(app: FastAPI) -> AsyncIterator[None]: logger.info(f"LLM_PROVIDER configured as: {llm_provider}") dspy_configured = False - # Try Z.AI GLM-4.7 if configured as provider (FREE!) + # Try Z.AI GLM if configured as provider (FREE!) if llm_provider == "zai" and settings.zai_api_token: try: # Z.AI uses OpenAI-compatible API format + # Use LLM_MODEL from settings (default: glm-4.5-flash for speed) + zai_model = settings.llm_model if settings.llm_model.startswith("glm-") else "glm-4.5-flash" lm = dspy.LM( - "openai/glm-4.7", + f"openai/{zai_model}", api_key=settings.zai_api_token, api_base="https://api.z.ai/api/coding/paas/v4", ) dspy.configure(lm=lm) - logger.info("Configured DSPy with Z.AI GLM-4.7 (FREE)") + logger.info(f"Configured DSPy with Z.AI {zai_model} (FREE)") dspy_configured = True except Exception as e: logger.warning(f"Failed to configure DSPy with Z.AI: {e}") @@ -2122,6 +2146,7 @@ async def person_search(request: PersonSearchRequest) -> PersonSearchResponse: pass return PersonSearchResponse( + context=PERSON_JSONLD_CONTEXT, # JSON-LD context for linked data query=request.query, results=result_dicts, result_count=len(result_dicts), @@ -2180,6 +2205,16 @@ async def dspy_query(request: DSPyQueryRequest) -> DSPyQueryResponse: "data": cached.get("visualization_data"), } + # Restore llm_response metadata (GLM 4.7 reasoning_content) from cache + llm_response_cached = cached_context.get("llm_response") + llm_response_obj = None + if llm_response_cached: + try: + llm_response_obj = LLMResponseMetadata(**llm_response_cached) + except Exception: + # Fall back to dict if LLMResponseMetadata fails + llm_response_obj = llm_response_cached # type: ignore[assignment] + response_data = { "question": request.question, "answer": cached.get("answer", ""), @@ -2192,6 +2227,7 @@ async def dspy_query(request: DSPyQueryRequest) -> DSPyQueryResponse: "llm_model_used": cached_context.get("llm_model"), "query_time_ms": round(elapsed_ms, 2), "cache_hit": True, + "llm_response": llm_response_obj, # GLM 4.7 reasoning_content from cache } return DSPyQueryResponse(**response_data) diff --git a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json index cca8bbf929..a896d67c22 100644 --- a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json +++ b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json @@ -9781,7 +9781,1138 @@ "CZ-32-VSE-L-OKV.yaml", "CZ-32-VSE-L-OKVV.yaml", "CZ-32-ZAD-L-CZCPZC.yaml", - "CZ-32-ZBI-L-MKC.yaml" + "CZ-32-ZBI-L-MKC.yaml", + "CZ-32-ZBI-L-MKH.yaml", + "CZ-32-ZBI-L-MKL.yaml", + "CZ-32-ZBI-L-MKP.yaml", + "CZ-32-ZBI-L-MKT.yaml", + "CZ-32-ZBI-L-MKVP.yaml", + "CZ-32-ZBI-L-MKZ.yaml", + "CZ-32-ZBI-L-OKT.yaml", + "CZ-32-ZBI-L-OKVL.yaml", + "CZ-32-ZBU-L-OKZ.yaml", + "CZ-32-ZBU-L-ZUD.yaml", + "JP-11-URE-L-UL-ureshinoshiureshino_library.yaml", + "JP-11-URE-L-UL.yaml", + "JP-11-URE-M-SYM.yaml", + "JP-11-URE-M-UFHMH.yaml", + "JP-11-WAK-L-LNIPH.yaml", + "JP-11-WAK-L-RL.yaml", + "JP-11-WAK-L-THMRNTC.yaml", + "JP-11-WAK-L-WCLSBL.yaml", + "JP-11-WAK-L-WPL.yaml", + "JP-11-WAK-M-NTCTM.yaml", + "JP-11-WAR-L-WCL.yaml", + "JP-11-WAR-L-WLK.yaml", + "JP-11-WAR-L-WLN.yaml", + "JP-11-WAR-L-WLT.yaml", + "JP-11-WAR-M-KKMM.yaml", + "JP-11-WAR-M-WMM.yaml", + "JP-11-YAS-A-YS-yashioshiritsu_shiryoukan.yaml", + "JP-11-YAS-A-YS.yaml", + "JP-11-YAS-L-YL-yashioshiritsuhachijo_library.yaml", + "JP-11-YAS-L-YL.yaml", + "JP-11-YAS-M-YCMM.yaml", + "JP-11-YOS-L-Y-yoshikawashiasahichikusentatoshoshitsu.yaml", + "JP-11-YOS-L-Y-yoshikawashichuokominkantoshoshitsu.yaml", + "JP-11-YOS-L-Y.yaml", + "JP-11-YOS-L-YCL.yaml", + "JP-12-ABI-L-ACL.yaml", + "JP-12-ABI-L-ACLFB.yaml", + "JP-12-ABI-L-ACLKB.yaml", + "JP-12-ABI-L-CL.yaml", + "JP-12-ABI-L-KGWSUL.yaml", + "JP-12-ABI-L-YIO.yaml", + "JP-12-ASA-L-APL.yaml", + "JP-12-ASA-L-CPEL.yaml", + "JP-12-ASA-M-OYM.yaml", + "JP-12-ASA-M-SSKFRKEM.yaml", + "JP-12-ASH-M-HCM.yaml", + "JP-12-ATS-M-HAOC.yaml", + "JP-12-ATS-M-HVH.yaml", + "JP-12-AWA-M-MMM.yaml", + "JP-12-CHI-A-CPA-chiba_prefectural_archives.yaml", + "JP-12-CHI-A-CPA.yaml", + "JP-12-CHI-L-C.yaml", + "JP-12-CHI-L-CCCL.yaml", + "JP-12-CHI-L-CCHL.yaml", + "JP-12-CHI-L-CCHLHDA.yaml", + "JP-12-CHI-L-CCIL.yaml", + "JP-12-CHI-L-CCLLCRRR.yaml", + "JP-12-CHI-L-CCML-chiba_city_midori_library.yaml", + "JP-12-CHI-L-CCML-chiba_city_miyako_library.yaml", + "JP-12-CHI-L-CCML.yaml", + "JP-12-CHI-L-CCMLAA.yaml", + "JP-12-CHI-L-CCMLSA.yaml", + "JP-12-CHI-L-CCMLTA.yaml", + "JP-12-CHI-L-CCMLUA.yaml", + "JP-12-CHI-L-CCWL.yaml", + "JP-12-CHI-L-CCWLIA.yaml", + "JP-12-CHI-L-CCWLNTA.yaml", + "JP-12-CHI-L-CKUGL.yaml", + "JP-12-CHI-L-CL-chibameitokutankidaigaku_library.yaml", + "JP-12-CHI-L-CL.yaml", + "JP-12-CHI-L-CLML.yaml", + "JP-12-CHI-L-CPAFRC.yaml", + "JP-12-CHI-L-CPAL.yaml", + "JP-12-CHI-L-CPCL.yaml", + "JP-12-CHI-L-CUL.yaml", + "JP-12-CHI-L-DSK.yaml", + "JP-12-CHI-L-JJ.yaml", + "JP-12-CHI-L-K.yaml", + "JP-12-CHI-L-KUISL.yaml", + "JP-12-CHI-L-LHSCU.yaml", + "CZ-32-ZDI-L-MKVZ.yaml", + "CZ-32-ZEL-L-MKHS.yaml", + "CZ-32-ZEL-L-MKVZR.yaml", + "CZ-32-ZER-M-PM.yaml", + "CZ-32-ZIC-L-OKZ.yaml", + "CZ-32-ZIH-L-MKB.yaml", + "CZ-32-ZIH-L-MKR.yaml", + "CZ-32-ZIH-L-MKS.yaml", + "CZ-32-ZIH-L-OKZ.yaml", + "CZ-32-ZRU-L-MKZS.yaml", + "CZ-32-ZVI-L-MKZ.yaml", + "CZ-41-ASS-L-TS.yaml", + "CZ-41-ASX-M-MA.yaml", + "CZ-41-BEC-L-MKVBNT.yaml", + "CZ-41-BOC-L-MKIB.yaml", + "CZ-41-BOC-L-OKAH.yaml", + "CZ-41-BOC-L-ZKVB.yaml", + "CZ-41-BOZ-L-ZKBD.yaml", + "CZ-41-BOZ-L-ZKVB.yaml", + "CZ-41-BRE-L-ZKVB.yaml", + "CZ-41-BUK-L-MKVB.yaml", + "CZ-41-CHE-A-AUMAVESC-archivalie_ulozene_mimo_archivy_v_evidenci_soka_ch.yaml", + "CZ-41-CHE-A-SOAC.yaml", + "CZ-41-CHE-E-ZSCK.yaml", + "CZ-41-CHE-G-GVUVCK.yaml", + "CZ-41-CHE-H-FKC.yaml", + "CZ-41-CHE-L-EC.yaml", + "CZ-41-CHE-L-KKNSNCLK.yaml", + "CZ-41-CHE-L-OKVM-obecni_knihovna_v_milhostove.yaml", + "CZ-41-CHE-L-OKVM.yaml", + "CZ-41-CHE-L-OKVN.yaml", + "CZ-41-CHE-L-OKVT.yaml", + "CZ-41-CHE-M-KMC.yaml", + "CZ-41-CHE-M-MCPOKKK.yaml", + "CZ-41-CHO-L-CCSRTK.yaml", + "CZ-41-CHO-L-OKVM.yaml", + "CZ-41-CHY-L-ZKC.yaml", + "CZ-41-CIT-L-MKC.yaml", + "CZ-41-DAL-L-OKD.yaml", + "CZ-41-DOL-L-OKVDZ.yaml", + "CZ-41-FRA-L-MKFL.yaml", + "CZ-41-HAB-L-MKSHPO.yaml", + "CZ-41-HAZ-L-OKH.yaml", + "CZ-41-HOR-A-AUMAVESKH.yaml", + "CZ-41-HOR-L-MKSVHSMK.yaml", + "CZ-41-HOR-L-ZKVHB.yaml", + "CZ-41-HRA-A-AUMAVESUH.yaml", + "CZ-41-HRA-L-MKVHUA.yaml", + "CZ-41-JAC-L-LLJSALK.yaml", + "CZ-41-JAC-L-MKKICJ.yaml", + "CZ-41-KAR-E-CISSRK.yaml", + "CZ-41-KAR-E-SUSKSKVSK.yaml", + "CZ-41-KAR-L-JDZSD.yaml", + "CZ-41-KAR-L-KKNSNVKVLK.yaml", + "CZ-41-KAR-L-KPSK.yaml", + "CZ-41-KAR-L-KSS.yaml", + "CZ-41-KAR-L-MKKV.yaml", + "CZ-41-KAR-L-OPMH.yaml", + "CZ-41-KAR-L-PUUP.yaml", + "CZ-41-KAR-L-VSFSSSSKVK.yaml", + "CZ-41-KAR-L-ZKVP.yaml", + "CZ-41-KAR-M-MKVPKKK.yaml", + "CZ-41-KAV-A-AUMAVESKV.yaml", + "CZ-41-KAV-A-MSPFUK.yaml", + "CZ-41-KAV-A-SOAKV.yaml", + "CZ-41-KAV-G-GUKV.yaml", + "CZ-41-KAV-L-EISPDVUUK.yaml", + "CZ-41-KAV-M-KMKV.yaml", + "CZ-41-KOL-L-ZKVK.yaml", + "CZ-41-KRA-L-ADSR.yaml", + "CZ-41-KRA-L-HDMM.yaml", + "CZ-41-KRA-L-K.yaml", + "CZ-41-KRA-L-MKJ.yaml", + "CZ-41-KRA-L-MKK-mistni_knihovna_krajkova.yaml", + "CZ-41-KRA-L-MKK.yaml", + "CZ-41-KRA-L-MKKP.yaml", + "CZ-41-KRA-L-OKK.yaml", + "CZ-41-KRA-L-OKKP.yaml", + "CZ-41-KYN-L-KLU.yaml", + "CZ-41-KYN-L-MKKNO.yaml", + "CZ-41-KYS-L-OKK.yaml", + "CZ-41-KYS-L-OKVS.yaml", + "CZ-41-KYS-L-ZKVS.yaml", + "CZ-41-LAB-M-MMFL.yaml", + "CZ-41-LAB-M-MMML.yaml", + "CZ-41-LIB-L-OKVL.yaml", + "CZ-41-LOK-L-NPUUOPVLK.yaml", + "CZ-41-LOM-L-MKVDN.yaml", + "CZ-41-LOM-L-OKL.yaml", + "CZ-41-LUB-L-KML.yaml", + "CZ-41-LUB-L-SSSRK.yaml", + "CZ-41-MAL-L-FCSCR.yaml", + "CZ-41-MAR-L-CSLLKLLU.yaml", + "CZ-41-MAR-L-MKML.yaml", + "CZ-41-MAR-L-OKVD.yaml", + "CZ-41-MAR-L-OKVM.yaml", + "CZ-41-MAR-L-OKVOK.yaml", + "CZ-41-MAR-L-OKVP-obecni_knihovna_v_podlesi.yaml", + "CZ-41-MAR-L-OKVP.yaml", + "CZ-41-MAR-L-OKVT.yaml", + "CZ-41-MAR-L-OKVTS.yaml", + "CZ-41-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich.yaml", + "CZ-41-MAR-L-VUB.yaml", + "CZ-41-NEJ-L-MKN.yaml", + "CZ-41-NEJ-L-OKVP.yaml", + "CZ-41-NEJ-L-VS.yaml", + "CZ-41-NOV-L-MKNR.yaml", + "CZ-41-NOV-L-MKNS.yaml", + "CZ-41-NOV-L-OKVM.yaml", + "CZ-41-NOV-L-ZKVD.yaml", + "CZ-41-OLO-L-MKO.yaml", + "CZ-41-OST-E-SPSOSK.yaml", + "CZ-41-OST-L-MKOPO.yaml", + "CZ-41-OST-L-SOSR.yaml", + "CZ-41-OST-L-ZKVH.yaml", + "CZ-41-OST-L-ZMA.yaml", + "CZ-41-OTO-L-ZKVO.yaml", + "CZ-41-OTR-L-ZKB.yaml", + "CZ-41-OTR-L-ZKVO.yaml", + "CZ-41-PLE-L-MKVP.yaml", + "CZ-41-ROT-L-MKKICMR.yaml", + "CZ-41-ROT-L-RSSR.yaml", + "CZ-41-ROV-L-MKR.yaml", + "CZ-41-SIN-L-MKS.yaml", + "CZ-41-SKA-L-OKVK.yaml", + "CZ-41-SKA-L-OKVNK.yaml", + "CZ-41-SOK-A-ASSUS.yaml", + "CZ-41-SOK-A-AUMAVESS-archivalie_ulozene_mimo_archivy_v_evidenci_soka_so.yaml", + "CZ-41-SOK-A-SOASSSVJ.yaml", + "CZ-41-SOK-E-GSK.yaml", + "CZ-41-SOK-L-KKNSNVSLK.yaml", + "CZ-41-SOK-L-SSTK.yaml", + "CZ-41-SOK-L-SUSVPS.yaml", + "CZ-41-SOK-M-KMSPO.yaml", + "CZ-41-STE-L-MKVS.yaml", + "CZ-41-STR-L-MKS.yaml", + "CZ-41-STR-L-ZKSNO.yaml", + "CZ-41-STR-L-ZKVS.yaml", + "CZ-41-SVA-L-MKS.yaml", + "CZ-41-TEP-H-BPK.yaml", + "CZ-41-TEP-H-KPTHK.yaml", + "CZ-41-TOU-L-ZKVKU.yaml", + "CZ-41-TOU-L-ZKVU.yaml", + "CZ-41-VAL-L-OKVV.yaml", + "CZ-41-VEL-L-OKVVH.yaml", + "CZ-41-VER-L-ZKVA.yaml", + "CZ-41-VER-L-ZKVV.yaml", + "CZ-41-VIN-L-MKV.yaml", + "CZ-41-VRE-L-OKVV.yaml", + "CZ-41-ZLU-L-KZ.yaml", + "CZ-42-ARN-L-OKA.yaml", + "CZ-42-BEC-L-MKB.yaml", + "CZ-42-BEC-L-OKVB.yaml", + "CZ-42-BEN-L-BS.yaml", + "CZ-42-BIL-L-KM.yaml", + "CZ-42-BIL-L-SDDB.yaml", + "CZ-42-BIL-L-SDSK.yaml", + "CZ-42-BLS-L-OKB.yaml", + "CZ-42-BOL-L-OKB.yaml", + "CZ-42-BOR-L-MKB.yaml", + "JP-12-CHI-L-LIDEJETO.yaml", + "JP-12-CHI-L-NIRSL.yaml", + "JP-12-CHI-L-OUJL.yaml", + "JP-12-CHI-L-SKCMCL.yaml", + "JP-12-CHI-L-SUCL.yaml", + "JP-12-CHI-L-SUSNNL.yaml", + "JP-12-CHI-L-TDCL.yaml", + "JP-12-CHI-L-TUISISC.yaml", + "JP-12-CHI-L-TUML.yaml", + "JP-12-CHI-L-UGUL.yaml", + "JP-12-CHI-M-CCFM.yaml", + "JP-12-CHI-M-CCMS.yaml", + "JP-12-CHI-M-CKUREM.yaml", + "JP-12-CHI-M-CPMA.yaml", + "JP-12-CHI-M-FM.yaml", + "JP-12-CHI-M-HM.yaml", + "JP-12-CHI-M-NHMIC.yaml", + "JP-12-CHO-L-CISL.yaml", + "JP-12-CHO-L-CL.yaml", + "JP-12-CHO-L-N.yaml", + "JP-12-CHO-L-S.yaml", + "JP-12-CHO-M-CHM.yaml", + "JP-12-CHO-M-HMH.yaml", + "JP-12-CHO-M-MMHF.yaml", + "JP-12-CHO-M-STMRHF.yaml", + "JP-12-CHO-M-UTMA.yaml", + "JP-12-CHU-M-KKAK.yaml", + "JP-12-ESA-M-ECLM.yaml", + "JP-12-FUK-M-YCCMM.yaml", + "JP-12-FUN-L-F-funabashishimiyamashiminsentatoshoshitsu.yaml", + "JP-12-FUN-L-F-funabashishiseibukominkantoshoshitsu.yaml", + "JP-12-FUN-L-F.yaml", + "JP-12-FUN-L-FL-funabashishichuo_library.yaml", + "JP-12-FUN-L-FL-funabashishihigashi_library.yaml", + "JP-12-FUN-L-FL-funabashishikita_library.yaml", + "JP-12-FUN-L-FL.yaml", + "JP-12-FUN-L-LSPNU.yaml", + "JP-12-FUN-L-NLF.yaml", + "JP-12-FUN-L-PCMSL.yaml", + "JP-12-FUN-L-SLF.yaml", + "JP-12-FUN-L-THUFL.yaml", + "JP-12-FUN-L-TUNMC.yaml", + "JP-12-FUN-M-CM.yaml", + "JP-12-FUN-M-FAPKB.yaml", + "JP-12-FUN-M-FHM.yaml", + "JP-12-FUN-M-FSCPK.yaml", + "JP-12-FUN-M-MPGSPNU.yaml", + "JP-12-FUN-M-MPGTU.yaml", + "JP-12-FUN-M-PCMSM.yaml", + "JP-12-FUT-L-TICTDBNSSC.yaml", + "JP-12-FUT-M-TZ.yaml", + "JP-12-GOR-L-HCCL.yaml", + "JP-12-GOR-M-GT.yaml", + "JP-12-HAB-M-HSC.yaml", + "JP-12-HOR-M-HNEERC.yaml", + "JP-12-HOR-M-NHM.yaml", + "JP-12-ICH-L-CUCL.yaml", + "JP-12-ICH-L-IL-ichiharashiritsuchuo_library.yaml", + "JP-12-ICH-L-IL-ichikawashigyotoku_library.yaml", + "JP-12-ICH-L-IL-ichikawashiichikawaekiminamiguchi_library.yaml", + "JP-12-ICH-L-IL-ichikawashiminamigyotoku_library.yaml", + "JP-12-ICH-L-IL-ichikawashishintoku_library.yaml", + "JP-12-ICH-L-IL.yaml", + "JP-12-ICH-L-ILH.yaml", + "JP-12-ICH-L-ISTKL.yaml", + "JP-12-ICH-L-LTUCMC.yaml", + "JP-12-ICH-L-SL.yaml", + "JP-12-ICH-L-TCCTIPSGL.yaml", + "JP-12-ICH-L-THUCCL.yaml", + "JP-12-ICH-L-TL-tokyokeieitankidaigaku_library.yaml", + "JP-12-ICH-L-TL.yaml", + "JP-12-ICH-L-WWSUMC.yaml", + "JP-12-ICH-M-CMSI.yaml", + "JP-12-ICH-M-MKKHS.yaml", + "JP-12-ICH-M-MMAI.yaml", + "JP-12-ICH-M-MMHI.yaml", + "JP-12-ICH-M-MMNHI.yaml", + "JP-12-ICH-M-WWSUM.yaml", + "JP-12-ICH-M-YGG.yaml", + "JP-12-IKU-M-MCM.yaml", + "JP-12-IMB-L-F.yaml", + "JP-12-IMB-L-SL.yaml", + "JP-12-IMB-M-BM.yaml", + "JP-12-INZ-L-IL-inzaishiritsuimba_library.yaml", + "JP-12-INZ-L-IL-inzaishiritsukobayashi_library.yaml", + "JP-12-INZ-L-IL-inzaishiritsumotono_library.yaml", + "JP-12-INZ-L-IL-inzaishiritsuoguradai_library.yaml", + "JP-12-INZ-L-IL-inzaishiritsusofuke_library.yaml", + "JP-12-INZ-L-IL.yaml", + "JP-12-INZ-L-J.yaml", + "CZ-42-BRE-L-MVKB.yaml", + "CZ-42-BRN-L-MKB.yaml", + "CZ-42-BRN-M-HMVSUB.yaml", + "CZ-42-BRN-M-MMB.yaml", + "CZ-42-BRO-A-AUMAVESHB.yaml", + "CZ-42-BRO-A-LTDUVUB.yaml", + "CZ-42-BRO-L-MKBNO.yaml", + "CZ-42-BUD-L-MKBNO.yaml", + "CZ-42-BUD-L-MKN.yaml", + "CZ-42-BUD-L-MKP.yaml", + "CZ-42-CER-L-MKC.yaml", + "CZ-42-CES-L-MKCK.yaml", + "CZ-42-CHA-L-MKVC.yaml", + "CZ-42-CHB-L-OKVC.yaml", + "CZ-42-CHO-A-SOACSSVK.yaml", + "CZ-42-CHO-L-CKPO.yaml", + "CZ-42-CHO-L-KZSNCZLKPC.yaml", + "CZ-42-CHO-L-OKC.yaml", + "CZ-42-CHO-L-OKVB-obecni_knihovna_v_blatne.yaml", + "CZ-42-CHO-L-OKVB.yaml", + "CZ-42-CHO-L-OKVK.yaml", + "CZ-42-CHO-L-OKVV.yaml", + "CZ-42-CHO-L-SKKSK.yaml", + "CZ-42-CHO-L-ZCS.yaml", + "CZ-42-CHO-M-OMVCPO.yaml", + "JP-12-INZ-L-NMSCHHL.yaml", + "JP-12-INZ-L-NMSLK.yaml", + "JP-12-INZ-L-T.yaml", + "JP-12-INZ-L-TL.yaml", + "JP-12-INZ-L-TRDI.yaml", + "JP-12-INZ-M-ISIHMMD.yaml", + "JP-12-ISU-L-GLF.yaml", + "JP-12-ISU-L-OLT.yaml", + "JP-12-ISU-L-SL.yaml", + "JP-12-ISU-M-ICM.yaml", + "JP-12-ISU-M-OMMHF.yaml", + "JP-12-IWA-M-ICAHMMH.yaml", + "JP-12-KAG-M-ACM.yaml", + "JP-12-KAG-M-MALM.yaml", + "JP-12-KAM-L-KL.yaml", + "JP-12-KAM-L-KPL.yaml", + "JP-12-KAM-M-KCLM.yaml", + "JP-12-KAM-M-KCMLHF.yaml", + "JP-12-KAM-M-KK.yaml", + "JP-12-KAM-M-KSW.yaml", + "JP-12-KAM-M-MFMKC.yaml", + "JP-12-KAM-M-SJTH.yaml", + "JP-12-KAM-M-THTJT.yaml", + "JP-12-KAS-L-ICRRLUT.yaml", + "JP-12-KAS-L-ISSPLUT.yaml", + "CZ-42-CHR-L-MKC.yaml", + "CZ-42-CIT-L-MKC.yaml", + "CZ-42-CIZ-L-CCV.yaml", + "CZ-42-CIZ-L-MKC.yaml", + "CZ-42-DEC-E-SSZZAEKK.yaml", + "CZ-42-DEC-L-CEDSR.yaml", + "CZ-42-DEC-L-DS.yaml", + "CZ-42-DEC-L-FS.yaml", + "CZ-42-DEC-L-KZSNDZDPOL.yaml", + "CZ-42-DEC-L-OKJ.yaml", + "CZ-42-DEC-L-OKVM.yaml", + "CZ-42-DEC-L-OKVSS.yaml", + "CZ-42-DEC-L-OKVT.yaml", + "CZ-42-DEC-L-SES.yaml", + "CZ-42-DEC-L-SUSR.yaml", + "CZ-42-DEC-M-OMVDPK.yaml", + "CZ-42-DEC-M-OMVDPO.yaml", + "CZ-42-DEC-O-SOAVLSOAD.yaml", + "CZ-42-DEC-O-SOAVLSOADP.yaml", + "CZ-42-DOB-L-OKD.yaml", + "CZ-42-DOB-L-OKVD.yaml", + "CZ-42-DOK-L-MKVD.yaml", + "CZ-42-DOL-L-MKDP.yaml", + "CZ-42-DOL-L-OKVDP.yaml", + "CZ-42-DUC-L-KP.yaml", + "JP-12-KAS-L-ISUKCL.yaml", + "JP-12-KAS-L-KCL.yaml", + "JP-12-KAS-L-KIUL.yaml", + "JP-12-KAS-L-KLE.yaml", + "JP-12-KAS-L-KLF-kashiwashiritsu_library_fujigokorobunkan.yaml", + "JP-12-KAS-L-KLF.yaml", + "JP-12-KAS-L-KLH.yaml", + "JP-12-KAS-L-KLKL.yaml", + "JP-12-KAS-L-KLM-kashiwashiritsu_library_matsubabunkan.yaml", + "JP-12-KAS-L-KLM.yaml", + "JP-12-KAS-L-KLN-kashiwashiritsu_library_nedobunkan.yaml", + "JP-12-KAS-L-KLN-kashiwashiritsu_library_nishiharabunkan.yaml", + "JP-12-KAS-L-KLN.yaml", + "JP-12-KAS-L-KLS-kashiwashiritsu_library_shindembarabunkan.yaml", + "JP-12-KAS-L-KLS-kashiwashiritsu_library_shonambunkan.yaml", + "JP-12-KAS-L-KLS.yaml", + "JP-12-KAS-L-KLT-kashiwashiritsu_library_takadabunkan.yaml", + "JP-12-KAS-L-KLT-kashiwashiritsu_library_takayanagibunkan.yaml", + "JP-12-KAS-L-KLT-kashiwashiritsu_library_toyoshikidaibunkan.yaml", + "JP-12-KAS-L-KLT.yaml", + "JP-12-KAS-L-KLUT.yaml", + "JP-12-KAS-L-LAORIUT.yaml", + "JP-12-KAS-L-NLK.yaml", + "JP-12-KAS-L-RUL.yaml", + "JP-12-KAT-L-IBUL.yaml", + "JP-12-KAT-L-K.yaml", + "JP-12-KAT-L-KL-katorishiritsuomigawa_library.yaml", + "JP-12-KAT-L-KL-katorishiritsusawarachuo_library.yaml", + "JP-12-KAT-L-KL.yaml", + "JP-12-KAT-L-TL.yaml", + "JP-12-KAT-L-TTL.yaml", + "JP-12-KAT-M-JCM.yaml", + "JP-12-KAT-M-KJT.yaml", + "JP-12-KAT-M-KSHM.yaml", + "JP-12-KAT-M-SVSC.yaml", + "JP-12-KIM-L-KCCL.yaml", + "JP-12-KIM-M-FMK.yaml", + "JP-12-KIM-M-KJMK.yaml", + "JP-12-KIM-M-THJ.yaml", + "JP-12-KIS-L-KL.yaml", + "JP-12-KIS-L-KPL.yaml", + "JP-12-KIS-L-SL.yaml", + "JP-12-KIS-L-SUL.yaml", + "JP-12-KIS-M-KHMKS.yaml", + "JP-12-KIT-M-MKMAH.yaml", + "JP-12-KIT-M-NFM.yaml", + "JP-12-MAT-L-CPWL.yaml", + "JP-12-MAT-L-KHCLRICTSU.yaml", + "JP-12-MAT-L-LHSCU.yaml", + "JP-12-MAT-L-LSDMNU.yaml", + "JP-12-MAT-L-ML.yaml", + "JP-12-MAT-L-MLA.yaml", + "JP-12-MAT-L-MLG.yaml", + "JP-12-MAT-L-MLH-matsudoshiritsu_library_hachigasakibunkan.yaml", + "JP-12-MAT-L-MLH.yaml", + "JP-12-MAT-L-MLK-matsudoshiritsu_library_koganebunkan.yaml", + "JP-12-MAT-L-MLK-matsudoshiritsu_library_koganeharabunkan.yaml", + "JP-12-MAT-L-MLK-matsudoshiritsu_library_koganekitabunkan.yaml", + "JP-12-MAT-L-MLK.yaml", + "JP-12-MAT-L-MLM-matsudoshiritsu_library_mabashihigashibunkan.yaml", + "JP-12-MAT-L-MLM-matsudoshiritsu_library_matsuhidaibunkan.yaml", + "JP-12-MAT-L-MLM-matsudoshiritsu_library_minoridaibunkan.yaml", + "JP-12-MAT-L-MLM-matsudoshiritsu_library_mutsumibunkan.yaml", + "JP-12-MAT-L-MLM.yaml", + "JP-12-MAT-L-MLN.yaml", + "CZ-42-DUC-M-MMD-muzeum_mesta_duchcova.yaml", + "CZ-42-DUC-M-MMDK.yaml", + "CZ-42-HAJ-L-OKHUD.yaml", + "CZ-42-HAV-L-MKL.yaml", + "CZ-42-HAV-L-MKVM.yaml", + "CZ-42-HOL-L-KH.yaml", + "CZ-42-HOR-L-MLKVHSK.yaml", + "CZ-42-HOR-L-OKVHJ.yaml", + "CZ-42-HOR-L-OKVHSS.yaml", + "CZ-42-HOS-L-MKH.yaml", + "CZ-42-HOS-L-MKVH.yaml", + "CZ-42-HRD-L-MKVH.yaml", + "CZ-42-HRI-L-MKH.yaml", + "CZ-42-HRO-L-MKH-mistni_knihovna_hrobce.yaml", + "CZ-42-HRU-L-MVKH.yaml", + "CZ-42-JET-L-OKVJ.yaml", + "CZ-42-JIC-A-AUMAVESJ-archivalie_ulozene_mimo_archivy_v_evidenci_soka_ji.yaml", + "CZ-42-JIC-A-AUMAVESNJ.yaml", + "CZ-42-JIR-L-MKVJ-mestska_knihovna_v_jirikove.yaml", + "CZ-42-JIR-L-OKP.yaml", + "CZ-42-KAD-E-SSTGACPOSK.yaml", + "CZ-42-KAD-L-NKSRLK.yaml", + "CZ-42-KAL-L-OKVK.yaml", + "CZ-42-KLA-L-MKKNOSMK.yaml", + "CZ-42-KLA-L-OKVO.yaml", + "CZ-42-KLA-L-ZKN.yaml", + "CZ-42-KLI-L-OKVK.yaml", + "CZ-42-KOM-L-SDVL.yaml", + "CZ-42-KOR-L-OKOK.yaml", + "CZ-42-KOS-L-MKK.yaml", + "CZ-42-KOS-L-MLKK.yaml", + "CZ-42-KRA-L-MKK.yaml", + "CZ-42-KRA-L-MKVKL.yaml", + "CZ-42-KRA-L-OKKD.yaml", + "CZ-42-KRE-L-MLKK.yaml", + "CZ-42-KRU-L-MKMK.yaml", + "CZ-42-KRU-L-SKSR.yaml", + "CZ-42-KRY-L-MKVK.yaml", + "CZ-42-KYT-L-OKVK.yaml", + "CZ-42-LEV-L-MKL.yaml", + "CZ-42-LIB-L-KL.yaml", + "CZ-42-LIB-L-MKL-mistni_knihovna_libceves.yaml", + "CZ-42-LIB-L-MKL-mistni_knihovna_libesice.yaml", + "CZ-42-LIB-L-MKL-mistni_knihovna_libochovany.yaml", + "CZ-42-LIB-L-MKL.yaml", + "CZ-42-LIB-L-OKL.yaml", + "CZ-42-LIT-A-AUMAVESLR-archivalie_ulozene_mimo_archivy_v_evidenci_soa_lit.yaml", + "CZ-42-LIT-A-AUMAVESLR.yaml", + "CZ-42-LIT-A-SOALSSVL.yaml", + "CZ-42-LIT-A-SOAVL.yaml", + "CZ-42-LIT-E-SSPHSLPKSD.yaml", + "CZ-42-LIT-G-SGVUVLPOUK.yaml", + "CZ-42-LIT-H-BLK.yaml", + "CZ-42-LIT-L-K.yaml", + "CZ-42-LIT-L-MKB.yaml", + "CZ-42-LIT-L-MKL-mistni_knihovna_libotenice.yaml", + "CZ-42-LIT-L-MKL.yaml", + "CZ-42-LIT-L-MKM.yaml", + "CZ-42-LIT-L-MKNK.yaml", + "CZ-42-LIT-L-MKT.yaml", + "CZ-42-LIT-L-MKVT.yaml", + "CZ-42-LIT-L-MKVZ.yaml", + "CZ-42-LIT-L-MLKVCJ.yaml", + "CZ-42-LIT-L-MN.yaml", + "CZ-42-LIT-L-POKKHMVL.yaml", + "CZ-42-LIT-L-URSRTK.yaml", + "CZ-42-LIT-M-OMVLPO.yaml", + "CZ-42-LIT-O-SOAVLK.yaml", + "CZ-42-LOM-L-MKVL.yaml", + "CZ-42-LOU-A-SOAL.yaml", + "CZ-42-LOU-L-ELS.yaml", + "CZ-42-LOU-L-MKD.yaml", + "CZ-42-LOU-L-MKL-mistni_knihovna_listany.yaml", + "CZ-42-LOU-L-MKP.yaml", + "CZ-42-LOU-L-MKVNV.yaml", + "CZ-42-LOU-L-MKVV.yaml", + "CZ-42-LOU-L-MKZ-mistni_knihovna_zemechy.yaml", + "CZ-42-LOU-L-MKZ.yaml", + "CZ-42-LOU-L-MLKLUL.yaml", + "CZ-42-LOU-L-NLPOSVILK.yaml", + "CZ-42-LOU-M-GBRMMUK.yaml", + "CZ-42-LOU-M-OMVLPK.yaml", + "CZ-42-LOU-M-OMVLPO-oblastni_muzeum_v_lounech_prispevkova_organizace.yaml", + "CZ-42-LOU-O-SOAVLSOAL.yaml", + "CZ-42-LOV-L-MKK-mistni_knihovna_keblice.yaml", + "CZ-42-LOV-L-MKK.yaml", + "CZ-42-LOV-L-MKL-mistni_knihovna_loveckovice.yaml", + "CZ-42-LOV-L-MKL.yaml", + "CZ-42-LOV-L-MKS.yaml", + "CZ-42-LOV-L-OKR.yaml", + "CZ-42-LOV-L-SS.yaml", + "CZ-42-LUB-L-OKL.yaml", + "CZ-42-MAL-L-MKM.yaml", + "CZ-42-MAL-L-MKT.yaml", + "CZ-42-MAL-L-MKVMB.yaml", + "CZ-42-MAL-L-MVKM.yaml", + "CZ-42-MAR-L-MKM.yaml", + "CZ-42-MAR-L-OKVM.yaml", + "CZ-42-MAR-L-OKVV.yaml", + "CZ-42-MED-L-MLKM.yaml", + "CZ-42-MER-L-VOKVM.yaml", + "CZ-42-MEZ-L-MKM.yaml", + "CZ-42-MIK-L-MK.yaml", + "CZ-42-MIK-M-MMM.yaml", + "CZ-42-MIS-L-OKVM.yaml", + "CZ-42-MOD-L-OKM.yaml", + "CZ-42-MOS-E-PCUNLPMOK.yaml", + "CZ-42-MOS-L-KZSNMZDPOL.yaml", + "CZ-42-MOS-L-MLKVB.yaml", + "CZ-42-MOS-L-SBS.yaml", + "CZ-42-MOS-L-SDL.yaml", + "CZ-42-MOS-L-SHD.yaml", + "CZ-42-MOS-L-SVT.yaml", + "CZ-42-MOS-L-SVZMA.yaml", + "CZ-42-MOS-L-VPSM.yaml", + "CZ-42-MOS-L-VTZOM.yaml", + "CZ-42-MOS-M-OMGVMPK.yaml", + "CZ-42-MOS-M-OMVMPO.yaml", + "CZ-42-MOS-O-OBUMK.yaml", + "CZ-42-NAC-A-AUMAVESN.yaml", + "JP-12-MAT-L-MLS.yaml", + "JP-12-MAT-L-MLT.yaml", + "JP-12-MAT-L-MLW.yaml", + "JP-12-MAT-L-MLY-matsudoshiritsu_library_yahashirabunkan.yaml", + "JP-12-MAT-L-MLY.yaml", + "JP-12-MAT-L-RL.yaml", + "JP-12-MAT-M-MM.yaml", + "JP-12-MAT-M-MS.yaml", + "JP-12-MAT-M-TMH.yaml", + "JP-12-MIN-L-ECL.yaml", + "CZ-42-NAC-M-RMN.yaml", + "CZ-42-NOV-L-MLKNVVH.yaml", + "CZ-42-NOV-L-OKN.yaml", + "CZ-42-NOV-L-OKNS.yaml", + "CZ-42-OBO-L-MKVO.yaml", + "CZ-42-OBR-L-KOP.yaml", + "CZ-42-OBR-L-ZKPOUVO.yaml", + "CZ-42-OHN-L-MLKO.yaml", + "CZ-42-OLD-L-OKVO.yaml", + "CZ-42-OSE-L-MKO.yaml", + "CZ-42-OTV-L-OKVO.yaml", + "CZ-42-PAN-L-OKFPPT.yaml", + "CZ-42-PER-L-MLKP.yaml", + "CZ-42-PER-L-OKVP.yaml", + "CZ-42-PET-L-MKVP.yaml", + "CZ-42-PET-L-OLKVP.yaml", + "CZ-42-PLO-L-MKMZ.yaml", + "CZ-42-PLO-L-MKP.yaml", + "CZ-42-POC-L-CSEP.yaml", + "CZ-42-POD-L-MKP.yaml", + "JP-12-MIN-L-ML.yaml", + "JP-12-MIN-M-ACDM.yaml", + "JP-12-MIN-M-AMA.yaml", + "JP-12-MIN-M-AMM.yaml", + "JP-12-MIN-M-KMM.yaml", + "JP-12-MIN-M-SMAM.yaml", + "JP-12-MOB-L-MPL.yaml", + "JP-12-MOB-M-MCMALH.yaml", + "JP-12-MOI-M-SSM.yaml", + "JP-12-MOM-M-MMM.yaml", + "JP-12-NAG-L-EL.yaml", + "JP-12-NAG-L-NL-nagareyamashiritsukino_library.yaml", + "JP-12-NAG-L-NL-nagareyamashiritsuminaminagareyamachiiki_library.yaml", + "JP-12-NAG-L-NL-nagareyamashiritsumorino_library.yaml", + "JP-12-NAG-L-NL.yaml", + "JP-12-NAG-L-NLH-nagareyamashiritsuchuo_library_hokububunkan.yaml", + "JP-12-NAG-L-NLH.yaml", + "JP-12-NAG-L-TGUNCL.yaml", + "JP-12-NAR-L-CLSL.yaml", + "JP-12-NAR-L-CLTL.yaml", + "JP-12-NAR-L-IUHWNL.yaml", + "JP-12-NAR-L-LCITNU.yaml", + "JP-12-NAR-L-N-naritashihabukominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashihashigadaikominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashikarabekominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashikuzumikominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashimisatodaichikukaikantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashinakagokominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashinaritakominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashisanrizukakomyuniteisentatoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashishimofusakominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashitaieikominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashitamatsukurikominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashitoyamakominkantoshoshitsu.yaml", + "JP-12-NAR-L-N-naritashitoyozumikominkantoshoshitsu.yaml", + "JP-12-NAR-L-N.yaml", + "JP-12-NAR-L-NL-narashinoshiritsuhigashinarashino_library.yaml", + "JP-12-NAR-L-NL-narashinoshiritsushinnarashino_library.yaml", + "JP-12-NAR-L-NL-narashinoshiritsuyatsu_library.yaml", + "JP-12-NAR-L-NL.yaml", + "JP-12-NAR-L-NLK.yaml", + "JP-12-NAR-L-NPL.yaml", + "JP-12-NAR-L-SPL.yaml", + "JP-12-NAR-M-NCMSOISF.yaml", + "JP-12-NAR-M-NCSMHF.yaml", + "JP-12-NAR-M-NMC.yaml", + "JP-12-NAR-M-NRM.yaml", + "JP-12-NAR-M-NYM.yaml", + "JP-12-NAR-M-SMH.yaml", + "JP-12-NAY-M-NO.yaml", + "JP-12-NIS-M-SSM.yaml", + "JP-12-NOB-M-NBP.yaml", + "JP-12-NOD-L-KIIFC.yaml", + "JP-12-NOD-L-NL-nodashiritsukita_library.yaml", + "JP-12-NOD-L-NL-nodashiritsuminami_library.yaml", + "JP-12-NOD-L-NL-nodashiritsusekiyado_library.yaml", + "JP-12-NOD-L-NL.yaml", + "JP-12-NOD-L-TL.yaml", + "JP-12-NOD-M-CPSJM.yaml", + "JP-12-NOD-M-IKM.yaml", + "JP-12-NOD-M-MHMA.yaml", + "JP-12-NOD-M-NCM.yaml", + "JP-12-NOD-M-SK.yaml", + "JP-12-NOP-L-HROEGRDIES.yaml", + "JP-12-NOP-M-ECAC.yaml", + "JP-12-OAM-L-O-oamishirasatoshitoshoshitsuchububunshitsu.yaml", + "JP-12-OAM-L-O-oamishirasatoshitoshoshitsushirasatobunshitsu.yaml", + "JP-12-OAM-L-O.yaml", + "JP-12-OBI-L-OCL.yaml", + "JP-12-OHM-M-APM.yaml", + "JP-12-OTA-M-OCMA.yaml", + "JP-12-SAI-M-PMH.yaml", + "JP-12-SAK-L-D.yaml", + "JP-12-SAK-L-K-kabushikigaishafujikurachizaibutoshoshitsu.yaml", + "JP-12-SAK-L-K.yaml", + "JP-12-SAK-L-LCRLTCC.yaml", + "JP-12-SAK-L-SCSL.yaml", + "JP-12-SAK-L-SL-sakurashiritsusakuraminami_library.yaml", + "JP-12-SAK-L-SL.yaml", + "JP-12-SAK-L-SLS.yaml", + "JP-12-SAK-M-HSFR.yaml", + "JP-12-SAK-M-KMDMA.yaml", + "JP-12-SAK-M-NMJH.yaml", + "JP-12-SAK-M-SJMM.yaml", + "JP-12-SAK-M-TMA.yaml", + "JP-12-SAK-M-WFMRHF.yaml", + "JP-12-SAM-L-K.yaml", + "JP-12-SAM-L-SL-sammushimatsuo_library.yaml", + "JP-12-SAM-L-SL-sammushisambunomori_library.yaml", + "JP-12-SAM-L-SL.yaml", + "JP-12-SAM-L-YLY.yaml", + "JP-12-SAM-L-YPL.yaml", + "JP-12-SAM-M-MAS.yaml", + "JP-12-SAM-M-SCMHF.yaml", + "JP-12-SAP-M-KDCM.yaml", + "JP-12-SHI-L-SL.yaml", + "JP-12-SHI-M-ETMMKF.yaml", + "JP-12-SHI-M-ICSC.yaml", + "JP-12-SHI-M-NAM.yaml", + "JP-12-SHI-M-SAM.yaml", + "JP-12-SHI-M-SCCCP.yaml", + "JP-12-SHI-M-SCHM.yaml", + "JP-12-SHI-M-SCSMHM.yaml", + "JP-12-SHI-M-STM.yaml", + "JP-12-SOD-L-M.yaml", + "JP-12-SOD-L-SL-sodegaurashiritsuhirakawa_library.yaml", + "JP-12-SOD-L-SL-sodegaurashiritsunagauraokanoue_library.yaml", + "JP-12-SOD-L-SL.yaml", + "JP-12-SOD-M-SCLM.yaml", + "JP-12-SOS-L-SL-sosashiritsunosaka_library.yaml", + "JP-12-SOS-L-SL.yaml", + "JP-12-SUE-M-HSRMH.yaml", + "JP-12-TAK-L-TCL.yaml", + "JP-12-TAK-M-TLHM.yaml", + "JP-12-TAT-L-TCL.yaml", + "JP-12-TAT-M-TCM.yaml", + "JP-12-TOG-L-JIUMML.yaml", + "JP-12-TOG-L-TL.yaml", + "JP-12-TOG-M-MMAJIU.yaml", + "JP-12-TOG-M-TSC.yaml", + "JP-12-TOM-L-TPL.yaml", + "JP-12-TOM-M-TCM.yaml", + "JP-12-TOY-M-TVSM.yaml", + "JP-12-URA-L-JL.yaml", + "JP-12-URA-L-MUUCMC.yaml", + "JP-12-URA-L-RUL.yaml", + "JP-12-URA-L-ULH-urayasushiritsu_library_hinodebunkan.yaml", + "JP-12-URA-L-ULH.yaml", + "JP-12-URA-L-ULM.yaml", + "JP-12-URA-L-ULN.yaml", + "JP-12-URA-L-ULT-urayasushiritsu_library_takasubunkan.yaml", + "JP-12-URA-L-ULT-urayasushiritsu_library_todaijimabunkan.yaml", + "JP-12-URA-L-ULT.yaml", + "JP-12-URA-L-UPL.yaml", + "JP-12-URA-M-UCFM.yaml", + "JP-12-YAC-L-SL.yaml", + "JP-12-YAC-L-TLY.yaml", + "JP-12-YAC-L-TYL.yaml", + "JP-12-YAC-L-YL-yachiyoshiritsukatsutadai_library.yaml", + "JP-12-YAC-L-YL-yachiyoshiritsumidorigaoka_library.yaml", + "JP-12-YAC-L-YL-yachiyoshiritsuyachiyodai_library.yaml", + "JP-12-YAC-L-YL.yaml", + "JP-12-YAC-L-YPL.yaml", + "JP-12-YAC-M-YCM.yaml", + "JP-12-YAK-M-YTM.yaml", + "JP-12-YOD-M-MCVH.yaml", + "JP-12-YOT-L-AL.yaml", + "JP-12-YOT-L-LCPEFCPC.yaml", + "JP-12-YOT-L-S.yaml", + "JP-12-YOT-L-YPL.yaml", + "JP-12-YUB-M-YR.yaml", + "JP-13-ADA-L-AL-adachikuritsuhanahata_library.yaml", + "JP-13-ADA-L-AL-adachikuritsuhozuka_library.yaml", + "JP-13-ADA-L-AL-adachikuritsuiko_library.yaml", + "JP-13-ADA-L-AL-adachikuritsukohoku_library.yaml", + "JP-13-ADA-L-AL-adachikuritsukounankomyunitei_library.yaml", + "JP-13-ADA-L-AL-adachikuritsumeda_library.yaml", + "JP-13-ADA-L-AL-adachikuritsuokimoto_library.yaml", + "JP-13-ADA-L-AL-adachikuritsusano_library.yaml", + "JP-13-ADA-L-AL-adachikuritsushikahama_library.yaml", + "JP-13-ADA-L-AL-adachikuritsushindenkomyunitei_library.yaml", + "JP-13-ADA-L-AL-adachikuritsutakenotsuka_library.yaml", + "JP-13-ADA-L-AL-adachikuritsutoneri_library.yaml", + "JP-13-ADA-L-AL-adachikuritsutowa_library.yaml", + "JP-13-ADA-L-AL-adachikuritsuyayoi_library.yaml", + "JP-13-ADA-L-AL.yaml", + "JP-13-ADA-L-BUTAL.yaml", + "JP-13-ADA-L-TDUMRCL.yaml", + "JP-13-ADA-L-TFUL.yaml", + "JP-13-ADA-L-TLSL.yaml", + "JP-13-ADA-L-TWSMULA.yaml", + "JP-13-ADA-M-ACM.yaml", + "JP-13-ADA-M-G.yaml", + "JP-13-ADA-M-SMA.yaml", + "JP-13-AIO-L-LMSKU.yaml", + "JP-13-AKA-L-HPL.yaml", + "JP-13-AKA-M-AMP.yaml", + "JP-13-AKI-L-AL-akirunoshichuo_library.yaml", + "JP-13-AKI-L-AL-akirunoshiitsukaichi_library.yaml", + "JP-13-AKI-L-AL.yaml", + "JP-13-AKI-L-ALE.yaml", + "JP-13-AKI-L-ALM-akirunoshichuo_library_masukobunshitsu.yaml", + "JP-13-AKI-L-ALM.yaml", + "JP-13-AKI-L-ALS.yaml", + "JP-13-AKI-L-ALY.yaml", + "JP-13-AKI-L-N.yaml", + "JP-13-AKI-M-ILM.yaml", + "JP-13-AKI-M-NK.yaml", + "JP-13-AMA-M-ASBWMBM.yaml", + "JP-13-ANA-L-AL.yaml", + "JP-13-ANA-L-ANCT.yaml", + "JP-13-ANA-M-ACAKFM.yaml", + "JP-13-ANA-M-ASC.yaml", + "JP-13-AOG-L-AL.yaml", + "JP-13-ARA-L-A-arakawakuritsukanshindotoshosabisusuteshon.yaml", + "JP-13-ARA-L-A.yaml", + "JP-13-ARA-L-ACPLCL.yaml", + "JP-13-ARA-L-ACPLML.yaml", + "JP-13-ARA-L-ACPLMSL.yaml", + "JP-13-ARA-L-ACPLNL.yaml", + "JP-13-ARA-L-ACPLOL.yaml", + "JP-13-ARA-L-HSLTMU.yaml", + "JP-13-ARA-L-TL.yaml", + "JP-13-ARA-L-TLH.yaml", + "JP-13-ARA-M-AFM.yaml", + "JP-13-ARA-M-YALM.yaml", + "JP-13-ASH-L-AL-ashikagatankidaigakufuzoku_library.yaml", + "JP-13-ASH-L-AL.yaml", + "JP-13-ASH-L-AUL.yaml", + "JP-13-ASH-L-K-kobeshiritsukobemachizukurikaikammachizukuriraibur.yaml", + "JP-13-ASH-M-ACMAH.yaml", + "JP-13-ASH-M-HSAG.yaml", + "JP-13-ASH-M-SM.yaml", + "JP-13-AWA-L-AL-awashiritsudonari_library.yaml", + "JP-13-AWA-L-AL-awashiritsuichiba_library.yaml", + "JP-13-AWA-L-AL-awashiritsuyoshinokasai_library.yaml", + "JP-13-AWA-L-AL.yaml", + "JP-13-AWA-M-DHM.yaml", + "JP-13-AWA-M-IFHM.yaml", + "JP-13-AZA-L-K.yaml", + "JP-13-BUN-A-UTA-university_of_tokyo_archives.yaml", + "JP-13-BUN-A-UTA.yaml", + "JP-13-BUN-L-AL.yaml", + "JP-13-BUN-L-B-bunkyokuritsuotsukakoemmidorinotoshoshitsu.yaml", + "JP-13-BUN-L-B.yaml", + "JP-13-BUN-L-BCMCL.yaml", + "JP-13-BUN-L-BL-bunkyogakuindaigakuhongo_library.yaml", + "JP-13-BUN-L-BL-bunkyokuritsuhonkomagome_library.yaml", + "JP-13-BUN-L-BL-bunkyokuritsukoishikawa_library.yaml", + "JP-13-BUN-L-BL-bunkyokuritsumejirodai_library.yaml", + "JP-13-BUN-L-BL-bunkyokuritsusengoku_library.yaml", + "JP-13-BUN-L-BL-bunkyokuritsusuidobata_library.yaml", + "JP-13-BUN-L-BL-bunkyokuritsuyushima_library.yaml", + "JP-13-BUN-L-BL.yaml", + "JP-13-BUN-L-CMJLPDMSZB.yaml", + "JP-13-BUN-L-CUSEL.yaml", + "JP-13-BUN-L-ECLL.yaml", + "JP-13-BUN-L-ERILUT.yaml", + "JP-13-BUN-L-FLLUT.yaml", + "JP-13-BUN-L-FPS.yaml", + "JP-13-BUN-L-GLUT.yaml", + "JP-13-BUN-L-GSEFELUT.yaml", + "JP-13-BUN-L-IASAL.yaml", + "JP-13-BUN-L-ISSLUT.yaml", + "JP-13-BUN-L-ISTOL.yaml", + "JP-13-BUN-L-ITPAJ.yaml", + "JP-13-BUN-L-JL.yaml", + "JP-13-BUN-L-JRA.yaml", + "JP-13-BUN-L-JWSUL.yaml", + "JP-13-BUN-L-KL.yaml", + "JP-13-BUN-L-KLS.yaml", + "JP-13-BUN-L-LEISTUT.yaml", + "JP-13-BUN-L-LEUT.yaml", + "JP-13-BUN-L-LHIUT.yaml", + "JP-13-BUN-L-LSSUT.yaml", + "JP-13-BUN-L-MERIL.yaml", + "JP-13-BUN-L-MLJMA.yaml", + "JP-13-BUN-L-MLUT.yaml", + "JP-13-BUN-L-MMSISAUT.yaml", + "JP-13-BUN-L-NIER.yaml", + "JP-13-BUN-L-NL.yaml", + "JP-13-BUN-L-OUL.yaml", + "JP-13-BUN-L-PMTL.yaml", + "JP-13-BUN-L-PSLUT.yaml", + "JP-13-BUN-L-TB.yaml", + "JP-13-BUN-L-TGUHCL.yaml", + "JP-13-BUN-L-TL-teiseigakuentankidaigakufuzoku_library.yaml", + "JP-13-BUN-L-TL.yaml", + "JP-13-BUN-L-TUL-toyo_university_library.yaml", + "JP-13-BUN-L-TUL.yaml", + "JP-13-BUN-L-ULALSUT.yaml", + "JP-13-BUN-L-UTGSHSFLL.yaml", + "JP-13-BUN-L-UTIIISGSII.yaml", + "JP-13-BUN-L-UTLOL.yaml", + "JP-13-BUN-M-BGGSSUT.yaml", + "JP-13-BUN-M-BHFM.yaml", + "JP-13-BUN-M-EBM.yaml", + "JP-13-BUN-M-IEMMTU.yaml", + "JP-13-BUN-M-JWSUNMH.yaml", + "JP-13-BUN-M-MOMM.yaml", + "JP-13-BUN-M-PMT.yaml", + "JP-13-BUN-M-TBM.yaml", + "JP-13-BUN-M-YMTYM.yaml", + "JP-13-CHI-A-IHA-the_imperial_household_archives.yaml", + "JP-13-CHI-A-IHA.yaml", + "JP-13-CHI-A-NAJ.yaml", + "JP-13-CHI-L-ADBIL.yaml", + "JP-13-CHI-L-ADTHOMN.yaml", + "JP-13-CHI-L-AHL.yaml", + "JP-13-CHI-L-ALNMMAT.yaml", + "JP-13-CHI-L-APC.yaml", + "JP-13-CHI-L-B.yaml", + "JP-13-CHI-L-BALBN.yaml", + "JP-13-CHI-L-BFGLINS.yaml", + "JP-13-CHI-L-BLJBA.yaml", + "JP-13-CHI-L-CAALBN.yaml", + "JP-13-CHI-L-CL-chiyodakuritsukandamachikado_library.yaml", + "JP-13-CHI-L-CL-chiyodakuritsushoheimachikado_library.yaml", + "JP-13-CHI-L-CL-chiyodakuritsuyombancho_library.yaml", + "JP-13-CHI-L-CL-the_chemistry_library.yaml", + "JP-13-CHI-L-CL.yaml", + "JP-13-CHI-L-CLBLBN.yaml", + "JP-13-CHI-L-COLBN.yaml", + "JP-13-CHI-L-CRIEPI.yaml", + "JP-13-CHI-L-D.yaml", + "JP-13-CHI-L-DBJISC.yaml", + "JP-13-CHI-L-DEIJL.yaml", + "JP-13-CHI-L-DHUML.yaml", + "JP-13-CHI-L-E.yaml", + "JP-13-CHI-L-EISU.yaml", + "JP-13-CHI-L-EL.yaml", + "JP-13-CHI-L-FALBN.yaml", + "JP-13-CHI-L-FCCJ.yaml", + "JP-13-CHI-L-FSALBN.yaml", + "JP-13-CHI-L-FTCLBN.yaml", + "JP-13-CHI-L-GRR.yaml", + "JP-13-CHI-L-GS.yaml", + "JP-13-CHI-L-GSMGUL.yaml", + "JP-13-CHI-L-H-hoseidaigakubungakubushiryoshitsu.yaml", + "JP-13-CHI-L-H-hoseidaigakukeieigakubushiryoshitsu.yaml", + "JP-13-CHI-L-H-hoseidaigakukokusaibunkagakubushiryoshitsu.yaml", + "JP-13-CHI-L-H-hoseidaigakukyariadezaingakubushiryoshitsu.yaml", + "JP-13-CHI-L-H-hoseidaigakukyoshokukateijumbishitsu.yaml", + "JP-13-CHI-L-H-hoseidaigakuningenkankyogakubushiryoshitsu.yaml", + "JP-13-CHI-L-H.yaml", + "JP-13-CHI-L-HLP.yaml", + "JP-13-CHI-L-HUIOS.yaml", + "JP-13-CHI-L-HUL.yaml", + "JP-13-CHI-L-HURCIJSH.yaml", + "JP-13-CHI-L-I-ippanshadanhojinnihomminkanhosoremmeikenkyujotosho.yaml", + "JP-13-CHI-L-I-ippanshadanhojinnihonkogyokurabujitsugyokashiryosh.yaml", + "JP-13-CHI-L-I-ippanshadanhojinnihonkotsukyokaitoshoshitsu.yaml", + "JP-13-CHI-L-I.yaml", + "JP-13-CHI-L-IACSU.yaml", + "JP-13-CHI-L-ICCSU.yaml", + "JP-13-CHI-L-ICIL.yaml", + "JP-13-CHI-L-ICSLHU.yaml", + "JP-13-CHI-L-IEIJ.yaml", + "JP-13-CHI-L-IHALBN.yaml", + "JP-13-CHI-L-IIPL.yaml", + "JP-13-CHI-L-IMTSU.yaml", + "JP-13-CHI-L-ITML.yaml", + "JP-13-CHI-L-J.yaml", + "JP-13-CHI-L-JACNTL.yaml", + "JP-13-CHI-L-JBHI.yaml", + "JP-13-CHI-L-JCGLBN.yaml", + "JP-13-CHI-L-JCMJL.yaml", + "JP-13-CHI-L-JDAL.yaml", + "JP-13-CHI-L-JIIAL.yaml", + "JP-13-CHI-L-JIIMA.yaml", + "JP-13-CHI-L-JJ.yaml", + "JP-13-CHI-L-JMCML.yaml", + "JP-13-CHI-L-JNPEA.yaml", + "JP-13-CHI-L-JPSEL.yaml", + "JP-13-CHI-L-JRIIMDB.yaml", + "JP-13-CHI-L-JTA.yaml", + "JP-13-CHI-L-JWWA.yaml", + "JP-13-CHI-L-K-kabushikigaishamitsubishijishosekkeigijutsujohobus.yaml", + "JP-13-CHI-L-K-kabushikigaishamitsuibussansenryakukenkyujosenryak.yaml", + "JP-13-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu.yaml", + "JP-13-CHI-L-K-koekishadanhojintokyochigakukyokaitoshoshitsu.yaml", + "JP-13-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu.yaml", + "JP-13-CHI-L-K.yaml", + "JP-13-CHI-L-KBLSU.yaml", + "JP-13-CHI-L-KG.yaml", + "JP-13-CHI-L-KK.yaml", + "JP-13-CHI-L-KLCL.yaml", + "JP-13-CHI-L-KLJC.yaml", + "JP-13-CHI-L-KRL.yaml", + "JP-13-CHI-L-LCGNMMAT.yaml", + "JP-13-CHI-L-LDDPPPRIMA.yaml", + "JP-13-CHI-L-LDL.yaml", + "JP-13-CHI-L-LEERRCNIEP.yaml", + "JP-13-CHI-L-LGIIJ.yaml", + "JP-13-CHI-L-LIICSU.yaml", + "JP-13-CHI-L-LNUSD.yaml", + "JP-13-CHI-L-LTBADTBA.yaml", + "JP-13-CHI-L-MAFFLBN.yaml", + "JP-13-CHI-L-MECSSTLBN.yaml", + "JP-13-CHI-L-MELBN.yaml", + "JP-13-CHI-L-METILBN.yaml", + "JP-13-CHI-L-MFLBN.yaml", + "JP-13-CHI-L-MHLWLBN.yaml", + "JP-13-CHI-L-MIACLBN.yaml", + "JP-13-CHI-L-MJLBN.yaml", + "JP-13-CHI-L-MK.yaml", + "JP-13-CHI-L-MLCL.yaml", + "JP-13-CHI-L-MLH.yaml", + "JP-13-CHI-L-MLITTLBN.yaml", + "JP-13-CHI-L-MLR.yaml", + "JP-13-CHI-L-MLT.yaml", + "JP-13-CHI-L-MMLNC.yaml", + "JP-13-CHI-L-MRII.yaml", + "JP-13-CHI-L-MRLTIMR.yaml", + "JP-13-CHI-L-MSCBRSTMU.yaml", + "JP-13-CHI-L-MSICLISC.yaml", + "JP-13-CHI-L-N.yaml", + "JP-13-CHI-L-NA.yaml", + "JP-13-CHI-L-NACPA.yaml", + "JP-13-CHI-L-NAL.yaml", + "JP-13-CHI-L-NAMAMPDRLD.yaml", + "JP-13-CHI-L-NB.yaml", + "JP-13-CHI-L-NCIPIT.yaml", + "JP-13-CHI-L-NDL.yaml", + "JP-13-CHI-L-NDUSLDTL.yaml", + "JP-13-CHI-L-NGA.yaml", + "JP-13-CHI-L-NL.yaml", + "JP-13-CHI-L-NLK.yaml", + "JP-13-CHI-L-NMNTRIHU.yaml", + "JP-13-CHI-L-NPALBN-national_police_agency_library_branch_of_the_ndl.yaml", + "JP-13-CHI-L-NPALBN.yaml", + "JP-13-CHI-L-NRIL-nomura_research_institute_ltd.yaml", + "JP-13-CHI-L-NRIL.yaml", + "JP-13-CHI-L-NSMM.yaml", + "JP-13-CHI-L-NUCEL.yaml", + "JP-13-CHI-L-NUCSTLS.yaml", + "JP-13-CHI-L-NULSL.yaml", + "JP-13-CHI-L-OGSAL.yaml", + "JP-13-CHI-L-OTCOECOD.yaml", + "JP-13-CHI-L-OWSUL.yaml", + "JP-13-CHI-L-POLBN.yaml", + "JP-13-CHI-L-RDEBNKSI.yaml", + "JP-13-CHI-L-RIEL.yaml", + "JP-13-CHI-L-RIIMHU.yaml", + "JP-13-CHI-L-RL.yaml", + "JP-13-CHI-L-ROISNIIL.yaml", + "JP-13-CHI-L-S.yaml", + "JP-13-CHI-L-SCLBN.yaml", + "JP-13-CHI-L-SL.yaml", + "JP-13-CHI-L-SML.yaml", + "JP-13-CHI-L-SSJ.yaml", + "JP-13-CHI-L-SUCL.yaml", + "JP-13-CHI-L-SUIACS.yaml", + "JP-13-CHI-L-SUIGC.yaml", + "JP-13-CHI-L-SULKB.yaml", + "JP-13-CHI-L-SULL.yaml", + "JP-13-CHI-L-SULSL.yaml", + "JP-13-CHI-L-SULYDBKB.yaml", + "JP-13-CHI-L-SUML.yaml", + "JP-13-CHI-L-T.yaml", + "JP-13-CHI-L-TCAJTLC.yaml", + "JP-13-CHI-L-TCCICSG.yaml", + "JP-13-CHI-L-TKGULOMSL.yaml", + "JP-13-CHI-L-TLS.yaml", + "JP-13-CHI-L-TMNFICLL.yaml", + "JP-13-CHI-L-YKBYA.yaml", + "JP-13-CHI-L-YYMLMS.yaml", + "JP-13-CHI-L-Z.yaml", + "JP-13-CHI-M-CCSHLM.yaml", + "JP-13-CHI-M-IMA.yaml", + "JP-13-CHI-M-JCM.yaml", + "JP-13-CHI-M-KWSUM.yaml", + "JP-13-CHI-M-MICSS.yaml", + "JP-13-CHI-M-MIMT.yaml", + "JP-13-CHI-M-MUM.yaml", + "JP-13-CHI-M-OWSUM.yaml", + "JP-13-CHI-M-PM.yaml", + "JP-13-CHI-M-SBAM.yaml", + "JP-13-CHI-M-SKNSMM.yaml", + "JP-13-CHI-M-SM.yaml", + "JP-13-CHI-M-TG.yaml", + "JP-13-CHI-M-TSG.yaml", + "JP-13-CHI-M-YYM.yaml", + "JP-13-CHO-L-CL.yaml", + "JP-13-CHO-L-CLC.yaml", + "JP-13-CHO-L-CLF.yaml", + "JP-13-CHO-L-CLJ-chofushiritsu_library_jindaijibunkan.yaml", + "JP-13-CHO-L-CLJ.yaml", + "JP-13-CHO-L-CLK.yaml", + "JP-13-CHO-L-CLM-chofushiritsu_library_miyanoshitabunkan.yaml", + "JP-13-CHO-L-CLM.yaml", + "JP-13-CHO-L-CLS-chofushiritsu_library_sazubunkan.yaml", + "JP-13-CHO-L-CLS.yaml", + "JP-13-CHO-L-CLW.yaml", + "JP-13-CHO-L-HCSC.yaml", + "JP-13-CHO-L-JAEAL.yaml", + "JP-13-CHO-L-SUL.yaml", + "JP-13-CHO-L-TGSMCL.yaml", + "JP-13-CHO-L-TGSMSL.yaml", + "JP-13-CHO-L-TL.yaml", + "JP-13-CHO-L-TLK.yaml", + "JP-13-CHO-L-UECL.yaml", + "JP-13-CHO-M-MSMM.yaml", + "JP-13-CHO-M-TMJBG.yaml", + "JP-13-CHU-A-BJA-bank_of_japan_archives.yaml", + "JP-13-CHU-A-BJA.yaml", + "JP-13-CHU-L-CIL.yaml", + "JP-13-CHU-L-CL-chuokuritsunihombashi_library.yaml", + "JP-13-CHU-L-CL-chuokuritsutsukishima_library.yaml", + "JP-13-CHU-L-CL.yaml", + "JP-13-CHU-L-DBSAS.yaml", + "JP-13-CHU-L-DIRLEF.yaml", + "JP-13-CHU-L-EPDCLL.yaml", + "JP-13-CHU-L-I.yaml", + "JP-13-CHU-L-ICR.yaml", + "JP-13-CHU-L-IRIL.yaml", + "JP-13-CHU-L-JCERL.yaml", + "JP-13-CHU-L-JISFL.yaml", + "JP-13-CHU-L-JLAJ.yaml", + "JP-13-CHU-L-JSA.yaml", + "JP-13-CHU-L-JSRISL.yaml", + "JP-13-CHU-L-K-kabushikigaishafujikeizaimanejimentodetakanrishits.yaml", + "JP-13-CHU-L-K.yaml", + "JP-13-CHU-L-KKL.yaml", + "JP-13-CHU-L-MLJCA.yaml", + "JP-13-CHU-L-NCCL.yaml", + "JP-13-CHU-L-NFCNMMAT.yaml", + "JP-13-CHU-L-NL.yaml", + "JP-13-CHU-L-RLT.yaml", + "JP-13-CHU-L-S-shimizukensetsukabushikigaishajohoshiryosenta.yaml", + "JP-13-CHU-L-S.yaml" ], - "last_index": 19 + "last_index": 499 } \ No newline at end of file diff --git a/data/custodian/CZ-32-ZBU-L-OKZ.yaml b/data/custodian/CZ-32-ZBU-L-OKZ.yaml index a21808ffb6..f3e82ef7d1 100644 --- a/data/custodian/CZ-32-ZBU-L-OKZ.yaml +++ b/data/custodian/CZ-32-ZBU-L-OKZ.yaml @@ -44,13 +44,13 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-32-ZBU-L-OKZ - valid_from: "2025-12-10T09:47:09Z" + valid_from: '2025-12-10T09:47:09Z' valid_to: null - reason: "Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ - ghcid: CZ-PL-ZBU-L-OKZ valid_from: null - valid_to: "2025-12-10T09:47:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:09Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PL-ZBU-L-OKZ ghcid_numeric: 13401753587918086075 valid_from: '2025-12-06T23:37:31.840455+00:00' @@ -214,3 +214,22 @@ location: postal_code: 330 22 street_address: Nádražní 192 normalization_timestamp: '2025-12-09T10:53:52.894247+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:47:57.243229+00:00' + source_url: https://www.zbuch.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zbuch.knihovna.cz/favicon.svg + source_url: https://www.zbuch.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T11:47:57.243229+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-32-ZIC-L-OKZ.yaml b/data/custodian/CZ-32-ZIC-L-OKZ.yaml index 126e45a52d..88c7a85102 100644 --- a/data/custodian/CZ-32-ZIC-L-OKZ.yaml +++ b/data/custodian/CZ-32-ZIC-L-OKZ.yaml @@ -211,3 +211,22 @@ location: country: *id005 postal_code: 341 62 normalization_timestamp: '2025-12-09T10:53:53.017105+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:58:01.505049+00:00' + source_url: https://plk.tritius.cz/library/okz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://plk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://plk.tritius.cz/library/okz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T11:58:01.505049+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-32-ZIH-L-MKB.yaml b/data/custodian/CZ-32-ZIH-L-MKB.yaml index cf63f8b437..e807be560b 100644 --- a/data/custodian/CZ-32-ZIH-L-MKB.yaml +++ b/data/custodian/CZ-32-ZIH-L-MKB.yaml @@ -41,13 +41,13 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-32-ZIH-L-MKB - valid_from: "2025-12-10T09:47:09Z" + valid_from: '2025-12-10T09:47:09Z' valid_to: null - reason: "Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ - ghcid: CZ-PL-ZIH-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:09Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PL-ZIH-L-MKB ghcid_numeric: 16283855960286343421 valid_from: '2025-12-06T23:37:31.348460+00:00' @@ -210,3 +210,28 @@ location: postal_code: 342 01 street_address: Bílenice 90 normalization_timestamp: '2025-12-09T10:53:53.043962+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:58:07.341166+00:00' + source_url: https://www.bilenice.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://duyn491kcolsw.cloudfront.net/files/2d/2di/2div3h.svg?ph=a8ced822e1 + source_url: https://www.bilenice.knihovna.cz + css_selector: '[document] > html.js.sizes > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T11:58:07.341166+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + - claim_type: og_image_url + claim_value: https://a8ced822e1.clvaw-cdnwnd.com/ef92da32ecee295ce657367e5f7354e9/200000000-e8fb4e8fb6/700/bodegones-1081331_960_720.jpg?ph=a8ced822e1 + source_url: https://www.bilenice.knihovna.cz + css_selector: '[document] > html.js.sizes > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-24T11:58:07.341166+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-32-ZIH-L-MKR.yaml b/data/custodian/CZ-32-ZIH-L-MKR.yaml index ab6ac30bb0..a3dc399ab2 100644 --- a/data/custodian/CZ-32-ZIH-L-MKR.yaml +++ b/data/custodian/CZ-32-ZIH-L-MKR.yaml @@ -41,13 +41,13 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-32-ZIH-L-MKR - valid_from: "2025-12-10T09:47:09Z" + valid_from: '2025-12-10T09:47:09Z' valid_to: null - reason: "Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ - ghcid: CZ-PL-ZIH-L-MKR valid_from: null - valid_to: "2025-12-10T09:47:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:09Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PL-ZIH-L-MKR ghcid_numeric: 3261466093079614262 valid_from: '2025-12-06T23:37:31.344737+00:00' @@ -210,3 +210,22 @@ location: postal_code: 342 01 street_address: Rozsedly 3 normalization_timestamp: '2025-12-09T10:53:53.073771+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:58:14.219458+00:00' + source_url: https://www.zihobce.eu/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zihobce.eu/skins/zihobce_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.zihobce.eu/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T11:58:14.219458+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-32-ZIH-L-OKZ.yaml b/data/custodian/CZ-32-ZIH-L-OKZ.yaml index e174e685ad..5a8eabc0fc 100644 --- a/data/custodian/CZ-32-ZIH-L-OKZ.yaml +++ b/data/custodian/CZ-32-ZIH-L-OKZ.yaml @@ -40,13 +40,13 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-32-ZIH-L-OKZ - valid_from: "2025-12-10T09:47:09Z" + valid_from: '2025-12-10T09:47:09Z' valid_to: null - reason: "Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ - ghcid: CZ-PL-ZIH-L-OKZ valid_from: null - valid_to: "2025-12-10T09:47:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:09Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PL-ZIH-L-OKZ ghcid_numeric: 1623851948236937450 valid_from: '2025-12-08T11:21:24.429319+00:00' @@ -222,3 +222,22 @@ location: country: *id006 postal_code: 331 65 normalization_timestamp: '2025-12-09T10:53:53.126657+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:58:21.953997+00:00' + source_url: https://plk.tritius.cz/library/zihle + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://plk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://plk.tritius.cz/library/zihle + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T11:58:21.953997+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-32-ZRU-L-MKZS.yaml b/data/custodian/CZ-32-ZRU-L-MKZS.yaml index 0b25c56d52..8f64393724 100644 --- a/data/custodian/CZ-32-ZRU-L-MKZS.yaml +++ b/data/custodian/CZ-32-ZRU-L-MKZS.yaml @@ -39,13 +39,13 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-32-ZRU-L-MKZS - valid_from: "2025-12-10T09:47:09Z" + valid_from: '2025-12-10T09:47:09Z' valid_to: null - reason: "Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PL to CZ-32 (Plzeň (Plzeňský)) per ISO 3166-2:CZ - ghcid: CZ-PL-ZRU-L-MKZS valid_from: null - valid_to: "2025-12-10T09:47:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:09Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PL-ZRU-L-MKZS ghcid_numeric: 6477272734731577176 valid_from: '2025-12-06T23:37:22.888890+00:00' @@ -104,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Místní knihovna Zruč-Senec @@ -220,3 +220,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:15.020607+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Zruč +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:58:28.154356+00:00' + source_url: https://www.zruc-senec.cz/organizace-v-obci/mistni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zruc-senec.cz/skins/zruc-senec.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.zruc-senec.cz/organizace-v-obci/mistni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T11:58:28.154356+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-41-BOC-L-MKIB.yaml b/data/custodian/CZ-41-BOC-L-MKIB.yaml index 30e7191be5..f4160f0070 100644 --- a/data/custodian/CZ-41-BOC-L-MKIB.yaml +++ b/data/custodian/CZ-41-BOC-L-MKIB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-BOC-L-MKIB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-BOC-L-MKIB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-BOC-L-MKIB ghcid_numeric: 14233958537733726811 valid_from: '2025-12-06T23:37:18.421411+00:00' @@ -215,3 +216,22 @@ location: postal_code: 364 71 street_address: Obuvnická 59 normalization_timestamp: '2025-12-09T10:52:54.928876+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:58:49.886354+00:00' + source_url: https://bochov.tritius.cz/?device=-1 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bochov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://bochov.tritius.cz/?device=-1 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T11:58:49.886354+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-BUK-L-MKVB.yaml b/data/custodian/CZ-41-BUK-L-MKVB.yaml index ef4033c7ca..7ec1586b1a 100644 --- a/data/custodian/CZ-41-BUK-L-MKVB.yaml +++ b/data/custodian/CZ-41-BUK-L-MKVB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-BUK-L-MKVB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-BUK-L-MKVB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-BUK-L-MKVB ghcid_numeric: 10444076842830960374 valid_from: '2025-12-06T23:37:40.005670+00:00' @@ -209,3 +210,22 @@ location: postal_code: 357 55 street_address: Bukovany čp. 145 normalization_timestamp: '2025-12-09T10:52:55.081090+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:59:18.543525+00:00' + source_url: https://bukovany-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bukovany-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://bukovany-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T11:59:18.543525+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-CHE-A-SOAC.yaml b/data/custodian/CZ-41-CHE-A-SOAC.yaml index 8050f6cfb9..02ea8defdc 100644 --- a/data/custodian/CZ-41-CHE-A-SOAC.yaml +++ b/data/custodian/CZ-41-CHE-A-SOAC.yaml @@ -252,3 +252,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Cheb official youtube_search_timestamp: '2025-12-09T09:31:01.888149+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:59:26.302286+00:00' + source_url: http://www.soaplzen.cz/soka-ch + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.soaplzen.cz/sites/default/files/easybreeze_favicon.ico + source_url: http://www.soaplzen.cz/soka-ch + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-24T11:59:26.302286+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-CHE-E-ZSCK.yaml b/data/custodian/CZ-41-CHE-E-ZSCK.yaml index 815a9a70bd..6eb5e3e244 100644 --- a/data/custodian/CZ-41-CHE-E-ZSCK.yaml +++ b/data/custodian/CZ-41-CHE-E-ZSCK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-CHE-E-ZSCK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-CHE-E-ZSCK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-CHE-E-ZSCK ghcid_numeric: 13076043673706031284 valid_from: '2025-12-08T11:21:31.942765+00:00' @@ -218,3 +219,22 @@ location: postal_code: 350 02 street_address: Obětí nacismu 16 normalization_timestamp: '2025-12-09T10:52:55.106628+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:59:33.080489+00:00' + source_url: https://www.6zscheb.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.6zscheb.cz/skins/6zscheb/favicons/safari-pinned-tab.svg + source_url: https://www.6zscheb.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T11:59:33.080489+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-41-CHE-L-OKVM-obecni_knihovna_v_milhostove.yaml b/data/custodian/CZ-41-CHE-L-OKVM-obecni_knihovna_v_milhostove.yaml index bf2b31b5d3..4ce3bcc7e9 100644 --- a/data/custodian/CZ-41-CHE-L-OKVM-obecni_knihovna_v_milhostove.yaml +++ b/data/custodian/CZ-41-CHE-L-OKVM-obecni_knihovna_v_milhostove.yaml @@ -209,3 +209,30 @@ location: postal_code: 350 02 street_address: Milhostov normalization_timestamp: '2025-12-09T10:52:55.214222+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:59:49.862781+00:00' + source_url: https://knihovnamilhostov.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnamilhostov.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnamilhostov.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T11:59:49.862781+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnamilhostov.webk.cz/themes/new/favicon.ico + source_url: https://knihovnamilhostov.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T11:59:49.862781+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-CHE-L-OKVM.yaml b/data/custodian/CZ-41-CHE-L-OKVM.yaml index e7f3d6654f..a48292becf 100644 --- a/data/custodian/CZ-41-CHE-L-OKVM.yaml +++ b/data/custodian/CZ-41-CHE-L-OKVM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-CHE-L-OKVM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-CHE-L-OKVM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-CHE-L-OKVM ghcid_numeric: 10047184037328461444 valid_from: '2025-12-06T23:37:39.785346+00:00' @@ -210,3 +211,30 @@ location: postal_code: 350 02 street_address: Milíkov 1 normalization_timestamp: '2025-12-09T10:52:55.240096+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:59:55.223551+00:00' + source_url: https://milikov.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://milikov.webk.cz/themes/new/blue/logo3.png + source_url: https://milikov.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T11:59:55.223551+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://milikov.webk.cz/themes/new/favicon.ico + source_url: https://milikov.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T11:59:55.223551+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-CHE-L-OKVN.yaml b/data/custodian/CZ-41-CHE-L-OKVN.yaml index f1fedf5048..d743915fd4 100644 --- a/data/custodian/CZ-41-CHE-L-OKVN.yaml +++ b/data/custodian/CZ-41-CHE-L-OKVN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-CHE-L-OKVN - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-CHE-L-OKVN valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-CHE-L-OKVN ghcid_numeric: 13828631244571463443 valid_from: '2025-12-06T23:37:39.794516+00:00' @@ -209,3 +210,30 @@ location: postal_code: 350 02 street_address: Nebanice 7 normalization_timestamp: '2025-12-09T10:52:55.272050+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:00:00.472104+00:00' + source_url: https://knihovnanebanice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnanebanice.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnanebanice.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:00:00.472104+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnanebanice.webk.cz/themes/new/favicon.ico + source_url: https://knihovnanebanice.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:00:00.472104+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-CHE-L-OKVT.yaml b/data/custodian/CZ-41-CHE-L-OKVT.yaml index f30a1461a7..d2f05a6e6b 100644 --- a/data/custodian/CZ-41-CHE-L-OKVT.yaml +++ b/data/custodian/CZ-41-CHE-L-OKVT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-CHE-L-OKVT - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-CHE-L-OKVT valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-CHE-L-OKVT ghcid_numeric: 6058768339673545373 valid_from: '2025-12-06T23:37:39.806414+00:00' @@ -208,3 +209,30 @@ location: postal_code: 350 02 street_address: Tuřany 7 normalization_timestamp: '2025-12-09T10:52:55.307645+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:00:05.855693+00:00' + source_url: https://knihovnaturany.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaturany.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnaturany.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:00:05.855693+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnaturany.webk.cz/themes/new/favicon.ico + source_url: https://knihovnaturany.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:00:05.855693+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-CHE-M-MCPOKKK.yaml b/data/custodian/CZ-41-CHE-M-MCPOKKK.yaml index b95ea2b1a3..d7d2fe0d2a 100644 --- a/data/custodian/CZ-41-CHE-M-MCPOKKK.yaml +++ b/data/custodian/CZ-41-CHE-M-MCPOKKK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-CHE-M-MCPOKKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-CHE-M-MCPOKKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-CHE-M-MCPOKKK ghcid_numeric: 16011353303040767542 valid_from: '2025-12-06T23:37:17.262819+00:00' @@ -214,3 +215,32 @@ location: postal_code: 350 11 street_address: náměstí Krále Jiřího z Poděbrad 493/4 normalization_timestamp: '2025-12-09T10:52:55.332244+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:00:14.059999+00:00' + source_url: https://knihovna.muzeumcheb.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovna.muzeumcheb.cz/custom/design/logoChebWide.png + source_url: https://knihovna.muzeumcheb.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > div > img' + retrieved_on: '2025-12-24T12:00:14.059999+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Muzeum Cheb + - claim_type: favicon_url + claim_value: https://knihovna.muzeumcheb.cz/favicon.png?v=2.3.0-32021 + source_url: https://knihovna.muzeumcheb.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:00:14.059999+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-CIT-L-MKC.yaml b/data/custodian/CZ-41-CIT-L-MKC.yaml index e3e25119f9..4010601f6a 100644 --- a/data/custodian/CZ-41-CIT-L-MKC.yaml +++ b/data/custodian/CZ-41-CIT-L-MKC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-CIT-L-MKC - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-CIT-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-CIT-L-MKC ghcid_numeric: 10557273152922197677 valid_from: '2025-12-06T23:37:39.974687+00:00' @@ -208,3 +209,22 @@ location: postal_code: 357 56 street_address: Citice 117 normalization_timestamp: '2025-12-09T10:52:55.424179+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:00:30.463041+00:00' + source_url: https://citice-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://citice-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://citice-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:00:30.463041+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-DOL-L-OKVDZ.yaml b/data/custodian/CZ-41-DOL-L-OKVDZ.yaml index b750be7306..7b9f14d9a6 100644 --- a/data/custodian/CZ-41-DOL-L-OKVDZ.yaml +++ b/data/custodian/CZ-41-DOL-L-OKVDZ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-DOL-L-OKVDZ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-DOL-L-OKVDZ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-DOL-L-OKVDZ ghcid_numeric: 16712015152975099595 valid_from: '2025-12-08T11:21:40.511686+00:00' @@ -213,3 +214,30 @@ location: postal_code: 354 97 street_address: Dolní Žandov 37 normalization_timestamp: '2025-12-09T10:52:55.473401+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:00:40.041670+00:00' + source_url: https://knihovnadolnizandov.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnadolnizandov.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnadolnizandov.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:00:40.041670+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnadolnizandov.webk.cz/themes/new/favicon.ico + source_url: https://knihovnadolnizandov.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:00:40.041670+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-FRA-L-MKFL.yaml b/data/custodian/CZ-41-FRA-L-MKFL.yaml index 26b74904cb..bb3b345053 100644 --- a/data/custodian/CZ-41-FRA-L-MKFL.yaml +++ b/data/custodian/CZ-41-FRA-L-MKFL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-FRA-L-MKFL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-FRA-L-MKFL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-FRA-L-MKFL ghcid_numeric: 8266602804460372178 valid_from: '2025-12-06T23:37:17.272275+00:00' @@ -219,3 +220,22 @@ location: postal_code: 351 01 street_address: Dlouhá 181/6 normalization_timestamp: '2025-12-09T10:52:55.499118+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:00:48.827543+00:00' + source_url: https://knihovnafl.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovnafl.tritius.cz/apple-touch-icon-180x180.png + source_url: https://knihovnafl.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:00:48.827543+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-HAB-L-MKSHPO.yaml b/data/custodian/CZ-41-HAB-L-MKSHPO.yaml index 5cb9ea03ac..bf75772f9c 100644 --- a/data/custodian/CZ-41-HAB-L-MKSHPO.yaml +++ b/data/custodian/CZ-41-HAB-L-MKSHPO.yaml @@ -229,3 +229,22 @@ location: postal_code: 357 09 street_address: Národní 400 normalization_timestamp: '2025-12-09T10:52:55.529750+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:00:54.380930+00:00' + source_url: https://www.mks-habartov.cz/knihovna/d-1098/p1=60 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mks-habartov.cz/html/images/favicon.ico + source_url: https://www.mks-habartov.cz/knihovna/d-1098/p1=60 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:00:54.380930+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-HAZ-L-OKH.yaml b/data/custodian/CZ-41-HAZ-L-OKH.yaml index 0705577c2d..5c2be58220 100644 --- a/data/custodian/CZ-41-HAZ-L-OKH.yaml +++ b/data/custodian/CZ-41-HAZ-L-OKH.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-HAZ-L-OKH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-HAZ-L-OKH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-HAZ-L-OKH ghcid_numeric: 9252879300870828780 valid_from: '2025-12-06T23:37:17.253828+00:00' @@ -216,3 +217,30 @@ location: country: *id005 postal_code: 351 32 normalization_timestamp: '2025-12-09T10:52:55.579473+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:01:00.140674+00:00' + source_url: https://www.knihovna-hazlov.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.knihovna-hazlov.cz/skins/knihovnahazlov_g3/images/logo.png + source_url: https://www.knihovna-hazlov.cz + css_selector: '#header > a.logo > img' + retrieved_on: '2025-12-24T12:01:00.140674+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Knihovna Hazlov + - claim_type: favicon_url + claim_value: https://www.knihovna-hazlov.cz/skins/knihovnahazlov_g3/favicons/safari-pinned-tab.svg + source_url: https://www.knihovna-hazlov.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:01:00.140674+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-41-HOR-L-MKSVHSMK.yaml b/data/custodian/CZ-41-HOR-L-MKSVHSMK.yaml index 89976c50f6..fc1a72f2fa 100644 --- a/data/custodian/CZ-41-HOR-L-MKSVHSMK.yaml +++ b/data/custodian/CZ-41-HOR-L-MKSVHSMK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-HOR-L-MKSVHSMK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-HOR-L-MKSVHSMK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-HOR-L-MKSVHSMK ghcid_numeric: 1716585593685681020 valid_from: '2025-12-06T23:37:24.683331+00:00' @@ -212,3 +213,28 @@ location: postal_code: 357 31 street_address: Dlouhá 717 normalization_timestamp: '2025-12-09T10:52:55.605128+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:01:09.500592+00:00' + source_url: https://www.hornislavkov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hornislavkov.cz/skins/hornislavkov.cz_lego3/favicons/safari-pinned-tab.svg + source_url: https://www.hornislavkov.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:01:09.500592+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://scontent-vie1-1.xx.fbcdn.net/hphotos-xaf1/t31.0-8/1978520_742695335742564_1817195756_o.jpg + source_url: https://www.hornislavkov.cz + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:01:09.500592+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-41-KAR-E-SUSKSKVSK.yaml b/data/custodian/CZ-41-KAR-E-SUSKSKVSK.yaml index 969c2e59ad..5c58dec594 100644 --- a/data/custodian/CZ-41-KAR-E-SUSKSKVSK.yaml +++ b/data/custodian/CZ-41-KAR-E-SUSKSKVSK.yaml @@ -223,3 +223,37 @@ location: postal_code: 360 05 street_address: nám. 17.listopadu 12 normalization_timestamp: '2025-12-09T10:52:55.770213+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:02:06.640916+00:00' + source_url: https://supskv.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://supskv.cz/wp-content/uploads/2024/01/Logo-web-nove-2024-2.jpg + source_url: https://supskv.cz + css_selector: '#masthead > div.site-branding:nth-of-type(2) > div.container > + div.site-brand-container > div.site-logo > a > img' + retrieved_on: '2025-12-24T12:02:06.640916+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: SUPŠKV + - claim_type: favicon_url + claim_value: https://supskv.cz/wp-content/uploads/fbrfg/safari-pinned-tab.svg + source_url: https://supskv.cz + css_selector: '[document] > html > head > link:nth-of-type(33)' + retrieved_on: '2025-12-24T12:02:06.640916+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://supskv.cz/wp-content/uploads/2024/03/Profilovka-SUPSKV2.jpg + source_url: https://supskv.cz + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T12:02:06.640916+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 9 diff --git a/data/custodian/CZ-41-KAR-L-KKNSNVKVLK.yaml b/data/custodian/CZ-41-KAR-L-KKNSNVKVLK.yaml index 097a7dd342..732adeb9bc 100644 --- a/data/custodian/CZ-41-KAR-L-KKNSNVKVLK.yaml +++ b/data/custodian/CZ-41-KAR-L-KKNSNVKVLK.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KAR-L-KKNSNVKVLK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KAR-L-KKNSNVKVLK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KAR-L-KKNSNVKVLK ghcid_numeric: 15163751149896773497 valid_from: '2025-12-06T23:37:18.347395+00:00' @@ -220,3 +221,22 @@ location: postal_code: 360 01 street_address: Bezručova 1190/19 normalization_timestamp: '2025-12-09T10:52:55.823037+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:02:16.062849+00:00' + source_url: https://kkn.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kkn.cz/templates/kkn/img/favicon.ico + source_url: https://kkn.cz + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:02:16.062849+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-KAR-L-MKKV.yaml b/data/custodian/CZ-41-KAR-L-MKKV.yaml index fff28295fa..3e7b241425 100644 --- a/data/custodian/CZ-41-KAR-L-MKKV.yaml +++ b/data/custodian/CZ-41-KAR-L-MKKV.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KAR-L-MKKV - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KAR-L-MKKV valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KAR-L-MKKV ghcid_numeric: 3526171183681722284 valid_from: '2025-12-06T23:37:26.233603+00:00' @@ -245,3 +246,28 @@ location: postal_code: 360 01 street_address: I.P. Pavlova 7 normalization_timestamp: '2025-12-09T10:52:55.872139+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:02:25.489292+00:00' + source_url: https://mestskaknihovnakv.cz/katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mestskaknihovnakv.cz/themes/mkkv/favicons/safari-pinned-tab.svg + source_url: https://mestskaknihovnakv.cz/katalog + css_selector: '[document] > html.js.js > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T12:02:25.489292+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mestskaknihovnakv.cz/sites/default/files/obrazky/mkkv.jpg + source_url: https://mestskaknihovnakv.cz/katalog + css_selector: '[document] > html.js.js > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T12:02:25.489292+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-41-KAR-L-VSFSSSSKVK.yaml b/data/custodian/CZ-41-KAR-L-VSFSSSSKVK.yaml index 1e153afed4..45711ad9a4 100644 --- a/data/custodian/CZ-41-KAR-L-VSFSSSSKVK.yaml +++ b/data/custodian/CZ-41-KAR-L-VSFSSSSKVK.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KAR-L-VSFSSSSKVK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KAR-L-VSFSSSSKVK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KAR-L-VSFSSSSKVK ghcid_numeric: 12494588424640715797 valid_from: '2025-12-08T11:21:32.513015+00:00' @@ -221,3 +222,28 @@ location: postal_code: 360 01 street_address: T.G. Masaryka 541/3 normalization_timestamp: '2025-12-09T10:52:55.936390+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:02:34.627921+00:00' + source_url: https://www.vsfs.cz/?id=1875-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vsfs.cz/2017/obsah/images/favicon.ico + source_url: https://www.vsfs.cz/?id=1875-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:02:34.627921+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.vsfs.cz/2017/obsah/images/vsfs_logo_fb.png + source_url: https://www.vsfs.cz/?id=1875-knihovna + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T12:02:34.627921+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-41-KAR-M-MKVPKKK.yaml b/data/custodian/CZ-41-KAR-M-MKVPKKK.yaml index 88052643d1..58e1bb4f41 100644 --- a/data/custodian/CZ-41-KAR-M-MKVPKKK.yaml +++ b/data/custodian/CZ-41-KAR-M-MKVPKKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KAR-M-MKVPKKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KAR-M-MKVPKKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KAR-M-MKVPKKK ghcid_numeric: 1534023288790012143 valid_from: '2025-12-06T23:37:24.590182+00:00' @@ -211,3 +212,32 @@ location: postal_code: 360 01 street_address: Pod Jelením skokem 393/30 normalization_timestamp: '2025-12-09T10:52:56.009027+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:02:45.048516+00:00' + source_url: https://kvmuz.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://kvmuz.cz/wp-content/uploads/2024/04/kvmuz_logo.png + source_url: https://kvmuz.cz + css_selector: '#masthead > div.elementor.elementor-12701 > div.elementor-element.elementor-element-edd313e + > div.e-con-inner > div.elementor-element.elementor-element-ef7d642 > div.elementor-element.elementor-element-fa6c22a + > div.elementor-widget-container > img.attachment-large.size-large' + retrieved_on: '2025-12-24T12:02:45.048516+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://kvmuz.cz/wp-content/uploads/2024/04/cropped-kvmuz_logo_notext-180x180.png + source_url: https://kvmuz.cz + css_selector: '[document] > html > head > link:nth-of-type(39)' + retrieved_on: '2025-12-24T12:02:45.048516+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-41-KAV-A-SOAKV.yaml b/data/custodian/CZ-41-KAV-A-SOAKV.yaml index ba55a4589b..c44b2e0059 100644 --- a/data/custodian/CZ-41-KAV-A-SOAKV.yaml +++ b/data/custodian/CZ-41-KAV-A-SOAKV.yaml @@ -266,3 +266,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Karlovy Vary official youtube_search_timestamp: '2025-12-09T09:31:06.515441+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:02:53.885625+00:00' + source_url: http://www.soaplzen.cz/soka-kv + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.soaplzen.cz/sites/default/files/easybreeze_favicon.ico + source_url: http://www.soaplzen.cz/soka-kv + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-24T12:02:53.885625+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-KAV-G-GUKV.yaml b/data/custodian/CZ-41-KAV-G-GUKV.yaml index 0781031be7..90cbcff228 100644 --- a/data/custodian/CZ-41-KAV-G-GUKV.yaml +++ b/data/custodian/CZ-41-KAV-G-GUKV.yaml @@ -39,10 +39,11 @@ ghcid: city_label: Karlovy Vary geonames_id: 3073803 ghcid_history: - - previous_ghcid_component: "KV" - new_ghcid_component: "KAV" - change_date: "2025-12-20T19:55:24Z" - reason: "Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Karlovy Vary" + - previous_ghcid_component: KV + new_ghcid_component: KAV + change_date: '2025-12-20T19:55:24Z' + reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: + Karlovy Vary' - ghcid: XX-XX-XXX-G-GUKV ghcid_numeric: 16110237952048732650 valid_from: '2025-12-06T23:37:44.558294+00:00' @@ -84,7 +85,8 @@ provenance: notes: - 'Country resolved 2025-12-06T23:54:40Z: XX→CZ via Wikidata P17' - 'Region resolved 2025-12-07T00:01:14Z: XX->41 via Wikidata P131 (CZ-41)' - - 'City resolved 2025-12-07T00:28:27Z: XXX->KV via Wikidata Q8502288 coords (50.2306,12.8725) -> Karlovy Vary (GeoNames:3073803)' + - 'City resolved 2025-12-07T00:28:27Z: XXX->KV via Wikidata Q8502288 coords (50.2306,12.8725) + -> Karlovy Vary (GeoNames:3073803)' - Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:12Z - Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:35Z - 'YouTube/Google Maps enrichment 2025-12-09T09:31:07Z: YouTube: not found' @@ -115,8 +117,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.85 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Galerie umění, Karlovy Vary @@ -209,11 +211,12 @@ wikidata_enrichment: instance_of: &id005 - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance - id: Q2085381 label: publishing company - description: company that prints and distributes pressed goods or electronic media + description: company that prints and distributes pressed goods or electronic + media wikidata_instance_of: *id005 wikidata_location: located_in_admin_entity: &id006 @@ -265,3 +268,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Galerie umění, Karlovy Vary official youtube_search_timestamp: '2025-12-09T09:31:07.203887+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:02:59.322656+00:00' + source_url: http://www.galeriekvary.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.galeriekvary.cz/wp-content/uploads/logo/logo_GU_barva_zare.png + source_url: http://www.galeriekvary.cz + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(38)' + retrieved_on: '2025-12-24T12:02:59.322656+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-41-KRA-L-MKJ.yaml b/data/custodian/CZ-41-KRA-L-MKJ.yaml index 9e090e1f39..e7123da30b 100644 --- a/data/custodian/CZ-41-KRA-L-MKJ.yaml +++ b/data/custodian/CZ-41-KRA-L-MKJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KRA-L-MKJ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KRA-L-MKJ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KRA-L-MKJ ghcid_numeric: 14594163256500582256 valid_from: '2025-12-06T23:37:39.996039+00:00' @@ -208,3 +209,22 @@ location: postal_code: 358 01 street_address: Jindřichovice 232 normalization_timestamp: '2025-12-09T10:52:56.146859+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:03:18.670498+00:00' + source_url: https://jindrichovice-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jindrichovice-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://jindrichovice-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:03:18.670498+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-KRA-L-MKK-mistni_knihovna_krajkova.yaml b/data/custodian/CZ-41-KRA-L-MKK-mistni_knihovna_krajkova.yaml index 412e435d78..d349cdd951 100644 --- a/data/custodian/CZ-41-KRA-L-MKK-mistni_knihovna_krajkova.yaml +++ b/data/custodian/CZ-41-KRA-L-MKK-mistni_knihovna_krajkova.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KRA-L-MKK-mistni_knihovna_krajkova - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KRA-L-MKK-mistni_knihovna_krajkova valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KRA-L-MKK-mistni_knihovna_krajkova ghcid_numeric: 10538484479138625415 valid_from: '2025-12-06T23:37:39.987343+00:00' @@ -208,3 +209,22 @@ location: postal_code: 357 08 street_address: Krajková 295 normalization_timestamp: '2025-12-09T10:52:56.174182+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:03:23.408003+00:00' + source_url: https://krajkova-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://krajkova-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://krajkova-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:03:23.408003+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-KRA-L-MKK.yaml b/data/custodian/CZ-41-KRA-L-MKK.yaml index b455a73ccb..917b800732 100644 --- a/data/custodian/CZ-41-KRA-L-MKK.yaml +++ b/data/custodian/CZ-41-KRA-L-MKK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KRA-L-MKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KRA-L-MKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KRA-L-MKK ghcid_numeric: 10626442174841393516 valid_from: '2025-12-06T23:37:39.962044+00:00' @@ -208,3 +209,22 @@ location: postal_code: 357 47 street_address: Radniční 1 normalization_timestamp: '2025-12-09T10:52:56.202097+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:03:28.107397+00:00' + source_url: https://krasno-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://krasno-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://krasno-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:03:28.107397+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-KRA-L-OKK.yaml b/data/custodian/CZ-41-KRA-L-OKK.yaml index fbce7283f2..4d053fe049 100644 --- a/data/custodian/CZ-41-KRA-L-OKK.yaml +++ b/data/custodian/CZ-41-KRA-L-OKK.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KRA-L-OKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KRA-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KRA-L-OKK ghcid_numeric: 4446425850140359831 valid_from: '2025-12-06T23:37:43.411338+00:00' @@ -104,8 +105,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Obecní knihovna Krásná @@ -210,3 +211,30 @@ location: geonames_id: 3072900 geonames_name: Krásná feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:03:37.432587+00:00' + source_url: https://knihovnakrasna.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnakrasna.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnakrasna.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:03:37.432587+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnakrasna.webk.cz/themes/new/favicon.ico + source_url: https://knihovnakrasna.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:03:37.432587+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-KRA-L-OKKP.yaml b/data/custodian/CZ-41-KRA-L-OKKP.yaml index a28a656d63..ec18705d90 100644 --- a/data/custodian/CZ-41-KRA-L-OKKP.yaml +++ b/data/custodian/CZ-41-KRA-L-OKKP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KRA-L-OKKP - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KRA-L-OKKP valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KRA-L-OKKP ghcid_numeric: 14599110197692774858 valid_from: '2025-12-06T23:37:26.424594+00:00' @@ -220,3 +221,22 @@ location: postal_code: 356 01 street_address: Lázeňská 114 normalization_timestamp: '2025-12-09T10:52:56.295933+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:03:46.128600+00:00' + source_url: https://www.knihovnakp.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovnakp.cz/img/favicon.ico + source_url: https://www.knihovnakp.cz + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T12:03:46.128600+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-KYN-L-KLU.yaml b/data/custodian/CZ-41-KYN-L-KLU.yaml index 160d8deba4..ff2a8b01dc 100644 --- a/data/custodian/CZ-41-KYN-L-KLU.yaml +++ b/data/custodian/CZ-41-KYN-L-KLU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-KYN-L-KLU - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-KYN-L-KLU valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-KYN-L-KLU ghcid_numeric: 5000551985546554346 valid_from: '2025-12-08T11:21:40.537042+00:00' @@ -210,3 +211,22 @@ location: postal_code: 357 51 street_address: Libavské Údolí 110 normalization_timestamp: '2025-12-09T10:52:56.327358+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:03:51.001699+00:00' + source_url: https://libavskeudoli-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://libavskeudoli-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://libavskeudoli-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:03:51.001699+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-LIB-L-OKVL.yaml b/data/custodian/CZ-41-LIB-L-OKVL.yaml index f8de749755..54b92147b6 100644 --- a/data/custodian/CZ-41-LIB-L-OKVL.yaml +++ b/data/custodian/CZ-41-LIB-L-OKVL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-LIB-L-OKVL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-LIB-L-OKVL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-LIB-L-OKVL ghcid_numeric: 9261206355159337495 valid_from: '2025-12-06T23:37:39.774571+00:00' @@ -214,3 +215,30 @@ location: postal_code: 351 31 street_address: Libá 99 normalization_timestamp: '2025-12-09T10:52:56.462729+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:04:40.877195+00:00' + source_url: https://knihovnaliba.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaliba.webk.cz/themes/new/blue/logo3.png + source_url: https://knihovnaliba.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:04:40.877195+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnaliba.webk.cz/themes/new/favicon.ico + source_url: https://knihovnaliba.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:04:40.877195+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-LOK-L-NPUUOPVLK.yaml b/data/custodian/CZ-41-LOK-L-NPUUOPVLK.yaml index 3b8e7ee38b..981e63948a 100644 --- a/data/custodian/CZ-41-LOK-L-NPUUOPVLK.yaml +++ b/data/custodian/CZ-41-LOK-L-NPUUOPVLK.yaml @@ -51,13 +51,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-LOK-L-NPUUOPVLK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-LOK-L-NPUUOPVLK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-LOK-L-NPUUOPVLK ghcid_numeric: 16074445015261747003 valid_from: '2025-12-08T11:21:32.368268+00:00' @@ -230,3 +231,22 @@ location: postal_code: 357 33 street_address: T. G. Masaryka 133/9 normalization_timestamp: '2025-12-09T10:52:56.492668+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:04:46.729924+00:00' + source_url: https://iispp.npu.cz/carmen/library/loket + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://iispp.npu.cz/carmen/apple-touch-icon-180x180.png + source_url: https://iispp.npu.cz/carmen/library/loket + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:04:46.729924+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-LOM-L-MKVDN.yaml b/data/custodian/CZ-41-LOM-L-MKVDN.yaml index 261c05717d..22630a2604 100644 --- a/data/custodian/CZ-41-LOM-L-MKVDN.yaml +++ b/data/custodian/CZ-41-LOM-L-MKVDN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-LOM-L-MKVDN - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-LOM-L-MKVDN valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-LOM-L-MKVDN ghcid_numeric: 17334631763734310775 valid_from: '2025-12-06T23:37:39.980819+00:00' @@ -208,3 +209,22 @@ location: postal_code: 357 04 street_address: Dolní Nivy 75 normalization_timestamp: '2025-12-09T10:52:56.525320+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:04:51.517920+00:00' + source_url: https://dolninivy-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://dolninivy-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://dolninivy-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:04:51.517920+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-LOM-L-OKL.yaml b/data/custodian/CZ-41-LOM-L-OKL.yaml index 45bb483e51..292b13a39b 100644 --- a/data/custodian/CZ-41-LOM-L-OKL.yaml +++ b/data/custodian/CZ-41-LOM-L-OKL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-LOM-L-OKL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-LOM-L-OKL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-LOM-L-OKL ghcid_numeric: 12445493509132731903 valid_from: '2025-12-06T23:37:27.339840+00:00' @@ -216,3 +217,22 @@ location: postal_code: '35601' street_address: Kraslická 44 normalization_timestamp: '2025-12-09T10:52:56.545103+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:04:56.518947+00:00' + source_url: https://katalog.obeclomnice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.obeclomnice.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.obeclomnice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:04:56.518947+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-MAR-L-MKML.yaml b/data/custodian/CZ-41-MAR-L-MKML.yaml index 50bae3f80e..af0b4a66ed 100644 --- a/data/custodian/CZ-41-MAR-L-MKML.yaml +++ b/data/custodian/CZ-41-MAR-L-MKML.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-MAR-L-MKML - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-MAR-L-MKML valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-MAR-L-MKML ghcid_numeric: 10498622330552758260 valid_from: '2025-12-06T23:37:17.285177+00:00' @@ -236,3 +237,22 @@ location: postal_code: 353 01 street_address: Hlavní 370/3 normalization_timestamp: '2025-12-09T10:52:56.636064+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:15.559432+00:00' + source_url: https://knihovnaml.tritius.cz/?device=2 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovnaml.tritius.cz/apple-touch-icon-180x180.png + source_url: https://knihovnaml.tritius.cz/?device=2 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:05:15.559432+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-MAR-L-OKVD.yaml b/data/custodian/CZ-41-MAR-L-OKVD.yaml index bc245c2084..b181af5bdb 100644 --- a/data/custodian/CZ-41-MAR-L-OKVD.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVD.yaml @@ -213,3 +213,30 @@ location: postal_code: 354 72 Drmoul street_address: Plzeňská 237 normalization_timestamp: '2025-12-09T10:52:56.680328+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:20.195452+00:00' + source_url: https://drmoul.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://drmoul.webk.cz/themes/new/green/logo1.png + source_url: https://drmoul.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:05:20.195452+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://drmoul.webk.cz/themes/new/favicon.ico + source_url: https://drmoul.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:05:20.195452+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-MAR-L-OKVM.yaml b/data/custodian/CZ-41-MAR-L-OKVM.yaml index 4985cdc546..0ab93a3742 100644 --- a/data/custodian/CZ-41-MAR-L-OKVM.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-MAR-L-OKVM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-MAR-L-OKVM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-MAR-L-OKVM ghcid_numeric: 923151983077473699 valid_from: '2025-12-06T23:37:39.788414+00:00' @@ -208,3 +209,30 @@ location: postal_code: 353 01 street_address: Mnichov 1 normalization_timestamp: '2025-12-09T10:52:56.712512+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:24.814553+00:00' + source_url: https://knihovnamnichov.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnamnichov.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnamnichov.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:05:24.814553+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnamnichov.webk.cz/themes/new/favicon.ico + source_url: https://knihovnamnichov.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:05:24.814553+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-MAR-L-OKVOK.yaml b/data/custodian/CZ-41-MAR-L-OKVOK.yaml index 69a6e83906..b6856c0e7b 100644 --- a/data/custodian/CZ-41-MAR-L-OKVOK.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVOK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-MAR-L-OKVOK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-MAR-L-OKVOK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-MAR-L-OKVOK ghcid_numeric: 3371073348008286726 valid_from: '2025-12-06T23:37:39.830481+00:00' @@ -212,3 +213,30 @@ location: postal_code: 353 01 street_address: Ovesné Kladruby 17 normalization_timestamp: '2025-12-09T10:52:56.737159+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:29.469280+00:00' + source_url: https://knihovnaovesnekladruby.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaovesnekladruby.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnaovesnekladruby.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:05:29.469280+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnaovesnekladruby.webk.cz/themes/new/favicon.ico + source_url: https://knihovnaovesnekladruby.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:05:29.469280+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-MAR-L-OKVP-obecni_knihovna_v_podlesi.yaml b/data/custodian/CZ-41-MAR-L-OKVP-obecni_knihovna_v_podlesi.yaml index 5ef92619e6..ce7543e777 100644 --- a/data/custodian/CZ-41-MAR-L-OKVP-obecni_knihovna_v_podlesi.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVP-obecni_knihovna_v_podlesi.yaml @@ -201,3 +201,22 @@ location: postal_code: 353 01 street_address: Podlesí normalization_timestamp: '2025-12-09T10:52:56.768279+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:37.240031+00:00' + source_url: http://www.dolnizandov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.dolnizandov.cz/skins/dolnizandov.cz_lego2/favicons/safari-pinned-tab.svg + source_url: http://www.dolnizandov.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:05:37.240031+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-41-MAR-L-OKVP.yaml b/data/custodian/CZ-41-MAR-L-OKVP.yaml index 00ea7f5bac..424f9e1391 100644 --- a/data/custodian/CZ-41-MAR-L-OKVP.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVP.yaml @@ -206,3 +206,22 @@ location: postal_code: 353 01 street_address: Prameny normalization_timestamp: '2025-12-09T10:52:56.797539+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:42.837718+00:00' + source_url: https://www.krnany.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.krnany.cz/skins/krnany.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.krnany.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:05:42.837718+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-41-MAR-L-OKVT.yaml b/data/custodian/CZ-41-MAR-L-OKVT.yaml index a5eabb512b..97b963a6c1 100644 --- a/data/custodian/CZ-41-MAR-L-OKVT.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-MAR-L-OKVT - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-MAR-L-OKVT valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-MAR-L-OKVT ghcid_numeric: 8272060371003774699 valid_from: '2025-12-06T23:37:39.815299+00:00' @@ -208,3 +209,30 @@ location: postal_code: 353 01 street_address: Trstěnice 85 normalization_timestamp: '2025-12-09T10:52:56.823880+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:47.460590+00:00' + source_url: https://knihovnatrstenice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnatrstenice.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnatrstenice.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:05:47.460590+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnatrstenice.webk.cz/themes/new/favicon.ico + source_url: https://knihovnatrstenice.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:05:47.460590+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-MAR-L-OKVTS.yaml b/data/custodian/CZ-41-MAR-L-OKVTS.yaml index 8a65607e4d..7542e31761 100644 --- a/data/custodian/CZ-41-MAR-L-OKVTS.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVTS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-MAR-L-OKVTS - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-MAR-L-OKVTS valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-MAR-L-OKVTS ghcid_numeric: 709447339837473746 valid_from: '2025-12-06T23:37:39.818486+00:00' @@ -208,3 +209,30 @@ location: postal_code: 353 01 street_address: Tři Sekery 82 normalization_timestamp: '2025-12-09T10:52:56.857920+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:54.711780+00:00' + source_url: https://knihovnatrisekery.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnatrisekery.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnatrisekery.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:05:54.711780+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnatrisekery.webk.cz/themes/new/favicon.ico + source_url: https://knihovnatrisekery.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:05:54.711780+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich.yaml b/data/custodian/CZ-41-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich.yaml index e812adf8f9..72c0148167 100644 --- a/data/custodian/CZ-41-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich.yaml +++ b/data/custodian/CZ-41-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-MAR-L-OKVV-obecni_knihovna_ve_vlkovicich ghcid_numeric: 5367093988281281737 valid_from: '2025-12-06T23:37:39.824765+00:00' @@ -208,3 +209,30 @@ location: postal_code: 353 01 street_address: Vlkovice 21 normalization_timestamp: '2025-12-09T10:52:56.896759+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:05:59.374085+00:00' + source_url: https://knihovnavlkovice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnavlkovice.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnavlkovice.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:05:59.374085+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnavlkovice.webk.cz/themes/new/favicon.ico + source_url: https://knihovnavlkovice.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:05:59.374085+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-NEJ-L-MKN.yaml b/data/custodian/CZ-41-NEJ-L-MKN.yaml index deecb07c84..9726f5b4f5 100644 --- a/data/custodian/CZ-41-NEJ-L-MKN.yaml +++ b/data/custodian/CZ-41-NEJ-L-MKN.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-NEJ-L-MKN - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-NEJ-L-MKN valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-NEJ-L-MKN ghcid_numeric: 8794493955917396016 valid_from: '2025-12-06T23:37:18.427870+00:00' @@ -215,3 +216,22 @@ location: postal_code: 362 21 street_address: nám. Karla IV. 398 normalization_timestamp: '2025-12-09T10:52:56.957882+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:06:07.871696+00:00' + source_url: https://kvk.tritius.cz/library/nejdek + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kvk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kvk.tritius.cz/library/nejdek + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:06:07.871696+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-NOV-L-MKNR.yaml b/data/custodian/CZ-41-NOV-L-MKNR.yaml index 9c7a556958..600892bf6e 100644 --- a/data/custodian/CZ-41-NOV-L-MKNR.yaml +++ b/data/custodian/CZ-41-NOV-L-MKNR.yaml @@ -36,13 +36,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-NOV-L-MKNR - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-NOV-L-MKNR valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-NOV-L-MKNR ghcid_numeric: 16781924144377633797 valid_from: '2025-12-06T23:37:21.235148+00:00' @@ -100,8 +101,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Městská knihovna Nová Role @@ -224,3 +225,22 @@ location: geonames_id: 3069662 geonames_name: Nová Role feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:06:22.408145+00:00' + source_url: https://novarole.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://novarole.tritius.cz/apple-touch-icon-180x180.png + source_url: https://novarole.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:06:22.408145+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-NOV-L-MKNS.yaml b/data/custodian/CZ-41-NOV-L-MKNS.yaml index 2eb89cc800..ee3ae1ee14 100644 --- a/data/custodian/CZ-41-NOV-L-MKNS.yaml +++ b/data/custodian/CZ-41-NOV-L-MKNS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-NOV-L-MKNS - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-NOV-L-MKNS valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-NOV-L-MKNS ghcid_numeric: 7409214947202884513 valid_from: '2025-12-06T23:37:19.982578+00:00' @@ -251,3 +252,22 @@ location: postal_code: 357 34 street_address: Masarykova 502 normalization_timestamp: '2025-12-09T10:52:57.084677+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:06:27.423877+00:00' + source_url: https://katalog.mkns.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.mkns.cz/apple-touch-icon-180x180.png + source_url: https://katalog.mkns.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:06:27.423877+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-OLO-L-MKO.yaml b/data/custodian/CZ-41-OLO-L-MKO.yaml index 055058c801..279408d284 100644 --- a/data/custodian/CZ-41-OLO-L-MKO.yaml +++ b/data/custodian/CZ-41-OLO-L-MKO.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-OLO-L-MKO - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-OLO-L-MKO valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-OLO-L-MKO ghcid_numeric: 7802484296919865003 valid_from: '2025-12-06T23:37:39.953230+00:00' @@ -279,3 +280,22 @@ location: postal_code: 357 07 street_address: Tovární 197 normalization_timestamp: '2025-12-09T10:52:57.170747+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:06:41.269308+00:00' + source_url: https://www.olovi.cz/mestska-knihovna-olovi + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.olovi.cz/image.php?nid=13796&oid=7800446 + source_url: https://www.olovi.cz/mestska-knihovna-olovi + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T12:06:41.269308+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-OST-E-SPSOSK.yaml b/data/custodian/CZ-41-OST-E-SPSOSK.yaml index 033d167d8c..edfc2ee306 100644 --- a/data/custodian/CZ-41-OST-E-SPSOSK.yaml +++ b/data/custodian/CZ-41-OST-E-SPSOSK.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-OST-E-SPSOSK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-OST-E-SPSOSK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-OST-E-SPSOSK ghcid_numeric: 7642944697609770456 valid_from: '2025-12-08T11:21:21.199668+00:00' @@ -109,8 +110,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Střední průmyslová škola, Ostrov - Školní knihovna @@ -218,3 +219,22 @@ location: geonames_id: 3068766 geonames_name: Ostrov feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:06:47.642569+00:00' + source_url: https://spsostrov.cz/skolni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://spsostrov.cz/themes/spsostrov/favicons/safari-pinned-tab.svg + source_url: https://spsostrov.cz/skolni-knihovna + css_selector: '[document] > html.js.wf-ingra-n8-active > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:06:47.642569+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-41-OST-L-MKOPO.yaml b/data/custodian/CZ-41-OST-L-MKOPO.yaml index 22f8e24bcd..f60c5252a5 100644 --- a/data/custodian/CZ-41-OST-L-MKOPO.yaml +++ b/data/custodian/CZ-41-OST-L-MKOPO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-OST-L-MKOPO - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-OST-L-MKOPO valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-OST-L-MKOPO ghcid_numeric: 7481996434421562254 valid_from: '2025-12-06T23:37:18.416223+00:00' @@ -224,3 +225,28 @@ location: postal_code: 363 01 street_address: Zámecký park 224 normalization_timestamp: '2025-12-09T10:52:57.226148+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:06:54.058932+00:00' + source_url: https://mkostrov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mkostrov.cz/favico/apple-icon-180x180.png + source_url: https://mkostrov.cz + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-24T12:06:54.058932+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://mkostrov.cz/images/logo_opengraphv3.png + source_url: https://mkostrov.cz + css_selector: '[document] > html > head > meta:nth-of-type(19)' + retrieved_on: '2025-12-24T12:06:54.058932+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 13 diff --git a/data/custodian/CZ-41-PLE-L-MKVP.yaml b/data/custodian/CZ-41-PLE-L-MKVP.yaml index ade181bc70..f464988950 100644 --- a/data/custodian/CZ-41-PLE-L-MKVP.yaml +++ b/data/custodian/CZ-41-PLE-L-MKVP.yaml @@ -211,3 +211,22 @@ location: postal_code: 351 35 street_address: nám. Svobody 52 normalization_timestamp: '2025-12-09T10:52:57.396222+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:07:22.602610+00:00' + source_url: https://www.mestoplesna.cz/knihovna/mestska-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mestoplesna.cz/skins/plesna_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.mestoplesna.cz/knihovna/mestska-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:07:22.602610+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-41-ROV-L-MKR.yaml b/data/custodian/CZ-41-ROV-L-MKR.yaml index 2adae5ddea..a0fc3b3281 100644 --- a/data/custodian/CZ-41-ROV-L-MKR.yaml +++ b/data/custodian/CZ-41-ROV-L-MKR.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-ROV-L-MKR - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-ROV-L-MKR valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-ROV-L-MKR ghcid_numeric: 7020296734490065669 valid_from: '2025-12-06T23:37:39.999114+00:00' @@ -205,3 +206,22 @@ location: postal_code: 357 65 street_address: Rovná 35 normalization_timestamp: '2025-12-09T10:52:57.472136+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:07:34.167533+00:00' + source_url: https://rovna-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rovna-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://rovna-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:07:34.167533+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-SIN-L-MKS.yaml b/data/custodian/CZ-41-SIN-L-MKS.yaml index d476dab8a9..2aae68af98 100644 --- a/data/custodian/CZ-41-SIN-L-MKS.yaml +++ b/data/custodian/CZ-41-SIN-L-MKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-SIN-L-MKS - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-SIN-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-SIN-L-MKS ghcid_numeric: 708111447463750223 valid_from: '2025-12-08T11:21:25.168085+00:00' @@ -210,3 +211,22 @@ location: postal_code: 357 06 street_address: Šindelová 117 normalization_timestamp: '2025-12-09T10:52:57.497566+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:07:38.914821+00:00' + source_url: https://sindelova-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sindelova-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://sindelova-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:07:38.914821+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-SKA-L-OKVK.yaml b/data/custodian/CZ-41-SKA-L-OKVK.yaml index 9cfb33c007..c7488ee2a1 100644 --- a/data/custodian/CZ-41-SKA-L-OKVK.yaml +++ b/data/custodian/CZ-41-SKA-L-OKVK.yaml @@ -211,3 +211,30 @@ location: postal_code: 351 34 street_address: Křižovatka 103 normalization_timestamp: '2025-12-09T10:52:57.525244+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:07:43.541710+00:00' + source_url: https://knihovnakrizovatka.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnakrizovatka.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnakrizovatka.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:07:43.541710+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnakrizovatka.webk.cz/themes/new/favicon.ico + source_url: https://knihovnakrizovatka.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:07:43.541710+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-SKA-L-OKVNK.yaml b/data/custodian/CZ-41-SKA-L-OKVNK.yaml index 5e7556eb13..2ebbbbd6d8 100644 --- a/data/custodian/CZ-41-SKA-L-OKVNK.yaml +++ b/data/custodian/CZ-41-SKA-L-OKVNK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-SKA-L-OKVNK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-SKA-L-OKVNK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-SKA-L-OKVNK ghcid_numeric: 12767763852792053302 valid_from: '2025-12-06T23:37:39.791484+00:00' @@ -208,3 +209,30 @@ location: postal_code: 351 34 street_address: Nový Kostel 27 normalization_timestamp: '2025-12-09T10:52:57.552153+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:07:48.149521+00:00' + source_url: https://knihovnanovykostel.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnanovykostel.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnanovykostel.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T12:07:48.149521+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnanovykostel.webk.cz/themes/new/favicon.ico + source_url: https://knihovnanovykostel.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:07:48.149521+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-SOK-E-GSK.yaml b/data/custodian/CZ-41-SOK-E-GSK.yaml index 0ed2f29a2d..e3bec80e2d 100644 --- a/data/custodian/CZ-41-SOK-E-GSK.yaml +++ b/data/custodian/CZ-41-SOK-E-GSK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-SOK-E-GSK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-SOK-E-GSK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-SOK-E-GSK ghcid_numeric: 12711541841048367910 valid_from: '2025-12-06T23:37:21.345955+00:00' @@ -210,3 +211,31 @@ location: postal_code: 356 11 street_address: Husitská 2053 normalization_timestamp: '2025-12-09T10:52:57.576355+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:07:59.024794+00:00' + source_url: https://www.gymso.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.gymso.cz/wp-content/themes/gymso/images/logo.svg + source_url: https://www.gymso.cz + css_selector: '[document] > html > body.home.blog > header.main-header--homepage.main-header + > div.main-header__top-row > div.main-header__top-row__content > a > img.logo' + retrieved_on: '2025-12-24T12:07:59.024794+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.gymso.cz/wp-content/uploads/2025/10/cropped-favicon-180x180.png + source_url: https://www.gymso.cz + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T12:07:59.024794+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-41-SOK-L-SSTK.yaml b/data/custodian/CZ-41-SOK-L-SSTK.yaml index 2b30399011..213c15e3bd 100644 --- a/data/custodian/CZ-41-SOK-L-SSTK.yaml +++ b/data/custodian/CZ-41-SOK-L-SSTK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-SOK-L-SSTK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-SOK-L-SSTK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-SOK-L-SSTK ghcid_numeric: 14773621638028794981 valid_from: '2025-12-06T23:37:19.946242+00:00' @@ -211,3 +212,28 @@ location: postal_code: 356 01 street_address: Tovární 2093 normalization_timestamp: '2025-12-09T10:52:57.634479+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:08:06.054354+00:00' + source_url: https://www.synthomer.com/about-us/global-locations/sokolov-czech-republic/?utm_source=mapy.com&utm_medium=ppd&utm_content=hledani&utm_term=Tov%C3%A1rn%C3%AD%202093&utm_campaign=firmy.cz-197566 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.synthomer.com/apple-icon-180x180.png + source_url: https://www.synthomer.com/about-us/global-locations/sokolov-czech-republic/?utm_source=mapy.com&utm_medium=ppd&utm_content=hledani&utm_term=Tov%C3%A1rn%C3%AD%202093&utm_campaign=firmy.cz-197566 + css_selector: '[document] > html.no-touch.loaded > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:08:06.054354+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.synthomer.com/media/hggp3k0g/shutterstock_1922200235.jpeg + source_url: https://www.synthomer.com/about-us/global-locations/sokolov-czech-republic/?utm_source=mapy.com&utm_medium=ppd&utm_content=hledani&utm_term=Tov%C3%A1rn%C3%AD%202093&utm_campaign=firmy.cz-197566 + css_selector: '[document] > html.no-touch.loaded > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T12:08:06.054354+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 13 diff --git a/data/custodian/CZ-41-STR-L-MKS.yaml b/data/custodian/CZ-41-STR-L-MKS.yaml index cc4782d4f0..854afe6a78 100644 --- a/data/custodian/CZ-41-STR-L-MKS.yaml +++ b/data/custodian/CZ-41-STR-L-MKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-STR-L-MKS - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-STR-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-STR-L-MKS ghcid_numeric: 11970002121306332549 valid_from: '2025-12-06T23:37:39.993279+00:00' @@ -208,3 +209,22 @@ location: postal_code: 358 01 street_address: Stříbrná 670 normalization_timestamp: '2025-12-09T10:52:57.715529+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:08:19.315431+00:00' + source_url: https://stribrna-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://stribrna-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://stribrna-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:08:19.315431+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-SVA-L-MKS.yaml b/data/custodian/CZ-41-SVA-L-MKS.yaml index 19f188ffd1..224cf3b2c6 100644 --- a/data/custodian/CZ-41-SVA-L-MKS.yaml +++ b/data/custodian/CZ-41-SVA-L-MKS.yaml @@ -215,3 +215,22 @@ location: postal_code: 357 03 street_address: ČSA 247 normalization_timestamp: '2025-12-09T10:52:57.828957+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:08:33.082893+00:00' + source_url: https://svatava-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://svatava-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://svatava-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:08:33.082893+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-TEP-H-KPTHK.yaml b/data/custodian/CZ-41-TEP-H-KPTHK.yaml index 4c26aecd15..a592cc4d2b 100644 --- a/data/custodian/CZ-41-TEP-H-KPTHK.yaml +++ b/data/custodian/CZ-41-TEP-H-KPTHK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-TEP-H-KPTHK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-TEP-H-KPTHK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-TEP-H-KPTHK ghcid_numeric: 8753210883081105004 valid_from: '2025-12-06T23:37:18.364527+00:00' @@ -215,3 +216,22 @@ location: postal_code: 364 61 street_address: Klášter č.p.1 normalization_timestamp: '2025-12-09T10:52:57.910634+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:08:43.921718+00:00' + source_url: https://klastertepla.cz/klasterni-knihovna/historie-knihovny.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://klastertepla.cz/kt.ico + source_url: https://klastertepla.cz/klasterni-knihovna/historie-knihovny.html + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-24T12:08:43.921718+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-VEL-L-OKVVH.yaml b/data/custodian/CZ-41-VEL-L-OKVVH.yaml index bd1065cf95..20e2296105 100644 --- a/data/custodian/CZ-41-VEL-L-OKVVH.yaml +++ b/data/custodian/CZ-41-VEL-L-OKVVH.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-VEL-L-OKVVH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-VEL-L-OKVVH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-VEL-L-OKVVH ghcid_numeric: 1747422620357135098 valid_from: '2025-12-06T23:37:39.782361+00:00' @@ -210,3 +211,22 @@ location: postal_code: 354 71 street_address: Velká Hleďsebe normalization_timestamp: '2025-12-09T10:52:58.011315+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:09:05.782839+00:00' + source_url: https://kvc.tritius.cz/library/velka-hledsebe?device=1 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kvc.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kvc.tritius.cz/library/velka-hledsebe?device=1 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:09:05.782839+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-41-VIN-L-MKV.yaml b/data/custodian/CZ-41-VIN-L-MKV.yaml index e559e66e59..413aa7fdb7 100644 --- a/data/custodian/CZ-41-VIN-L-MKV.yaml +++ b/data/custodian/CZ-41-VIN-L-MKV.yaml @@ -213,3 +213,22 @@ location: postal_code: 357 44 street_address: Vintířov 61 normalization_timestamp: '2025-12-09T10:52:58.077841+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:09:19.805801+00:00' + source_url: https://vintirov-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vintirov-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://vintirov-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:09:19.805801+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-41-VRE-L-OKVV.yaml b/data/custodian/CZ-41-VRE-L-OKVV.yaml index 716e60bb9f..a582b524d9 100644 --- a/data/custodian/CZ-41-VRE-L-OKVV.yaml +++ b/data/custodian/CZ-41-VRE-L-OKVV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-41-VRE-L-OKVV - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KA to CZ-41 (Karlovy Vary (Karlovarský)) + per ISO 3166-2:CZ - ghcid: CZ-KA-VRE-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KA-VRE-L-OKVV ghcid_numeric: 5095545501988238189 valid_from: '2025-12-06T23:37:39.977760+00:00' @@ -212,3 +213,22 @@ location: postal_code: 357 43 street_address: Vřesová 3 normalization_timestamp: '2025-12-09T10:52:58.102812+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:09:24.540960+00:00' + source_url: https://vresova-katalog.mksokolov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vresova-katalog.mksokolov.cz/themes/root/images/vufind-favicon.ico + source_url: https://vresova-katalog.mksokolov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:09:24.540960+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ARN-L-OKA.yaml b/data/custodian/CZ-42-ARN-L-OKA.yaml index cc63fe71c7..cd5c5e63d9 100644 --- a/data/custodian/CZ-42-ARN-L-OKA.yaml +++ b/data/custodian/CZ-42-ARN-L-OKA.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ARN-L-OKA - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ARN-L-OKA valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ARN-L-OKA ghcid_numeric: 13275823119967121596 valid_from: '2025-12-06T23:37:41.190518+00:00' @@ -212,3 +213,37 @@ location: postal_code: 407 14 street_address: Arnoltice 34 normalization_timestamp: '2025-12-09T10:54:13.809820+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:09:42.935165+00:00' + source_url: http://www.ouarnoltice.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.ouarnoltice.cz/images/local/v-202510061025/znak.svg + source_url: http://www.ouarnoltice.cz + css_selector: '[document] > html.no-js > body > header.header.-home-header > div.centered.-wide + > div.header__heading-container > img.header__logo' + retrieved_on: '2025-12-24T12:09:42.935165+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Znak Arnoltice + - claim_type: favicon_url + claim_value: http://www.ouarnoltice.cz/images/local/icons/favicon.svg + source_url: http://www.ouarnoltice.cz + css_selector: '[document] > html.no-js > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:09:42.935165+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ouarnoltice.cz/images/local/v-202510061025/logo-social-networks.jpg + source_url: http://www.ouarnoltice.cz + css_selector: '[document] > html.no-js > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:09:42.935165+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-BEC-L-MKB.yaml b/data/custodian/CZ-42-BEC-L-MKB.yaml index 8e9e013ac8..5e16d5cf5e 100644 --- a/data/custodian/CZ-42-BEC-L-MKB.yaml +++ b/data/custodian/CZ-42-BEC-L-MKB.yaml @@ -206,3 +206,22 @@ location: postal_code: 411 86 street_address: Bechlín 162 normalization_timestamp: '2025-12-09T10:54:13.834722+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:09:47.833660+00:00' + source_url: https://bechlin-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bechlin-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://bechlin-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:09:47.833660+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-BIL-L-KM.yaml b/data/custodian/CZ-42-BIL-L-KM.yaml index 96f131a22c..ea01da36d5 100644 --- a/data/custodian/CZ-42-BIL-L-KM.yaml +++ b/data/custodian/CZ-42-BIL-L-KM.yaml @@ -181,3 +181,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q2326815 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:03.205378+00:00' + source_url: https://www.knihovnamerunice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovnamerunice.cz/skins/knihovnamerunice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.knihovnamerunice.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:10:03.205378+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-BIL-L-SDSK.yaml b/data/custodian/CZ-42-BIL-L-SDSK.yaml index 713487d031..e18318d84c 100644 --- a/data/custodian/CZ-42-BIL-L-SDSK.yaml +++ b/data/custodian/CZ-42-BIL-L-SDSK.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-BIL-L-SDSK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-BIL-L-SDSK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-BIL-L-SDSK ghcid_numeric: 10518492538635858722 valid_from: '2025-12-06T23:37:17.456327+00:00' @@ -218,3 +219,22 @@ location: country: *id007 postal_code: 418 01 normalization_timestamp: '2025-12-09T10:54:13.978196+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:10.575335+00:00' + source_url: https://www.sdas.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sdas.cz/src/images/favicons/apple-icon-180x180.png + source_url: https://www.sdas.cz + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:10:10.575335+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 13 diff --git a/data/custodian/CZ-42-BLS-L-OKB.yaml b/data/custodian/CZ-42-BLS-L-OKB.yaml index a35869c1e6..2a844d949d 100644 --- a/data/custodian/CZ-42-BLS-L-OKB.yaml +++ b/data/custodian/CZ-42-BLS-L-OKB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-BLS-L-OKB - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-BLS-L-OKB valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-BLS-L-OKB ghcid_numeric: 2721747066063788546 valid_from: '2025-12-06T23:37:41.548652+00:00' @@ -208,3 +209,22 @@ location: postal_code: 439 88 street_address: Nerudova 1 normalization_timestamp: '2025-12-09T10:54:14.020481+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:17.216198+00:00' + source_url: https://tritius.mekzatec.cz/library/blsany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mekzatec.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mekzatec.cz/library/blsany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:10:17.216198+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-BOL-L-OKB.yaml b/data/custodian/CZ-42-BOL-L-OKB.yaml index b7723b08c6..7d04be8c3b 100644 --- a/data/custodian/CZ-42-BOL-L-OKB.yaml +++ b/data/custodian/CZ-42-BOL-L-OKB.yaml @@ -219,3 +219,22 @@ location: postal_code: 431 21 street_address: Boleboř 57 normalization_timestamp: '2025-12-09T10:54:14.053176+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:22.800535+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/bolebor + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/bolebor + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:10:22.800535+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-BOR-L-MKB.yaml b/data/custodian/CZ-42-BOR-L-MKB.yaml index f68bb70bbd..8866798108 100644 --- a/data/custodian/CZ-42-BOR-L-MKB.yaml +++ b/data/custodian/CZ-42-BOR-L-MKB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-BOR-L-MKB - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-BOR-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-BOR-L-MKB ghcid_numeric: 9991362085365591522 valid_from: '2025-12-06T23:37:26.483578+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Místní knihovna Bořislav @@ -209,3 +210,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:12.657389+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Bořislav +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:28.985348+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/borislav + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/borislav + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:10:28.985348+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-BRE-L-MVKB.yaml b/data/custodian/CZ-42-BRE-L-MVKB.yaml index 9faba701f8..d6b78b975d 100644 --- a/data/custodian/CZ-42-BRE-L-MVKB.yaml +++ b/data/custodian/CZ-42-BRE-L-MVKB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-BRE-L-MVKB - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-BRE-L-MVKB valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-BRE-L-MVKB ghcid_numeric: 14224218243385237290 valid_from: '2025-12-06T23:37:41.254321+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 45 street_address: Štefánikova 82 normalization_timestamp: '2025-12-09T10:54:14.104010+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:34.449881+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/brezno + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/brezno + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:10:34.449881+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-BRN-L-MKB.yaml b/data/custodian/CZ-42-BRN-L-MKB.yaml index 88cb5f20c8..19bb74cf8b 100644 --- a/data/custodian/CZ-42-BRN-L-MKB.yaml +++ b/data/custodian/CZ-42-BRN-L-MKB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-BRN-L-MKB - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-BRN-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-BRN-L-MKB ghcid_numeric: 17263519821302680711 valid_from: '2025-12-06T23:37:41.354877+00:00' @@ -212,3 +213,22 @@ location: postal_code: 411 19 street_address: Brníkov 106 normalization_timestamp: '2025-12-09T10:54:14.130392+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:39.308858+00:00' + source_url: https://brnikov-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://brnikov-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://brnikov-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:10:39.308858+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-BRN-M-MMB.yaml b/data/custodian/CZ-42-BRN-M-MMB.yaml index 25a4e6c0e6..52c011fc28 100644 --- a/data/custodian/CZ-42-BRN-M-MMB.yaml +++ b/data/custodian/CZ-42-BRN-M-MMB.yaml @@ -1216,3 +1216,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/mF-wZjzHk9k/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:10:46.452294+00:00' + source_url: https://www.muzeumbrna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.muzeumbrna.cz/front/_starter/fav/safari-pinned-tab.svg + source_url: https://www.muzeumbrna.cz + css_selector: '[document] > html.show--consent > head > link:nth-of-type(13)' + retrieved_on: '2025-12-24T12:10:46.452294+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://static.viaaurea.eu//t/muzeumbrna.cz/images/9130.jpg/o-w:800|h:800|fit:crop-50-50/s-2ffdb849d4ca?_ts=1706789404 + source_url: https://www.muzeumbrna.cz + css_selector: '[document] > html.show--consent > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T12:10:46.452294+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-42-BRO-L-MKBNO.yaml b/data/custodian/CZ-42-BRO-L-MKBNO.yaml index 0914eb538b..fd7557408f 100644 --- a/data/custodian/CZ-42-BRO-L-MKBNO.yaml +++ b/data/custodian/CZ-42-BRO-L-MKBNO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-BRO-L-MKBNO - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-BRO-L-MKBNO valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-BRO-L-MKBNO ghcid_numeric: 12245727763634698787 valid_from: '2025-12-06T23:37:41.429752+00:00' @@ -208,3 +209,22 @@ location: postal_code: 411 81 street_address: Brozany nad Ohří 350 normalization_timestamp: '2025-12-09T10:54:14.155596+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:12:53.064004+00:00' + source_url: https://brozany-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://brozany-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://brozany-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:12:53.064004+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-BUD-L-MKBNO.yaml b/data/custodian/CZ-42-BUD-L-MKBNO.yaml index 98bb9136a8..0cc0adb986 100644 --- a/data/custodian/CZ-42-BUD-L-MKBNO.yaml +++ b/data/custodian/CZ-42-BUD-L-MKBNO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-BUD-L-MKBNO - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-BUD-L-MKBNO valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-BUD-L-MKBNO ghcid_numeric: 15361878527561950395 valid_from: '2025-12-06T23:37:18.601009+00:00' @@ -216,3 +217,28 @@ location: postal_code: 411 18 street_address: Školská 322 normalization_timestamp: '2025-12-09T10:54:14.178541+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:13:00.159037+00:00' + source_url: https://budyne.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://duyn491kcolsw.cloudfront.net/files/2d/2di/2div3h.svg?ph=52b12a5cea + source_url: https://budyne.knihovna.cz + css_selector: '[document] > html.js.sizes > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:13:00.159037+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + - claim_type: og_image_url + claim_value: https://52b12a5cea.clvaw-cdnwnd.com/9f7fbaf0ce8eac6131e89cd44505a07b/200000192-f04ebf04ed/700/LOGO-col.png?ph=52b12a5cea + source_url: https://budyne.knihovna.cz + css_selector: '[document] > html.js.sizes > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-24T12:13:00.159037+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-42-CES-L-MKCK.yaml b/data/custodian/CZ-42-CES-L-MKCK.yaml index c87bba8df0..e3fcbe68ca 100644 --- a/data/custodian/CZ-42-CES-L-MKCK.yaml +++ b/data/custodian/CZ-42-CES-L-MKCK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CES-L-MKCK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CES-L-MKCK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CES-L-MKCK ghcid_numeric: 13330142640920894784 valid_from: '2025-12-08T11:21:34.594561+00:00' @@ -221,3 +222,22 @@ location: postal_code: 407 21 street_address: Komenského 481 normalization_timestamp: '2025-12-09T10:54:14.283893+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:13:20.116478+00:00' + source_url: https://ckknihovna.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ckknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://ckknihovna.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:13:20.116478+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHB-L-OKVC.yaml b/data/custodian/CZ-42-CHB-L-OKVC.yaml index cc07f11e3d..1418d3d9e8 100644 --- a/data/custodian/CZ-42-CHB-L-OKVC.yaml +++ b/data/custodian/CZ-42-CHB-L-OKVC.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CHB-L-OKVC - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CHB-L-OKVC valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CHB-L-OKVC ghcid_numeric: 9406307324806480427 valid_from: '2025-12-06T23:37:41.323207+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 57 street_address: Chbany 19 normalization_timestamp: '2025-12-09T10:54:14.336966+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:01.032672+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/chbany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/chbany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:01.032672+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHO-L-CKPO.yaml b/data/custodian/CZ-42-CHO-L-CKPO.yaml index 8d0231c691..cc5a50bc96 100644 --- a/data/custodian/CZ-42-CHO-L-CKPO.yaml +++ b/data/custodian/CZ-42-CHO-L-CKPO.yaml @@ -179,3 +179,31 @@ wikidata_enrichment: instance_of: - Q2326815 located_in: Q146356 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:08.883186+00:00' + source_url: https://chomutovskaknihovna.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://chomutovskaknihovna.tritius.cz/images/comgate_logo.png + source_url: https://chomutovskaknihovna.tritius.cz + css_selector: '#footer > div.container > nav.row.hidden-print > div.col-sm-12.col-md-6 + > div.comgate-logo > span > img' + retrieved_on: '2025-12-24T12:14:08.883186+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Comgate + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:08.883186+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHO-L-OKC.yaml b/data/custodian/CZ-42-CHO-L-OKC.yaml index 8635e6cd24..6714580a62 100644 --- a/data/custodian/CZ-42-CHO-L-OKC.yaml +++ b/data/custodian/CZ-42-CHO-L-OKC.yaml @@ -215,3 +215,22 @@ location: postal_code: 417 53 street_address: Tyršova 56 normalization_timestamp: '2025-12-09T10:54:14.391149+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:17.517574+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/chotejovice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/chotejovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:17.517574+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHO-L-OKVB-obecni_knihovna_v_blatne.yaml b/data/custodian/CZ-42-CHO-L-OKVB-obecni_knihovna_v_blatne.yaml index 453fe76b9d..11122e7d20 100644 --- a/data/custodian/CZ-42-CHO-L-OKVB-obecni_knihovna_v_blatne.yaml +++ b/data/custodian/CZ-42-CHO-L-OKVB-obecni_knihovna_v_blatne.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CHO-L-OKVB-obecni_knihovna_v_blatne - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CHO-L-OKVB-obecni_knihovna_v_blatne valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CHO-L-OKVB-obecni_knihovna_v_blatne ghcid_numeric: 13316460585372269779 valid_from: '2025-12-06T23:37:41.302583+00:00' @@ -212,3 +213,22 @@ location: postal_code: 430 01 street_address: Blatno 1 normalization_timestamp: '2025-12-09T10:54:14.415934+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:23.516686+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/blatno + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/blatno + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:23.516686+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHO-L-OKVB.yaml b/data/custodian/CZ-42-CHO-L-OKVB.yaml index b7d8acaa6b..1f10cf2682 100644 --- a/data/custodian/CZ-42-CHO-L-OKVB.yaml +++ b/data/custodian/CZ-42-CHO-L-OKVB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CHO-L-OKVB - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CHO-L-OKVB valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CHO-L-OKVB ghcid_numeric: 12504728136404443676 valid_from: '2025-12-06T23:37:41.291019+00:00' @@ -214,3 +215,22 @@ location: postal_code: 430 01 street_address: Bílence 45 normalization_timestamp: '2025-12-09T10:54:14.442391+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:30.203154+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/bilence + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/bilence + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:30.203154+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHO-L-OKVK.yaml b/data/custodian/CZ-42-CHO-L-OKVK.yaml index 45d7b935e1..0cd8a25531 100644 --- a/data/custodian/CZ-42-CHO-L-OKVK.yaml +++ b/data/custodian/CZ-42-CHO-L-OKVK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CHO-L-OKVK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CHO-L-OKVK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CHO-L-OKVK ghcid_numeric: 16669272234726585170 valid_from: '2025-12-06T23:37:41.320307+00:00' @@ -212,3 +213,22 @@ location: postal_code: 430 01 street_address: Křimov 1 normalization_timestamp: '2025-12-09T10:54:14.467574+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:35.910261+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/krimov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/krimov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:35.910261+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHO-L-OKVV.yaml b/data/custodian/CZ-42-CHO-L-OKVV.yaml index aa5cb12bcd..9d1cec2775 100644 --- a/data/custodian/CZ-42-CHO-L-OKVV.yaml +++ b/data/custodian/CZ-42-CHO-L-OKVV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CHO-L-OKVV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CHO-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CHO-L-OKVV ghcid_numeric: 7061372218483594045 valid_from: '2025-12-06T23:37:41.285347+00:00' @@ -208,3 +209,22 @@ location: postal_code: 430 01 street_address: Všehrdy 29 normalization_timestamp: '2025-12-09T10:54:14.493725+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:41.666081+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/vsehrdy + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/vsehrdy + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:41.666081+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CHR-L-MKC.yaml b/data/custodian/CZ-42-CHR-L-MKC.yaml index c672e2ea74..f5e5ab6a14 100644 --- a/data/custodian/CZ-42-CHR-L-MKC.yaml +++ b/data/custodian/CZ-42-CHR-L-MKC.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CHR-L-MKC - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CHR-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CHR-L-MKC ghcid_numeric: 9533138026999224517 valid_from: '2025-12-06T23:37:41.143177+00:00' @@ -222,3 +223,22 @@ location: postal_code: 407 44 street_address: Chřibská 197 normalization_timestamp: '2025-12-09T10:54:14.553210+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:54.521093+00:00' + source_url: https://decin.tritius.cz/library/region + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://decin.tritius.cz/apple-touch-icon-180x180.png + source_url: https://decin.tritius.cz/library/region + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:14:54.521093+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-CIT-L-MKC.yaml b/data/custodian/CZ-42-CIT-L-MKC.yaml index cb3c47a0c0..3bbaabbccd 100644 --- a/data/custodian/CZ-42-CIT-L-MKC.yaml +++ b/data/custodian/CZ-42-CIT-L-MKC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CIT-L-MKC - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CIT-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CIT-L-MKC ghcid_numeric: 8083077140325280206 valid_from: '2025-12-06T23:37:41.579025+00:00' @@ -205,3 +206,22 @@ location: postal_code: 439 02 street_address: Zeměšská 219 normalization_timestamp: '2025-12-09T10:54:14.581958+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:01.873072+00:00' + source_url: https://www.obec-citoliby.cz/mestys/mistni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-citoliby.cz/skins/obec-citoliby.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.obec-citoliby.cz/mestys/mistni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:15:01.873072+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-CIZ-L-MKC.yaml b/data/custodian/CZ-42-CIZ-L-MKC.yaml index c89fccfca2..74114ca174 100644 --- a/data/custodian/CZ-42-CIZ-L-MKC.yaml +++ b/data/custodian/CZ-42-CIZ-L-MKC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-CIZ-L-MKC - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-CIZ-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-CIZ-L-MKC ghcid_numeric: 9459489336741360858 valid_from: '2025-12-08T11:21:32.155312+00:00' @@ -216,3 +217,22 @@ location: postal_code: 411 12 street_address: Jiráskova 143 normalization_timestamp: '2025-12-09T10:54:14.630679+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:08.790196+00:00' + source_url: https://cizkovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://cizkovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://cizkovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:15:08.790196+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DEC-L-CEDSR.yaml b/data/custodian/CZ-42-DEC-L-CEDSR.yaml index daa56a2ed5..89bf7c2e4a 100644 --- a/data/custodian/CZ-42-DEC-L-CEDSR.yaml +++ b/data/custodian/CZ-42-DEC-L-CEDSR.yaml @@ -163,3 +163,22 @@ location: postal_code: 405 35 street_address: Ústecká 37 normalization_timestamp: '2025-12-09T06:52:51.140576+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:19.946738+00:00' + source_url: https://www.constellium.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.constellium.com/src/images/favicon/favicon-192X192.png?v=aa27c60b4bf75b2aac42ac941dd27577 + source_url: https://www.constellium.com + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:15:19.946738+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-42-DEC-L-KZSNDZDPOL.yaml b/data/custodian/CZ-42-DEC-L-KZSNDZDPOL.yaml index 06d9fe5121..dd249c348d 100644 --- a/data/custodian/CZ-42-DEC-L-KZSNDZDPOL.yaml +++ b/data/custodian/CZ-42-DEC-L-KZSNDZDPOL.yaml @@ -185,3 +185,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q6150991 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:30.047102+00:00' + source_url: https://www.kzcr.eu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kzcr.eu/favicon.ico + source_url: https://www.kzcr.eu + css_selector: '#html > head > link' + retrieved_on: '2025-12-24T12:15:30.047102+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DEC-L-OKVM.yaml b/data/custodian/CZ-42-DEC-L-OKVM.yaml index e6f460e603..364c181667 100644 --- a/data/custodian/CZ-42-DEC-L-OKVM.yaml +++ b/data/custodian/CZ-42-DEC-L-OKVM.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DEC-L-OKVM - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DEC-L-OKVM valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DEC-L-OKVM ghcid_numeric: 4947272586813454972 valid_from: '2025-12-06T23:37:41.204567+00:00' @@ -209,3 +210,22 @@ location: postal_code: 405 02 street_address: Malšovice 162 normalization_timestamp: '2025-12-09T10:54:14.763252+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:38.688355+00:00' + source_url: https://www.malsovice.cz/knihovna/ms-1793/p1=1793 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.malsovice.cz/html/images/favicon.ico + source_url: https://www.malsovice.cz/knihovna/ms-1793/p1=1793 + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T12:15:38.688355+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DEC-L-OKVT.yaml b/data/custodian/CZ-42-DEC-L-OKVT.yaml index 792d3aa3c1..1c8db00e0d 100644 --- a/data/custodian/CZ-42-DEC-L-OKVT.yaml +++ b/data/custodian/CZ-42-DEC-L-OKVT.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DEC-L-OKVT - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DEC-L-OKVT valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DEC-L-OKVT ghcid_numeric: 8503432323095652670 valid_from: '2025-12-06T23:37:41.152024+00:00' @@ -209,3 +210,30 @@ location: postal_code: 407 02 street_address: Těchlovice 37 normalization_timestamp: '2025-12-09T10:54:14.826809+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:47.136377+00:00' + source_url: https://www.techlovice-dc.cz/sluzby-v-obci + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.techlovice-dc.cz/images/logo.png + source_url: https://www.techlovice-dc.cz/sluzby-v-obci + css_selector: '#sp-logo > div.sp-column > div.logo > a > img.sp-default-logo.hidden-xs' + retrieved_on: '2025-12-24T12:15:47.136377+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Obec Těchlovice nad Labem + - claim_type: favicon_url + claim_value: https://www.techlovice-dc.cz/templates/etchemical/images/favicon.ico + source_url: https://www.techlovice-dc.cz/sluzby-v-obci + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:15:47.136377+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DEC-M-OMVDPK.yaml b/data/custodian/CZ-42-DEC-M-OMVDPK.yaml index 5a16c1899d..84bc28c032 100644 --- a/data/custodian/CZ-42-DEC-M-OMVDPK.yaml +++ b/data/custodian/CZ-42-DEC-M-OMVDPK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DEC-M-OMVDPK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DEC-M-OMVDPK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DEC-M-OMVDPK ghcid_numeric: 17334021466502877472 valid_from: '2025-12-06T23:37:17.469690+00:00' @@ -210,3 +211,22 @@ location: postal_code: 405 02 street_address: České mládeže 1/31 normalization_timestamp: '2025-12-09T10:54:14.911453+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:56.494812+00:00' + source_url: https://muzeumdc.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeumdc.cz/themes/muzeobot/favicon.ico + source_url: https://muzeumdc.cz + css_selector: '[document] > html.js.adaptivetheme > head > link' + retrieved_on: '2025-12-24T12:15:56.494812+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DEC-O-SOAVLSOAD.yaml b/data/custodian/CZ-42-DEC-O-SOAVLSOAD.yaml index f77e7a0a78..be13b5f0f9 100644 --- a/data/custodian/CZ-42-DEC-O-SOAVLSOAD.yaml +++ b/data/custodian/CZ-42-DEC-O-SOAVLSOAD.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DEC-O-SOAVLSOAD - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DEC-O-SOAVLSOAD valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DEC-O-SOAVLSOAD ghcid_numeric: 7506656398510481685 valid_from: '2025-12-06T23:37:17.466837+00:00' @@ -217,3 +218,29 @@ location: postal_code: 405 01 street_address: Dlouhá jízda 1253 - Zámek normalization_timestamp: '2025-12-09T10:54:14.944449+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:20:45.436298+00:00' + source_url: https://www.soalitomerice.cz/soka-decin + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: https://www.soalitomerice.cz/soka-decin + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:20:45.436298+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/decin-1-300x204.jpg + source_url: https://www.soalitomerice.cz/soka-decin + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T12:20:45.436298+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-DEC-O-SOAVLSOADP.yaml b/data/custodian/CZ-42-DEC-O-SOAVLSOADP.yaml index bbcfe78b77..386be3a6fc 100644 --- a/data/custodian/CZ-42-DEC-O-SOAVLSOADP.yaml +++ b/data/custodian/CZ-42-DEC-O-SOAVLSOADP.yaml @@ -185,3 +185,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q65768699 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:09.509444+00:00' + source_url: https://katalog.soalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.soalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.soalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:16:09.509444+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DOB-L-OKD.yaml b/data/custodian/CZ-42-DOB-L-OKD.yaml index 46e253e1ee..d689a749e4 100644 --- a/data/custodian/CZ-42-DOB-L-OKD.yaml +++ b/data/custodian/CZ-42-DOB-L-OKD.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DOB-L-OKD - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DOB-L-OKD valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DOB-L-OKD ghcid_numeric: 14062687077089191871 valid_from: '2025-12-06T23:37:41.233914+00:00' @@ -212,3 +213,22 @@ location: postal_code: 407 41 street_address: Dobrná 45 normalization_timestamp: '2025-12-09T10:54:14.982448+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:14.534276+00:00' + source_url: https://www.obec-dobrna.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-dobrna.cz/image.php?nid=18098&oid=7910471 + source_url: https://www.obec-dobrna.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-24T12:16:14.534276+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DOK-L-MKVD.yaml b/data/custodian/CZ-42-DOK-L-MKVD.yaml index 7d3b8a37a9..fe135e0cd6 100644 --- a/data/custodian/CZ-42-DOK-L-MKVD.yaml +++ b/data/custodian/CZ-42-DOK-L-MKVD.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DOK-L-MKVD - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DOK-L-MKVD valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DOK-L-MKVD ghcid_numeric: 13671869916207537569 valid_from: '2025-12-06T23:37:41.512174+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 82 street_address: Doksany 108 normalization_timestamp: '2025-12-09T10:54:15.039906+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:21.625337+00:00' + source_url: https://doksany-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://doksany-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://doksany-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:16:21.625337+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DOL-L-MKDP.yaml b/data/custodian/CZ-42-DOL-L-MKDP.yaml index 8cf3e07081..693c4b90b9 100644 --- a/data/custodian/CZ-42-DOL-L-MKDP.yaml +++ b/data/custodian/CZ-42-DOL-L-MKDP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DOL-L-MKDP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DOL-L-MKDP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DOL-L-MKDP ghcid_numeric: 1381829174215449324 valid_from: '2025-12-06T23:37:41.172405+00:00' @@ -209,3 +210,22 @@ location: postal_code: 407 82 street_address: Vilémovská 126 normalization_timestamp: '2025-12-09T10:54:15.079367+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:30.699168+00:00' + source_url: https://decin.tritius.cz/library/skat + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://decin.tritius.cz/apple-touch-icon-180x180.png + source_url: https://decin.tritius.cz/library/skat + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:16:30.699168+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-DOL-L-OKVDP.yaml b/data/custodian/CZ-42-DOL-L-OKVDP.yaml index b99ed7635a..b9dae7e01f 100644 --- a/data/custodian/CZ-42-DOL-L-OKVDP.yaml +++ b/data/custodian/CZ-42-DOL-L-OKVDP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DOL-L-OKVDP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DOL-L-OKVDP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DOL-L-OKVDP ghcid_numeric: 14616217452448890542 valid_from: '2025-12-06T23:37:41.225100+00:00' @@ -209,3 +210,28 @@ location: postal_code: 407 55 street_address: Dolní Podluží 6 normalization_timestamp: '2025-12-09T10:54:15.109216+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:38.811617+00:00' + source_url: https://www.dolnipodluzi.cz/knihovna/katalog-on-line + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.dolnipodluzi.cz/skins/dolnipodluzi.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.dolnipodluzi.cz/knihovna/katalog-on-line + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:16:38.811617+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.dolnipodluzi.cz/data/editor/152cs_1.jpg + source_url: https://www.dolnipodluzi.cz/knihovna/katalog-on-line + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:16:38.811617+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-42-DUC-M-MMD-muzeum_mesta_duchcova.yaml b/data/custodian/CZ-42-DUC-M-MMD-muzeum_mesta_duchcova.yaml index 7d9d680144..e9732315c8 100644 --- a/data/custodian/CZ-42-DUC-M-MMD-muzeum_mesta_duchcova.yaml +++ b/data/custodian/CZ-42-DUC-M-MMD-muzeum_mesta_duchcova.yaml @@ -246,3 +246,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Muzeum města Duchcova official youtube_search_timestamp: '2025-12-09T09:31:18.429940+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:12:53.804130+00:00' + source_url: http://www.muzeumduchcov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.muzeumduchcov.cz/html/images/favicon.ico + source_url: http://www.muzeumduchcov.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T13:12:53.804130+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-DUC-M-MMDK.yaml b/data/custodian/CZ-42-DUC-M-MMDK.yaml index a799cacf5e..b59126c1f0 100644 --- a/data/custodian/CZ-42-DUC-M-MMDK.yaml +++ b/data/custodian/CZ-42-DUC-M-MMDK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-DUC-M-MMDK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-DUC-M-MMDK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-DUC-M-MMDK ghcid_numeric: 7177926183231315319 valid_from: '2025-12-06T23:37:16.532341+00:00' @@ -210,3 +211,22 @@ location: postal_code: 419 01 street_address: Masarykova 7 normalization_timestamp: '2025-12-09T10:54:15.148175+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:12:59.019406+00:00' + source_url: http://www.duchcov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.duchcov.cz/html/images/favicon.ico + source_url: http://www.duchcov.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T13:12:59.019406+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-HAJ-L-OKHUD.yaml b/data/custodian/CZ-42-HAJ-L-OKHUD.yaml index 5be3d35477..9418be270c 100644 --- a/data/custodian/CZ-42-HAJ-L-OKHUD.yaml +++ b/data/custodian/CZ-42-HAJ-L-OKHUD.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-HAJ-L-OKHUD - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-HAJ-L-OKHUD valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-HAJ-L-OKHUD ghcid_numeric: 12860805435189841495 valid_from: '2025-12-06T23:37:26.464629+00:00' @@ -104,8 +105,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Obecní knihovna Háj u Duchcova @@ -215,3 +216,22 @@ location: geonames_id: 3076002 geonames_name: Háj u Duchcova feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:13:05.479398+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/hajuduchcova + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/hajuduchcova + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:13:05.479398+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-HOR-L-OKVHJ.yaml b/data/custodian/CZ-42-HOR-L-OKVHJ.yaml index 2815661cee..7dc493ba5b 100644 --- a/data/custodian/CZ-42-HOR-L-OKVHJ.yaml +++ b/data/custodian/CZ-42-HOR-L-OKVHJ.yaml @@ -210,3 +210,22 @@ location: postal_code: 435 43 street_address: Horská 23/13 normalization_timestamp: '2025-12-09T10:54:15.302294+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:13:36.817295+00:00' + source_url: https://www.hornijiretin.cz/kultura-a-sport/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hornijiretin.cz/www/hornijiretin/fs/design/favicon/apple-touch-icon.png + source_url: https://www.hornijiretin.cz/kultura-a-sport/knihovna + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T13:13:36.817295+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 120x120 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-42-HOR-L-OKVHSS.yaml b/data/custodian/CZ-42-HOR-L-OKVHSS.yaml index c9c2a3abeb..d95cbc4cc2 100644 --- a/data/custodian/CZ-42-HOR-L-OKVHSS.yaml +++ b/data/custodian/CZ-42-HOR-L-OKVHSS.yaml @@ -218,3 +218,22 @@ location: postal_code: 431 82 street_address: Hora Svatého Šebestiana 3 normalization_timestamp: '2025-12-09T10:54:15.328314+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:13:42.622873+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/sebestian + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/sebestian + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:13:42.622873+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-HOS-L-MKH.yaml b/data/custodian/CZ-42-HOS-L-MKH.yaml index 19bdcb6289..7a480f671e 100644 --- a/data/custodian/CZ-42-HOS-L-MKH.yaml +++ b/data/custodian/CZ-42-HOS-L-MKH.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-HOS-L-MKH - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-HOS-L-MKH valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-HOS-L-MKH ghcid_numeric: 14579124317592786783 valid_from: '2025-12-06T23:37:41.423469+00:00' @@ -209,3 +210,22 @@ location: postal_code: 411 72 street_address: nám. Svobody 2 normalization_timestamp: '2025-12-09T10:54:15.353959+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:13:47.610363+00:00' + source_url: https://hostka-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hostka-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://hostka-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:13:47.610363+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-HOS-L-MKVH.yaml b/data/custodian/CZ-42-HOS-L-MKVH.yaml index 477bfe3fbb..9b03c77db8 100644 --- a/data/custodian/CZ-42-HOS-L-MKVH.yaml +++ b/data/custodian/CZ-42-HOS-L-MKVH.yaml @@ -215,3 +215,22 @@ location: postal_code: 417 52 street_address: Školní nám. 110 normalization_timestamp: '2025-12-09T10:54:15.382057+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:13:53.849121+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/hostomice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/hostomice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:13:53.849121+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-HRD-L-MKVH.yaml b/data/custodian/CZ-42-HRD-L-MKVH.yaml index 86a4c0be4a..564efc73da 100644 --- a/data/custodian/CZ-42-HRD-L-MKVH.yaml +++ b/data/custodian/CZ-42-HRD-L-MKVH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-HRD-L-MKVH - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-HRD-L-MKVH valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-HRD-L-MKVH ghcid_numeric: 7494727320801065163 valid_from: '2025-12-06T23:37:42.886926+00:00' @@ -208,3 +209,22 @@ location: postal_code: 412 01 street_address: Hrdly 4 normalization_timestamp: '2025-12-09T10:54:15.409272+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:13:58.735769+00:00' + source_url: https://hrdly-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hrdly-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://hrdly-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:13:58.735769+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-HRO-L-MKH-mistni_knihovna_hrobce.yaml b/data/custodian/CZ-42-HRO-L-MKH-mistni_knihovna_hrobce.yaml index ba99ef97c3..2cbe598c77 100644 --- a/data/custodian/CZ-42-HRO-L-MKH-mistni_knihovna_hrobce.yaml +++ b/data/custodian/CZ-42-HRO-L-MKH-mistni_knihovna_hrobce.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-HRO-L-MKH-mistni_knihovna_hrobce - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-HRO-L-MKH-mistni_knihovna_hrobce valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-HRO-L-MKH-mistni_knihovna_hrobce ghcid_numeric: 1655384769361475375 valid_from: '2025-12-06T23:37:41.455051+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 83 street_address: Ke Hřišti 14 normalization_timestamp: '2025-12-09T10:54:15.466635+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:05.852329+00:00' + source_url: https://hrobce-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hrobce-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://hrobce-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:14:05.852329+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-HRU-L-MVKH.yaml b/data/custodian/CZ-42-HRU-L-MVKH.yaml index 8e48d97439..afaefbdb27 100644 --- a/data/custodian/CZ-42-HRU-L-MVKH.yaml +++ b/data/custodian/CZ-42-HRU-L-MVKH.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-HRU-L-MVKH - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-HRU-L-MVKH valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-HRU-L-MVKH ghcid_numeric: 6911023533399401354 valid_from: '2025-12-06T23:37:41.236828+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 43 street_address: Hrušovany 15 normalization_timestamp: '2025-12-09T10:54:15.495591+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:11.664944+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/hrusovany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/hrusovany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:14:11.664944+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-JIR-L-MKVJ-mestska_knihovna_v_jirikove.yaml b/data/custodian/CZ-42-JIR-L-MKVJ-mestska_knihovna_v_jirikove.yaml index c778168ce3..85aa5392d9 100644 --- a/data/custodian/CZ-42-JIR-L-MKVJ-mestska_knihovna_v_jirikove.yaml +++ b/data/custodian/CZ-42-JIR-L-MKVJ-mestska_knihovna_v_jirikove.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-JIR-L-MKVJ-mestska_knihovna_v_jirikove - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-JIR-L-MKVJ-mestska_knihovna_v_jirikove valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-JIR-L-MKVJ-mestska_knihovna_v_jirikove ghcid_numeric: 2245507203523280936 valid_from: '2025-12-06T23:37:41.175619+00:00' @@ -212,3 +213,22 @@ location: postal_code: 407 53 street_address: Filipovská 680 normalization_timestamp: '2025-12-09T10:54:15.575616+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:24.467459+00:00' + source_url: https://decin.tritius.cz/library/jirikov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://decin.tritius.cz/apple-touch-icon-180x180.png + source_url: https://decin.tritius.cz/library/jirikov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:14:24.467459+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-JIR-L-OKP.yaml b/data/custodian/CZ-42-JIR-L-OKP.yaml index 52a8c50f42..d4cd7f6aaa 100644 --- a/data/custodian/CZ-42-JIR-L-OKP.yaml +++ b/data/custodian/CZ-42-JIR-L-OKP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-JIR-L-OKP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-JIR-L-OKP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-JIR-L-OKP ghcid_numeric: 15492678664182836827 valid_from: '2025-12-06T23:37:41.326012+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 11 street_address: Pesvice 7 normalization_timestamp: '2025-12-09T10:54:15.613983+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:30.160091+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/pesvice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/pesvice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:14:30.160091+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-KAD-E-SSTGACPOSK.yaml b/data/custodian/CZ-42-KAD-E-SSTGACPOSK.yaml index ae28815486..c641f4d34f 100644 --- a/data/custodian/CZ-42-KAD-E-SSTGACPOSK.yaml +++ b/data/custodian/CZ-42-KAD-E-SSTGACPOSK.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KAD-E-SSTGACPOSK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KAD-E-SSTGACPOSK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KAD-E-SSTGACPOSK ghcid_numeric: 13608804899227770474 valid_from: '2025-12-08T11:21:26.947490+00:00' @@ -226,3 +227,22 @@ location: postal_code: 432 01 street_address: 5.května 680 normalization_timestamp: '2025-12-09T10:54:15.647615+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:35.271575+00:00' + source_url: https://www.tgacv.cz/kontakty/kadan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tgacv.cz/wp-content/themes/tgacvtheme/img/favicon.ico + source_url: https://www.tgacv.cz/kontakty/kadan + css_selector: '[document] > html.js_active.vc_desktop > head > link:nth-of-type(17)' + retrieved_on: '2025-12-24T13:14:35.271575+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-KAL-L-OKVK.yaml b/data/custodian/CZ-42-KAL-L-OKVK.yaml index 866e378cde..865c600965 100644 --- a/data/custodian/CZ-42-KAL-L-OKVK.yaml +++ b/data/custodian/CZ-42-KAL-L-OKVK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KAL-L-OKVK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KAL-L-OKVK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KAL-L-OKVK ghcid_numeric: 9126864688690092085 valid_from: '2025-12-06T23:37:41.308205+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 32 street_address: Kalek 7 normalization_timestamp: '2025-12-09T10:54:15.703289+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:42.788623+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/kalek + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/kalek + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:14:42.788623+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-KLA-L-MKKNOSMK.yaml b/data/custodian/CZ-42-KLA-L-MKKNOSMK.yaml index 787b6eadf5..6a24c7a60d 100644 --- a/data/custodian/CZ-42-KLA-L-MKKNOSMK.yaml +++ b/data/custodian/CZ-42-KLA-L-MKKNOSMK.yaml @@ -178,3 +178,22 @@ wikidata_enrichment: official_website: http://www.knihovnaklasterec.cz instance_of: - Q7075 +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:47.641431+00:00' + source_url: https://katalog.knihovnaklasterec.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnaklasterec.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovnaklasterec.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:14:47.641431+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-KLA-L-OKVO.yaml b/data/custodian/CZ-42-KLA-L-OKVO.yaml index ccaebb7822..990b82cec6 100644 --- a/data/custodian/CZ-42-KLA-L-OKVO.yaml +++ b/data/custodian/CZ-42-KLA-L-OKVO.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KLA-L-OKVO - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KLA-L-OKVO valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KLA-L-OKVO ghcid_numeric: 2777310621191358516 valid_from: '2025-12-06T23:37:41.296897+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 51 street_address: Okounov 64 normalization_timestamp: '2025-12-09T10:54:15.739656+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:14:53.199433+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/okounov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/okounov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:14:53.199433+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-KOS-L-MKK.yaml b/data/custodian/CZ-42-KOS-L-MKK.yaml index 406b0458bd..82a6d6a53b 100644 --- a/data/custodian/CZ-42-KOS-L-MKK.yaml +++ b/data/custodian/CZ-42-KOS-L-MKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KOS-L-MKK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KOS-L-MKK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KOS-L-MKK ghcid_numeric: 17197781039375059041 valid_from: '2025-12-06T23:37:26.467944+00:00' @@ -210,3 +211,22 @@ location: postal_code: 417 23 street_address: Mírové nám. 2 normalization_timestamp: '2025-12-09T10:54:15.872773+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:16:12.315764+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/kostany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/kostany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:16:12.315764+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-KOS-L-MLKK.yaml b/data/custodian/CZ-42-KOS-L-MLKK.yaml index 9a948d8583..20940ebe7f 100644 --- a/data/custodian/CZ-42-KOS-L-MLKK.yaml +++ b/data/custodian/CZ-42-KOS-L-MLKK.yaml @@ -214,3 +214,28 @@ location: geocoding_timestamp: '2025-12-09T21:40:15.165617+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Koštice +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:16:18.213764+00:00' + source_url: https://www.facebook.com/knihovnakostice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://static.xx.fbcdn.net/rsrc.php/y1/r/ay1hV6OlegS.ico + source_url: https://www.facebook.com/knihovnakostice + css_selector: '#facebook > head > link' + retrieved_on: '2025-12-24T13:16:18.213764+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://scontent.frtm1-3.fna.fbcdn.net/v/t39.30808-1/308018291_420937773489541_7475957564515577271_n.jpg?stp=dst-jpg_tt6&cstp=mx600x600&ctp=s600x600&_nc_cat=107&ccb=1-7&_nc_sid=3ab345&_nc_ohc=jgptRT2umsAQ7kNvwFW44cj&_nc_oc=AdmyNd83ygdI6XgUiR2UxgOAYMe5GbK0vYh7ck_mU4rn-UJV-4W47VvkF1WunFGAgQ8&_nc_zt=24&_nc_ht=scontent.frtm1-3.fna&_nc_gid=fzoj7wBbwsNEaI891p3ntQ&oh=00_AflREV7xHQltNlg2lxhRYA0r28n2-M5ApGvpVB1YRh4dpg&oe=6951AE9C + source_url: https://www.facebook.com/knihovnakostice + css_selector: '#facebook > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T13:16:18.213764+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-42-KRA-L-MKK.yaml b/data/custodian/CZ-42-KRA-L-MKK.yaml index e10314df97..372fff2425 100644 --- a/data/custodian/CZ-42-KRA-L-MKK.yaml +++ b/data/custodian/CZ-42-KRA-L-MKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KRA-L-MKK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KRA-L-MKK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KRA-L-MKK ghcid_numeric: 10190597648805676120 valid_from: '2025-12-06T23:37:41.334794+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 87 street_address: Rovné 67 normalization_timestamp: '2025-12-09T10:54:15.930594+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:16:23.927056+00:00' + source_url: https://krabcice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://krabcice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://krabcice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:16:23.927056+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-KRA-L-MKVKL.yaml b/data/custodian/CZ-42-KRA-L-MKVKL.yaml index cfdfdc98ce..ee4634ba32 100644 --- a/data/custodian/CZ-42-KRA-L-MKVKL.yaml +++ b/data/custodian/CZ-42-KRA-L-MKVKL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KRA-L-MKVKL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KRA-L-MKVKL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KRA-L-MKVKL ghcid_numeric: 17259118914568121452 valid_from: '2025-12-06T23:37:41.149010+00:00' @@ -209,3 +210,31 @@ location: postal_code: 407 46 street_address: Masarykova 1094/4 normalization_timestamp: '2025-12-09T10:54:15.973791+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:16:30.165045+00:00' + source_url: https://krasnalipa.cz/knihovna.php + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://krasnalipa.cz/img/logo1.svg + source_url: https://krasnalipa.cz/knihovna.php + css_selector: '[document] > html > body > header.fixed > div.container > div.row + > div.col-sm-3 > a.logo:nth-of-type(2) > img' + retrieved_on: '2025-12-24T13:16:30.165045+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Krásná Lípa + - claim_type: favicon_url + claim_value: https://krasnalipa.cz/favicon.ico + source_url: https://krasnalipa.cz/knihovna.php + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:16:30.165045+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-KRA-L-OKKD.yaml b/data/custodian/CZ-42-KRA-L-OKKD.yaml index d077563d28..c5a193b3a5 100644 --- a/data/custodian/CZ-42-KRA-L-OKKD.yaml +++ b/data/custodian/CZ-42-KRA-L-OKKD.yaml @@ -209,3 +209,22 @@ location: postal_code: 439 72 street_address: Krásný Dvůr 117 normalization_timestamp: '2025-12-09T10:54:16.013634+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:16:40.738647+00:00' + source_url: https://tritius.mekzatec.cz/library/krasnydvur + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mekzatec.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mekzatec.cz/library/krasnydvur + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:16:40.738647+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-KRE-L-MLKK.yaml b/data/custodian/CZ-42-KRE-L-MLKK.yaml index ef74b3e532..b572dbe208 100644 --- a/data/custodian/CZ-42-KRE-L-MLKK.yaml +++ b/data/custodian/CZ-42-KRE-L-MLKK.yaml @@ -40,13 +40,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KRE-L-MLKK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KRE-L-MLKK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KRE-L-MLKK ghcid_numeric: 9787875698591389376 valid_from: '2025-12-06T23:37:26.537923+00:00' @@ -208,3 +209,22 @@ location: country: *id006 postal_code: 417 65 normalization_timestamp: '2025-12-09T10:54:16.040178+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:16:47.046303+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/kremyz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/kremyz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:16:47.046303+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-KRY-L-MKVK.yaml b/data/custodian/CZ-42-KRY-L-MKVK.yaml index 962a9794b1..fdfbc97b6d 100644 --- a/data/custodian/CZ-42-KRY-L-MKVK.yaml +++ b/data/custodian/CZ-42-KRY-L-MKVK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-KRY-L-MKVK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-KRY-L-MKVK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-KRY-L-MKVK ghcid_numeric: 5412177627223720283 valid_from: '2025-12-06T23:37:23.206113+00:00' @@ -210,3 +211,22 @@ location: postal_code: 439 81 street_address: Hlavní 67 normalization_timestamp: '2025-12-09T10:54:16.112716+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:16:58.810249+00:00' + source_url: https://www.kryry.cz/kontakty/mestska-knihovna-kryry + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kryry.cz/skins/kryry.cz_lego3/favicons/safari-pinned-tab.svg + source_url: https://www.kryry.cz/kontakty/mestska-knihovna-kryry + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:16:58.810249+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-LEV-L-MKL.yaml b/data/custodian/CZ-42-LEV-L-MKL.yaml index 2b03947885..79697b7474 100644 --- a/data/custodian/CZ-42-LEV-L-MKL.yaml +++ b/data/custodian/CZ-42-LEV-L-MKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LEV-L-MKL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LEV-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LEV-L-MKL ghcid_numeric: 16283153436647101464 valid_from: '2025-12-06T23:37:41.494372+00:00' @@ -208,3 +209,22 @@ location: postal_code: 411 45 street_address: Levín 58 normalization_timestamp: '2025-12-09T10:54:16.166054+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:17:06.714133+00:00' + source_url: https://levin-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://levin-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://levin-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:17:06.714133+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libesice.yaml b/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libesice.yaml index d73140b77e..391d4c60ef 100644 --- a/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libesice.yaml +++ b/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libesice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIB-L-MKL-mistni_knihovna_libesice - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIB-L-MKL-mistni_knihovna_libesice valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIB-L-MKL-mistni_knihovna_libesice ghcid_numeric: 919413321109729561 valid_from: '2025-12-06T23:37:41.460686+00:00' @@ -208,3 +209,22 @@ location: postal_code: 411 46 street_address: Liběšice 6 normalization_timestamp: '2025-12-09T10:54:16.244327+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:17:48.960802+00:00' + source_url: https://libesice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://libesice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://libesice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:17:48.960802+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libochovany.yaml b/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libochovany.yaml index 0223de7db7..db83dd5b3a 100644 --- a/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libochovany.yaml +++ b/data/custodian/CZ-42-LIB-L-MKL-mistni_knihovna_libochovany.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIB-L-MKL-mistni_knihovna_libochovany - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIB-L-MKL-mistni_knihovna_libochovany valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIB-L-MKL-mistni_knihovna_libochovany ghcid_numeric: 14903092336744921005 valid_from: '2025-12-06T23:37:41.438321+00:00' @@ -208,3 +209,22 @@ location: postal_code: 411 03 street_address: Libochovany 114 normalization_timestamp: '2025-12-09T10:54:16.267019+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:17:54.004789+00:00' + source_url: https://libochovany-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://libochovany-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://libochovany-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:17:54.004789+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIB-L-MKL.yaml b/data/custodian/CZ-42-LIB-L-MKL.yaml index 82b75b9f52..914d806450 100644 --- a/data/custodian/CZ-42-LIB-L-MKL.yaml +++ b/data/custodian/CZ-42-LIB-L-MKL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIB-L-MKL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIB-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIB-L-MKL ghcid_numeric: 16355919841047582519 valid_from: '2025-12-06T23:37:18.590385+00:00' @@ -220,3 +221,22 @@ location: postal_code: 411 17 street_address: náměstí 5.května 868 normalization_timestamp: '2025-12-09T10:54:16.292838+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:18:02.528301+00:00' + source_url: https://usk.tritius.cz/library/libochovice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://usk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://usk.tritius.cz/library/libochovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:18:02.528301+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-LIB-L-OKL.yaml b/data/custodian/CZ-42-LIB-L-OKL.yaml index 8364f038ee..4537806be0 100644 --- a/data/custodian/CZ-42-LIB-L-OKL.yaml +++ b/data/custodian/CZ-42-LIB-L-OKL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIB-L-OKL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIB-L-OKL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIB-L-OKL ghcid_numeric: 9175211667548133144 valid_from: '2025-12-06T23:37:41.546015+00:00' @@ -208,3 +209,22 @@ location: postal_code: 439 75 street_address: Libočany 103 normalization_timestamp: '2025-12-09T10:54:16.320855+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:18:09.608034+00:00' + source_url: https://tritius.mekzatec.cz/library/libocany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mekzatec.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mekzatec.cz/library/libocany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:18:09.608034+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-LIT-A-SOALSSVL.yaml b/data/custodian/CZ-42-LIT-A-SOALSSVL.yaml index 2e01e7e004..af0895c259 100644 --- a/data/custodian/CZ-42-LIT-A-SOALSSVL.yaml +++ b/data/custodian/CZ-42-LIT-A-SOALSSVL.yaml @@ -227,3 +227,29 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Litoměřice se sídlem v Lovosicích official youtube_search_timestamp: '2025-12-09T09:31:21.725441+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:18:21.872844+00:00' + source_url: https://www.soalitomerice.cz/en/soka-litomericelovosice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: https://www.soalitomerice.cz/en/soka-litomericelovosice + css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T13:18:21.872844+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/sokalt.jpg + source_url: https://www.soalitomerice.cz/en/soka-litomericelovosice + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T13:18:21.872844+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-LIT-A-SOAVL.yaml b/data/custodian/CZ-42-LIT-A-SOAVL.yaml index 6d2d38df31..733f67e909 100644 --- a/data/custodian/CZ-42-LIT-A-SOAVL.yaml +++ b/data/custodian/CZ-42-LIT-A-SOAVL.yaml @@ -272,3 +272,29 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní oblastní archiv v Litoměřicích official youtube_search_timestamp: '2025-12-09T09:31:22.392746+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:18:28.680737+00:00' + source_url: http://www.soalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: http://www.soalitomerice.cz + css_selector: '[document] > html.td-md-is-chrome > body.home.page-template-default + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T13:18:28.680737+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2018/03/FB-post.png + source_url: http://www.soalitomerice.cz + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T13:18:28.680737+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-LIT-E-SSPHSLPKSD.yaml b/data/custodian/CZ-42-LIT-E-SSPHSLPKSD.yaml index 616a34a49b..90d576d47b 100644 --- a/data/custodian/CZ-42-LIT-E-SSPHSLPKSD.yaml +++ b/data/custodian/CZ-42-LIT-E-SSPHSLPKSD.yaml @@ -214,3 +214,22 @@ location: postal_code: 412 01 street_address: Dlouhá 6 normalization_timestamp: '2025-12-09T10:54:16.345668+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:18:54.133807+00:00' + source_url: http://sslitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://sslitomerice.cz/images/banners/logo-koly.jpg + source_url: http://sslitomerice.cz + css_selector: '[document] > html > body > link' + retrieved_on: '2025-12-24T13:18:54.133807+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-G-SGVUVLPOUK.yaml b/data/custodian/CZ-42-LIT-G-SGVUVLPOUK.yaml index 06e038a36b..16611bac78 100644 --- a/data/custodian/CZ-42-LIT-G-SGVUVLPOUK.yaml +++ b/data/custodian/CZ-42-LIT-G-SGVUVLPOUK.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-G-SGVUVLPOUK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-G-SGVUVLPOUK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-G-SGVUVLPOUK ghcid_numeric: 11302846229521530175 valid_from: '2025-12-08T11:21:24.437960+00:00' @@ -228,3 +229,22 @@ location: postal_code: 412 01 street_address: Michalská 29/7 normalization_timestamp: '2025-12-09T10:54:16.377283+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:19:00.423175+00:00' + source_url: https://muzeum.tritius.cz/library/sgvultm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeum.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeum.tritius.cz/library/sgvultm + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:19:00.423175+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-LIT-H-BLK.yaml b/data/custodian/CZ-42-LIT-H-BLK.yaml index c614444393..d7fa1f283d 100644 --- a/data/custodian/CZ-42-LIT-H-BLK.yaml +++ b/data/custodian/CZ-42-LIT-H-BLK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-H-BLK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-H-BLK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-H-BLK ghcid_numeric: 4208244385050083623 valid_from: '2025-12-06T23:37:24.428968+00:00' @@ -211,3 +212,28 @@ location: postal_code: 412 01 street_address: Dómské náměstí 1/1 normalization_timestamp: '2025-12-09T10:54:16.407301+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:19:06.722005+00:00' + source_url: https://www.dltm.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.dltm.cz/apple-icon?d37d331a05d68dd3 + source_url: https://www.dltm.cz + css_selector: '[document] > html.show--consent > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T13:19:06.722005+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 1024x1024 + - claim_type: og_image_url + claim_value: https://www.dltm.cz/cs/opengraph-image-1v6f2j?652406943d2ee9 + source_url: https://www.dltm.cz + css_selector: '[document] > html.show--consent > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T13:19:06.722005+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/CZ-42-LIT-L-MKB.yaml b/data/custodian/CZ-42-LIT-L-MKB.yaml index 2be694d5e9..f0fc4c463a 100644 --- a/data/custodian/CZ-42-LIT-L-MKB.yaml +++ b/data/custodian/CZ-42-LIT-L-MKB.yaml @@ -209,3 +209,22 @@ location: postal_code: 412 01 street_address: Brňany 93 normalization_timestamp: '2025-12-09T10:54:16.449850+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:19:13.674768+00:00' + source_url: https://brnany-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://brnany-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://brnany-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:19:13.674768+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-MKL-mistni_knihovna_libotenice.yaml b/data/custodian/CZ-42-LIT-L-MKL-mistni_knihovna_libotenice.yaml index 40c2dc3b99..dea6152f7f 100644 --- a/data/custodian/CZ-42-LIT-L-MKL-mistni_knihovna_libotenice.yaml +++ b/data/custodian/CZ-42-LIT-L-MKL-mistni_knihovna_libotenice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-L-MKL-mistni_knihovna_libotenice - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-L-MKL-mistni_knihovna_libotenice valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-L-MKL-mistni_knihovna_libotenice ghcid_numeric: 6640488925661426579 valid_from: '2025-12-06T23:37:41.506366+00:00' @@ -205,3 +206,22 @@ location: postal_code: 412 01 street_address: Libotenice 134 normalization_timestamp: '2025-12-09T10:54:16.471364+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:19:18.704606+00:00' + source_url: https://libotenice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://libotenice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://libotenice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:19:18.704606+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-MKL.yaml b/data/custodian/CZ-42-LIT-L-MKL.yaml index 2286c8c572..3ef9234d6e 100644 --- a/data/custodian/CZ-42-LIT-L-MKL.yaml +++ b/data/custodian/CZ-42-LIT-L-MKL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-L-MKL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-L-MKL ghcid_numeric: 10166916885910181991 valid_from: '2025-12-06T23:37:18.750021+00:00' @@ -233,3 +234,22 @@ location: postal_code: 436 01 street_address: Soukenická 982 normalization_timestamp: '2025-12-09T10:54:16.503966+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:19:24.406330+00:00' + source_url: https://katalog.knihovna-litvinov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-litvinov.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-litvinov.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:19:24.406330+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-MKNK.yaml b/data/custodian/CZ-42-LIT-L-MKNK.yaml index 603eb6d86d..1c6f9fcff4 100644 --- a/data/custodian/CZ-42-LIT-L-MKNK.yaml +++ b/data/custodian/CZ-42-LIT-L-MKNK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-L-MKNK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-L-MKNK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-L-MKNK ghcid_numeric: 15376728136877060475 valid_from: '2025-12-06T23:37:41.401499+00:00' @@ -212,3 +213,22 @@ location: postal_code: 412 01 street_address: Nové Kopisty 73 normalization_timestamp: '2025-12-09T10:54:16.551453+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:02.171224+00:00' + source_url: https://novekopisty-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://novekopisty-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://novekopisty-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:20:02.171224+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-MKT.yaml b/data/custodian/CZ-42-LIT-L-MKT.yaml index 32e040e843..023fc3d044 100644 --- a/data/custodian/CZ-42-LIT-L-MKT.yaml +++ b/data/custodian/CZ-42-LIT-L-MKT.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-L-MKT - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-L-MKT valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-L-MKT ghcid_numeric: 3402795017221825244 valid_from: '2025-12-06T23:37:41.474600+00:00' @@ -208,3 +209,22 @@ location: postal_code: 412 01 street_address: Třebušín 33 normalization_timestamp: '2025-12-09T10:54:16.579295+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:07.062597+00:00' + source_url: https://trebusin-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trebusin-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://trebusin-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:20:07.062597+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-MKVT.yaml b/data/custodian/CZ-42-LIT-L-MKVT.yaml index da739cf398..9f124c5114 100644 --- a/data/custodian/CZ-42-LIT-L-MKVT.yaml +++ b/data/custodian/CZ-42-LIT-L-MKVT.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-L-MKVT - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-L-MKVT valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-L-MKVT ghcid_numeric: 13966977027844247847 valid_from: '2025-12-06T23:37:43.482874+00:00' @@ -208,3 +209,22 @@ location: postal_code: 412 01 street_address: Trnovany 37 normalization_timestamp: '2025-12-09T10:54:16.607476+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:11.831506+00:00' + source_url: https://trnovany-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trnovany-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://trnovany-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:20:11.831506+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-MKVZ.yaml b/data/custodian/CZ-42-LIT-L-MKVZ.yaml index c0a4a8c4cd..c433443b82 100644 --- a/data/custodian/CZ-42-LIT-L-MKVZ.yaml +++ b/data/custodian/CZ-42-LIT-L-MKVZ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-L-MKVZ - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-L-MKVZ valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-L-MKVZ ghcid_numeric: 8389896262244289732 valid_from: '2025-12-08T11:21:31.693882+00:00' @@ -212,3 +213,22 @@ location: postal_code: 412 01 street_address: Velké Žernoseky 32 normalization_timestamp: '2025-12-09T10:54:16.633464+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:16.620003+00:00' + source_url: https://vzernoseky-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vzernoseky-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://vzernoseky-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:20:16.620003+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-POKKHMVL.yaml b/data/custodian/CZ-42-LIT-L-POKKHMVL.yaml index 0de67be374..e40b56751f 100644 --- a/data/custodian/CZ-42-LIT-L-POKKHMVL.yaml +++ b/data/custodian/CZ-42-LIT-L-POKKHMVL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-L-POKKHMVL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-L-POKKHMVL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-L-POKKHMVL ghcid_numeric: 8449846097564550470 valid_from: '2025-12-06T23:37:18.587460+00:00' @@ -246,3 +247,22 @@ location: postal_code: 412 01 street_address: Mírové nám. 26 normalization_timestamp: '2025-12-09T10:54:16.714285+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:30.166350+00:00' + source_url: https://katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:20:30.166350+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-L-URSRTK.yaml b/data/custodian/CZ-42-LIT-L-URSRTK.yaml index 2dfa3e4dea..7adc54c589 100644 --- a/data/custodian/CZ-42-LIT-L-URSRTK.yaml +++ b/data/custodian/CZ-42-LIT-L-URSRTK.yaml @@ -216,3 +216,22 @@ location: postal_code: 436 70 street_address: Záluží 1 normalization_timestamp: '2025-12-09T10:54:16.741134+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:36.364182+00:00' + source_url: https://www.unipetrolrpa.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.unipetrolrpa.cz/logotypes404/favicon.ico + source_url: https://www.unipetrolrpa.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T13:20:36.364182+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LIT-O-SOAVLK.yaml b/data/custodian/CZ-42-LIT-O-SOAVLK.yaml index 157084cb21..1616f90ef0 100644 --- a/data/custodian/CZ-42-LIT-O-SOAVLK.yaml +++ b/data/custodian/CZ-42-LIT-O-SOAVLK.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LIT-O-SOAVLK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LIT-O-SOAVLK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LIT-O-SOAVLK ghcid_numeric: 17983967168889669391 valid_from: '2025-12-06T23:37:18.550107+00:00' @@ -287,3 +288,29 @@ location: postal_code: 412 01 street_address: Krajská 48/1 normalization_timestamp: '2025-12-09T10:54:16.775613+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:47.187195+00:00' + source_url: https://www.soalitomerice.cz/litomerice-krajska + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: https://www.soalitomerice.cz/litomerice-krajska + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T13:20:47.187195+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/soal-300x204.jpg + source_url: https://www.soalitomerice.cz/litomerice-krajska + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T13:20:47.187195+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-LOM-L-MKVL.yaml b/data/custodian/CZ-42-LOM-L-MKVL.yaml index a39791787c..109fe16db9 100644 --- a/data/custodian/CZ-42-LOM-L-MKVL.yaml +++ b/data/custodian/CZ-42-LOM-L-MKVL.yaml @@ -213,3 +213,22 @@ location: postal_code: 435 11 street_address: nám. Republiky 13 normalization_timestamp: '2025-12-09T10:54:16.804717+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:20:53.897135+00:00' + source_url: https://www.mesto-lom.cz/organizace/mestska-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mesto-lom.cz/skins/mesto-lom.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.mesto-lom.cz/organizace/mestska-knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T13:20:53.897135+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-42-LOU-A-SOAL.yaml b/data/custodian/CZ-42-LOU-A-SOAL.yaml index 05c2989e63..477d064983 100644 --- a/data/custodian/CZ-42-LOU-A-SOAL.yaml +++ b/data/custodian/CZ-42-LOU-A-SOAL.yaml @@ -253,3 +253,29 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Louny official youtube_search_timestamp: '2025-12-09T09:31:23.724882+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:21:01.486418+00:00' + source_url: http://www.soalitomerice.cz/soka-louny + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: http://www.soalitomerice.cz/soka-louny + css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T13:21:01.486418+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/IMG_0545-300x200.jpg + source_url: http://www.soalitomerice.cz/soka-louny + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T13:21:01.486418+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-LOU-L-MKD.yaml b/data/custodian/CZ-42-LOU-L-MKD.yaml index f17a3b7b4b..e0268471bf 100644 --- a/data/custodian/CZ-42-LOU-L-MKD.yaml +++ b/data/custodian/CZ-42-LOU-L-MKD.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-L-MKD - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-L-MKD valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-L-MKD ghcid_numeric: 18088492374168272423 valid_from: '2025-12-06T23:37:41.604895+00:00' @@ -205,3 +206,22 @@ location: postal_code: 440 01 street_address: Pražská 53 normalization_timestamp: '2025-12-09T10:54:16.850158+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:21:10.453111+00:00' + source_url: https://www.dobromerice.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.dobromerice.cz/skins/dobromerice.cz_lego3/favicons/safari-pinned-tab.svg + source_url: https://www.dobromerice.cz/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:21:10.453111+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-LOU-L-MKL-mistni_knihovna_listany.yaml b/data/custodian/CZ-42-LOU-L-MKL-mistni_knihovna_listany.yaml index aa77ad16fc..46454e7126 100644 --- a/data/custodian/CZ-42-LOU-L-MKL-mistni_knihovna_listany.yaml +++ b/data/custodian/CZ-42-LOU-L-MKL-mistni_knihovna_listany.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-L-MKL-mistni_knihovna_listany - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-L-MKL-mistni_knihovna_listany valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-L-MKL-mistni_knihovna_listany ghcid_numeric: 6342134483097892873 valid_from: '2025-12-06T23:37:41.562586+00:00' @@ -205,3 +206,22 @@ location: postal_code: 440 01 street_address: U Sv. Jána 100 normalization_timestamp: '2025-12-09T10:54:16.876106+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:21:18.191870+00:00' + source_url: https://www.obec-listany.cz/obec-162/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-listany.cz/skins/obec-listany.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.obec-listany.cz/obec-162/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:21:18.191870+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-LOU-L-MKP.yaml b/data/custodian/CZ-42-LOU-L-MKP.yaml index c3c5114a6f..69982dd03d 100644 --- a/data/custodian/CZ-42-LOU-L-MKP.yaml +++ b/data/custodian/CZ-42-LOU-L-MKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-L-MKP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-L-MKP ghcid_numeric: 5534526683484801557 valid_from: '2025-12-06T23:37:41.554136+00:00' @@ -205,3 +206,22 @@ location: postal_code: 440 01 street_address: Pnětluky 26 normalization_timestamp: '2025-12-09T10:54:16.901058+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:21:22.823574+00:00' + source_url: http://www.knihovnyln.cz/pnetluky + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.knihovnyln.cz/favicon2.png + source_url: http://www.knihovnyln.cz/pnetluky + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T13:21:22.823574+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LOU-L-MKVV.yaml b/data/custodian/CZ-42-LOU-L-MKVV.yaml index cd7129452b..2882621f75 100644 --- a/data/custodian/CZ-42-LOU-L-MKVV.yaml +++ b/data/custodian/CZ-42-LOU-L-MKVV.yaml @@ -206,3 +206,22 @@ location: postal_code: 440 01 street_address: Vršovice 132 normalization_timestamp: '2025-12-09T10:54:16.957027+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:22:10.443182+00:00' + source_url: http://www.obecvrsovice.cz/index.php/knihovnamistni + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.obecvrsovice.cz/image.php?nid=21144&oid=10556277&width=32 + source_url: http://www.obecvrsovice.cz/index.php/knihovnamistni + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-24T13:22:10.443182+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LOU-L-MKZ-mistni_knihovna_zemechy.yaml b/data/custodian/CZ-42-LOU-L-MKZ-mistni_knihovna_zemechy.yaml index 255070c75b..cc36ca5109 100644 --- a/data/custodian/CZ-42-LOU-L-MKZ-mistni_knihovna_zemechy.yaml +++ b/data/custodian/CZ-42-LOU-L-MKZ-mistni_knihovna_zemechy.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-L-MKZ-mistni_knihovna_zemechy - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-L-MKZ-mistni_knihovna_zemechy valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-L-MKZ-mistni_knihovna_zemechy ghcid_numeric: 14961996404889674237 valid_from: '2025-12-06T23:37:43.652785+00:00' @@ -213,3 +214,22 @@ location: postal_code: 440 01 street_address: Zeměchy 50 normalization_timestamp: '2025-12-09T10:54:16.985400+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:22:15.619530+00:00' + source_url: https://www.jimlin.cz/knihovna-zemechy + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jimlin.cz/image.php?nid=17015&oid=9257269&width=32 + source_url: https://www.jimlin.cz/knihovna-zemechy + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-24T13:22:15.619530+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LOU-L-MKZ.yaml b/data/custodian/CZ-42-LOU-L-MKZ.yaml index 2017d7fb5d..ae11c392a5 100644 --- a/data/custodian/CZ-42-LOU-L-MKZ.yaml +++ b/data/custodian/CZ-42-LOU-L-MKZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-L-MKZ - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-L-MKZ valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-L-MKZ ghcid_numeric: 14697058101100696037 valid_from: '2025-12-06T23:37:41.600921+00:00' @@ -205,3 +206,22 @@ location: postal_code: 440 01 street_address: Zbrašín 23 normalization_timestamp: '2025-12-09T10:54:17.013385+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:22:23.311236+00:00' + source_url: https://www.zbrasin.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zbrasin.cz/skins/zbrasin_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.zbrasin.cz/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:22:23.311236+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-LOU-M-GBRMMUK.yaml b/data/custodian/CZ-42-LOU-M-GBRMMUK.yaml index 54d5d42829..0588ba3936 100644 --- a/data/custodian/CZ-42-LOU-M-GBRMMUK.yaml +++ b/data/custodian/CZ-42-LOU-M-GBRMMUK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-M-GBRMMUK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-M-GBRMMUK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-M-GBRMMUK ghcid_numeric: 14190073733404747170 valid_from: '2025-12-06T23:37:24.615986+00:00' @@ -217,3 +218,22 @@ location: postal_code: 440 01 street_address: Pivovarská 29-34 normalization_timestamp: '2025-12-09T10:54:17.110314+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:22:36.856712+00:00' + source_url: https://www.gbr.cz/?s=453 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.gbr.cz/style/favicon/safari-pinned-tab.svg + source_url: https://www.gbr.cz/?s=453 + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T13:22:36.856712+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-LOU-M-OMVLPK.yaml b/data/custodian/CZ-42-LOU-M-OMVLPK.yaml index aaa7bb51e3..db050a1d1f 100644 --- a/data/custodian/CZ-42-LOU-M-OMVLPK.yaml +++ b/data/custodian/CZ-42-LOU-M-OMVLPK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-M-OMVLPK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-M-OMVLPK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-M-OMVLPK ghcid_numeric: 15606374325157822260 valid_from: '2025-12-06T23:37:24.511567+00:00' @@ -210,3 +211,22 @@ location: postal_code: 440 01 street_address: Pivovarská 28 normalization_timestamp: '2025-12-09T10:54:17.151437+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:22:42.890270+00:00' + source_url: https://muzeum.tritius.cz/library/louny + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeum.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeum.tritius.cz/library/louny + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:22:42.890270+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-LOU-O-SOAVLSOAL.yaml b/data/custodian/CZ-42-LOU-O-SOAVLSOAL.yaml index 3efe6ae6ac..a879c5f893 100644 --- a/data/custodian/CZ-42-LOU-O-SOAVLSOAL.yaml +++ b/data/custodian/CZ-42-LOU-O-SOAVLSOAL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOU-O-SOAVLSOAL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOU-O-SOAVLSOAL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOU-O-SOAVLSOAL ghcid_numeric: 3356964814195238783 valid_from: '2025-12-06T23:37:43.253664+00:00' @@ -212,3 +213,29 @@ location: postal_code: 440 01 street_address: Pod Nemocnicí 3127 normalization_timestamp: '2025-12-09T10:54:17.176761+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:22:52.541522+00:00' + source_url: https://www.soalitomerice.cz/soka-louny + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: https://www.soalitomerice.cz/soka-louny + css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T13:22:52.541522+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/IMG_0545-300x200.jpg + source_url: https://www.soalitomerice.cz/soka-louny + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T13:22:52.541522+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-LOV-L-MKK-mistni_knihovna_keblice.yaml b/data/custodian/CZ-42-LOV-L-MKK-mistni_knihovna_keblice.yaml index f93711546b..d86ce1872b 100644 --- a/data/custodian/CZ-42-LOV-L-MKK-mistni_knihovna_keblice.yaml +++ b/data/custodian/CZ-42-LOV-L-MKK-mistni_knihovna_keblice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOV-L-MKK-mistni_knihovna_keblice - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOV-L-MKK-mistni_knihovna_keblice valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOV-L-MKK-mistni_knihovna_keblice ghcid_numeric: 7215755034706468749 valid_from: '2025-12-06T23:37:41.427032+00:00' @@ -208,3 +209,22 @@ location: postal_code: 410 02 street_address: Keblice 68 normalization_timestamp: '2025-12-09T10:54:17.202403+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:22:57.383212+00:00' + source_url: https://keblice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://keblice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://keblice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:22:57.383212+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LOV-L-MKK.yaml b/data/custodian/CZ-42-LOV-L-MKK.yaml index 1d23fd683b..b95cdf09e7 100644 --- a/data/custodian/CZ-42-LOV-L-MKK.yaml +++ b/data/custodian/CZ-42-LOV-L-MKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOV-L-MKK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOV-L-MKK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOV-L-MKK ghcid_numeric: 9539121337536411160 valid_from: '2025-12-06T23:37:41.337728+00:00' @@ -205,3 +206,22 @@ location: postal_code: 410 02 street_address: Křesín 77 normalization_timestamp: '2025-12-09T10:54:17.229123+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:23:02.223478+00:00' + source_url: https://kresin-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kresin-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://kresin-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:23:02.223478+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LOV-L-MKL-mistni_knihovna_loveckovice.yaml b/data/custodian/CZ-42-LOV-L-MKL-mistni_knihovna_loveckovice.yaml index b59398f264..13ed360c2d 100644 --- a/data/custodian/CZ-42-LOV-L-MKL-mistni_knihovna_loveckovice.yaml +++ b/data/custodian/CZ-42-LOV-L-MKL-mistni_knihovna_loveckovice.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOV-L-MKL-mistni_knihovna_loveckovice - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOV-L-MKL-mistni_knihovna_loveckovice valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOV-L-MKL-mistni_knihovna_loveckovice ghcid_numeric: 7408490042263807179 valid_from: '2025-12-06T23:37:41.471777+00:00' @@ -209,3 +210,22 @@ location: postal_code: 411 45 street_address: Lovečkovice 57 normalization_timestamp: '2025-12-09T10:54:17.256030+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:23:07.020380+00:00' + source_url: https://loveckovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://loveckovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://loveckovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:23:07.020380+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LOV-L-MKL.yaml b/data/custodian/CZ-42-LOV-L-MKL.yaml index 210a5cb3ea..9982796677 100644 --- a/data/custodian/CZ-42-LOV-L-MKL.yaml +++ b/data/custodian/CZ-42-LOV-L-MKL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOV-L-MKL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOV-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOV-L-MKL ghcid_numeric: 1792927413582296544 valid_from: '2025-12-06T23:37:18.597796+00:00' @@ -223,3 +224,22 @@ location: postal_code: 410 02 street_address: Osvoboditelů 48/55 normalization_timestamp: '2025-12-09T10:54:17.281424+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:23:15.455638+00:00' + source_url: https://lovosice.tritius.cz/?device=5 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lovosice.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lovosice.tritius.cz/?device=5 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:23:15.455638+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-LOV-L-MKS.yaml b/data/custodian/CZ-42-LOV-L-MKS.yaml index 709440027c..ca3cf70ab7 100644 --- a/data/custodian/CZ-42-LOV-L-MKS.yaml +++ b/data/custodian/CZ-42-LOV-L-MKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOV-L-MKS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOV-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOV-L-MKS ghcid_numeric: 3119974398824951984 valid_from: '2025-12-06T23:37:41.369764+00:00' @@ -208,3 +209,22 @@ location: postal_code: 410 02 street_address: Siřejovice 119 normalization_timestamp: '2025-12-09T10:54:17.299440+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:23:20.304750+00:00' + source_url: https://sirejovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sirejovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://sirejovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:23:20.304750+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LOV-L-OKR.yaml b/data/custodian/CZ-42-LOV-L-OKR.yaml index ea6e9bcad2..bd921b58d8 100644 --- a/data/custodian/CZ-42-LOV-L-OKR.yaml +++ b/data/custodian/CZ-42-LOV-L-OKR.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LOV-L-OKR - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LOV-L-OKR valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LOV-L-OKR ghcid_numeric: 1979765896467268294 valid_from: '2025-12-06T23:37:43.672867+00:00' @@ -76,7 +77,8 @@ provenance: extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml' confidence_score: 0.95 notes: - - Removed incorrect wikidata_enrichment on 2025-12-08T08:18:47.771490+00:00. Re-enrichment required with proper matching. + - Removed incorrect wikidata_enrichment on 2025-12-08T08:18:47.771490+00:00. Re-enrichment + required with proper matching. - Canonical location normalized on 2025-12-09T12:10:21Z ch_annotator: convention_id: ch_annotator-v1_7_0 @@ -105,8 +107,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Obecní knihovna Radovesice @@ -209,3 +211,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:24.725482+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Lovosice +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:23:25.133381+00:00' + source_url: https://radovesice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://radovesice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://radovesice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:23:25.133381+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-LUB-L-OKL.yaml b/data/custodian/CZ-42-LUB-L-OKL.yaml index 47495b0aa2..e9db74f460 100644 --- a/data/custodian/CZ-42-LUB-L-OKL.yaml +++ b/data/custodian/CZ-42-LUB-L-OKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-LUB-L-OKL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-LUB-L-OKL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-LUB-L-OKL ghcid_numeric: 12850306937224184808 valid_from: '2025-12-06T23:37:41.526369+00:00' @@ -208,3 +209,22 @@ location: postal_code: 439 83 street_address: Podbořanská 239 normalization_timestamp: '2025-12-09T10:54:17.372761+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:23:37.329054+00:00' + source_url: https://tritius.mekzatec.cz/library/lubenec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mekzatec.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mekzatec.cz/library/lubenec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:23:37.329054+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-MAL-L-MVKM.yaml b/data/custodian/CZ-42-MAL-L-MVKM.yaml index bfbb94126b..a304c2ff6d 100644 --- a/data/custodian/CZ-42-MAL-L-MVKM.yaml +++ b/data/custodian/CZ-42-MAL-L-MVKM.yaml @@ -213,3 +213,22 @@ location: postal_code: 431 02 street_address: Zelená 3 normalization_timestamp: '2025-12-09T10:54:17.490641+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:24:53.828104+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/malkov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/malkov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:24:53.828104+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-MAR-L-MKM.yaml b/data/custodian/CZ-42-MAR-L-MKM.yaml index 1cb94bf187..eb52792220 100644 --- a/data/custodian/CZ-42-MAR-L-MKM.yaml +++ b/data/custodian/CZ-42-MAR-L-MKM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-MAR-L-MKM - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-MAR-L-MKM valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-MAR-L-MKM ghcid_numeric: 8613463265771276480 valid_from: '2025-12-06T23:37:41.343341+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 19 street_address: Pohořice 24 normalization_timestamp: '2025-12-09T10:54:17.532375+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:24:58.916615+00:00' + source_url: https://martineves-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://martineves-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://martineves-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:24:58.916615+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-MAR-L-OKVM.yaml b/data/custodian/CZ-42-MAR-L-OKVM.yaml index dc72beb558..2075e399e4 100644 --- a/data/custodian/CZ-42-MAR-L-OKVM.yaml +++ b/data/custodian/CZ-42-MAR-L-OKVM.yaml @@ -209,3 +209,22 @@ location: postal_code: 407 42 street_address: Markvartice 280 normalization_timestamp: '2025-12-09T10:54:17.578438+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:35:29.512093+00:00' + source_url: https://www.markvartice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.markvartice.cz/templates/dd_bicycleclub_55/favicon.ico + source_url: https://www.markvartice.cz + css_selector: '[document] > html.chrome.chrome135 > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T13:35:29.512093+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-MED-L-MLKM.yaml b/data/custodian/CZ-42-MED-L-MLKM.yaml index f9a77d47c0..8e1e9800d3 100644 --- a/data/custodian/CZ-42-MED-L-MLKM.yaml +++ b/data/custodian/CZ-42-MED-L-MLKM.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-MED-L-MLKM - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-MED-L-MLKM valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-MED-L-MLKM ghcid_numeric: 8208773731184624544 valid_from: '2025-12-06T23:37:41.242617+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 84 street_address: Nádražní 212 normalization_timestamp: '2025-12-09T10:54:17.670511+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:35:37.118567+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/medenec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/medenec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:35:37.118567+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-MIS-L-OKVM.yaml b/data/custodian/CZ-42-MIS-L-OKVM.yaml index 0f869f2c7a..f15a3c7353 100644 --- a/data/custodian/CZ-42-MIS-L-OKVM.yaml +++ b/data/custodian/CZ-42-MIS-L-OKVM.yaml @@ -213,3 +213,22 @@ location: postal_code: 431 58 street_address: Místo 81 normalization_timestamp: '2025-12-09T10:54:17.790572+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:35:53.381565+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/misto + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/misto + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:35:53.381565+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-MOD-L-OKM.yaml b/data/custodian/CZ-42-MOD-L-OKM.yaml index 8e3a41b189..aa6a98c5f7 100644 --- a/data/custodian/CZ-42-MOD-L-OKM.yaml +++ b/data/custodian/CZ-42-MOD-L-OKM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-MOD-L-OKM - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-MOD-L-OKM valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-MOD-L-OKM ghcid_numeric: 15667290726691596021 valid_from: '2025-12-06T23:37:26.541957+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Obecní knihovna Modlany @@ -206,3 +207,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:11.044853+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Modlany +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:35:59.567511+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/modlany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/modlany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:35:59.567511+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-MOS-L-KZSNMZDPOL.yaml b/data/custodian/CZ-42-MOS-L-KZSNMZDPOL.yaml index de59930912..b3ffc01878 100644 --- a/data/custodian/CZ-42-MOS-L-KZSNMZDPOL.yaml +++ b/data/custodian/CZ-42-MOS-L-KZSNMZDPOL.yaml @@ -185,3 +185,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q6150991 +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:36:06.689067+00:00' + source_url: https://www.kzcr.eu/cz/kz/vikz/lekarska-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kzcr.eu/favicon.ico + source_url: https://www.kzcr.eu/cz/kz/vikz/lekarska-knihovna + css_selector: '#html > head > link' + retrieved_on: '2025-12-24T13:36:06.689067+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-NOV-L-MLKNVVH.yaml b/data/custodian/CZ-42-NOV-L-MLKNVVH.yaml index 0920f89ca9..6bff1758ba 100644 --- a/data/custodian/CZ-42-NOV-L-MLKNVVH.yaml +++ b/data/custodian/CZ-42-NOV-L-MLKNVVH.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-NOV-L-MLKNVVH - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-NOV-L-MLKNVVH valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-NOV-L-MLKNVVH ghcid_numeric: 15491733141777176193 valid_from: '2025-12-06T23:37:41.619157+00:00' @@ -205,3 +206,22 @@ location: postal_code: 435 45 street_address: Nová Ves v Horách 33 normalization_timestamp: '2025-12-09T10:54:18.109166+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:41:07.898133+00:00' + source_url: https://www.novavesvhorach.cz/obcan/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.novavesvhorach.cz/skins/novavesvhorach.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.novavesvhorach.cz/obcan/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:41:07.898133+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-NOV-L-OKN.yaml b/data/custodian/CZ-42-NOV-L-OKN.yaml index 50cc2d738d..24ef722667 100644 --- a/data/custodian/CZ-42-NOV-L-OKN.yaml +++ b/data/custodian/CZ-42-NOV-L-OKN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-NOV-L-OKN - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-NOV-L-OKN valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-NOV-L-OKN ghcid_numeric: 11633582708033472106 valid_from: '2025-12-06T23:37:26.547325+00:00' @@ -210,3 +211,22 @@ location: postal_code: 417 31 street_address: Kostelní 85/1 normalization_timestamp: '2025-12-09T10:54:18.138018+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:41:15.570543+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/novosedlice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/novosedlice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:41:15.570543+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-NOV-L-OKNS.yaml b/data/custodian/CZ-42-NOV-L-OKNS.yaml index 177e134ced..1f45b82e8e 100644 --- a/data/custodian/CZ-42-NOV-L-OKNS.yaml +++ b/data/custodian/CZ-42-NOV-L-OKNS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-NOV-L-OKNS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-NOV-L-OKNS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-NOV-L-OKNS ghcid_numeric: 15515601106713406003 valid_from: '2025-12-06T23:37:41.529079+00:00' @@ -208,3 +209,22 @@ location: postal_code: 438 01 street_address: Hlavní 13 normalization_timestamp: '2025-12-09T10:54:18.189515+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:41:22.058871+00:00' + source_url: https://tritius.mekzatec.cz/library/novesedlo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mekzatec.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mekzatec.cz/library/novesedlo + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:41:22.058871+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-OBR-L-KOP.yaml b/data/custodian/CZ-42-OBR-L-KOP.yaml index fcace4ed5a..e61637fea1 100644 --- a/data/custodian/CZ-42-OBR-L-KOP.yaml +++ b/data/custodian/CZ-42-OBR-L-KOP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-OBR-L-KOP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-OBR-L-KOP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-OBR-L-KOP ghcid_numeric: 9913029122054222030 valid_from: '2025-12-06T23:37:41.665275+00:00' @@ -205,3 +206,28 @@ location: postal_code: 435 21 street_address: Patokryje 35 normalization_timestamp: '2025-12-09T10:54:18.262627+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:41:36.278309+00:00' + source_url: https://www.patokryje.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.patokryje.cz/wp-content/uploads/2016/03/cropped-erb_patokryje-barva-bez-textu-180x180.jpg + source_url: https://www.patokryje.cz/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(30)' + retrieved_on: '2025-12-24T13:41:36.278309+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.patokryje.cz/wp-content/uploads/2020/04/kniha.jpg + source_url: https://www.patokryje.cz/knihovna + css_selector: '[document] > html.js > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T13:41:36.278309+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-42-OBR-L-ZKPOUVO.yaml b/data/custodian/CZ-42-OBR-L-ZKPOUVO.yaml index 75425aab05..47418f5999 100644 --- a/data/custodian/CZ-42-OBR-L-ZKPOUVO.yaml +++ b/data/custodian/CZ-42-OBR-L-ZKPOUVO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-OBR-L-ZKPOUVO - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-OBR-L-ZKPOUVO valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-OBR-L-ZKPOUVO ghcid_numeric: 16958024055243118593 valid_from: '2025-12-08T11:21:39.740336+00:00' @@ -210,3 +211,22 @@ location: postal_code: 435 21 street_address: Mírová 127 normalization_timestamp: '2025-12-09T10:54:18.294992+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:42:01.414834+00:00' + source_url: https://www.ouobrnice.cz/obcan/knihovna-icva + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ouobrnice.cz/skins/ouobrnice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.ouobrnice.cz/obcan/knihovna-icva + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:42:01.414834+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-OHN-L-MLKO.yaml b/data/custodian/CZ-42-OHN-L-MLKO.yaml index 40f0180501..a82972cc3a 100644 --- a/data/custodian/CZ-42-OHN-L-MLKO.yaml +++ b/data/custodian/CZ-42-OHN-L-MLKO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-OHN-L-MLKO - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-OHN-L-MLKO valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-OHN-L-MLKO ghcid_numeric: 5972049917556104316 valid_from: '2025-12-06T23:37:26.550281+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Místní lidová knihovna Ohníč @@ -209,3 +210,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:23.406721+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Ohníč +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:42:07.469780+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/ohnic + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/ohnic + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:42:07.469780+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-OLD-L-OKVO.yaml b/data/custodian/CZ-42-OLD-L-OKVO.yaml index 7fa89fedc6..e4696e1f2b 100644 --- a/data/custodian/CZ-42-OLD-L-OKVO.yaml +++ b/data/custodian/CZ-42-OLD-L-OKVO.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-OLD-L-OKVO - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-OLD-L-OKVO valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-OLD-L-OKVO ghcid_numeric: 2847271248213640977 valid_from: '2025-12-06T23:37:26.756658+00:00' @@ -209,3 +210,22 @@ location: country: *id007 postal_code: 417 24 normalization_timestamp: '2025-12-09T10:54:18.353643+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:42:13.534839+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/oldrichov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/oldrichov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:42:13.534839+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-OTV-L-OKVO.yaml b/data/custodian/CZ-42-OTV-L-OKVO.yaml index c0e2ec3024..c03c767114 100644 --- a/data/custodian/CZ-42-OTV-L-OKVO.yaml +++ b/data/custodian/CZ-42-OTV-L-OKVO.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-OTV-L-OKVO - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-OTV-L-OKVO valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-OTV-L-OKVO ghcid_numeric: 8071800898444226109 valid_from: '2025-12-06T23:37:41.260211+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 11 street_address: Školní 95 normalization_timestamp: '2025-12-09T10:54:18.409432+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:42:26.183395+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/otvice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/otvice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:42:26.183395+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-PAN-L-OKFPPT.yaml b/data/custodian/CZ-42-PAN-L-OKFPPT.yaml index 2cf2592f41..71765eabaa 100644 --- a/data/custodian/CZ-42-PAN-L-OKFPPT.yaml +++ b/data/custodian/CZ-42-PAN-L-OKFPPT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PAN-L-OKFPPT - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PAN-L-OKFPPT valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PAN-L-OKFPPT ghcid_numeric: 4841698840978535040 valid_from: '2025-12-06T23:37:41.559690+00:00' @@ -205,3 +206,22 @@ location: postal_code: 439 05 street_address: Panenský Týnec 10 normalization_timestamp: '2025-12-09T10:54:18.435368+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:42:32.259559+00:00' + source_url: https://www.panenskytynec.cz/obcan/knihovna/sluzby + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.panenskytynec.cz/skins/panenskytynec.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.panenskytynec.cz/obcan/knihovna/sluzby + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T13:42:32.259559+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-42-PER-L-MLKP.yaml b/data/custodian/CZ-42-PER-L-MLKP.yaml index 2f9534e9e4..14c4a62b01 100644 --- a/data/custodian/CZ-42-PER-L-MLKP.yaml +++ b/data/custodian/CZ-42-PER-L-MLKP.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PER-L-MLKP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PER-L-MLKP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PER-L-MLKP ghcid_numeric: 13822123065358348683 valid_from: '2025-12-06T23:37:23.282220+00:00' @@ -104,8 +105,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Místní lidová knihovna Peruc @@ -215,3 +216,22 @@ location: geonames_id: 3068411 geonames_name: Peruc feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:42:37.247572+00:00' + source_url: https://katalog.mkln.cz/library/peruc + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.mkln.cz/apple-touch-icon-180x180.png + source_url: https://katalog.mkln.cz/library/peruc + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:42:37.247572+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-PER-L-OKVP.yaml b/data/custodian/CZ-42-PER-L-OKVP.yaml index 2be9a9a07d..1e4d06486c 100644 --- a/data/custodian/CZ-42-PER-L-OKVP.yaml +++ b/data/custodian/CZ-42-PER-L-OKVP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PER-L-OKVP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PER-L-OKVP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PER-L-OKVP ghcid_numeric: 2292458713153583203 valid_from: '2025-12-06T23:37:22.153869+00:00' @@ -214,3 +215,22 @@ location: postal_code: 431 63 street_address: Hlavní 159 normalization_timestamp: '2025-12-09T10:54:18.491432+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:42:42.950366+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/perstejn + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/perstejn + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:42:42.950366+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-PET-L-OLKVP.yaml b/data/custodian/CZ-42-PET-L-OLKVP.yaml index aa13384bd4..760f3845c8 100644 --- a/data/custodian/CZ-42-PET-L-OLKVP.yaml +++ b/data/custodian/CZ-42-PET-L-OLKVP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PET-L-OLKVP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PET-L-OLKVP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PET-L-OLKVP ghcid_numeric: 944920782545019963 valid_from: '2025-12-06T23:37:41.239735+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 53 street_address: Pětipsy 58 normalization_timestamp: '2025-12-09T10:54:18.554123+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:43:21.256311+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/petipsy + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/petipsy + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T13:43:21.256311+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-PLO-L-MKMZ.yaml b/data/custodian/CZ-42-PLO-L-MKMZ.yaml index 605182057a..ed8f084f13 100644 --- a/data/custodian/CZ-42-PLO-L-MKMZ.yaml +++ b/data/custodian/CZ-42-PLO-L-MKMZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PLO-L-MKMZ - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PLO-L-MKMZ valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PLO-L-MKMZ ghcid_numeric: 16373936948648074238 valid_from: '2025-12-08T11:21:41.041645+00:00' @@ -210,3 +211,22 @@ location: postal_code: 410 02 street_address: Zahradní 245 normalization_timestamp: '2025-12-09T10:54:18.580512+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:43:26.135907+00:00' + source_url: https://mzernoseky-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mzernoseky-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://mzernoseky-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:43:26.135907+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-PLO-L-MKP.yaml b/data/custodian/CZ-42-PLO-L-MKP.yaml index 974163d491..1bfc7836f5 100644 --- a/data/custodian/CZ-42-PLO-L-MKP.yaml +++ b/data/custodian/CZ-42-PLO-L-MKP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PLO-L-MKP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PLO-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PLO-L-MKP ghcid_numeric: 12732155072419949186 valid_from: '2025-12-06T23:37:41.363843+00:00' @@ -209,3 +210,22 @@ location: postal_code: 411 42 street_address: Ploskovice 2 normalization_timestamp: '2025-12-09T10:54:18.619705+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:43:30.976241+00:00' + source_url: https://ploskovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ploskovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://ploskovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:43:30.976241+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-POL-L-MKP.yaml b/data/custodian/CZ-42-POL-L-MKP.yaml index 5f819c864e..aa218a3aa4 100644 --- a/data/custodian/CZ-42-POL-L-MKP.yaml +++ b/data/custodian/CZ-42-POL-L-MKP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-POL-L-MKP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-POL-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-POL-L-MKP ghcid_numeric: 16062442890072931044 valid_from: '2025-12-06T23:37:20.685416+00:00' @@ -210,3 +211,22 @@ location: postal_code: 411 47 street_address: Polepy 205 normalization_timestamp: '2025-12-09T10:54:18.746429+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:43:44.240196+00:00' + source_url: https://polepy-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://polepy-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://polepy-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:43:44.240196+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-PRA-L-MKPNL.yaml b/data/custodian/CZ-42-PRA-L-MKPNL.yaml index 748a46fca0..2a3f39b81d 100644 --- a/data/custodian/CZ-42-PRA-L-MKPNL.yaml +++ b/data/custodian/CZ-42-PRA-L-MKPNL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PRA-L-MKPNL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PRA-L-MKPNL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PRA-L-MKPNL ghcid_numeric: 8432756851016648197 valid_from: '2025-12-06T23:37:41.441110+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 33 street_address: Prackovice nad Labem 124 normalization_timestamp: '2025-12-09T10:54:18.851783+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T16:57:33.654623+00:00' + source_url: https://prackovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prackovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://prackovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T16:57:33.654623+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-PRA-L-MKVLNL.yaml b/data/custodian/CZ-42-PRA-L-MKVLNL.yaml index 31dbaee70a..15152b009c 100644 --- a/data/custodian/CZ-42-PRA-L-MKVLNL.yaml +++ b/data/custodian/CZ-42-PRA-L-MKVLNL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-PRA-L-MKVLNL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-PRA-L-MKVLNL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-PRA-L-MKVLNL ghcid_numeric: 14959669496969103741 valid_from: '2025-12-06T23:37:41.443846+00:00' @@ -206,3 +207,22 @@ location: postal_code: 411 33 street_address: Litochovice nad Labem 2 normalization_timestamp: '2025-12-09T10:54:18.879504+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T16:57:38.626852+00:00' + source_url: https://litochovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://litochovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://litochovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T16:57:38.626852+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-PRO-L-MKP.yaml b/data/custodian/CZ-42-PRO-L-MKP.yaml index bbf350389c..f2d09bbffd 100644 --- a/data/custodian/CZ-42-PRO-L-MKP.yaml +++ b/data/custodian/CZ-42-PRO-L-MKP.yaml @@ -218,3 +218,22 @@ location: postal_code: 417 12 street_address: Náměstí Svobody 700 normalization_timestamp: '2025-12-09T10:54:18.937468+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T16:58:18.905369+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/probostov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/probostov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T16:58:18.905369+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-RAD-L-MKR.yaml b/data/custodian/CZ-42-RAD-L-MKR.yaml index c41d84b5b4..0433efba75 100644 --- a/data/custodian/CZ-42-RAD-L-MKR.yaml +++ b/data/custodian/CZ-42-RAD-L-MKR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-RAD-L-MKR - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-RAD-L-MKR valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-RAD-L-MKR ghcid_numeric: 6101792441540714235 valid_from: '2025-12-06T23:37:41.348843+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 19 street_address: Radešín 120 normalization_timestamp: '2025-12-09T10:54:18.966305+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T16:58:24.742945+00:00' + source_url: https://radesin-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://radesin-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://radesin-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T16:58:24.742945+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-RAD-L-OKR.yaml b/data/custodian/CZ-42-RAD-L-OKR.yaml index 7c0a84c82a..d477407b69 100644 --- a/data/custodian/CZ-42-RAD-L-OKR.yaml +++ b/data/custodian/CZ-42-RAD-L-OKR.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-RAD-L-OKR - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-RAD-L-OKR valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-RAD-L-OKR ghcid_numeric: 716789286482570631 valid_from: '2025-12-06T23:37:22.176873+00:00' @@ -216,3 +217,22 @@ location: postal_code: 431 55 street_address: Radonice 76 normalization_timestamp: '2025-12-09T10:54:19.011328+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T16:58:32.497486+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/radonice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/radonice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T16:58:32.497486+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-REJ-G-GBR.yaml b/data/custodian/CZ-42-REJ-G-GBR.yaml index fbcece1f2d..7939dd2b45 100644 --- a/data/custodian/CZ-42-REJ-G-GBR.yaml +++ b/data/custodian/CZ-42-REJ-G-GBR.yaml @@ -278,3 +278,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Galerie Benedikta Rejta official youtube_search_timestamp: '2025-12-09T09:31:27.674517+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T17:23:28.783371+00:00' + source_url: https://www.gbr.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.gbr.cz/style/favicon/safari-pinned-tab.svg + source_url: https://www.gbr.cz + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T17:23:28.783371+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-ROH-L-MKR.yaml b/data/custodian/CZ-42-ROH-L-MKR.yaml index 066cb0ff76..4f40d940d7 100644 --- a/data/custodian/CZ-42-ROH-L-MKR.yaml +++ b/data/custodian/CZ-42-ROH-L-MKR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ROH-L-MKR - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ROH-L-MKR valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ROH-L-MKR ghcid_numeric: 17384640758410013173 valid_from: '2025-12-06T23:37:41.457766+00:00' @@ -207,3 +208,22 @@ location: postal_code: 412 01 street_address: Doksanská 72 normalization_timestamp: '2025-12-09T10:54:19.102918+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T17:38:51.924487+00:00' + source_url: https://rohatce-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rohatce-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://rohatce-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T17:38:51.924487+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ROU-L-MKC.yaml b/data/custodian/CZ-42-ROU-L-MKC.yaml index 244bd717a0..a3519113b0 100644 --- a/data/custodian/CZ-42-ROU-L-MKC.yaml +++ b/data/custodian/CZ-42-ROU-L-MKC.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ROU-L-MKC - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ROU-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ROU-L-MKC ghcid_numeric: 17595373229422557713 valid_from: '2025-12-06T23:37:41.404308+00:00' @@ -209,3 +210,22 @@ location: postal_code: 413 01 street_address: Ctiněves 61 normalization_timestamp: '2025-12-09T10:54:19.293061+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T18:31:55.640842+00:00' + source_url: https://ctineves-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ctineves-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://ctineves-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T18:31:55.640842+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ROU-L-MKD-mistni_knihovna_dobrin.yaml b/data/custodian/CZ-42-ROU-L-MKD-mistni_knihovna_dobrin.yaml index 634a27ca3e..8e81003244 100644 --- a/data/custodian/CZ-42-ROU-L-MKD-mistni_knihovna_dobrin.yaml +++ b/data/custodian/CZ-42-ROU-L-MKD-mistni_knihovna_dobrin.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ROU-L-MKD-mistni_knihovna_dobrin - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ROU-L-MKD-mistni_knihovna_dobrin valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ROU-L-MKD-mistni_knihovna_dobrin ghcid_numeric: 11506292948689378236 valid_from: '2025-12-06T23:37:41.483668+00:00' @@ -205,3 +206,22 @@ location: postal_code: 413 01 street_address: Lihovarský statek 17 normalization_timestamp: '2025-12-09T10:54:19.316995+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T18:49:46.043130+00:00' + source_url: https://dobrin-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://dobrin-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://dobrin-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T18:49:46.043130+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ROU-L-MKD.yaml b/data/custodian/CZ-42-ROU-L-MKD.yaml index 714509917e..26b2fc03ad 100644 --- a/data/custodian/CZ-42-ROU-L-MKD.yaml +++ b/data/custodian/CZ-42-ROU-L-MKD.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ROU-L-MKD - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ROU-L-MKD valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ROU-L-MKD ghcid_numeric: 9755406429786679700 valid_from: '2025-12-06T23:37:41.410445+00:00' @@ -209,3 +210,22 @@ location: postal_code: 413 01 street_address: Dušníky 65 normalization_timestamp: '2025-12-09T10:54:19.345292+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T18:57:10.650164+00:00' + source_url: https://dusniky-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://dusniky-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://dusniky-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T18:57:10.650164+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ROU-L-MKK-mistni_knihovna_kyskovice.yaml b/data/custodian/CZ-42-ROU-L-MKK-mistni_knihovna_kyskovice.yaml index 7c3533204f..1de53f0675 100644 --- a/data/custodian/CZ-42-ROU-L-MKK-mistni_knihovna_kyskovice.yaml +++ b/data/custodian/CZ-42-ROU-L-MKK-mistni_knihovna_kyskovice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ROU-L-MKK-mistni_knihovna_kyskovice - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ROU-L-MKK-mistni_knihovna_kyskovice valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ROU-L-MKK-mistni_knihovna_kyskovice ghcid_numeric: 5530622660361680141 valid_from: '2025-12-06T23:37:41.395252+00:00' @@ -205,3 +206,22 @@ location: postal_code: 413 01 street_address: Kyškovice 5 normalization_timestamp: '2025-12-09T10:54:19.373095+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T18:57:15.762498+00:00' + source_url: https://kyskovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kyskovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://kyskovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T18:57:15.762498+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ROU-L-MKV-mistni_knihovna_vetla.yaml b/data/custodian/CZ-42-ROU-L-MKV-mistni_knihovna_vetla.yaml index d05dd5e3b5..9c400c0cf0 100644 --- a/data/custodian/CZ-42-ROU-L-MKV-mistni_knihovna_vetla.yaml +++ b/data/custodian/CZ-42-ROU-L-MKV-mistni_knihovna_vetla.yaml @@ -206,3 +206,22 @@ location: postal_code: 413 01 street_address: K Sovici 16 normalization_timestamp: '2025-12-09T10:54:19.449518+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T18:59:29.382195+00:00' + source_url: https://vetla-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vetla-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://vetla-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T18:59:29.382195+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ROU-L-MKV.yaml b/data/custodian/CZ-42-ROU-L-MKV.yaml index 003fbd9295..589a54afba 100644 --- a/data/custodian/CZ-42-ROU-L-MKV.yaml +++ b/data/custodian/CZ-42-ROU-L-MKV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ROU-L-MKV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ROU-L-MKV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ROU-L-MKV ghcid_numeric: 16555989355490272033 valid_from: '2025-12-06T23:37:41.383440+00:00' @@ -205,3 +206,22 @@ location: postal_code: 413 01 street_address: Na Průhonu 270 normalization_timestamp: '2025-12-09T10:54:19.489868+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T19:14:36.762600+00:00' + source_url: https://vedomice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vedomice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://vedomice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T19:14:36.762600+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ROU-M-PMK.yaml b/data/custodian/CZ-42-ROU-M-PMK.yaml index 73b52a708a..a85aa6b73e 100644 --- a/data/custodian/CZ-42-ROU-M-PMK.yaml +++ b/data/custodian/CZ-42-ROU-M-PMK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ROU-M-PMK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ROU-M-PMK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ROU-M-PMK ghcid_numeric: 17655103223651851861 valid_from: '2025-12-06T23:37:43.451521+00:00' @@ -208,3 +209,22 @@ location: postal_code: 413 01 street_address: Náměstí Jana z Dražic 101 normalization_timestamp: '2025-12-09T10:54:19.540873+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T19:49:39.102944+00:00' + source_url: https://katalog.podripskemuzeum.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.podripskemuzeum.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.podripskemuzeum.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T19:49:39.102944+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-RTY-L-OKRNB.yaml b/data/custodian/CZ-42-RTY-L-OKRNB.yaml index e12675ff06..544d02ce35 100644 --- a/data/custodian/CZ-42-RTY-L-OKRNB.yaml +++ b/data/custodian/CZ-42-RTY-L-OKRNB.yaml @@ -210,3 +210,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:15.356189+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Rtyně nad Bílinou +logo_enrichment: + enrichment_timestamp: '2025-12-24T20:00:28.336330+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/rtynenb + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/rtynenb + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T20:00:28.336330+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-RUM-L-KZSMNVUNLZ.yaml b/data/custodian/CZ-42-RUM-L-KZSMNVUNLZ.yaml index 9df1b482b0..96d1805c21 100644 --- a/data/custodian/CZ-42-RUM-L-KZSMNVUNLZ.yaml +++ b/data/custodian/CZ-42-RUM-L-KZSMNVUNLZ.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-RUM-L-KZSMNVUNLZ - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-RUM-L-KZSMNVUNLZ valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-RUM-L-KZSMNVUNLZ ghcid_numeric: 4219323818988055852 valid_from: '2025-12-08T11:21:36.255370+00:00' @@ -224,3 +225,22 @@ location: postal_code: 408 01 street_address: Jiráskova 1378/4 normalization_timestamp: '2025-12-09T10:54:19.598112+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T20:00:33.863207+00:00' + source_url: https://www.kzcr.eu/cz/kz/o-spolecnosti/tiskove-zpravy/1/#ca13781 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kzcr.eu/favicon.ico + source_url: https://www.kzcr.eu/cz/kz/o-spolecnosti/tiskove-zpravy/1/#ca13781 + css_selector: '#html > head > link' + retrieved_on: '2025-12-24T20:00:33.863207+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-RUM-L-MKR.yaml b/data/custodian/CZ-42-RUM-L-MKR.yaml index ae9e9e5363..de2e2130e7 100644 --- a/data/custodian/CZ-42-RUM-L-MKR.yaml +++ b/data/custodian/CZ-42-RUM-L-MKR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-RUM-L-MKR - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-RUM-L-MKR valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-RUM-L-MKR ghcid_numeric: 16717771757975281882 valid_from: '2025-12-06T23:37:17.520545+00:00' @@ -229,3 +230,22 @@ location: postal_code: 408 01 street_address: tř. 9.května 150/29 normalization_timestamp: '2025-12-09T10:54:19.632728+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T20:34:06.188056+00:00' + source_url: https://rumburk.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rumburk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://rumburk.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T20:34:06.188056+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-RUM-M-KOMVDPOPR.yaml b/data/custodian/CZ-42-RUM-M-KOMVDPOPR.yaml index c19be59ac9..b79f85edfd 100644 --- a/data/custodian/CZ-42-RUM-M-KOMVDPOPR.yaml +++ b/data/custodian/CZ-42-RUM-M-KOMVDPOPR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-RUM-M-KOMVDPOPR - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-RUM-M-KOMVDPOPR valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-RUM-M-KOMVDPOPR ghcid_numeric: 15672696304010963325 valid_from: '2025-12-06T23:37:43.262557+00:00' @@ -210,3 +211,22 @@ location: postal_code: 408 01 street_address: Na Valech 401/4 normalization_timestamp: '2025-12-09T10:54:19.658386+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T20:50:33.148134+00:00' + source_url: http://www.muzeumdc.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.muzeumdc.cz/themes/muzeobot/favicon.ico + source_url: http://www.muzeumdc.cz + css_selector: '[document] > html.js.adaptivetheme > head > link' + retrieved_on: '2025-12-24T20:50:33.148134+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-SNE-L-MKS.yaml b/data/custodian/CZ-42-SNE-L-MKS.yaml index 03b70ac8b0..7483c49181 100644 --- a/data/custodian/CZ-42-SNE-L-MKS.yaml +++ b/data/custodian/CZ-42-SNE-L-MKS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-SNE-L-MKS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-SNE-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-SNE-L-MKS ghcid_numeric: 13971976362187298066 valid_from: '2025-12-06T23:37:41.373162+00:00' @@ -209,3 +210,22 @@ location: postal_code: 411 74 street_address: Snědovice 99 normalization_timestamp: '2025-12-09T10:54:19.747930+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:01:35.375306+00:00' + source_url: https://snedovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://snedovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://snedovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:01:35.375306+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-SPO-L-OKVOS.yaml b/data/custodian/CZ-42-SPO-L-OKVOS.yaml index a1eec1812f..b23f033ed5 100644 --- a/data/custodian/CZ-42-SPO-L-OKVOS.yaml +++ b/data/custodian/CZ-42-SPO-L-OKVOS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-SPO-L-OKVOS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-SPO-L-OKVOS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-SPO-L-OKVOS ghcid_numeric: 2883062320989706892 valid_from: '2025-12-06T23:37:41.276773+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 01 street_address: U Koupaliště 494 normalization_timestamp: '2025-12-09T10:54:19.781404+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:07:16.137216+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/sporice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/sporice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:07:16.137216+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-STA-L-OKS.yaml b/data/custodian/CZ-42-STA-L-OKS.yaml index f5e6d5a062..68f6a22161 100644 --- a/data/custodian/CZ-42-STA-L-OKS.yaml +++ b/data/custodian/CZ-42-STA-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-STA-L-OKS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-STA-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-STA-L-OKS ghcid_numeric: 806948340397023385 valid_from: '2025-12-06T23:37:26.508739+00:00' @@ -219,3 +220,22 @@ location: postal_code: 439 49 street_address: Postoloprtská 8 normalization_timestamp: '2025-12-09T10:54:19.820258+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:07:56.578604+00:00' + source_url: https://tritius.mekzatec.cz/library/stankovice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mekzatec.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mekzatec.cz/library/stankovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:07:56.578604+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-STA-L-OKSK.yaml b/data/custodian/CZ-42-STA-L-OKSK.yaml index 9273db277f..1008f02770 100644 --- a/data/custodian/CZ-42-STA-L-OKSK.yaml +++ b/data/custodian/CZ-42-STA-L-OKSK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-STA-L-OKSK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-STA-L-OKSK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-STA-L-OKSK ghcid_numeric: 3391646922136415249 valid_from: '2025-12-06T23:37:41.198913+00:00' @@ -209,3 +210,22 @@ location: postal_code: 407 61 street_address: Staré Křečany 44 normalization_timestamp: '2025-12-09T10:54:19.874199+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:05.963800+00:00' + source_url: https://decin.tritius.cz/library/skat + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://decin.tritius.cz/apple-touch-icon-180x180.png + source_url: https://decin.tritius.cz/library/skat + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:08:05.963800+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-STE-E-VOSOTSSSKP.yaml b/data/custodian/CZ-42-STE-E-VOSOTSSSKP.yaml index 9b645c695e..c0cc1712d0 100644 --- a/data/custodian/CZ-42-STE-E-VOSOTSSSKP.yaml +++ b/data/custodian/CZ-42-STE-E-VOSOTSSSKP.yaml @@ -222,3 +222,32 @@ location: postal_code: 411 08 street_address: Kostelní 134 normalization_timestamp: '2025-12-09T10:54:19.907157+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:11.545564+00:00' + source_url: https://www.odbornaskola.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.odbornaskola.cz/wp-content/uploads/2023/09/UK_VOSOT_RGB-314x50.png + source_url: https://www.odbornaskola.cz + css_selector: '#masthead > div.main-header-bar-wrap > div.main-header-bar > div.ast-container + > div.ast-flex.main-header-container > div.site-branding > div.ast-site-identity + > span.site-logo-img > a.custom-logo-link > img.custom-logo' + retrieved_on: '2025-12-24T21:08:11.545564+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: VOŠ ot a SŠ Štětí + - claim_type: favicon_url + claim_value: https://www.odbornaskola.cz/wp-content/uploads/2020/02/navlogo-1.png + source_url: https://www.odbornaskola.cz + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-24T21:08:11.545564+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-STR-L-MKSV.yaml b/data/custodian/CZ-42-STR-L-MKSV.yaml index b71bd99847..99bbb757ad 100644 --- a/data/custodian/CZ-42-STR-L-MKSV.yaml +++ b/data/custodian/CZ-42-STR-L-MKSV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-STR-L-MKSV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-STR-L-MKSV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-STR-L-MKSV ghcid_numeric: 11079551098283234910 valid_from: '2025-12-06T23:37:41.376174+00:00' @@ -208,3 +209,22 @@ location: postal_code: 411 84 street_address: Straškov-Vodochody 120 normalization_timestamp: '2025-12-09T10:54:19.974596+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:21.268566+00:00' + source_url: https://straskov-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://straskov-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://straskov-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:08:21.268566+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-SUL-L-MKS.yaml b/data/custodian/CZ-42-SUL-L-MKS.yaml index efa31bc8d4..3af6203f5d 100644 --- a/data/custodian/CZ-42-SUL-L-MKS.yaml +++ b/data/custodian/CZ-42-SUL-L-MKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-SUL-L-MKS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-SUL-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-SUL-L-MKS ghcid_numeric: 12637422944341883034 valid_from: '2025-12-06T23:37:41.398743+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 11 street_address: Náves 5 normalization_timestamp: '2025-12-09T10:54:20.003902+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:26.381060+00:00' + source_url: https://sulejovice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sulejovice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://sulejovice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:08:26.381060+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-SVE-L-OKS.yaml b/data/custodian/CZ-42-SVE-L-OKS.yaml index b46ee8a4a6..f08ef9ba85 100644 --- a/data/custodian/CZ-42-SVE-L-OKS.yaml +++ b/data/custodian/CZ-42-SVE-L-OKS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-SVE-L-OKS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-SVE-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-SVE-L-OKS ghcid_numeric: 9281891818272410137 valid_from: '2025-12-06T23:37:26.760099+00:00' @@ -214,3 +215,22 @@ location: postal_code: 417 53 street_address: Preissigovo náměstí 4 normalization_timestamp: '2025-12-09T10:54:20.032343+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:33.055452+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/svetec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/svetec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:08:33.055452+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-TEP-A-SOAT-statni_okresni_archiv_teplice.yaml b/data/custodian/CZ-42-TEP-A-SOAT-statni_okresni_archiv_teplice.yaml index 0231bb99c2..ada9973729 100644 --- a/data/custodian/CZ-42-TEP-A-SOAT-statni_okresni_archiv_teplice.yaml +++ b/data/custodian/CZ-42-TEP-A-SOAT-statni_okresni_archiv_teplice.yaml @@ -250,3 +250,29 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Teplice official youtube_search_timestamp: '2025-12-09T09:31:28.349086+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:41.082488+00:00' + source_url: http://www.soalitomerice.cz/soka-teplice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: http://www.soalitomerice.cz/soka-teplice + css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:08:41.082488+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/sokatp.jpg + source_url: http://www.soalitomerice.cz/soka-teplice + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T21:08:41.082488+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-TEP-E-KTCK.yaml b/data/custodian/CZ-42-TEP-E-KTCK.yaml index 21d5f9093e..df5768adbc 100644 --- a/data/custodian/CZ-42-TEP-E-KTCK.yaml +++ b/data/custodian/CZ-42-TEP-E-KTCK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TEP-E-KTCK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TEP-E-KTCK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TEP-E-KTCK ghcid_numeric: 7965636977019626502 valid_from: '2025-12-08T11:21:26.625824+00:00' @@ -215,3 +216,22 @@ location: postal_code: 415 01 street_address: Českobratrská 862/15 normalization_timestamp: '2025-12-09T10:54:20.059287+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:47.783257+00:00' + source_url: https://skola.tritius.cz/library/teplice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://skola.tritius.cz/apple-touch-icon-180x180.png + source_url: https://skola.tritius.cz/library/teplice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:08:47.783257+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-TEP-E-VOSZSSZPK.yaml b/data/custodian/CZ-42-TEP-E-VOSZSSZPK.yaml index fa2047776d..25f432ae73 100644 --- a/data/custodian/CZ-42-TEP-E-VOSZSSZPK.yaml +++ b/data/custodian/CZ-42-TEP-E-VOSZSSZPK.yaml @@ -55,13 +55,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TEP-E-VOSZSSZPK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TEP-E-VOSZSSZPK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TEP-E-VOSZSSZPK ghcid_numeric: 977536508792571448 valid_from: '2025-12-08T11:21:25.401458+00:00' @@ -234,3 +235,22 @@ location: postal_code: 415 01 street_address: Kapelní 2 normalization_timestamp: '2025-12-09T10:54:20.088117+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:53.180220+00:00' + source_url: https://www.szsvzs.cz/knihovna-moskevska + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.szsvzs.cz/image.php?nid=12268&oid=9729226&width=32 + source_url: https://www.szsvzs.cz/knihovna-moskevska + css_selector: '[document] > html > head > link:nth-of-type(34)' + retrieved_on: '2025-12-24T21:08:53.180220+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-TEP-L-RKTPO.yaml b/data/custodian/CZ-42-TEP-L-RKTPO.yaml index dbe4010c92..8c4b392bf0 100644 --- a/data/custodian/CZ-42-TEP-L-RKTPO.yaml +++ b/data/custodian/CZ-42-TEP-L-RKTPO.yaml @@ -182,3 +182,22 @@ wikidata_enrichment: image: https://commons.wikimedia.org/wiki/Special:FilePath/Teplice-Lipova-13.jpg instance_of: - Q114617264 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:08.535200+00:00' + source_url: https://tritius.knihovna-teplice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:09:08.535200+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-TEP-M-RMVTPK.yaml b/data/custodian/CZ-42-TEP-M-RMVTPK.yaml index 4210744288..be99ba548a 100644 --- a/data/custodian/CZ-42-TEP-M-RMVTPK.yaml +++ b/data/custodian/CZ-42-TEP-M-RMVTPK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TEP-M-RMVTPK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TEP-M-RMVTPK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TEP-M-RMVTPK ghcid_numeric: 9062048079462307905 valid_from: '2025-12-06T23:37:20.229838+00:00' @@ -210,3 +211,22 @@ location: postal_code: 415 01 street_address: Zámecké nám. 14 normalization_timestamp: '2025-12-09T10:54:20.343400+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:27.207059+00:00' + source_url: https://muzeum-teplice.tritius.cz/?device=1 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeum-teplice.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeum-teplice.tritius.cz/?device=1 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:09:27.207059+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-TEP-O-SOAVLSOAT.yaml b/data/custodian/CZ-42-TEP-O-SOAVLSOAT.yaml index 99d1064f2e..1cd383e112 100644 --- a/data/custodian/CZ-42-TEP-O-SOAVLSOAT.yaml +++ b/data/custodian/CZ-42-TEP-O-SOAVLSOAT.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TEP-O-SOAVLSOAT - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TEP-O-SOAVLSOAT valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TEP-O-SOAVLSOAT ghcid_numeric: 4712832240853310579 valid_from: '2025-12-06T23:37:43.259602+00:00' @@ -220,3 +221,29 @@ location: postal_code: 415 01 street_address: Školní 8 normalization_timestamp: '2025-12-09T10:54:20.383657+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:38.067612+00:00' + source_url: https://www.soalitomerice.cz/soka-teplice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: https://www.soalitomerice.cz/soka-teplice + css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:09:38.067612+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/sokatp.jpg + source_url: https://www.soalitomerice.cz/soka-teplice + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T21:09:38.067612+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-42-TER-L-MKT.yaml b/data/custodian/CZ-42-TER-L-MKT.yaml index cf282fb64c..ebec769b2a 100644 --- a/data/custodian/CZ-42-TER-L-MKT.yaml +++ b/data/custodian/CZ-42-TER-L-MKT.yaml @@ -224,3 +224,22 @@ location: postal_code: 411 55 street_address: Wieserův dům - Dlouhá 25 normalization_timestamp: '2025-12-09T10:54:20.506433+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:45.547251+00:00' + source_url: https://katalog.knihovna-terezin.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-terezin.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-terezin.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:09:45.547251+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-TER-L-VSAPSRK.yaml b/data/custodian/CZ-42-TER-L-VSAPSRK.yaml index 1ddb6ffeff..ae290d2b9f 100644 --- a/data/custodian/CZ-42-TER-L-VSAPSRK.yaml +++ b/data/custodian/CZ-42-TER-L-VSAPSRK.yaml @@ -47,13 +47,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TER-L-VSAPSRK - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TER-L-VSAPSRK valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TER-L-VSAPSRK ghcid_numeric: 14247199792365414210 valid_from: '2025-12-08T11:21:26.761226+00:00' @@ -178,3 +179,22 @@ location: postal_code: 411 55 street_address: Akademická 409 normalization_timestamp: '2025-12-09T06:52:55.471331+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:51.878417+00:00' + source_url: https://www.vsaps.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vsaps.cz/favicon.ico + source_url: https://www.vsaps.cz + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:09:51.878417+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-TER-M-PTNKP.yaml b/data/custodian/CZ-42-TER-M-PTNKP.yaml index 95b7d75642..e6b4df8ba7 100644 --- a/data/custodian/CZ-42-TER-M-PTNKP.yaml +++ b/data/custodian/CZ-42-TER-M-PTNKP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TER-M-PTNKP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TER-M-PTNKP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TER-M-PTNKP ghcid_numeric: 8689602745858177669 valid_from: '2025-12-06T23:37:18.559228+00:00' @@ -220,3 +221,22 @@ location: postal_code: 411 55 street_address: Památník Terezín, Principova alej 304 normalization_timestamp: '2025-12-09T10:54:20.545027+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:10:01.060975+00:00' + source_url: https://pamatnik-terezin.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://pamatnik-terezin.tritius.cz/apple-touch-icon-180x180.png + source_url: https://pamatnik-terezin.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:10:01.060975+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-TRE-L-MKP.yaml b/data/custodian/CZ-42-TRE-L-MKP.yaml index 2ed1eb36ce..08f4795138 100644 --- a/data/custodian/CZ-42-TRE-L-MKP.yaml +++ b/data/custodian/CZ-42-TRE-L-MKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TRE-L-MKP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TRE-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TRE-L-MKP ghcid_numeric: 2101163875839955146 valid_from: '2025-12-06T23:37:41.520731+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 15 street_address: Podsedice 29 normalization_timestamp: '2025-12-09T10:54:20.568524+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:10:09.896375+00:00' + source_url: https://www.obecpodsedice.cz/kultura-a-sport/knihovna-podsedice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obecpodsedice.cz/skins/obecpodsedice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.obecpodsedice.cz/kultura-a-sport/knihovna-podsedice + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:10:09.896375+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-TRE-L-MKVS.yaml b/data/custodian/CZ-42-TRE-L-MKVS.yaml index 6464176cd5..56ec220a90 100644 --- a/data/custodian/CZ-42-TRE-L-MKVS.yaml +++ b/data/custodian/CZ-42-TRE-L-MKVS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-TRE-L-MKVS - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-TRE-L-MKVS valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-TRE-L-MKVS ghcid_numeric: 9035440079171153355 valid_from: '2025-12-06T23:37:41.515073+00:00' @@ -205,3 +206,22 @@ location: postal_code: 411 15 street_address: Solany 66 normalization_timestamp: '2025-12-09T10:54:20.728132+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:10:15.821611+00:00' + source_url: https://solany-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://solany-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://solany-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:10:15.821611+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-TUC-L-MKT.yaml b/data/custodian/CZ-42-TUC-L-MKT.yaml index 5c7cc0c169..510e780941 100644 --- a/data/custodian/CZ-42-TUC-L-MKT.yaml +++ b/data/custodian/CZ-42-TUC-L-MKT.yaml @@ -206,3 +206,22 @@ location: postal_code: 439 69 street_address: Tuchořice 123 normalization_timestamp: '2025-12-09T10:54:20.889188+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:11:11.894599+00:00' + source_url: https://www.tuchorice.cz/obec/mistni-knihovna-tuchorice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tuchorice.cz/skins/tuchorice.cz_lego/favicons/safari-pinned-tab.svg + source_url: https://www.tuchorice.cz/obec/mistni-knihovna-tuchorice + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:11:11.894599+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-UDL-L-OKVU.yaml b/data/custodian/CZ-42-UDL-L-OKVU.yaml index 28e4ed6711..7bbd18b949 100644 --- a/data/custodian/CZ-42-UDL-L-OKVU.yaml +++ b/data/custodian/CZ-42-UDL-L-OKVU.yaml @@ -218,3 +218,22 @@ location: postal_code: 431 41 street_address: Máchova 474 normalization_timestamp: '2025-12-09T10:54:20.920368+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:12:08.074025+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/udlice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/udlice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:12:08.074025+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-UJE-L-MLKU.yaml b/data/custodian/CZ-42-UJE-L-MLKU.yaml index 35d7a90bb5..d17090fe0c 100644 --- a/data/custodian/CZ-42-UJE-L-MLKU.yaml +++ b/data/custodian/CZ-42-UJE-L-MLKU.yaml @@ -220,3 +220,22 @@ location: postal_code: 415 01 street_address: nám. Boženy Němcové 2 normalization_timestamp: '2025-12-09T10:54:20.953642+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:12:39.221690+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/ujezdecek + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/ujezdecek + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:12:39.221690+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-UNL-M-MMUNL.yaml b/data/custodian/CZ-42-UNL-M-MMUNL.yaml index 9445301dc8..7483015ee1 100644 --- a/data/custodian/CZ-42-UNL-M-MMUNL.yaml +++ b/data/custodian/CZ-42-UNL-M-MMUNL.yaml @@ -264,3 +264,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Muzeum města Ústí nad Labem official youtube_search_timestamp: '2025-12-09T09:31:30.331184+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:22:55.771074+00:00' + source_url: http://www.muzeumusti.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.muzeumusti.cz/wp-content/uploads/2025/01/favi.jpg + source_url: http://www.muzeumusti.cz + css_selector: '[document] > html.js.cssanimations > head > link:nth-of-type(34)' + retrieved_on: '2025-12-24T21:22:55.771074+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-UST-L-NPUUOPVUNL.yaml b/data/custodian/CZ-42-UST-L-NPUUOPVUNL.yaml index d0f9c1a48a..0ffdde5f9b 100644 --- a/data/custodian/CZ-42-UST-L-NPUUOPVUNL.yaml +++ b/data/custodian/CZ-42-UST-L-NPUUOPVUNL.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-UST-L-NPUUOPVUNL - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-UST-L-NPUUOPVUNL valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-UST-L-NPUUOPVUNL ghcid_numeric: 17721533513222719452 valid_from: '2025-12-08T11:21:29.274567+00:00' @@ -229,3 +230,22 @@ location: postal_code: 400 07 street_address: Podmokelská 1/15 normalization_timestamp: '2025-12-09T10:54:21.096967+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:23:45.442560+00:00' + source_url: https://iispp.npu.cz/carmen/library/unl + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://iispp.npu.cz/carmen/apple-touch-icon-180x180.png + source_url: https://iispp.npu.cz/carmen/library/unl + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:23:45.442560+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-UST-L-OUSTK.yaml b/data/custodian/CZ-42-UST-L-OUSTK.yaml index 58176ad46f..4b3c1d2107 100644 --- a/data/custodian/CZ-42-UST-L-OUSTK.yaml +++ b/data/custodian/CZ-42-UST-L-OUSTK.yaml @@ -181,3 +181,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1438040 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:23:54.458665+00:00' + source_url: https://www.orlenunicre.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.orlenunicre.cz/logotypes404/favicon.ico + source_url: https://www.orlenunicre.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:23:54.458665+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-UST-L-SSTK.yaml b/data/custodian/CZ-42-UST-L-SSTK.yaml index 0a042a04fa..acf30f3e84 100644 --- a/data/custodian/CZ-42-UST-L-SSTK.yaml +++ b/data/custodian/CZ-42-UST-L-SSTK.yaml @@ -221,3 +221,28 @@ location: postal_code: 400 32 street_address: Revoluční 1930/86 normalization_timestamp: '2025-12-09T10:54:21.217310+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:04.457163+00:00' + source_url: https://www.spolchemie.cz/cs + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.spolchemie.cz/wp-content/uploads/2023/03/favicon@4x.png + source_url: https://www.spolchemie.cz/cs + css_selector: '[document] > html > head > link:nth-of-type(40)' + retrieved_on: '2025-12-24T21:24:04.457163+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://www.spolchemie.cz/wp-content/uploads/2023/03/show-image-1.jpg + source_url: https://www.spolchemie.cz/cs + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T21:24:04.457163+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-42-UST-L-UJPVK.yaml b/data/custodian/CZ-42-UST-L-UJPVK.yaml index 7a23218d45..f270004806 100644 --- a/data/custodian/CZ-42-UST-L-UJPVK.yaml +++ b/data/custodian/CZ-42-UST-L-UJPVK.yaml @@ -183,3 +183,22 @@ wikidata_enrichment: image: https://commons.wikimedia.org/wiki/Special:FilePath/VK_UJEP_-_volný_výběr.jpg instance_of: - Q1622062 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:18.019834+00:00' + source_url: https://arl.ujep.cz/arl-ujep/cs/index + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://arl.ujep.cz/i2/user/ujep/img/logo.svg + source_url: https://arl.ujep.cz/arl-ujep/cs/index + css_selector: '#logo > a > img' + retrieved_on: '2025-12-24T21:24:18.019834+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo UJEP + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-42-UST-M-OMVUNLPOK.yaml b/data/custodian/CZ-42-UST-M-OMVUNLPOK.yaml index 6f46e9883e..e6c8d9d13a 100644 --- a/data/custodian/CZ-42-UST-M-OMVUNLPOK.yaml +++ b/data/custodian/CZ-42-UST-M-OMVUNLPOK.yaml @@ -225,3 +225,32 @@ location: postal_code: 400 01 street_address: Masarykova 3 normalization_timestamp: '2025-12-09T10:54:21.384084+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:30.059532+00:00' + source_url: https://muzeum-usti.kpsys.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://muzeum-usti.kpsys.cz/custom/design/main-menu-logo.png + source_url: https://muzeum-usti.kpsys.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > h1.unset-style > img' + retrieved_on: '2025-12-24T21:24:30.059532+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://muzeum-usti.kpsys.cz/favicon.png?v=2.3.0-32021 + source_url: https://muzeum-usti.kpsys.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T21:24:30.059532+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-VAL-L-OKV.yaml b/data/custodian/CZ-42-VAL-L-OKV.yaml index e93915aa90..513143c1a0 100644 --- a/data/custodian/CZ-42-VAL-L-OKV.yaml +++ b/data/custodian/CZ-42-VAL-L-OKV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VAL-L-OKV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VAL-L-OKV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VAL-L-OKV ghcid_numeric: 5188572806471686928 valid_from: '2025-12-06T23:37:41.158304+00:00' @@ -237,3 +238,22 @@ location: postal_code: 407 24 street_address: Valkeřice 299 normalization_timestamp: '2025-12-09T10:54:21.413083+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:36.909205+00:00' + source_url: https://www.valkerice.cz/firmy-a-sluzby + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.valkerice.cz/image.php?nid=19154&oid=8235716&width=36 + source_url: https://www.valkerice.cz/firmy-a-sluzby + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-24T21:24:36.909205+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-VEJ-L-MKSS.yaml b/data/custodian/CZ-42-VEJ-L-MKSS.yaml index 797ccf64c7..85ad9557c7 100644 --- a/data/custodian/CZ-42-VEJ-L-MKSS.yaml +++ b/data/custodian/CZ-42-VEJ-L-MKSS.yaml @@ -218,3 +218,28 @@ location: postal_code: 431 91 street_address: Pohraniční stráže 1272/2 normalization_timestamp: '2025-12-09T10:54:21.567972+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:49.199853+00:00' + source_url: https://www.vejprty.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vejprty.cz/apple-icon-180x180.png + source_url: https://www.vejprty.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T21:24:49.199853+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.vejprty.cz/images/upload/facebookshare.jpg + source_url: https://www.vejprty.cz/knihovna + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:24:49.199853+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 13 diff --git a/data/custodian/CZ-42-VEJ-L-OKVKH.yaml b/data/custodian/CZ-42-VEJ-L-OKVKH.yaml index 627d1f94a9..d7bfb0d368 100644 --- a/data/custodian/CZ-42-VEJ-L-OKVKH.yaml +++ b/data/custodian/CZ-42-VEJ-L-OKVKH.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VEJ-L-OKVKH - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VEJ-L-OKVKH valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VEJ-L-OKVKH ghcid_numeric: 3859426789740173311 valid_from: '2025-12-06T23:37:41.317367+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 91 street_address: Kryštofovy Hamry 64 normalization_timestamp: '2025-12-09T10:54:21.651810+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:57.073732+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/hamry + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/hamry + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:24:57.073732+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-VEL-L-MKV-mistni_knihovna_velteze.yaml b/data/custodian/CZ-42-VEL-L-MKV-mistni_knihovna_velteze.yaml index f68afe2bed..475431a717 100644 --- a/data/custodian/CZ-42-VEL-L-MKV-mistni_knihovna_velteze.yaml +++ b/data/custodian/CZ-42-VEL-L-MKV-mistni_knihovna_velteze.yaml @@ -47,13 +47,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VEL-L-MKV-mistni_knihovna_velteze - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VEL-L-MKV-mistni_knihovna_velteze valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VEL-L-MKV-mistni_knihovna_velteze ghcid_numeric: 12196137094559154939 valid_from: '2025-12-06T23:37:41.551291+00:00' @@ -211,3 +212,22 @@ location: postal_code: 439 01 street_address: Veltěže 73 normalization_timestamp: '2025-12-09T10:54:21.840240+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:02.545666+00:00' + source_url: https://www.velteze.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.velteze.cz/image.php?nid=18055&oid=7851271 + source_url: https://www.velteze.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(25)' + retrieved_on: '2025-12-24T21:25:02.545666+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-VEL-L-MKVM.yaml b/data/custodian/CZ-42-VEL-L-MKVM.yaml index 130d8ebdbc..f2aef49ef7 100644 --- a/data/custodian/CZ-42-VEL-L-MKVM.yaml +++ b/data/custodian/CZ-42-VEL-L-MKVM.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VEL-L-MKVM - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VEL-L-MKVM valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VEL-L-MKVM ghcid_numeric: 769460936760024499 valid_from: '2025-12-06T23:37:41.466190+00:00' @@ -209,3 +210,22 @@ location: postal_code: 411 33 street_address: Milešov 16 normalization_timestamp: '2025-12-09T10:54:21.889276+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:07.569307+00:00' + source_url: https://milesov-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://milesov-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://milesov-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:25:07.569307+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-VEL-L-MKVS.yaml b/data/custodian/CZ-42-VEL-L-MKVS.yaml index 224d58557c..79e0c2d1ea 100644 --- a/data/custodian/CZ-42-VEL-L-MKVS.yaml +++ b/data/custodian/CZ-42-VEL-L-MKVS.yaml @@ -217,3 +217,22 @@ location: postal_code: 407 78 street_address: Šluknovská 422 normalization_timestamp: '2025-12-09T10:54:21.919377+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:13.409216+00:00' + source_url: https://decin.tritius.cz/library/region + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://decin.tritius.cz/apple-touch-icon-180x180.png + source_url: https://decin.tritius.cz/library/region + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:25:13.409216+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-VEL-L-OKVVB-obecni_knihovna_ve_velke_bukovine.yaml b/data/custodian/CZ-42-VEL-L-OKVVB-obecni_knihovna_ve_velke_bukovine.yaml index 0836db7eb8..999eada7f0 100644 --- a/data/custodian/CZ-42-VEL-L-OKVVB-obecni_knihovna_ve_velke_bukovine.yaml +++ b/data/custodian/CZ-42-VEL-L-OKVVB-obecni_knihovna_ve_velke_bukovine.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VEL-L-OKVVB-obecni_knihovna_ve_velke_bukovine - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VEL-L-OKVVB-obecni_knihovna_ve_velke_bukovine valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VEL-L-OKVVB-obecni_knihovna_ve_velke_bukovine ghcid_numeric: 832439224361722411 valid_from: '2025-12-06T23:37:41.219577+00:00' @@ -207,3 +208,22 @@ location: postal_code: 407 29 street_address: Velká Bukovina 178 normalization_timestamp: '2025-12-09T10:54:21.958767+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:20.700888+00:00' + source_url: https://www.velka-bukovina.cz/obec-1/organizace/knihovna/knihovna-14cs.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.velka-bukovina.cz/skins/velka-bukovina.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.velka-bukovina.cz/obec-1/organizace/knihovna/knihovna-14cs.html + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:25:20.700888+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-42-VER-L-OKVV.yaml b/data/custodian/CZ-42-VER-L-OKVV.yaml index 46c10160e5..7297bcbe88 100644 --- a/data/custodian/CZ-42-VER-L-OKVV.yaml +++ b/data/custodian/CZ-42-VER-L-OKVV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VER-L-OKVV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VER-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VER-L-OKVV ghcid_numeric: 1745864676903069746 valid_from: '2025-12-06T23:37:41.222355+00:00' @@ -209,3 +210,22 @@ location: postal_code: 407 25 street_address: Mírové nám. 332 normalization_timestamp: '2025-12-09T10:54:22.072833+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:26:30.683515+00:00' + source_url: https://www.vernerice.cz/mistni%2Dlidova%2Dknihovna/ds-1093/p1=7145 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vernerice.cz/html/images/favicon.ico + source_url: https://www.vernerice.cz/mistni%2Dlidova%2Dknihovna/ds-1093/p1=7145 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:26:30.683515+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-VIL-L-OVKV.yaml b/data/custodian/CZ-42-VIL-L-OVKV.yaml index 6ef531757f..7ff454dff6 100644 --- a/data/custodian/CZ-42-VIL-L-OVKV.yaml +++ b/data/custodian/CZ-42-VIL-L-OVKV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VIL-L-OVKV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VIL-L-OVKV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VIL-L-OVKV ghcid_numeric: 1542153570629370612 valid_from: '2025-12-06T23:37:41.137370+00:00' @@ -210,3 +211,22 @@ location: postal_code: 407 80 street_address: Vilémov 172 normalization_timestamp: '2025-12-09T10:54:22.101265+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:26:37.193247+00:00' + source_url: https://decin.tritius.cz/library/vilemov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://decin.tritius.cz/apple-touch-icon-180x180.png + source_url: https://decin.tritius.cz/library/vilemov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:26:37.193247+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-VRS-L-MVKV.yaml b/data/custodian/CZ-42-VRS-L-MVKV.yaml index ea0ace0443..e2fc48f53c 100644 --- a/data/custodian/CZ-42-VRS-L-MVKV.yaml +++ b/data/custodian/CZ-42-VRS-L-MVKV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VRS-L-MVKV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VRS-L-MVKV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VRS-L-MVKV ghcid_numeric: 16442626536132142888 valid_from: '2025-12-06T23:37:41.251360+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 15 street_address: Vrskmaň 46 normalization_timestamp: '2025-12-09T10:54:22.160610+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:27:51.765566+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/vrskman + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/vrskman + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:27:51.765566+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-VSE-L-OKVV.yaml b/data/custodian/CZ-42-VSE-L-OKVV.yaml index 495ff6e147..7482acba05 100644 --- a/data/custodian/CZ-42-VSE-L-OKVV.yaml +++ b/data/custodian/CZ-42-VSE-L-OKVV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VSE-L-OKVV - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VSE-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VSE-L-OKVV ghcid_numeric: 14545001969032799002 valid_from: '2025-12-06T23:37:41.269329+00:00' @@ -212,3 +213,22 @@ location: postal_code: 431 11 street_address: Všestudy 40 normalization_timestamp: '2025-12-09T10:54:22.211542+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:27:58.204091+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/vsestudy + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/vsestudy + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:27:58.204091+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-VYS-L-OKVV.yaml b/data/custodian/CZ-42-VYS-L-OKVV.yaml index 218467c764..af87d03c95 100644 --- a/data/custodian/CZ-42-VYS-L-OKVV.yaml +++ b/data/custodian/CZ-42-VYS-L-OKVV.yaml @@ -213,3 +213,31 @@ location: postal_code: 431 83 street_address: Výsluní 14 normalization_timestamp: '2025-12-09T10:54:22.403947+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:03.191858+00:00' + source_url: https://chomutovskaknihovna.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://chomutovskaknihovna.tritius.cz/images/comgate_logo.png + source_url: https://chomutovskaknihovna.tritius.cz + css_selector: '#footer > div.container > nav.row.hidden-print > div.col-sm-12.col-md-6 + > div.comgate-logo > span > img' + retrieved_on: '2025-12-24T21:28:03.191858+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Comgate + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:28:03.191858+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-VYS-L-OKVVP.yaml b/data/custodian/CZ-42-VYS-L-OKVVP.yaml index 797d79085a..7d60d47d5e 100644 --- a/data/custodian/CZ-42-VYS-L-OKVVP.yaml +++ b/data/custodian/CZ-42-VYS-L-OKVVP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-VYS-L-OKVVP - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-VYS-L-OKVVP valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-VYS-L-OKVVP ghcid_numeric: 11811898973940774783 valid_from: '2025-12-06T23:37:41.266304+00:00' @@ -218,3 +219,22 @@ location: postal_code: 431 59 street_address: Vysoká Pec 46 normalization_timestamp: '2025-12-09T10:54:22.476019+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:09.012749+00:00' + source_url: https://chomutovskaknihovna.tritius.cz/library/vysokapec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chomutovskaknihovna.tritius.cz/apple-touch-icon-180x180.png + source_url: https://chomutovskaknihovna.tritius.cz/library/vysokapec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:28:09.012749+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-ZAB-L-MKZ.yaml b/data/custodian/CZ-42-ZAB-L-MKZ.yaml index d7a382a635..9f17d99c9c 100644 --- a/data/custodian/CZ-42-ZAB-L-MKZ.yaml +++ b/data/custodian/CZ-42-ZAB-L-MKZ.yaml @@ -215,3 +215,22 @@ location: postal_code: 417 71 street_address: Zabrušany 1 normalization_timestamp: '2025-12-09T10:54:22.531505+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:18.526634+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/zabrusany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/zabrusany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:28:18.526634+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-ZAL-L-MKZ-mistni_knihovna_zalhostice.yaml b/data/custodian/CZ-42-ZAL-L-MKZ-mistni_knihovna_zalhostice.yaml index de27b5763c..ea4e9c2d3e 100644 --- a/data/custodian/CZ-42-ZAL-L-MKZ-mistni_knihovna_zalhostice.yaml +++ b/data/custodian/CZ-42-ZAL-L-MKZ-mistni_knihovna_zalhostice.yaml @@ -211,3 +211,22 @@ location: postal_code: 411 01 street_address: Žalhostice 120 normalization_timestamp: '2025-12-09T10:54:22.579337+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:25.661765+00:00' + source_url: https://zalhostice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://zalhostice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://zalhostice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:28:25.661765+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ZAL-L-MKZ.yaml b/data/custodian/CZ-42-ZAL-L-MKZ.yaml index 71a77aa3b0..3eefa3d33a 100644 --- a/data/custodian/CZ-42-ZAL-L-MKZ.yaml +++ b/data/custodian/CZ-42-ZAL-L-MKZ.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ZAL-L-MKZ - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ZAL-L-MKZ valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ZAL-L-MKZ ghcid_numeric: 16699404067078526816 valid_from: '2025-12-08T11:21:34.953126+00:00' @@ -219,3 +220,22 @@ location: postal_code: 417 63 street_address: Pražská 93 normalization_timestamp: '2025-12-09T10:54:22.632310+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:32.120685+00:00' + source_url: https://tritius.knihovna-teplice.cz/library/zalany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna-teplice.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna-teplice.cz/library/zalany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:28:32.120685+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-42-ZAT-L-CISR.yaml b/data/custodian/CZ-42-ZAT-L-CISR.yaml index 9c8f638cd1..f8819ec76f 100644 --- a/data/custodian/CZ-42-ZAT-L-CISR.yaml +++ b/data/custodian/CZ-42-ZAT-L-CISR.yaml @@ -177,3 +177,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1438040 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:52.542907+00:00' + source_url: https://www.chizatec.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.chizatec.cz/favicon.gif + source_url: https://www.chizatec.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:28:52.542907+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ZAT-M-RMKPVZ.yaml b/data/custodian/CZ-42-ZAT-M-RMKPVZ.yaml index 341307b718..7ce9f9c174 100644 --- a/data/custodian/CZ-42-ZAT-M-RMKPVZ.yaml +++ b/data/custodian/CZ-42-ZAT-M-RMKPVZ.yaml @@ -248,3 +248,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Regionální muzeum K. A. Polánka v Žatci official youtube_search_timestamp: '2025-12-09T09:31:32.968080+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:29:00.304177+00:00' + source_url: http://www.muzeumzatec.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.muzeumzatec.cz/imgs/favicon.ico + source_url: http://www.muzeumzatec.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:29:00.304177+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.muzeumzatec.cz/imgs/logo-text.png + source_url: http://www.muzeumzatec.cz + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T21:29:00.304177+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-42-ZIT-L-MKZ.yaml b/data/custodian/CZ-42-ZIT-L-MKZ.yaml index 8104963f81..8efd612719 100644 --- a/data/custodian/CZ-42-ZIT-L-MKZ.yaml +++ b/data/custodian/CZ-42-ZIT-L-MKZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ZIT-L-MKZ - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ZIT-L-MKZ valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ZIT-L-MKZ ghcid_numeric: 5157532294314258383 valid_from: '2025-12-08T11:21:37.990045+00:00' @@ -210,3 +211,22 @@ location: postal_code: 411 41 street_address: Žitenice 81 normalization_timestamp: '2025-12-09T10:54:22.751614+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:29:07.498342+00:00' + source_url: https://zitenice-katalog.knihovnalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://zitenice-katalog.knihovnalitomerice.cz/themes/root/images/vufind-favicon.ico + source_url: https://zitenice-katalog.knihovnalitomerice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:29:07.498342+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-42-ZIZ-L-OKZ.yaml b/data/custodian/CZ-42-ZIZ-L-OKZ.yaml index 03d41a607a..88aada7652 100644 --- a/data/custodian/CZ-42-ZIZ-L-OKZ.yaml +++ b/data/custodian/CZ-42-ZIZ-L-OKZ.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-42-ZIZ-L-OKZ - valid_from: "2025-12-10T09:47:11Z" + valid_from: '2025-12-10T09:47:11Z' valid_to: null - reason: "Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-US to CZ-42 (Ústí nad Labem (Ústecký)) per + ISO 3166-2:CZ - ghcid: CZ-US-ZIZ-L-OKZ valid_from: null - valid_to: "2025-12-10T09:47:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:11Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-US-ZIZ-L-OKZ ghcid_numeric: 8040318733164741350 valid_from: '2025-12-08T11:21:24.402865+00:00' @@ -213,3 +214,22 @@ location: country: *id005 postal_code: 438 01 normalization_timestamp: '2025-12-09T10:54:22.790970+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:29:17.224363+00:00' + source_url: https://tritius.mekzatec.cz/library/zizelice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mekzatec.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mekzatec.cz/library/zizelice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:29:17.224363+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-BEN-L-MKVBUS.yaml b/data/custodian/CZ-51-BEN-L-MKVBUS.yaml index ff5a25ab13..63ecc36571 100644 --- a/data/custodian/CZ-51-BEN-L-MKVBUS.yaml +++ b/data/custodian/CZ-51-BEN-L-MKVBUS.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-BEN-L-MKVBUS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-BEN-L-MKVBUS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-BEN-L-MKVBUS ghcid_numeric: 18374670929889882835 valid_from: '2025-12-06T23:37:37.490668+00:00' @@ -205,3 +206,28 @@ location: postal_code: 512 06 street_address: Benešov u Semil 125 normalization_timestamp: '2025-12-09T10:53:07.700773+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:29:22.563277+00:00' + source_url: http://www.benesovusemil.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.benesovusemil.cz/favicon.ico + source_url: http://www.benesovusemil.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:29:22.563277+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.benesovusemil.cz/galerie/1442151.png + source_url: http://www.benesovusemil.cz + css_selector: '[document] > html > head > meta:nth-of-type(17)' + retrieved_on: '2025-12-24T21:29:22.563277+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-51-CES-L-OKB.yaml b/data/custodian/CZ-51-CES-L-OKB.yaml index e72760cb8f..98e41f7ab7 100644 --- a/data/custodian/CZ-51-CES-L-OKB.yaml +++ b/data/custodian/CZ-51-CES-L-OKB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-CES-L-OKB - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-CES-L-OKB valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-CES-L-OKB ghcid_numeric: 12805950568065830756 valid_from: '2025-12-06T23:37:37.324959+00:00' @@ -210,3 +211,22 @@ location: postal_code: 463 43 street_address: Bílá 9 normalization_timestamp: '2025-12-09T10:53:08.031398+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:42:02.024655+00:00' + source_url: https://www.bila.knihovna.cz/on-line-katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bila.knihovna.cz/favicon.svg + source_url: https://www.bila.knihovna.cz/on-line-katalog + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:42:02.024655+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-CES-L-PMKCD.yaml b/data/custodian/CZ-51-CES-L-PMKCD.yaml index 31bb249a18..2d3c93fd60 100644 --- a/data/custodian/CZ-51-CES-L-PMKCD.yaml +++ b/data/custodian/CZ-51-CES-L-PMKCD.yaml @@ -183,3 +183,22 @@ wikidata_enrichment: image: https://commons.wikimedia.org/wiki/Special:FilePath/Český_Dub,_knihovna.jpg instance_of: - Q114617264 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:42:42.779842+00:00' + source_url: https://lck.tritius.cz/library/cdub + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lck.tritius.cz/library/cdub + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:42:42.779842+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-CES-M-VMGVCL.yaml b/data/custodian/CZ-51-CES-M-VMGVCL.yaml index 4706cbac27..f32af97ac8 100644 --- a/data/custodian/CZ-51-CES-M-VMGVCL.yaml +++ b/data/custodian/CZ-51-CES-M-VMGVCL.yaml @@ -680,3 +680,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/fWQmpQFDNyM/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:42:50.080853+00:00' + source_url: https://www.muzeumcl.cz/knihovna/on-line-katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.muzeumcl.cz/assets/favicon/apple-icon-180x180.png + source_url: https://www.muzeumcl.cz/knihovna/on-line-katalog + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T21:42:50.080853+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 13 diff --git a/data/custodian/CZ-51-CHR-L-MKC.yaml b/data/custodian/CZ-51-CHR-L-MKC.yaml index f192e0c2f7..17d09d652f 100644 --- a/data/custodian/CZ-51-CHR-L-MKC.yaml +++ b/data/custodian/CZ-51-CHR-L-MKC.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-CHR-L-MKC - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-CHR-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-CHR-L-MKC ghcid_numeric: 9345300043549049955 valid_from: '2025-12-06T23:37:20.956081+00:00' @@ -223,3 +224,22 @@ location: postal_code: 463 31 street_address: Liberecká 40 normalization_timestamp: '2025-12-09T10:53:08.198026+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:43:02.859894+00:00' + source_url: https://www.chrastava.eu/volny-cas/kultura/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.chrastava.eu/skins/chrastava.eu_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.chrastava.eu/volny-cas/kultura/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:43:02.859894+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-CVI-L-MKVC.yaml b/data/custodian/CZ-51-CVI-L-MKVC.yaml index 08ec061980..8c0bcbb2d9 100644 --- a/data/custodian/CZ-51-CVI-L-MKVC.yaml +++ b/data/custodian/CZ-51-CVI-L-MKVC.yaml @@ -227,3 +227,22 @@ location: postal_code: 471 54 street_address: Jiráskova 95 normalization_timestamp: '2025-12-09T10:53:08.277777+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:43:20.619406+00:00' + source_url: https://cvikov.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://cvikov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://cvikov.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:43:20.619406+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-DRZ-L-MKD.yaml b/data/custodian/CZ-51-DRZ-L-MKD.yaml index 1f3e8376a3..bb8a66efca 100644 --- a/data/custodian/CZ-51-DRZ-L-MKD.yaml +++ b/data/custodian/CZ-51-DRZ-L-MKD.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-DRZ-L-MKD - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-DRZ-L-MKD valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-DRZ-L-MKD ghcid_numeric: 1078338167186492791 valid_from: '2025-12-06T23:37:37.174111+00:00' @@ -203,3 +204,22 @@ location: postal_code: 468 24 street_address: Držkov 9 normalization_timestamp: '2025-12-09T10:53:08.441769+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:45:13.270153+00:00' + source_url: https://www.drzkov.cz/obec-1/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.drzkov.cz/skins/drzkov.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.drzkov.cz/obec-1/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:45:13.270153+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-FRY-L-MKF.yaml b/data/custodian/CZ-51-FRY-L-MKF.yaml index 69c07de012..e80a35daaf 100644 --- a/data/custodian/CZ-51-FRY-L-MKF.yaml +++ b/data/custodian/CZ-51-FRY-L-MKF.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-FRY-L-MKF - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-FRY-L-MKF valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-FRY-L-MKF ghcid_numeric: 3485509174361512590 valid_from: '2025-12-06T23:37:21.640221+00:00' @@ -212,3 +213,22 @@ location: postal_code: 464 01 street_address: Bělíkova 977 normalization_timestamp: '2025-12-09T10:53:08.553249+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:23.631925+00:00' + source_url: https://lck.tritius.cz/library/frydlant + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lck.tritius.cz/library/frydlant + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:46:23.631925+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-FRY-L-MKVV.yaml b/data/custodian/CZ-51-FRY-L-MKVV.yaml index d1ca1b9c50..fc8724f279 100644 --- a/data/custodian/CZ-51-FRY-L-MKVV.yaml +++ b/data/custodian/CZ-51-FRY-L-MKVV.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-FRY-L-MKVV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-FRY-L-MKVV valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-FRY-L-MKVV ghcid_numeric: 5850129882042577028 valid_from: '2025-12-06T23:37:37.273928+00:00' @@ -222,3 +223,22 @@ location: postal_code: 464 01 street_address: Višňová 162 normalization_timestamp: '2025-12-09T10:53:08.598186+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:28.770261+00:00' + source_url: https://visnova.knihovna.cz/on-line-katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://visnova.knihovna.cz/favicon.svg + source_url: https://visnova.knihovna.cz/on-line-katalog + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:46:28.770261+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-FRY-M-MMF.yaml b/data/custodian/CZ-51-FRY-M-MMF.yaml index cfd5d75d64..857ce2f1d7 100644 --- a/data/custodian/CZ-51-FRY-M-MMF.yaml +++ b/data/custodian/CZ-51-FRY-M-MMF.yaml @@ -234,3 +234,23 @@ location: youtube_status: NOT_FOUND youtube_search_query: Městské muzeum Frýdlant official youtube_search_timestamp: '2025-12-09T09:31:39.570356+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:34.977427+00:00' + source_url: https://www.mesto-frydlant.cz/cs/turista/zajimavosti-a-cile-ve-frydlantu/mestske-muzeum-radnice.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mesto-frydlant.cz/favicon.ico + source_url: https://www.mesto-frydlant.cz/cs/turista/zajimavosti-a-cile-ve-frydlantu/mestske-muzeum-radnice.html + css_selector: '[document] > html.wf-opensans-n3-active.wf-opensans-n7-active > + head > link' + retrieved_on: '2025-12-24T21:46:34.977427+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-FRY-M-MUFOKMMFK.yaml b/data/custodian/CZ-51-FRY-M-MUFOKMMFK.yaml index 523cf0193c..96d01fbdce 100644 --- a/data/custodian/CZ-51-FRY-M-MUFOKMMFK.yaml +++ b/data/custodian/CZ-51-FRY-M-MUFOKMMFK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-FRY-M-MUFOKMMFK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-FRY-M-MUFOKMMFK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-FRY-M-MUFOKMMFK ghcid_numeric: 1189310278334514383 valid_from: '2025-12-08T11:21:36.510940+00:00' @@ -220,3 +221,23 @@ location: postal_code: 464 13 street_address: nám. T.G. Masaryka 37, Radnice - budova A - Městské muzeum normalization_timestamp: '2025-12-09T10:53:08.630240+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:39.663858+00:00' + source_url: https://www.mesto-frydlant.cz/cs/turista/zajimavosti-a-cile-ve-frydlantu/mestske-muzeum-radnice.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mesto-frydlant.cz/favicon.ico + source_url: https://www.mesto-frydlant.cz/cs/turista/zajimavosti-a-cile-ve-frydlantu/mestske-muzeum-radnice.html + css_selector: '[document] > html.wf-opensans-n3-active.wf-opensans-n7-active > + head > link' + retrieved_on: '2025-12-24T21:46:39.663858+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-HAB-L-MKVC.yaml b/data/custodian/CZ-51-HAB-L-MKVC.yaml index 57feff89ab..c361141253 100644 --- a/data/custodian/CZ-51-HAB-L-MKVC.yaml +++ b/data/custodian/CZ-51-HAB-L-MKVC.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-HAB-L-MKVC - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-HAB-L-MKVC valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-HAB-L-MKVC ghcid_numeric: 1970180256050700929 valid_from: '2025-12-08T11:21:40.078251+00:00' @@ -215,3 +216,22 @@ location: postal_code: 463 73 street_address: Černousy 47 normalization_timestamp: '2025-12-09T10:53:08.659093+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:44.739365+00:00' + source_url: https://cernousy.kniholib.cz/arl-lir/cs/vyhledavani + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://cernousy.kniholib.cz/i2/user/lir/img/loga/cernousy.svg + source_url: https://cernousy.kniholib.cz/arl-lir/cs/vyhledavani + css_selector: '#brand > img.logo.img-fluid' + retrieved_on: '2025-12-24T21:46:44.739365+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Místní knihovna v Černousech + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-51-HAR-L-MKH.yaml b/data/custodian/CZ-51-HAR-L-MKH.yaml index 28a11a9e57..07804f17e4 100644 --- a/data/custodian/CZ-51-HAR-L-MKH.yaml +++ b/data/custodian/CZ-51-HAR-L-MKH.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-HAR-L-MKH - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-HAR-L-MKH valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-HAR-L-MKH ghcid_numeric: 8303947510533015012 valid_from: '2025-12-06T23:37:19.937001+00:00' @@ -215,3 +216,22 @@ location: postal_code: 512 46 street_address: Nový Svět 77 normalization_timestamp: '2025-12-09T10:53:08.737664+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:47:01.063320+00:00' + source_url: https://www.harrachov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.harrachov.cz/skins/harrachov.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.harrachov.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:47:01.063320+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 7 diff --git a/data/custodian/CZ-51-HEJ-L-OKLL.yaml b/data/custodian/CZ-51-HEJ-L-OKLL.yaml index a5e0e9ceaf..55cc5156e4 100644 --- a/data/custodian/CZ-51-HEJ-L-OKLL.yaml +++ b/data/custodian/CZ-51-HEJ-L-OKLL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-HEJ-L-OKLL - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-HEJ-L-OKLL valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-HEJ-L-OKLL ghcid_numeric: 12440771565510859039 valid_from: '2025-12-06T23:37:37.316931+00:00' @@ -210,3 +211,22 @@ location: postal_code: 463 62 street_address: Lázně Libverda 16 normalization_timestamp: '2025-12-09T10:53:08.802696+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:47:10.730325+00:00' + source_url: https://libverda.kniholib.cz/arl-lir/cs/index + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://libverda.kniholib.cz/i2/user/lir/img/loga/libverda.svg + source_url: https://libverda.kniholib.cz/arl-lir/cs/index + css_selector: '#brand > img.logo.img-fluid' + retrieved_on: '2025-12-24T21:47:10.730325+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Obecní knihovna Lázně Libverda + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-51-HOD-L-MKHNM.yaml b/data/custodian/CZ-51-HOD-L-MKHNM.yaml index c170d8717b..15056411ca 100644 --- a/data/custodian/CZ-51-HOD-L-MKHNM.yaml +++ b/data/custodian/CZ-51-HOD-L-MKHNM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-HOD-L-MKHNM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-HOD-L-MKHNM valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-HOD-L-MKHNM ghcid_numeric: 16437463022261739043 valid_from: '2025-12-06T23:37:21.035221+00:00' @@ -219,3 +220,22 @@ location: postal_code: 463 42 street_address: Mánesova 560 normalization_timestamp: '2025-12-09T10:53:08.831621+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:47:17.582858+00:00' + source_url: https://lck.tritius.cz/library/hodkovice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lck.tritius.cz/library/hodkovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:47:17.582858+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-HOR-L-MKVV.yaml b/data/custodian/CZ-51-HOR-L-MKVV.yaml index 2dfca834f6..5c68126097 100644 --- a/data/custodian/CZ-51-HOR-L-MKVV.yaml +++ b/data/custodian/CZ-51-HOR-L-MKVV.yaml @@ -208,3 +208,22 @@ location: postal_code: 512 36 street_address: Valteřice 149 normalization_timestamp: '2025-12-09T10:53:08.975621+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:48:04.486095+00:00' + source_url: https://www.knihovnahbranna.cz/knihovna-valterice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovnahbranna.cz/wp-content/uploads/fbrfg/safari-pinned-tab.svg + source_url: https://www.knihovnahbranna.cz/knihovna-valterice + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-24T21:48:04.486095+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-HUN-L-OKS.yaml b/data/custodian/CZ-51-HUN-L-OKS.yaml index 998b602153..c4972db7be 100644 --- a/data/custodian/CZ-51-HUN-L-OKS.yaml +++ b/data/custodian/CZ-51-HUN-L-OKS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-HUN-L-OKS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-HUN-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-HUN-L-OKS ghcid_numeric: 8938613874478248125 valid_from: '2025-12-06T23:37:37.184946+00:00' @@ -210,3 +211,22 @@ location: postal_code: 468 22 street_address: Huntířov 63 normalization_timestamp: '2025-12-09T10:53:09.043967+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:48:16.077918+00:00' + source_url: http://www.knihovnaskuhrov.webz.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.webzdarma.cz/favicon.png + source_url: http://www.knihovnaskuhrov.webz.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:48:16.077918+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-JAB-A-SOAJNN.yaml b/data/custodian/CZ-51-JAB-A-SOAJNN.yaml index 257f772784..bbb616055a 100644 --- a/data/custodian/CZ-51-JAB-A-SOAJNN.yaml +++ b/data/custodian/CZ-51-JAB-A-SOAJNN.yaml @@ -254,3 +254,29 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Jablonec nad Nisou official youtube_search_timestamp: '2025-12-09T09:31:40.238457+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:48:23.771342+00:00' + source_url: http://www.soalitomerice.cz/soka-jablonec-nad-nisou + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: http://www.soalitomerice.cz/soka-jablonec-nad-nisou + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:48:23.771342+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/SOkA_Jbc_nova_budova.jpg + source_url: http://www.soalitomerice.cz/soka-jablonec-nad-nisou + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T21:48:23.771342+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-51-JAB-L-MKJNJ.yaml b/data/custodian/CZ-51-JAB-L-MKJNJ.yaml index 5614e3009d..35b29a19f8 100644 --- a/data/custodian/CZ-51-JAB-L-MKJNJ.yaml +++ b/data/custodian/CZ-51-JAB-L-MKJNJ.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JAB-L-MKJNJ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JAB-L-MKJNJ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JAB-L-MKJNJ ghcid_numeric: 11150446251847420996 valid_from: '2025-12-06T23:37:19.934108+00:00' @@ -210,3 +211,22 @@ location: country: *id005 postal_code: 512 43 normalization_timestamp: '2025-12-09T10:53:09.164274+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:48:39.869242+00:00' + source_url: https://semily.tritius.cz/library/jablonecko + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://semily.tritius.cz/apple-touch-icon-180x180.png + source_url: https://semily.tritius.cz/library/jablonecko + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:48:39.869242+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-JAB-L-MKJNN.yaml b/data/custodian/CZ-51-JAB-L-MKJNN.yaml index 504d5a32b8..cc7ff9dac7 100644 --- a/data/custodian/CZ-51-JAB-L-MKJNN.yaml +++ b/data/custodian/CZ-51-JAB-L-MKJNN.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JAB-L-MKJNN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JAB-L-MKJNN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JAB-L-MKJNN ghcid_numeric: 14807024650471571280 valid_from: '2025-12-06T23:37:18.033414+00:00' @@ -257,3 +258,22 @@ location: postal_code: 466 01 street_address: Dolní nám. 1 normalization_timestamp: '2025-12-09T10:53:09.194535+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:48:45.361350+00:00' + source_url: https://knihovna.mestojablonec.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.mestojablonec.cz/favicon.ico + source_url: https://knihovna.mestojablonec.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:48:45.361350+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-JAB-L-MKM.yaml b/data/custodian/CZ-51-JAB-L-MKM.yaml index 9571437ad1..0d0d182eb1 100644 --- a/data/custodian/CZ-51-JAB-L-MKM.yaml +++ b/data/custodian/CZ-51-JAB-L-MKM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JAB-L-MKM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JAB-L-MKM valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JAB-L-MKM ghcid_numeric: 16390084808458576736 valid_from: '2025-12-06T23:37:37.199348+00:00' @@ -210,3 +211,28 @@ location: postal_code: 468 01 street_address: Maršovice 52 normalization_timestamp: '2025-12-09T10:53:09.222551+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:48:51.317258+00:00' + source_url: https://marsovice.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://duyn491kcolsw.cloudfront.net/files/2d/2di/2div3h.svg?ph=d28b46e372 + source_url: https://marsovice.knihovna.cz + css_selector: '[document] > html.js.sizes > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:48:51.317258+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + - claim_type: og_image_url + claim_value: https://d28b46e372.clvaw-cdnwnd.com/486a0b1ba7f13a74f3008fa725730472/200000004-f0fcdf1f5c/700/webnode-logo.png?ph=d28b46e372 + source_url: https://marsovice.knihovna.cz + css_selector: '[document] > html.js.sizes > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-24T21:48:51.317258+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-51-JAB-L-NJNNPLK.yaml b/data/custodian/CZ-51-JAB-L-NJNNPLK.yaml index 3872248080..2cfb92d3b3 100644 --- a/data/custodian/CZ-51-JAB-L-NJNNPLK.yaml +++ b/data/custodian/CZ-51-JAB-L-NJNNPLK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JAB-L-NJNNPLK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JAB-L-NJNNPLK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JAB-L-NJNNPLK ghcid_numeric: 1049258277421026832 valid_from: '2025-12-06T23:37:17.999794+00:00' @@ -214,3 +215,22 @@ location: postal_code: 466 01 street_address: Nemocniční 4446/15 normalization_timestamp: '2025-12-09T10:53:09.275576+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:49:28.553788+00:00' + source_url: https://www.nemjbc.cz/cs/oddeleni/hospodarsko-technicka-sprava/knihovna-a-spisovna.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nemjbc.cz/favicon.ico + source_url: https://www.nemjbc.cz/cs/oddeleni/hospodarsko-technicka-sprava/knihovna-a-spisovna.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:49:28.553788+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-JAB-L-UPHULPJNN.yaml b/data/custodian/CZ-51-JAB-L-UPHULPJNN.yaml index 4e5c92682a..bf118c15ce 100644 --- a/data/custodian/CZ-51-JAB-L-UPHULPJNN.yaml +++ b/data/custodian/CZ-51-JAB-L-UPHULPJNN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JAB-L-UPHULPJNN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JAB-L-UPHULPJNN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JAB-L-UPHULPJNN ghcid_numeric: 15302932310651012079 valid_from: '2025-12-08T11:21:38.649036+00:00' @@ -219,3 +220,22 @@ location: postal_code: 466 01 street_address: Jungmannova 10 normalization_timestamp: '2025-12-09T10:53:09.315992+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:49:37.406095+00:00' + source_url: https://www.uhul.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nli.gov.cz/wp-content/uploads/2024/12/cropped-nli_500_500-180x180.jpg + source_url: https://www.uhul.cz + css_selector: '[document] > html.no-js.realfactory-mmenu-right > head > link:nth-of-type(36)' + retrieved_on: '2025-12-24T21:49:37.406095+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-JEN-L-OKVJ.yaml b/data/custodian/CZ-51-JEN-L-OKVJ.yaml index e5063c605d..ef4b394efe 100644 --- a/data/custodian/CZ-51-JEN-L-OKVJ.yaml +++ b/data/custodian/CZ-51-JEN-L-OKVJ.yaml @@ -208,3 +208,22 @@ location: postal_code: 468 33 street_address: Jenišovice 180 normalization_timestamp: '2025-12-09T10:53:09.386301+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:49:49.978092+00:00' + source_url: https://www.jenisovice.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jenisovice.cz/image.php?nid=19594&oid=8705779&width=36 + source_url: https://www.jenisovice.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:49:49.978092+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-JER-L-MKVJ.yaml b/data/custodian/CZ-51-JER-L-MKVJ.yaml index eceb72fec2..d04178f988 100644 --- a/data/custodian/CZ-51-JER-L-MKVJ.yaml +++ b/data/custodian/CZ-51-JER-L-MKVJ.yaml @@ -213,3 +213,22 @@ location: postal_code: 463 12 street_address: Pastevní 274 normalization_timestamp: '2025-12-09T10:53:09.410506+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:49:55.063403+00:00' + source_url: https://jermanice.kniholib.cz/arl-lir/cs/index + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://jermanice.kniholib.cz/i2/user/lir/img/loga/jermanice.svg + source_url: https://jermanice.kniholib.cz/arl-lir/cs/index + css_selector: '#brand > img.logo.img-fluid' + retrieved_on: '2025-12-24T21:49:55.063403+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Místní knihovna v Jeřmanicích + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-51-JIL-L-MKJH.yaml b/data/custodian/CZ-51-JIL-L-MKJH.yaml index 0a47d465cc..8ed963d1a3 100644 --- a/data/custodian/CZ-51-JIL-L-MKJH.yaml +++ b/data/custodian/CZ-51-JIL-L-MKJH.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JIL-L-MKJH - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JIL-L-MKJH valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JIL-L-MKJH ghcid_numeric: 2464077647617122300 valid_from: '2025-12-06T23:37:19.922865+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Městská knihovna Jaroslava Havlíčka @@ -228,3 +229,22 @@ location: geonames_id: 3074187 geonames_name: Jilemnice feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:33.514891+00:00' + source_url: https://lck.tritius.cz/library/jilemnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lck.tritius.cz/library/jilemnice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:50:33.514891+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-JIL-L-MKJVK.yaml b/data/custodian/CZ-51-JIL-L-MKJVK.yaml index 036d79f764..d9b3f108a2 100644 --- a/data/custodian/CZ-51-JIL-L-MKJVK.yaml +++ b/data/custodian/CZ-51-JIL-L-MKJVK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JIL-L-MKJVK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JIL-L-MKJVK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JIL-L-MKJVK ghcid_numeric: 14776056080498032945 valid_from: '2025-12-06T23:37:37.459093+00:00' @@ -210,3 +211,22 @@ location: postal_code: 514 01 street_address: Jestřabí 71 normalization_timestamp: '2025-12-09T10:53:09.485708+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:39.618811+00:00' + source_url: https://www.jestrabivkrk.cz/obec/mistni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jestrabivkrk.cz/skins/jestrabivkrk_lego/favicons/safari-pinned-tab.svg + source_url: https://www.jestrabivkrk.cz/obec/mistni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:50:39.618811+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-JIL-L-MKLO.yaml b/data/custodian/CZ-51-JIL-L-MKLO.yaml index a7f74a0fda..703b1b68d9 100644 --- a/data/custodian/CZ-51-JIL-L-MKLO.yaml +++ b/data/custodian/CZ-51-JIL-L-MKLO.yaml @@ -211,3 +211,22 @@ location: postal_code: 514 01 street_address: Levínská Olešnice normalization_timestamp: '2025-12-09T10:53:09.521974+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:46.846021+00:00' + source_url: https://www.levinskaolesnice.cz/obec-1/kulturni-a-sportovni-vybavenost/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.levinskaolesnice.cz/skins/levinskaolesnice.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.levinskaolesnice.cz/obec-1/kulturni-a-sportovni-vybavenost/knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:50:46.846021+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-51-JIL-L-OKK-obecni_knihovna_kundratice.yaml b/data/custodian/CZ-51-JIL-L-OKK-obecni_knihovna_kundratice.yaml index 7fc71a7acd..660456ff39 100644 --- a/data/custodian/CZ-51-JIL-L-OKK-obecni_knihovna_kundratice.yaml +++ b/data/custodian/CZ-51-JIL-L-OKK-obecni_knihovna_kundratice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JIL-L-OKK-obecni_knihovna_kundratice - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JIL-L-OKK-obecni_knihovna_kundratice valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JIL-L-OKK-obecni_knihovna_kundratice ghcid_numeric: 16071159724286361428 valid_from: '2025-12-06T23:37:37.507029+00:00' @@ -210,3 +211,30 @@ location: postal_code: 514 01 street_address: Kundratice 134 normalization_timestamp: '2025-12-09T10:53:09.656011+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:55.567257+00:00' + source_url: https://knihovnakundratice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnakundratice.webk.cz/themes/new/blue/logo2.png + source_url: https://knihovnakundratice.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T21:50:55.567257+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnakundratice.webk.cz/themes/new/favicon.ico + source_url: https://knihovnakundratice.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T21:50:55.567257+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-JIL-L-OKK.yaml b/data/custodian/CZ-51-JIL-L-OKK.yaml index 15f3bea61e..940f62021a 100644 --- a/data/custodian/CZ-51-JIL-L-OKK.yaml +++ b/data/custodian/CZ-51-JIL-L-OKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-JIL-L-OKK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-JIL-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-JIL-L-OKK ghcid_numeric: 11125323433882102795 valid_from: '2025-12-06T23:37:37.363720+00:00' @@ -210,3 +211,22 @@ location: postal_code: 514 01 street_address: Kruh 165 normalization_timestamp: '2025-12-09T10:53:09.683663+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:51:00.711753+00:00' + source_url: https://www.obeckruh.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obeckruh.cz/image.php?nid=16789&oid=12671274 + source_url: https://www.obeckruh.cz + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T21:51:00.711753+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-JIL-M-KMJ.yaml b/data/custodian/CZ-51-JIL-M-KMJ.yaml index cd7750c595..a0c44e13d8 100644 --- a/data/custodian/CZ-51-JIL-M-KMJ.yaml +++ b/data/custodian/CZ-51-JIL-M-KMJ.yaml @@ -265,3 +265,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Krkonošské muzeum Jilemnice official youtube_search_timestamp: '2025-12-09T09:31:40.912570+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:51:05.635988+00:00' + source_url: https://www.krnap.cz/navstevnici/muzea/krkonosske-muzeum-jilemnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.krnap.cz/images/favicon/safari-pinned-tab.svg + source_url: https://www.krnap.cz/navstevnici/muzea/krkonosske-muzeum-jilemnice + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:51:05.635988+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.krnap.cz/media/mk0baavq/zamek_w.jpg + source_url: https://www.krnap.cz/navstevnici/muzea/krkonosske-muzeum-jilemnice + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T21:51:05.635988+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-51-JOS-L-OKJD.yaml b/data/custodian/CZ-51-JOS-L-OKJD.yaml index 6df142dc90..5f9dc59376 100644 --- a/data/custodian/CZ-51-JOS-L-OKJD.yaml +++ b/data/custodian/CZ-51-JOS-L-OKJD.yaml @@ -211,3 +211,30 @@ location: postal_code: 468 44 street_address: Josefův Důl 210 normalization_timestamp: '2025-12-09T10:53:09.742794+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:51:18.838009+00:00' + source_url: https://knihovnajosefuvdul.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnajosefuvdul.files.webk.cz/logov.png + source_url: https://knihovnajosefuvdul.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T21:51:18.838009+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnajosefuvdul.webk.cz/themes/new/favicon.ico + source_url: https://knihovnajosefuvdul.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T21:51:18.838009+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-KOS-L-OKVK.yaml b/data/custodian/CZ-51-KOS-L-OKVK.yaml index 3fa36b1e37..d19c37a777 100644 --- a/data/custodian/CZ-51-KOS-L-OKVK.yaml +++ b/data/custodian/CZ-51-KOS-L-OKVK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-KOS-L-OKVK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-KOS-L-OKVK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-KOS-L-OKVK ghcid_numeric: 10078930859472608431 valid_from: '2025-12-06T23:37:37.504328+00:00' @@ -210,3 +211,22 @@ location: postal_code: 512 02 street_address: Košťálov 201 normalization_timestamp: '2025-12-09T10:53:09.786486+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:51:26.562149+00:00' + source_url: https://semily.tritius.cz/library/kostalov/?device=1 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://semily.tritius.cz/apple-touch-icon-180x180.png + source_url: https://semily.tritius.cz/library/kostalov/?device=1 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:51:26.562149+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-KRI-L-MKZ.yaml b/data/custodian/CZ-51-KRI-L-MKZ.yaml index e0c54a1e7e..d06a81a810 100644 --- a/data/custodian/CZ-51-KRI-L-MKZ.yaml +++ b/data/custodian/CZ-51-KRI-L-MKZ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-KRI-L-MKZ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-KRI-L-MKZ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-KRI-L-MKZ ghcid_numeric: 16399505776591541989 valid_from: '2025-12-06T23:37:37.355043+00:00' @@ -210,3 +211,22 @@ location: postal_code: 463 53 street_address: Zdislava 12 normalization_timestamp: '2025-12-09T10:53:09.924001+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:52:18.016057+00:00' + source_url: https://zdislava.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://zdislava.knihovna.cz/favicon.svg + source_url: https://zdislava.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:52:18.016057+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-LIB-A-SOAL-statni_okresni_archiv_liberec.yaml b/data/custodian/CZ-51-LIB-A-SOAL-statni_okresni_archiv_liberec.yaml index f95f085953..08af02c47d 100644 --- a/data/custodian/CZ-51-LIB-A-SOAL-statni_okresni_archiv_liberec.yaml +++ b/data/custodian/CZ-51-LIB-A-SOAL-statni_okresni_archiv_liberec.yaml @@ -258,3 +258,29 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Liberec official youtube_search_timestamp: '2025-12-09T09:31:43.566526+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:52:28.328113+00:00' + source_url: http://www.soalitomerice.cz/soka-liberec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: http://www.soalitomerice.cz/soka-liberec + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:52:28.328113+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/sokalib.jpg + source_url: http://www.soalitomerice.cz/soka-liberec + css_selector: '[document] > html.td-md-is-os-x.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T21:52:28.328113+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-51-LIB-E-SZSVOSZLK.yaml b/data/custodian/CZ-51-LIB-E-SZSVOSZLK.yaml index c74dff32ca..e81796e5a7 100644 --- a/data/custodian/CZ-51-LIB-E-SZSVOSZLK.yaml +++ b/data/custodian/CZ-51-LIB-E-SZSVOSZLK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LIB-E-SZSVOSZLK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LIB-E-SZSVOSZLK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LIB-E-SZSVOSZLK ghcid_numeric: 8536887695210791580 valid_from: '2025-12-08T11:21:27.999277+00:00' @@ -221,3 +222,33 @@ location: postal_code: 460 31 street_address: Kostelní 8/9 normalization_timestamp: '2025-12-09T10:53:09.957503+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:52:33.660061+00:00' + source_url: https://www.libereckazdravka.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.libereckazdravka.cz/wp-content/uploads/2024/06/liberecka_zdravka_logo_szs_a_vos_zdravotnicka_liberec.jpg + source_url: https://www.libereckazdravka.cz + css_selector: '#header-grid > nav.header--row.header-main > div.header--row-inner.header-main-inner + > div.container > div.row.row--wrapper > div.hfg-slot.left > div.builder-item.desktop-right + > div.item--inner.builder-item--logo > div.site-logo > a.brand > div.title-with-logo + > img.neve-site-logo.skip-lazy' + retrieved_on: '2025-12-24T21:52:33.660061+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.libereckazdravka.cz/wp-content/uploads/2019/01/cropped-logo-szs-vos-zdravotnicka-liberec-180x180.png + source_url: https://www.libereckazdravka.cz + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-24T21:52:33.660061+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-LIB-G-OGLPK.yaml b/data/custodian/CZ-51-LIB-G-OGLPK.yaml index 20dcab024b..0990f81202 100644 --- a/data/custodian/CZ-51-LIB-G-OGLPK.yaml +++ b/data/custodian/CZ-51-LIB-G-OGLPK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LIB-G-OGLPK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LIB-G-OGLPK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LIB-G-OGLPK ghcid_numeric: 4428364738466372782 valid_from: '2025-12-06T23:37:26.780326+00:00' @@ -214,3 +215,22 @@ location: postal_code: 460 01 street_address: Masarykova 723/14 normalization_timestamp: '2025-12-09T10:53:10.005486+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:52:44.401304+00:00' + source_url: https://muzeum.tritius.cz/library/ogl + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeum.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeum.tritius.cz/library/ogl + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:52:44.401304+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-LIB-L-MKVKU.yaml b/data/custodian/CZ-51-LIB-L-MKVKU.yaml index 8b4be814ce..1bfc97c90d 100644 --- a/data/custodian/CZ-51-LIB-L-MKVKU.yaml +++ b/data/custodian/CZ-51-LIB-L-MKVKU.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LIB-L-MKVKU - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LIB-L-MKVKU valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LIB-L-MKVKU ghcid_numeric: 11216850102806826666 valid_from: '2025-12-08T11:21:25.617099+00:00' @@ -215,3 +216,22 @@ location: postal_code: 460 01 street_address: Kryštofovo Údolí normalization_timestamp: '2025-12-09T10:53:10.175609+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:55:10.793394+00:00' + source_url: https://www.krystofovoudoli.eu/obec/obcanska-vybavenost/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.krystofovoudoli.eu/skins/krystofovoudoli.eu_lego2/favicons/apple-touch-icon.png + source_url: https://www.krystofovoudoli.eu/obec/obcanska-vybavenost/knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:55:10.793394+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-51-LIB-L-MLKL.yaml b/data/custodian/CZ-51-LIB-L-MLKL.yaml index 2714381c07..5bb4cee169 100644 --- a/data/custodian/CZ-51-LIB-L-MLKL.yaml +++ b/data/custodian/CZ-51-LIB-L-MLKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LIB-L-MLKL - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LIB-L-MLKL valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LIB-L-MLKL ghcid_numeric: 1807032568687001446 valid_from: '2025-12-06T23:37:37.375764+00:00' @@ -220,3 +221,29 @@ location: postal_code: 512 03 street_address: Libštát 198 normalization_timestamp: '2025-12-09T10:53:10.204570+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:55:17.792318+00:00' + source_url: http://libstat.info/zivot-v-libstate/kultura/knihovna + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://libstat.info/site/templates/styles/images/Libstat-logo.png + source_url: http://libstat.info/zivot-v-libstate/kultura/knihovna + css_selector: '#masthead-navbar > div.uk-navbar-left.uk-width-1-3@m > div.uk-navbar-item + > div.uk-text-left.uk-flex-column > div > a > img' + retrieved_on: '2025-12-24T21:55:17.792318+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Městys Libštát logo + - claim_type: og_image_url + claim_value: http://libstat.info/site/assets/files/1/libstat-logotyp-zakladni_seda-50.jpg + source_url: http://libstat.info/zivot-v-libstate/kultura/knihovna + css_selector: '#html-head > meta:nth-of-type(17)' + retrieved_on: '2025-12-24T21:55:17.792318+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/CZ-51-LIB-L-TUVLUK.yaml b/data/custodian/CZ-51-LIB-L-TUVLUK.yaml index ff444e2c2b..6b8aa4678e 100644 --- a/data/custodian/CZ-51-LIB-L-TUVLUK.yaml +++ b/data/custodian/CZ-51-LIB-L-TUVLUK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LIB-L-TUVLUK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LIB-L-TUVLUK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LIB-L-TUVLUK ghcid_numeric: 12974295947550070119 valid_from: '2025-12-06T23:37:18.456837+00:00' @@ -229,3 +230,32 @@ location: postal_code: 461 17 street_address: Voroněžská 13 normalization_timestamp: '2025-12-09T10:53:10.306492+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:55:33.329822+00:00' + source_url: https://knihovna-opac.tul.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovna-opac.tul.cz/custom/design/UKN logo bile.png + source_url: https://knihovna-opac.tul.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > h1.unset-style > a > img' + retrieved_on: '2025-12-24T21:55:33.329822+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Univerzitní knihovna TUL + - claim_type: favicon_url + claim_value: https://knihovna-opac.tul.cz/favicon.png?v=2.3.0-32021 + source_url: https://knihovna-opac.tul.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T21:55:33.329822+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-LIB-L-VSOITK.yaml b/data/custodian/CZ-51-LIB-L-VSOITK.yaml index 5d886bd75e..8e7074af3f 100644 --- a/data/custodian/CZ-51-LIB-L-VSOITK.yaml +++ b/data/custodian/CZ-51-LIB-L-VSOITK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LIB-L-VSOITK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LIB-L-VSOITK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LIB-L-VSOITK ghcid_numeric: 13695756708314373129 valid_from: '2025-12-06T23:37:18.447236+00:00' @@ -218,3 +219,28 @@ location: postal_code: 460 01 street_address: Svárovská 619 normalization_timestamp: '2025-12-09T10:53:10.389714+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:55:44.492667+00:00' + source_url: https://www.vuts.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vuts.cz/assets/template/images/favicon.ico + source_url: https://www.vuts.cz + css_selector: '[document] > html.no-js.show--consent > head > link' + retrieved_on: '2025-12-24T21:55:44.492667+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.vuts.cz/opengraph.jpg + source_url: https://www.vuts.cz + css_selector: '[document] > html.no-js.show--consent > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T21:55:44.492667+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/CZ-51-LIB-O-SOAVLSOAL.yaml b/data/custodian/CZ-51-LIB-O-SOAVLSOAL.yaml index ae1f597f35..3846ba519b 100644 --- a/data/custodian/CZ-51-LIB-O-SOAVLSOAL.yaml +++ b/data/custodian/CZ-51-LIB-O-SOAVLSOAL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LIB-O-SOAVLSOAL - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LIB-O-SOAVLSOAL valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LIB-O-SOAVLSOAL ghcid_numeric: 8484089271116582539 valid_from: '2025-12-06T23:37:26.359238+00:00' @@ -218,3 +219,29 @@ location: postal_code: 460 10 street_address: Vilová 339/24 normalization_timestamp: '2025-12-09T10:53:10.472460+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:55:57.351611+00:00' + source_url: http://www.soalitomerice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: http://www.soalitomerice.cz + css_selector: '[document] > html.td-md-is-chrome > body.home.page-template-default + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:55:57.351611+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2018/03/FB-post.png + source_url: http://www.soalitomerice.cz + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T21:55:57.351611+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-51-LOM-L-KISPOMK.yaml b/data/custodian/CZ-51-LOM-L-KISPOMK.yaml index d8bd8504ff..d8332b4851 100644 --- a/data/custodian/CZ-51-LOM-L-KISPOMK.yaml +++ b/data/custodian/CZ-51-LOM-L-KISPOMK.yaml @@ -177,3 +177,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q114617264 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:56:04.472239+00:00' + source_url: http://www.kislomnice.cz/knihovna/ms-69/p1=69 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.kislomnice.cz/html/images/favicon.ico + source_url: http://www.kislomnice.cz/knihovna/ms-69/p1=69 + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T21:56:04.472239+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-LOM-L-MKVS-mistni_knihovna_ve_struzinci.yaml b/data/custodian/CZ-51-LOM-L-MKVS-mistni_knihovna_ve_struzinci.yaml index 3011af7641..e290757e49 100644 --- a/data/custodian/CZ-51-LOM-L-MKVS-mistni_knihovna_ve_struzinci.yaml +++ b/data/custodian/CZ-51-LOM-L-MKVS-mistni_knihovna_ve_struzinci.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-LOM-L-MKVS-mistni_knihovna_ve_struzinci - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-LOM-L-MKVS-mistni_knihovna_ve_struzinci valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-LOM-L-MKVS-mistni_knihovna_ve_struzinci ghcid_numeric: 6831684614450846890 valid_from: '2025-12-06T23:37:37.473914+00:00' @@ -210,3 +211,22 @@ location: postal_code: 512 51 street_address: Stružinec 112 normalization_timestamp: '2025-12-09T10:53:10.534789+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:56:10.422620+00:00' + source_url: https://www.struzinec.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.struzinec.cz/wp-content/uploads/2017/06/favicon.jpg + source_url: https://www.struzinec.cz/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(16)' + retrieved_on: '2025-12-24T21:56:10.422620+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-MAL-L-VKVMS.yaml b/data/custodian/CZ-51-MAL-L-VKVMS.yaml index b7bd7cc40f..f207213f3e 100644 --- a/data/custodian/CZ-51-MAL-L-VKVMS.yaml +++ b/data/custodian/CZ-51-MAL-L-VKVMS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-MAL-L-VKVMS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-MAL-L-VKVMS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-MAL-L-VKVMS ghcid_numeric: 15714453496329178681 valid_from: '2025-12-06T23:37:37.190526+00:00' @@ -210,3 +211,28 @@ location: postal_code: 468 31 street_address: Vranové I. 387 normalization_timestamp: '2025-12-09T10:53:10.640346+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:56:31.652499+00:00' + source_url: https://www.mala-skala.cz/volny-cas/kultura-1/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mala-skala.cz/skins/mala-skalacz_lego/favicons/safari-pinned-tab.svg + source_url: https://www.mala-skala.cz/volny-cas/kultura-1/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T21:56:31.652499+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.mala-skala.cz/data/editor/222cs_1.jpg + source_url: https://www.mala-skala.cz/volny-cas/kultura-1/knihovna + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:56:31.652499+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-51-MAR-L-OKMVK.yaml b/data/custodian/CZ-51-MAR-L-OKMVK.yaml index 31243eb596..8e9ff2739c 100644 --- a/data/custodian/CZ-51-MAR-L-OKMVK.yaml +++ b/data/custodian/CZ-51-MAR-L-OKMVK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-MAR-L-OKMVK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-MAR-L-OKMVK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-MAR-L-OKMVK ghcid_numeric: 17011316482357292333 valid_from: '2025-12-06T23:37:37.396150+00:00' @@ -207,3 +208,22 @@ location: postal_code: 512 32 street_address: Martinice v Krkonoších 131 normalization_timestamp: '2025-12-09T10:53:10.746992+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:12:33.110640+00:00' + source_url: https://www.martinicevkrk.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.martinicevkrk.cz/image.php?nid=1327&oid=6515320 + source_url: https://www.martinicevkrk.cz + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-24T22:12:33.110640+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-MIM-L-MKM.yaml b/data/custodian/CZ-51-MIM-L-MKM.yaml index ed04b45d3c..66e8ed1531 100644 --- a/data/custodian/CZ-51-MIM-L-MKM.yaml +++ b/data/custodian/CZ-51-MIM-L-MKM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-MIM-L-MKM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-MIM-L-MKM valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-MIM-L-MKM ghcid_numeric: 8350655555661955239 valid_from: '2025-12-06T23:37:17.388560+00:00' @@ -219,3 +220,22 @@ location: postal_code: 471 24 street_address: Svébořická 309 normalization_timestamp: '2025-12-09T10:53:10.778455+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:12:47.097093+00:00' + source_url: https://katalog.knihovnamimon.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnamimon.cz/favicon.png?v=2.3.0-32021 + source_url: https://katalog.knihovnamimon.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:12:47.097093+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-MIM-L-MSK.yaml b/data/custodian/CZ-51-MIM-L-MSK.yaml index b3d4974d67..4e00e76e5d 100644 --- a/data/custodian/CZ-51-MIM-L-MSK.yaml +++ b/data/custodian/CZ-51-MIM-L-MSK.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-MIM-L-MSK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-MIM-L-MSK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-MIM-L-MSK ghcid_numeric: 10127294403969323627 valid_from: '2025-12-06T23:37:17.363779+00:00' @@ -162,3 +163,22 @@ location: postal_code: 471 24 street_address: Pertoltická 142/IV normalization_timestamp: '2025-12-09T06:51:51.315213+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:28:51.898665+00:00' + source_url: http://www.mitop.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mitop.cz/index_htm_files/favicon.ico + source_url: http://www.mitop.cz + css_selector: '[document] > html.xr_bgh0 > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:28:51.898665+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/ico + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-MRI-L-MKVM.yaml b/data/custodian/CZ-51-MRI-L-MKVM.yaml index 7acd79c492..a16321d3e7 100644 --- a/data/custodian/CZ-51-MRI-L-MKVM.yaml +++ b/data/custodian/CZ-51-MRI-L-MKVM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-MRI-L-MKVM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-MRI-L-MKVM valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-MRI-L-MKVM ghcid_numeric: 5758094847330904981 valid_from: '2025-12-06T23:37:37.455989+00:00' @@ -210,3 +211,22 @@ location: postal_code: 512 04 street_address: Mříčná 211 normalization_timestamp: '2025-12-09T10:53:10.937565+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:29:53.645372+00:00' + source_url: https://www.mricna.cz/volny-cas/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mricna.cz/skins/mricna.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.mricna.cz/volny-cas/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:29:53.645372+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-NOV-E-VOSSSSNBK.yaml b/data/custodian/CZ-51-NOV-E-VOSSSSNBK.yaml index cacab61317..dd60199aa2 100644 --- a/data/custodian/CZ-51-NOV-E-VOSSSSNBK.yaml +++ b/data/custodian/CZ-51-NOV-E-VOSSSSNBK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-NOV-E-VOSSSSNBK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-NOV-E-VOSSSSNBK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-NOV-E-VOSSSSNBK ghcid_numeric: 10601646847195799392 valid_from: '2025-12-08T11:21:37.145543+00:00' @@ -224,3 +225,22 @@ location: postal_code: 473 01 street_address: Wolkerova 316 normalization_timestamp: '2025-12-09T10:53:10.964642+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:30:00.827377+00:00' + source_url: https://www.glassschool.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.glassschool.cz/html/images/favicon.ico + source_url: https://www.glassschool.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:30:00.827377+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-NOV-L-OKNVNN.yaml b/data/custodian/CZ-51-NOV-L-OKNVNN.yaml index a660962f46..5abb7011c3 100644 --- a/data/custodian/CZ-51-NOV-L-OKNVNN.yaml +++ b/data/custodian/CZ-51-NOV-L-OKNVNN.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-NOV-L-OKNVNN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-NOV-L-OKNVNN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-NOV-L-OKNVNN ghcid_numeric: 311099440864967292 valid_from: '2025-12-06T23:37:37.176822+00:00' @@ -210,3 +211,22 @@ location: postal_code: 468 27 street_address: Nová Ves nad Nisou 281 normalization_timestamp: '2025-12-09T10:53:11.171349+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:31:27.188709+00:00' + source_url: https://www.novavesnn.cz/obec-123/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.novavesnn.cz/skins/novavesnn.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.novavesnn.cz/obec-123/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:31:27.188709+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-OSE-L-MKO.yaml b/data/custodian/CZ-51-OSE-L-MKO.yaml index c1142c6b13..5d98a0b3cc 100644 --- a/data/custodian/CZ-51-OSE-L-MKO.yaml +++ b/data/custodian/CZ-51-OSE-L-MKO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-OSE-L-MKO - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-OSE-L-MKO valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-OSE-L-MKO ghcid_numeric: 2065614108875602819 valid_from: '2025-12-06T23:37:37.299988+00:00' @@ -218,3 +219,22 @@ location: postal_code: 463 52 street_address: Náměstí 103 normalization_timestamp: '2025-12-09T10:53:11.317469+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:32:36.915688+00:00' + source_url: https://www.osecna.knihovna.cz/online-katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.osecna.knihovna.cz/favicon.svg + source_url: https://www.osecna.knihovna.cz/online-katalog + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:32:36.915688+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-PLA-L-OKP.yaml b/data/custodian/CZ-51-PLA-L-OKP.yaml index 1eda030740..a6f57ffd9a 100644 --- a/data/custodian/CZ-51-PLA-L-OKP.yaml +++ b/data/custodian/CZ-51-PLA-L-OKP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-PLA-L-OKP - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-PLA-L-OKP valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-PLA-L-OKP ghcid_numeric: 11630545964521769924 valid_from: '2025-12-06T23:37:37.179464+00:00' @@ -216,3 +217,22 @@ location: postal_code: 468 46 street_address: Plavy 186 normalization_timestamp: '2025-12-09T10:53:11.453962+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:32:55.903740+00:00' + source_url: http://plavy.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://plavy.knihovna.cz/favicon.svg + source_url: http://plavy.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:32:55.903740+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-PON-L-MKP.yaml b/data/custodian/CZ-51-PON-L-MKP.yaml index d4db6bf1b8..265657f812 100644 --- a/data/custodian/CZ-51-PON-L-MKP.yaml +++ b/data/custodian/CZ-51-PON-L-MKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-PON-L-MKP - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-PON-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-PON-L-MKP ghcid_numeric: 5259905102056317712 valid_from: '2025-12-06T23:37:37.410402+00:00' @@ -210,3 +211,22 @@ location: postal_code: 512 42 street_address: Poniklá 148 normalization_timestamp: '2025-12-09T10:53:11.472521+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:33:04.367294+00:00' + source_url: https://semily.tritius.cz/library/ponikla + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://semily.tritius.cz/apple-touch-icon-180x180.png + source_url: https://semily.tritius.cz/library/ponikla + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:33:04.367294+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-PRI-L-OKVP.yaml b/data/custodian/CZ-51-PRI-L-OKVP.yaml index 0f420a5300..4827b91a46 100644 --- a/data/custodian/CZ-51-PRI-L-OKVP.yaml +++ b/data/custodian/CZ-51-PRI-L-OKVP.yaml @@ -211,3 +211,22 @@ location: postal_code: 463 46 street_address: Příšovice 66 normalization_timestamp: '2025-12-09T10:53:11.526786+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:33:14.534895+00:00' + source_url: https://prisovice.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prisovice.knihovna.cz/favicon.svg + source_url: https://prisovice.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:33:14.534895+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-RAS-L-MKIC.yaml b/data/custodian/CZ-51-RAS-L-MKIC.yaml index f938491382..5242fbd481 100644 --- a/data/custodian/CZ-51-RAS-L-MKIC.yaml +++ b/data/custodian/CZ-51-RAS-L-MKIC.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-RAS-L-MKIC - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-RAS-L-MKIC valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-RAS-L-MKIC ghcid_numeric: 3901481600781472333 valid_from: '2025-12-06T23:37:18.509063+00:00' @@ -223,3 +224,22 @@ location: postal_code: 463 61 street_address: Fučíkova 421 normalization_timestamp: '2025-12-09T10:53:11.637349+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:00.298998+00:00' + source_url: https://lck.tritius.cz/library/raspenava + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lck.tritius.cz/library/raspenava + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:34:00.298998+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-ROK-L-MKRNJ.yaml b/data/custodian/CZ-51-ROK-L-MKRNJ.yaml index 98a2b8903d..3270c6d126 100644 --- a/data/custodian/CZ-51-ROK-L-MKRNJ.yaml +++ b/data/custodian/CZ-51-ROK-L-MKRNJ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-ROK-L-MKRNJ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-ROK-L-MKRNJ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-ROK-L-MKRNJ ghcid_numeric: 1305934881516400745 valid_from: '2025-12-06T23:37:19.931133+00:00' @@ -212,3 +213,22 @@ location: postal_code: 512 44 street_address: Dolní Rokytnice 172 normalization_timestamp: '2025-12-09T10:53:11.657583+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:06.389005+00:00' + source_url: https://semily.tritius.cz/library/rokytnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://semily.tritius.cz/apple-touch-icon-180x180.png + source_url: https://semily.tritius.cz/library/rokytnice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:34:06.389005+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-ROV-L-MKRPT.yaml b/data/custodian/CZ-51-ROV-L-MKRPT.yaml index 6f5f5e05b2..b4f877de83 100644 --- a/data/custodian/CZ-51-ROV-L-MKRPT.yaml +++ b/data/custodian/CZ-51-ROV-L-MKRPT.yaml @@ -209,3 +209,22 @@ location: country: *id005 postal_code: 512 63 normalization_timestamp: '2025-12-09T10:53:11.685194+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:12.471700+00:00' + source_url: https://www.rovensko.cz/mesto/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rovensko.cz/skins/rovensko.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.rovensko.cz/mesto/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:34:12.471700+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-ROZ-L-OKRUJ.yaml b/data/custodian/CZ-51-ROZ-L-OKRUJ.yaml index cc683a5055..e6898a18e0 100644 --- a/data/custodian/CZ-51-ROZ-L-OKRUJ.yaml +++ b/data/custodian/CZ-51-ROZ-L-OKRUJ.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-ROZ-L-OKRUJ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-ROZ-L-OKRUJ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-ROZ-L-OKRUJ ghcid_numeric: 4250718843500592335 valid_from: '2025-12-06T23:37:23.318739+00:00' @@ -208,3 +209,30 @@ location: country: *id005 postal_code: 512 31 normalization_timestamp: '2025-12-09T10:53:11.713526+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:24.595901+00:00' + source_url: https://www.roztoky-u-jilemnice.cz/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.roztoky-u-jilemnice.cz/wp-content/uploads/logo_roztoky.png + source_url: https://www.roztoky-u-jilemnice.cz/obecni-knihovna + css_selector: '#titles > a.logo > picture > source > img.tranz.webpexpress-processed' + retrieved_on: '2025-12-24T22:34:24.595901+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Obec Roztoky u Jilemnice + - claim_type: favicon_url + claim_value: https://www.roztoky-u-jilemnice.cz/wp-content/uploads/erb_roztoky-298x300.png + source_url: https://www.roztoky-u-jilemnice.cz/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(35)' + retrieved_on: '2025-12-24T22:34:24.595901+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-51-RYC-L-MKVRUJNN.yaml b/data/custodian/CZ-51-RYC-L-MKVRUJNN.yaml index 88b4410399..92463774b0 100644 --- a/data/custodian/CZ-51-RYC-L-MKVRUJNN.yaml +++ b/data/custodian/CZ-51-RYC-L-MKVRUJNN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-RYC-L-MKVRUJNN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-RYC-L-MKVRUJNN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-RYC-L-MKVRUJNN ghcid_numeric: 15985851063727133398 valid_from: '2025-12-06T23:37:21.309699+00:00' @@ -216,3 +217,22 @@ location: postal_code: 468 02 street_address: Náměstí Míru 720 normalization_timestamp: '2025-12-09T10:53:11.741587+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:30.549458+00:00' + source_url: https://lck.tritius.cz/library/rujnn + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lck.tritius.cz/library/rujnn + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:34:30.549458+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-SEM-A-SOAS-statni_okresni_archiv_semily.yaml b/data/custodian/CZ-51-SEM-A-SOAS-statni_okresni_archiv_semily.yaml index 72852da664..82c3aa3c97 100644 --- a/data/custodian/CZ-51-SEM-A-SOAS-statni_okresni_archiv_semily.yaml +++ b/data/custodian/CZ-51-SEM-A-SOAS-statni_okresni_archiv_semily.yaml @@ -253,3 +253,29 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Semily official youtube_search_timestamp: '2025-12-09T09:31:50.830008+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:40.191062+00:00' + source_url: http://www.soalitomerice.cz/en/soka-semily + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: http://www.soalitomerice.cz/en/soka-semily + css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:34:40.191062+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/sokasem.jpg + source_url: http://www.soalitomerice.cz/en/soka-semily + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T22:34:40.191062+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-51-SEM-L-MKL.yaml b/data/custodian/CZ-51-SEM-L-MKL.yaml index 732070c1b2..d870db5b92 100644 --- a/data/custodian/CZ-51-SEM-L-MKL.yaml +++ b/data/custodian/CZ-51-SEM-L-MKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SEM-L-MKL - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SEM-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SEM-L-MKL ghcid_numeric: 11619535086097358071 valid_from: '2025-12-06T23:37:37.404777+00:00' @@ -212,3 +213,22 @@ location: postal_code: 513 01 street_address: Háje nad Jizerou - Loukov 57 normalization_timestamp: '2025-12-09T10:53:11.785939+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:48.832853+00:00' + source_url: https://www.hajenadjizerou.cz/volny-cas/kultura + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hajenadjizerou.cz/skins/hajenadjizerou.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.hajenadjizerou.cz/volny-cas/kultura + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:34:48.832853+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-SEM-L-MKSPO.yaml b/data/custodian/CZ-51-SEM-L-MKSPO.yaml index 270897f7ce..be9e5c5229 100644 --- a/data/custodian/CZ-51-SEM-L-MKSPO.yaml +++ b/data/custodian/CZ-51-SEM-L-MKSPO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SEM-L-MKSPO - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SEM-L-MKSPO valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SEM-L-MKSPO ghcid_numeric: 8316133712239839588 valid_from: '2025-12-06T23:37:19.920025+00:00' @@ -226,3 +227,22 @@ location: postal_code: 513 01 street_address: Tyršova 49 normalization_timestamp: '2025-12-09T10:53:11.805676+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:54.958173+00:00' + source_url: https://semily.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://semily.tritius.cz/apple-touch-icon-180x180.png + source_url: https://semily.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:34:54.958173+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-SEM-L-MKVS.yaml b/data/custodian/CZ-51-SEM-L-MKVS.yaml index e0936d2099..e5726b1422 100644 --- a/data/custodian/CZ-51-SEM-L-MKVS.yaml +++ b/data/custodian/CZ-51-SEM-L-MKVS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SEM-L-MKVS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SEM-L-MKVS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SEM-L-MKVS ghcid_numeric: 11840534174627301928 valid_from: '2025-12-06T23:37:37.379007+00:00' @@ -210,3 +211,22 @@ location: postal_code: 513 01 street_address: Smrčí 32 normalization_timestamp: '2025-12-09T10:53:11.928844+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:07.975045+00:00' + source_url: http://www.smrci.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.smrci.knihovna.cz/favicon.svg + source_url: http://www.smrci.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:35:07.975045+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-51-SEM-L-MSNVSLK.yaml b/data/custodian/CZ-51-SEM-L-MSNVSLK.yaml index 65666e91c9..dbd486e013 100644 --- a/data/custodian/CZ-51-SEM-L-MSNVSLK.yaml +++ b/data/custodian/CZ-51-SEM-L-MSNVSLK.yaml @@ -51,13 +51,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SEM-L-MSNVSLK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SEM-L-MSNVSLK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SEM-L-MSNVSLK ghcid_numeric: 12592382379874114161 valid_from: '2025-12-06T23:37:24.566533+00:00' @@ -221,3 +222,31 @@ location: postal_code: 513 31 street_address: 3. května 421 normalization_timestamp: '2025-12-09T10:53:11.992583+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:13.294786+00:00' + source_url: https://www.nemjil.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.nemjil.cz/static/images/logo.png + source_url: https://www.nemjil.cz + css_selector: '#masthead > div.mid-header.pb-0 > div.container.d-flex > div.site-identity + > h1.site-title > a > img' + retrieved_on: '2025-12-24T22:35:13.294786+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo + - claim_type: favicon_url + claim_value: https://www.nemjil.cz/static/images/logo.png + source_url: https://www.nemjil.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:35:13.294786+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-SEM-L-OKVC.yaml b/data/custodian/CZ-51-SEM-L-OKVC.yaml index 2a93d4a404..5e7ef0157f 100644 --- a/data/custodian/CZ-51-SEM-L-OKVC.yaml +++ b/data/custodian/CZ-51-SEM-L-OKVC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SEM-L-OKVC - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SEM-L-OKVC valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SEM-L-OKVC ghcid_numeric: 12877930688898357321 valid_from: '2025-12-06T23:37:37.372812+00:00' @@ -210,3 +211,22 @@ location: postal_code: 513 01 street_address: Chuchelna 269 normalization_timestamp: '2025-12-09T10:53:12.018209+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:19.601203+00:00' + source_url: https://www.chuchelna.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.chuchelna.cz/wp-content/uploads/2021/05/favi.png + source_url: https://www.chuchelna.cz/obec/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(15)' + retrieved_on: '2025-12-24T22:35:19.601203+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-SEM-M-MPG.yaml b/data/custodian/CZ-51-SEM-M-MPG.yaml index 1b1cc29474..df8b9a9a34 100644 --- a/data/custodian/CZ-51-SEM-M-MPG.yaml +++ b/data/custodian/CZ-51-SEM-M-MPG.yaml @@ -238,3 +238,37 @@ location: youtube_status: NOT_FOUND youtube_search_query: Muzeum a Pojizerská galerie official youtube_search_timestamp: '2025-12-09T09:31:51.503927+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:27.195555+00:00' + source_url: http://www.muzeumsemily.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://muzeumsemily.cz/assets/images/svg/logo.svg + source_url: http://www.muzeumsemily.cz + css_selector: '[document] > html.js > body.t-events.p-akce-v-muzeu > header.c-header + > div.c-header__layout.c-header__layout--with-hamburger > a.c-logo > img.c-logo__img.w-auto' + retrieved_on: '2025-12-24T22:35:27.195555+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Muzeum a Pojizerská galerie Semily, p. o. + - claim_type: favicon_url + claim_value: http://www.muzeumsemily.cz/assets/favicon/safari-pinned-tab.svg + source_url: http://www.muzeumsemily.cz + css_selector: '[document] > html.js > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:35:27.195555+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://muzeumsemily.cz/media/site/9e96581fc0-1673879869/muzeum-1200x630-crop-1.jpg + source_url: http://www.muzeumsemily.cz + css_selector: '[document] > html.js > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T22:35:27.195555+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-51-SEM-O-SOAVLSOAS.yaml b/data/custodian/CZ-51-SEM-O-SOAVLSOAS.yaml index 19bdf10731..a85ce29099 100644 --- a/data/custodian/CZ-51-SEM-O-SOAVLSOAS.yaml +++ b/data/custodian/CZ-51-SEM-O-SOAVLSOAS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SEM-O-SOAVLSOAS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SEM-O-SOAVLSOAS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SEM-O-SOAVLSOAS ghcid_numeric: 6384114552995364043 valid_from: '2025-12-06T23:37:19.852418+00:00' @@ -220,3 +221,29 @@ location: postal_code: 513 01 street_address: Archivní 570 normalization_timestamp: '2025-12-09T10:53:12.068195+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:35.236024+00:00' + source_url: https://www.soalitomerice.cz/soka-semily + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png + source_url: https://www.soalitomerice.cz/soka-semily + css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single + > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:35:35.236024+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/sokasem.jpg + source_url: https://www.soalitomerice.cz/soka-semily + css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T22:35:35.236024+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-51-SEN-M-SMKS.yaml b/data/custodian/CZ-51-SEN-M-SMKS.yaml index 681ce6322b..ce778350aa 100644 --- a/data/custodian/CZ-51-SEN-M-SMKS.yaml +++ b/data/custodian/CZ-51-SEN-M-SMKS.yaml @@ -274,3 +274,32 @@ location: youtube_status: NOT_FOUND youtube_search_query: Sklářské muzeum, Kamenický Šenov official youtube_search_timestamp: '2025-12-09T09:31:52.179478+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:41.258537+00:00' + source_url: http://www.muzeumskla.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.muzeumskla.cz/skins/muzeumskla.cz_lego2/images/logo.png + source_url: http://www.muzeumskla.cz + css_selector: '[document] > html > body.homepage.body_multipage > header.gcm-header + > div.gcm-header__container.gcm-container > div.gcm-header__row.gcm-row > div.gcm-header__left + > a.gcm-crest > img.gcm-crest__img' + retrieved_on: '2025-12-24T22:35:41.258537+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Sklářského muzeum Kamenický Šenov + - claim_type: favicon_url + claim_value: http://www.muzeumskla.cz/skins/muzeumskla.cz_lego2/favicons/apple-touch-icon.png + source_url: http://www.muzeumskla.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:35:41.258537+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-51-SIM-L-MKVS.yaml b/data/custodian/CZ-51-SIM-L-MKVS.yaml index 0757f65e29..e594c739b8 100644 --- a/data/custodian/CZ-51-SIM-L-MKVS.yaml +++ b/data/custodian/CZ-51-SIM-L-MKVS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SIM-L-MKVS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SIM-L-MKVS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SIM-L-MKVS ghcid_numeric: 13988885889870162848 valid_from: '2025-12-08T11:21:34.352604+00:00' @@ -215,3 +216,20 @@ location: postal_code: 463 12 street_address: Minkovická 70 normalization_timestamp: '2025-12-09T10:53:12.095097+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:46.156952+00:00' + source_url: https://mistni-knihovna-v-simonovicich.estranky.cz/clanky/online-katalog.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www004.estranky.cz/resources/estranky.cz/global/img/logo-est.jpg + source_url: https://mistni-knihovna-v-simonovicich.estranky.cz/clanky/online-katalog.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T22:35:46.156952+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/CZ-51-SLA-L-MKVS.yaml b/data/custodian/CZ-51-SLA-L-MKVS.yaml index 561b6697a4..9beab237da 100644 --- a/data/custodian/CZ-51-SLA-L-MKVS.yaml +++ b/data/custodian/CZ-51-SLA-L-MKVS.yaml @@ -219,3 +219,22 @@ location: postal_code: 512 01 street_address: Slaná 94 normalization_timestamp: '2025-12-09T10:53:12.149569+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:36:23.680938+00:00' + source_url: https://www.obecslana.cz/mistni-knihovna-ve-slane/ms-3988/p1=3988 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obecslana.cz/html/images/favicon.ico + source_url: https://www.obecslana.cz/mistni-knihovna-ve-slane/ms-3988/p1=3988 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:36:23.680938+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-STU-L-OKS.yaml b/data/custodian/CZ-51-STU-L-OKS.yaml index 9d58e97eaa..c6fbbe0654 100644 --- a/data/custodian/CZ-51-STU-L-OKS.yaml +++ b/data/custodian/CZ-51-STU-L-OKS.yaml @@ -35,13 +35,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-STU-L-OKS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-STU-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-STU-L-OKS ghcid_numeric: 16332589305011014928 valid_from: '2025-12-06T23:37:26.168773+00:00' @@ -99,8 +100,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Obecní knihovna Studenec @@ -209,3 +210,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:21.842025+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Studenec +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:37:24.225480+00:00' + source_url: https://www.studenec.cz/kultura-a-sport/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.studenec.cz/skins/studenec.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.studenec.cz/kultura-a-sport/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:37:24.225480+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-SYC-L-MKVZ.yaml b/data/custodian/CZ-51-SYC-L-MKVZ.yaml index b741e1675b..2bb7332400 100644 --- a/data/custodian/CZ-51-SYC-L-MKVZ.yaml +++ b/data/custodian/CZ-51-SYC-L-MKVZ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-SYC-L-MKVZ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-SYC-L-MKVZ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-SYC-L-MKVZ ghcid_numeric: 3181096880097355720 valid_from: '2025-12-08T11:21:26.911055+00:00' @@ -215,3 +216,22 @@ location: postal_code: 463 44 street_address: Žďárek 60 normalization_timestamp: '2025-12-09T10:53:12.537789+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:39:19.314614+00:00' + source_url: https://www.zdarek.net/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zdarek.net/file.php?nid=10766&oid=7665240 + source_url: https://www.zdarek.net/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T22:39:19.314614+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-TAN-L-MKT.yaml b/data/custodian/CZ-51-TAN-L-MKT.yaml index ae4e1d61f2..ec73f6c63a 100644 --- a/data/custodian/CZ-51-TAN-L-MKT.yaml +++ b/data/custodian/CZ-51-TAN-L-MKT.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-TAN-L-MKT - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-TAN-L-MKT valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-TAN-L-MKT ghcid_numeric: 12069065619585416742 valid_from: '2025-12-06T23:37:18.036527+00:00' @@ -219,3 +220,22 @@ location: postal_code: 468 41 street_address: Krkonošská 350 normalization_timestamp: '2025-12-09T10:53:12.588735+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:39:34.872574+00:00' + source_url: https://lck.tritius.cz/library/tanvald + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://lck.tritius.cz/library/tanvald + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:39:34.872574+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-TAT-L-OKVT.yaml b/data/custodian/CZ-51-TAT-L-OKVT.yaml index 3555fe4346..b2a25d2656 100644 --- a/data/custodian/CZ-51-TAT-L-OKVT.yaml +++ b/data/custodian/CZ-51-TAT-L-OKVT.yaml @@ -211,3 +211,22 @@ location: postal_code: 512 53 street_address: Tatobity 85 normalization_timestamp: '2025-12-09T10:53:12.626832+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:39:44.010165+00:00' + source_url: https://tatobity.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tatobity.cz/wp-content/uploads/2018/09/apple-touch-icon-180x180.png + source_url: https://tatobity.cz/obec/knihovna + css_selector: '[document] > html.chrome.chrome135 > head > link:nth-of-type(40)' + retrieved_on: '2025-12-24T22:39:44.010165+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 13 diff --git a/data/custodian/CZ-51-TUR-E-SUSVOSK.yaml b/data/custodian/CZ-51-TUR-E-SUSVOSK.yaml index 3bdb82b532..cf00a82b61 100644 --- a/data/custodian/CZ-51-TUR-E-SUSVOSK.yaml +++ b/data/custodian/CZ-51-TUR-E-SUSVOSK.yaml @@ -183,3 +183,32 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1076099 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:39:51.830961+00:00' + source_url: https://www.sups.info + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.sups.info/images/SUPS/logotype_v2020_short.png + source_url: https://www.sups.info + css_selector: '[document] > html.uk-notouch > body.tm-isblog > div.tm-top-block.tm-grid-block:nth-of-type(2) + > nav.tm-navbar.uk-navbar > div.uk-container.uk-container-center > div.uk-navbar-content.uk-navbar-center:nth-of-type(2) + > a.tm-logo-small > p > img.uk-responsive-height' + retrieved_on: '2025-12-24T22:39:51.830961+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Špéra + - claim_type: favicon_url + claim_value: https://www.sups.info/templates/yoo_eat/apple_touch_icon.png + source_url: https://www.sups.info + css_selector: '[document] > html.uk-notouch > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:39:51.830961+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-51-TUR-L-MKAMTPO.yaml b/data/custodian/CZ-51-TUR-L-MKAMTPO.yaml index bfab79d213..af636c6251 100644 --- a/data/custodian/CZ-51-TUR-L-MKAMTPO.yaml +++ b/data/custodian/CZ-51-TUR-L-MKAMTPO.yaml @@ -183,3 +183,22 @@ wikidata_enrichment: instance_of: - Q7075 inception: +2003-08-13T00:00:00Z +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:40:03.511856+00:00' + source_url: https://knihovna.turnov.cz/katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.turnov.cz/wp-content/uploads/2015/08/favicon.png + source_url: https://knihovna.turnov.cz/katalog + css_selector: '[document] > html.js > head > link:nth-of-type(19)' + retrieved_on: '2025-12-24T22:40:03.511856+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-TUR-L-MKL.yaml b/data/custodian/CZ-51-TUR-L-MKL.yaml index ccdb40946c..972f3c019c 100644 --- a/data/custodian/CZ-51-TUR-L-MKL.yaml +++ b/data/custodian/CZ-51-TUR-L-MKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-TUR-L-MKL - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-TUR-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-TUR-L-MKL ghcid_numeric: 2112383149586439589 valid_from: '2025-12-06T23:37:37.469898+00:00' @@ -210,3 +211,22 @@ location: postal_code: 511 01 street_address: Loučky 34 normalization_timestamp: '2025-12-09T10:53:12.754121+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:40:09.784349+00:00' + source_url: https://www.loucky.info/volny-cas/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.loucky.info/skins/loucky.info_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.loucky.info/volny-cas/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:40:09.784349+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-TUR-L-OKHS.yaml b/data/custodian/CZ-51-TUR-L-OKHS.yaml index 5954bf4a8e..3a65df05b0 100644 --- a/data/custodian/CZ-51-TUR-L-OKHS.yaml +++ b/data/custodian/CZ-51-TUR-L-OKHS.yaml @@ -211,3 +211,22 @@ location: postal_code: 511 01 street_address: Doubravice 37 normalization_timestamp: '2025-12-09T10:53:12.804534+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:40:18.124418+00:00' + source_url: https://obechrubaskala.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://obechrubaskala.cz/skins/obechrubaskala.cz_lego3/favicons/safari-pinned-tab.svg + source_url: https://obechrubaskala.cz/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:40:18.124418+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-TUR-L-OKVK.yaml b/data/custodian/CZ-51-TUR-L-OKVK.yaml index 26b8eb5a35..1931c8bac9 100644 --- a/data/custodian/CZ-51-TUR-L-OKVK.yaml +++ b/data/custodian/CZ-51-TUR-L-OKVK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-TUR-L-OKVK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-TUR-L-OKVK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-TUR-L-OKVK ghcid_numeric: 8711955126371930552 valid_from: '2025-12-06T23:37:37.413483+00:00' @@ -210,3 +211,22 @@ location: postal_code: 511 01 street_address: Karlovice 12 normalization_timestamp: '2025-12-09T10:53:12.882518+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:40:30.156101+00:00' + source_url: https://www.karlovice-sedmihorky.cz/kultura-a-sport/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.karlovice-sedmihorky.cz/wp-content/uploads/2017/04/apple-touch-icon-180x180.png + source_url: https://www.karlovice-sedmihorky.cz/kultura-a-sport/knihovna + css_selector: '[document] > html.chrome.chrome123 > head > link:nth-of-type(38)' + retrieved_on: '2025-12-24T22:40:30.156101+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 13 diff --git a/data/custodian/CZ-51-TUR-L-OKVL.yaml b/data/custodian/CZ-51-TUR-L-OKVL.yaml index 6bac0e99cb..42404d2991 100644 --- a/data/custodian/CZ-51-TUR-L-OKVL.yaml +++ b/data/custodian/CZ-51-TUR-L-OKVL.yaml @@ -211,3 +211,22 @@ location: postal_code: 511 01 street_address: Loktuše normalization_timestamp: '2025-12-09T10:53:12.908973+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:40:38.717814+00:00' + source_url: https://www.mirova.cz/obec-7/knihovna-vesec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mirova.cz/skins/mirova/favicons/safari-pinned-tab.svg + source_url: https://www.mirova.cz/obec-7/knihovna-vesec + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:40:38.717814+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-TUR-M-MCRVTK.yaml b/data/custodian/CZ-51-TUR-M-MCRVTK.yaml index f13fb070a0..68c44f02ec 100644 --- a/data/custodian/CZ-51-TUR-M-MCRVTK.yaml +++ b/data/custodian/CZ-51-TUR-M-MCRVTK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-TUR-M-MCRVTK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-TUR-M-MCRVTK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-TUR-M-MCRVTK ghcid_numeric: 13877178060079883076 valid_from: '2025-12-08T11:21:36.355669+00:00' @@ -216,3 +217,22 @@ location: postal_code: 511 01 street_address: Skálova 71 normalization_timestamp: '2025-12-09T10:53:12.981840+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:40:51.162049+00:00' + source_url: https://muzeum-turnov.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeum-turnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeum-turnov.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:40:51.162049+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-51-VEV-L-MZKB.yaml b/data/custodian/CZ-51-VEV-L-MZKB.yaml index 7a8a3dda10..1d04ee3965 100644 --- a/data/custodian/CZ-51-VEV-L-MZKB.yaml +++ b/data/custodian/CZ-51-VEV-L-MZKB.yaml @@ -353,3 +353,22 @@ wikidata_enrichment: email: mailto:mzk@mzk.cz wikidata_collection: collection_items_count: '325' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:02.783864+00:00' + source_url: https://www.mzk.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mzk.cz/themes/custom/awesome/favicons/favicon.svg + source_url: https://www.mzk.cz + css_selector: '[document] > html.js.show--consent > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T22:41:02.783864+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-51-VIC-L-MKVNJ.yaml b/data/custodian/CZ-51-VIC-L-MKVNJ.yaml index f727bbd612..390b2eaa51 100644 --- a/data/custodian/CZ-51-VIC-L-MKVNJ.yaml +++ b/data/custodian/CZ-51-VIC-L-MKVNJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-VIC-L-MKVNJ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-VIC-L-MKVNJ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-VIC-L-MKVNJ ghcid_numeric: 8048116013674511796 valid_from: '2025-12-06T23:37:37.430180+00:00' @@ -216,3 +217,22 @@ location: postal_code: 512 41 street_address: Víchová nad Jizerou 140 normalization_timestamp: '2025-12-09T10:53:13.046183+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:07.719881+00:00' + source_url: https://www.vichovanj.cz/sluzby/ms-6069/p1=6069 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vichovanj.cz/html/images/favicon.ico + source_url: https://www.vichovanj.cz/sluzby/ms-6069/p1=6069 + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:41:07.719881+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-VRA-L-KIV.yaml b/data/custodian/CZ-51-VRA-L-KIV.yaml index c99a8801b2..b130009279 100644 --- a/data/custodian/CZ-51-VRA-L-KIV.yaml +++ b/data/custodian/CZ-51-VRA-L-KIV.yaml @@ -185,3 +185,22 @@ wikidata_enrichment: image: https://commons.wikimedia.org/wiki/Special:FilePath/Vratislavice_nad_Nisou_(Liberec_XXX)_-_knihovna_čp._342_v_ulici_Nad_Školou_(1).jpg instance_of: - Q2326815 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:47.197901+00:00' + source_url: https://katalog.igivratislavice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.igivratislavice.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.igivratislavice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:41:47.197901+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-VSE-L-OKFJTVV.yaml b/data/custodian/CZ-51-VSE-L-OKFJTVV.yaml index 97e45d181d..d0328d97c4 100644 --- a/data/custodian/CZ-51-VSE-L-OKFJTVV.yaml +++ b/data/custodian/CZ-51-VSE-L-OKFJTVV.yaml @@ -211,3 +211,22 @@ location: postal_code: 512 65 street_address: Všeň 10 normalization_timestamp: '2025-12-09T10:53:13.131455+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:55.689540+00:00' + source_url: https://vsen.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vsen.cz/wp-content/uploads/2019/01/apple-touch-icon-180x180.png + source_url: https://vsen.cz/obec/knihovna + css_selector: '[document] > html.chrome.chrome134 > head > link:nth-of-type(33)' + retrieved_on: '2025-12-24T22:41:55.689540+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 13 diff --git a/data/custodian/CZ-51-ZEL-L-MLKV.yaml b/data/custodian/CZ-51-ZEL-L-MLKV.yaml index 94cb7bd750..6c7aba60a2 100644 --- a/data/custodian/CZ-51-ZEL-L-MLKV.yaml +++ b/data/custodian/CZ-51-ZEL-L-MLKV.yaml @@ -211,3 +211,22 @@ location: postal_code: 468 22 street_address: Vlastiboř 102 normalization_timestamp: '2025-12-09T10:53:13.284997+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:17.698339+00:00' + source_url: https://www.obec-vlastibor.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-vlastibor.cz/skins/obec-vlastibor.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.obec-vlastibor.cz/obec/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:43:17.698339+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-ZEL-L-OKK.yaml b/data/custodian/CZ-51-ZEL-L-OKK.yaml index b6107bf1f8..3ee3369cea 100644 --- a/data/custodian/CZ-51-ZEL-L-OKK.yaml +++ b/data/custodian/CZ-51-ZEL-L-OKK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-ZEL-L-OKK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-ZEL-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-ZEL-L-OKK ghcid_numeric: 13663605414442401482 valid_from: '2025-12-06T23:37:37.204848+00:00' @@ -210,3 +211,22 @@ location: postal_code: 468 22 street_address: Koberovy 140 normalization_timestamp: '2025-12-09T10:53:13.309649+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:24.635020+00:00' + source_url: https://www.koberovy.cz/volny-cas/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.koberovy.cz/skins/koberovy.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.koberovy.cz/volny-cas/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:43:24.635020+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-ZEL-L-OKL.yaml b/data/custodian/CZ-51-ZEL-L-OKL.yaml index e729702f24..3ef2725a36 100644 --- a/data/custodian/CZ-51-ZEL-L-OKL.yaml +++ b/data/custodian/CZ-51-ZEL-L-OKL.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-ZEL-L-OKL - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-ZEL-L-OKL valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-ZEL-L-OKL ghcid_numeric: 6355527962289710047 valid_from: '2025-12-06T23:37:37.237993+00:00' @@ -205,3 +206,22 @@ location: postal_code: 468 22 street_address: Líšný 60 normalization_timestamp: '2025-12-09T10:53:13.328773+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:32.136522+00:00' + source_url: https://www.lisny.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lisny.cz/skins/lisny.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.lisny.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:43:32.136522+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-51-ZEL-L-OKR.yaml b/data/custodian/CZ-51-ZEL-L-OKR.yaml index b39f47e24b..14797525f4 100644 --- a/data/custodian/CZ-51-ZEL-L-OKR.yaml +++ b/data/custodian/CZ-51-ZEL-L-OKR.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-ZEL-L-OKR - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-ZEL-L-OKR valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-ZEL-L-OKR ghcid_numeric: 15082446326735200535 valid_from: '2025-12-06T23:37:37.212931+00:00' @@ -210,3 +211,22 @@ location: postal_code: 468 22 street_address: Radčice 90 normalization_timestamp: '2025-12-09T10:53:13.357599+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:38.059751+00:00' + source_url: https://www.radcice.eu/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.radcice.eu/image.php?nid=19750&oid=8564629&width=32 + source_url: https://www.radcice.eu/knihovna + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-24T22:43:38.059751+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-51-ZLA-L-OKZO.yaml b/data/custodian/CZ-51-ZLA-L-OKZO.yaml index 40e3820b16..e614316dd3 100644 --- a/data/custodian/CZ-51-ZLA-L-OKZO.yaml +++ b/data/custodian/CZ-51-ZLA-L-OKZO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-51-ZLA-L-OKZO - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-LI to CZ-51 (Liberec (Liberecký)) per ISO + 3166-2:CZ - ghcid: CZ-LI-ZLA-L-OKZO valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-LI-ZLA-L-OKZO ghcid_numeric: 17513998794732833767 valid_from: '2025-12-06T23:37:26.808262+00:00' @@ -203,3 +204,22 @@ location: postal_code: 468 47 street_address: Zlatá Olešnice 172 normalization_timestamp: '2025-12-09T10:53:13.382527+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:45.274105+00:00' + source_url: https://www.zlata-olesnice.cz/obec/sluzby-v-obci/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zlata-olesnice.cz/skins/zlata-olesnice.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.zlata-olesnice.cz/obec/sluzby-v-obci/knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:43:45.274105+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-52-BAT-L-OKB.yaml b/data/custodian/CZ-52-BAT-L-OKB.yaml index 3eeec7d3cd..3fb567af9a 100644 --- a/data/custodian/CZ-52-BAT-L-OKB.yaml +++ b/data/custodian/CZ-52-BAT-L-OKB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BAT-L-OKB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BAT-L-OKB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BAT-L-OKB ghcid_numeric: 5379210306635824947 valid_from: '2025-12-06T23:37:35.599132+00:00' @@ -220,3 +221,22 @@ location: postal_code: 542 32 street_address: Batňovice 161 normalization_timestamp: '2025-12-09T10:52:58.160152+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:52.013491+00:00' + source_url: https://trutnov.tritius.cz/library/batnovice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/batnovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:43:52.013491+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-BEL-L-OKBNO.yaml b/data/custodian/CZ-52-BEL-L-OKBNO.yaml index 151b15f058..160319ca17 100644 --- a/data/custodian/CZ-52-BEL-L-OKBNO.yaml +++ b/data/custodian/CZ-52-BEL-L-OKBNO.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BEL-L-OKBNO - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BEL-L-OKBNO valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BEL-L-OKBNO ghcid_numeric: 7765583151419869442 valid_from: '2025-12-06T23:37:34.905052+00:00' @@ -214,3 +215,22 @@ location: postal_code: 503 46 street_address: Běleč nad Orlicí 22 normalization_timestamp: '2025-12-09T10:52:58.184406+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:58.269286+00:00' + source_url: https://belec.trebechovicko.cz/obecni%2Dknihovna%2Dbelec%2Dnad%2Dorlici/d-20715/p1=6647 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://belec.trebechovicko.cz/html/images/favicon.ico + source_url: https://belec.trebechovicko.cz/obecni%2Dknihovna%2Dbelec%2Dnad%2Dorlici/d-20715/p1=6647 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:43:58.269286+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-BER-L-MKB.yaml b/data/custodian/CZ-52-BER-L-MKB.yaml index f4cff6dd52..458eb0931b 100644 --- a/data/custodian/CZ-52-BER-L-MKB.yaml +++ b/data/custodian/CZ-52-BER-L-MKB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BER-L-MKB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BER-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BER-L-MKB ghcid_numeric: 13425548582754137191 valid_from: '2025-12-06T23:37:35.602252+00:00' @@ -214,3 +215,22 @@ location: postal_code: 542 04 street_address: Bernartice 77 normalization_timestamp: '2025-12-09T10:52:58.211582+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:06.204991+00:00' + source_url: https://trutnov.tritius.cz/library/bernartice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/bernartice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:44:06.204991+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-BER-L-OKL.yaml b/data/custodian/CZ-52-BER-L-OKL.yaml index f362a329e6..d117cc927c 100644 --- a/data/custodian/CZ-52-BER-L-OKL.yaml +++ b/data/custodian/CZ-52-BER-L-OKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BER-L-OKL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BER-L-OKL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BER-L-OKL ghcid_numeric: 13500538661192928640 valid_from: '2025-12-06T23:37:35.605311+00:00' @@ -210,3 +211,22 @@ location: postal_code: 542 04 street_address: Lampertice 210 normalization_timestamp: '2025-12-09T10:52:58.237508+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:12.228145+00:00' + source_url: https://trutnov.tritius.cz/library/lampertice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/lampertice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:44:12.228145+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-BIL-E-ZSMSBTSKVL.yaml b/data/custodian/CZ-52-BIL-E-ZSMSBTSKVL.yaml index 5b1f8dcd89..1116904197 100644 --- a/data/custodian/CZ-52-BIL-E-ZSMSBTSKVL.yaml +++ b/data/custodian/CZ-52-BIL-E-ZSMSBTSKVL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BIL-E-ZSMSBTSKVL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BIL-E-ZSMSBTSKVL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BIL-E-ZSMSBTSKVL ghcid_numeric: 13061106158070528725 valid_from: '2025-12-08T11:21:36.964273+00:00' @@ -219,3 +220,22 @@ location: postal_code: 544 72 street_address: Bílá Třemešná 313 normalization_timestamp: '2025-12-09T10:52:58.265998+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:18.042420+00:00' + source_url: https://knihovna.zsbt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.zsbt.cz/apple-touch-icon-180x180.png + source_url: https://knihovna.zsbt.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:44:18.042420+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-BIL-L-OKVBT.yaml b/data/custodian/CZ-52-BIL-L-OKVBT.yaml index 9a7849b4c0..e4dbcd3bcd 100644 --- a/data/custodian/CZ-52-BIL-L-OKVBT.yaml +++ b/data/custodian/CZ-52-BIL-L-OKVBT.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BIL-L-OKVBT - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BIL-L-OKVBT valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BIL-L-OKVBT ghcid_numeric: 1246894732633475092 valid_from: '2025-12-06T23:37:35.608121+00:00' @@ -214,3 +215,22 @@ location: postal_code: 544 72 street_address: Bílá Třemešná 315 normalization_timestamp: '2025-12-09T10:52:58.294249+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:23.791038+00:00' + source_url: https://trutnov.tritius.cz/library/bilatremesna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/bilatremesna + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:44:23.791038+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-BOH-L-MKB.yaml b/data/custodian/CZ-52-BOH-L-MKB.yaml index bb4afe25ff..018de1f1fa 100644 --- a/data/custodian/CZ-52-BOH-L-MKB.yaml +++ b/data/custodian/CZ-52-BOH-L-MKB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BOH-L-MKB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BOH-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BOH-L-MKB ghcid_numeric: 11178994225268303741 valid_from: '2025-12-06T23:37:34.911464+00:00' @@ -210,3 +211,22 @@ location: postal_code: 503 23 street_address: Boharyně 53 normalization_timestamp: '2025-12-09T10:52:58.319060+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:28.703265+00:00' + source_url: https://www.boharyne.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.boharyne.cz/image.php?nid=703&oid=10125736&width=32 + source_url: https://www.boharyne.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:44:28.703265+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-BOL-L-MKB.yaml b/data/custodian/CZ-52-BOL-L-MKB.yaml index a71bdb1788..76ffa618b0 100644 --- a/data/custodian/CZ-52-BOL-L-MKB.yaml +++ b/data/custodian/CZ-52-BOL-L-MKB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BOL-L-MKB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BOL-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BOL-L-MKB ghcid_numeric: 6081079844612873701 valid_from: '2025-12-06T23:37:35.419314+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 31 street_address: Bolehošť 10 normalization_timestamp: '2025-12-09T10:52:58.345903+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:33.504927+00:00' + source_url: https://bolehost-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bolehost-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://bolehost-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:44:33.504927+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-BOR-L-MKB.yaml b/data/custodian/CZ-52-BOR-L-MKB.yaml index 2bdd1ccf3e..393d828f21 100644 --- a/data/custodian/CZ-52-BOR-L-MKB.yaml +++ b/data/custodian/CZ-52-BOR-L-MKB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BOR-L-MKB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BOR-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BOR-L-MKB ghcid_numeric: 8752807463113465027 valid_from: '2025-12-06T23:37:26.601639+00:00' @@ -214,3 +215,22 @@ location: postal_code: 517 24 street_address: Husova 240 normalization_timestamp: '2025-12-09T10:52:58.369757+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:39.899388+00:00' + source_url: https://vck.tritius.cz/library/borohradek + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://vck.tritius.cz/library/borohradek + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:44:39.899388+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-BOR-L-OKVB.yaml b/data/custodian/CZ-52-BOR-L-OKVB.yaml index 35acac489d..736f239285 100644 --- a/data/custodian/CZ-52-BOR-L-OKVB.yaml +++ b/data/custodian/CZ-52-BOR-L-OKVB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BOR-L-OKVB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BOR-L-OKVB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BOR-L-OKVB ghcid_numeric: 11951461533508145525 valid_from: '2025-12-06T23:37:35.616456+00:00' @@ -210,3 +211,22 @@ location: postal_code: 544 77 street_address: Borovnice 1 normalization_timestamp: '2025-12-09T10:52:58.395270+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:47.489775+00:00' + source_url: https://trutnov.tritius.cz/library/borovnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/borovnice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:44:47.489775+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-BRE-H-KPK.yaml b/data/custodian/CZ-52-BRE-H-KPK.yaml index 04785ba8e9..cee604114f 100644 --- a/data/custodian/CZ-52-BRE-H-KPK.yaml +++ b/data/custodian/CZ-52-BRE-H-KPK.yaml @@ -228,3 +228,34 @@ location: youtube_status: NOT_FOUND youtube_search_query: Kapucínská provinční knihovna official youtube_search_timestamp: '2025-12-09T09:31:56.868179+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:55.423151+00:00' + source_url: https://knihovna.kapucini.cz/katalog-praha + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovna.kapucini.cz/wp-content/uploads/2022/04/LogoProvincie-m-61x74.png + source_url: https://knihovna.kapucini.cz/katalog-praha + css_selector: '#ast-desktop-header > div.ast-main-header-wrap.main-header-bar-wrap + > div.ast-primary-header-bar.ast-primary-header > div.site-primary-header-wrap.ast-builder-grid-row-container + > div.ast-builder-grid-row.ast-builder-grid-row-has-sides > div.site-header-primary-section-left.site-header-section + > div.ast-builder-layout-element.ast-flex > div.site-branding.ast-site-identity + > span.site-logo-img > a.custom-logo-link > img.custom-logo' + retrieved_on: '2025-12-24T22:44:55.423151+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Provinční knihovna + - claim_type: favicon_url + claim_value: https://knihovna.kapucini.cz/wp-content/uploads/2022/04/cropped-LogoProvincie-m-180x180.png + source_url: https://knihovna.kapucini.cz/katalog-praha + css_selector: '[document] > html > head > link:nth-of-type(38)' + retrieved_on: '2025-12-24T22:44:55.423151+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-BRE-L-UVNVFNP.yaml b/data/custodian/CZ-52-BRE-L-UVNVFNP.yaml index 37ee2fe38e..d7667b9c6a 100644 --- a/data/custodian/CZ-52-BRE-L-UVNVFNP.yaml +++ b/data/custodian/CZ-52-BRE-L-UVNVFNP.yaml @@ -243,3 +243,22 @@ youtube_status: NOT_FOUND youtube_search_query: Ústřední vojenská nemocnice - Vojenská fakultní nemocnice Praha official youtube_search_timestamp: '2025-12-09T09:31:59.529238+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:12.583838+00:00' + source_url: https://www.uvn.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.uvn.cz/templates/ja_simpli/favicon.ico + source_url: https://www.uvn.cz + css_selector: '[document] > html.js.no-touch > head > link' + retrieved_on: '2025-12-24T22:45:12.583838+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-52-BRE-O-MZVCOAZIUV.yaml b/data/custodian/CZ-52-BRE-O-MZVCOAZIUV.yaml index 610c5c3335..ae5d88e1b2 100644 --- a/data/custodian/CZ-52-BRE-O-MZVCOAZIUV.yaml +++ b/data/custodian/CZ-52-BRE-O-MZVCOAZIUV.yaml @@ -244,3 +244,22 @@ youtube_status: NOT_FOUND youtube_search_query: Ministerstvo zahraničních věcí ČR - Odbor administrativy a zpracování informací - Ústřední vědecká knihovna official youtube_search_timestamp: '2025-12-09T09:32:00.201487+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:17.699428+00:00' + source_url: https://mzv.gov.cz/jnp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mzv.gov.cz/public/ac/7e/61/477117_609311_favicon.ico + source_url: https://mzv.gov.cz/jnp + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:45:17.699428+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-BRO-L-MKK.yaml b/data/custodian/CZ-52-BRO-L-MKK.yaml index e138fd6629..102bd8d184 100644 --- a/data/custodian/CZ-52-BRO-L-MKK.yaml +++ b/data/custodian/CZ-52-BRO-L-MKK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BRO-L-MKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BRO-L-MKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BRO-L-MKK ghcid_numeric: 14869843805043063069 valid_from: '2025-12-06T23:37:35.270196+00:00' @@ -214,3 +215,32 @@ location: postal_code: 550 01 street_address: Křinice 176 normalization_timestamp: '2025-12-09T10:52:58.425823+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:24.040288+00:00' + source_url: https://krinice.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://krinice.mknachod.cz/custom/design/logo.png + source_url: https://krinice.mknachod.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > div > img' + retrieved_on: '2025-12-24T22:45:24.040288+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://krinice.mknachod.cz/favicon.png?v=2.3.0-32021 + source_url: https://krinice.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:45:24.040288+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-BUT-L-KB.yaml b/data/custodian/CZ-52-BUT-L-KB.yaml index 3ca1d5f45f..8bdb916daa 100644 --- a/data/custodian/CZ-52-BUT-L-KB.yaml +++ b/data/custodian/CZ-52-BUT-L-KB.yaml @@ -40,13 +40,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-BUT-L-KB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-BUT-L-KB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-BUT-L-KB ghcid_numeric: 9125954385929802276 valid_from: '2025-12-06T23:37:43.611821+00:00' @@ -166,3 +167,22 @@ location: postal_code: 506 01 street_address: Butoves 47 normalization_timestamp: '2025-12-09T06:51:35.398343+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:33.196884+00:00' + source_url: https://butoves.knihovna.jicin.cz/#!/search-form + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://butoves.knihovna.jicin.cz/favicon.png?v=2.3.0-32021 + source_url: https://butoves.knihovna.jicin.cz/#!/search-form + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:45:33.196884+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-BYL-M-MMNB.yaml b/data/custodian/CZ-52-BYL-M-MMNB.yaml index 476669286e..8ee7952338 100644 --- a/data/custodian/CZ-52-BYL-M-MMNB.yaml +++ b/data/custodian/CZ-52-BYL-M-MMNB.yaml @@ -43,18 +43,20 @@ ghcid: latitude: 50.20304 longitude: 15.5344 ghcid_history: - - previous_ghcid_component: "BL" - new_ghcid_component: "BYL" - change_date: "2025-12-20T19:55:24Z" - reason: "Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Bydzovska Lhotka" + - previous_ghcid_component: BL + new_ghcid_component: BYL + change_date: '2025-12-20T19:55:24Z' + reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: + Bydzovska Lhotka' - ghcid: CZ-52-BL-M-MMNB - valid_from: "2025-12-10T09:46:51Z" + valid_from: '2025-12-10T09:46:51Z' valid_to: null - reason: "Corrected region code from CZ-521 to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-521 to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-521-BL-M-MMNB valid_from: null - valid_to: "2025-12-10T09:46:51Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:46:51Z' + reason: Previous GHCID with incorrect region code - ghcid: XX-XX-XXX-M-MMNB ghcid_numeric: 1666424988131637889 valid_from: '2025-12-06T23:37:43.702558+00:00' @@ -267,3 +269,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Městské muzeum Nový Bydžov official youtube_search_timestamp: '2025-12-09T09:34:05.141904+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:38.868641+00:00' + source_url: https://www.novybydzov.cz/muzeum.asp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.novybydzov.cz/html/images/favicon.ico + source_url: https://www.novybydzov.cz/muzeum.asp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:45:38.868641+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CAK-L-VTUSPOZVTK.yaml b/data/custodian/CZ-52-CAK-L-VTUSPOZVTK.yaml index 754f2cc860..c977c1564e 100644 --- a/data/custodian/CZ-52-CAK-L-VTUSPOZVTK.yaml +++ b/data/custodian/CZ-52-CAK-L-VTUSPOZVTK.yaml @@ -238,3 +238,28 @@ youtube_status: NOT_FOUND youtube_search_query: Vojenský technický ústav, s. p. - odštěpný závod VTÚLaPVO - Technická knihovna official youtube_search_timestamp: '2025-12-09T09:32:00.862658+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:43.866331+00:00' + source_url: https://www.vtusp.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vtusp.cz/files/themes/vtu/icons/safari-pinned-tab.svg + source_url: https://www.vtusp.cz + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T22:45:43.866331+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.vtusp.cz/files/uploads/2020/05/logo-vtu.svg + source_url: https://www.vtusp.cz + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T22:45:43.866331+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-52-CER-L-MKC.yaml b/data/custodian/CZ-52-CER-L-MKC.yaml index e8eafd841e..072a71a54b 100644 --- a/data/custodian/CZ-52-CER-L-MKC.yaml +++ b/data/custodian/CZ-52-CER-L-MKC.yaml @@ -216,3 +216,22 @@ location: postal_code: 517 04 street_address: Černíkovice čp. 55 normalization_timestamp: '2025-12-09T10:52:58.478412+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:51.489344+00:00' + source_url: https://www.cernikovice.cz/obec-1/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.cernikovice.cz/skins/cernikovice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.cernikovice.cz/obec-1/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:45:51.489344+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-CER-L-OKVCD.yaml b/data/custodian/CZ-52-CER-L-OKVCD.yaml index 526dccaf4d..3d3fd56e61 100644 --- a/data/custodian/CZ-52-CER-L-OKVCD.yaml +++ b/data/custodian/CZ-52-CER-L-OKVCD.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CER-L-OKVCD - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CER-L-OKVCD valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CER-L-OKVCD ghcid_numeric: 16436913262343600587 valid_from: '2025-12-08T11:21:37.570988+00:00' @@ -219,3 +220,22 @@ location: postal_code: 543 44 street_address: Černý Důl 48 normalization_timestamp: '2025-12-09T10:52:58.537205+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:59.264289+00:00' + source_url: https://trutnov.tritius.cz/library/cernydul + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/cernydul + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:45:59.264289+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-CER-L-OKVCH.yaml b/data/custodian/CZ-52-CER-L-OKVCH.yaml index cb96cf6442..7d7d75214a 100644 --- a/data/custodian/CZ-52-CER-L-OKVCH.yaml +++ b/data/custodian/CZ-52-CER-L-OKVCH.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CER-L-OKVCH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CER-L-OKVCH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CER-L-OKVCH ghcid_numeric: 1082789985098784656 valid_from: '2025-12-08T11:21:38.912902+00:00' @@ -215,3 +216,22 @@ location: postal_code: 549 41 street_address: Červená Hora 58 normalization_timestamp: '2025-12-09T10:52:58.566479+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:06.098222+00:00' + source_url: https://www.cervenahora.cz/nase-obec/spolky-sdruzeni/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.cervenahora.cz/skins/cervenahora.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.cervenahora.cz/nase-obec/spolky-sdruzeni/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:46:06.098222+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-CES-L-KUMMZK.yaml b/data/custodian/CZ-52-CES-L-KUMMZK.yaml index dd3fd2795d..da3dba2577 100644 --- a/data/custodian/CZ-52-CES-L-KUMMZK.yaml +++ b/data/custodian/CZ-52-CES-L-KUMMZK.yaml @@ -177,3 +177,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q2326815 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:15.713942+00:00' + source_url: https://knihovna.obecmokre.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.obecmokre.cz/image.php?nid=21397&oid=12186952 + source_url: https://knihovna.obecmokre.cz + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T22:46:15.713942+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CES-L-MKC.yaml b/data/custodian/CZ-52-CES-L-MKC.yaml index 51e9558df3..c436527bbb 100644 --- a/data/custodian/CZ-52-CES-L-MKC.yaml +++ b/data/custodian/CZ-52-CES-L-MKC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CES-L-MKC - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CES-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CES-L-MKC ghcid_numeric: 6995611214771296913 valid_from: '2025-12-08T11:21:39.251036+00:00' @@ -215,3 +216,22 @@ location: postal_code: 517 50 street_address: Čestice 94 normalization_timestamp: '2025-12-09T10:52:58.627136+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:20.899821+00:00' + source_url: https://cestice-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://cestice-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://cestice-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:46:20.899821+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CES-L-MKCM.yaml b/data/custodian/CZ-52-CES-L-MKCM.yaml index c96f30520a..14c4c4598b 100644 --- a/data/custodian/CZ-52-CES-L-MKCM.yaml +++ b/data/custodian/CZ-52-CES-L-MKCM.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CES-L-MKCM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CES-L-MKCM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CES-L-MKCM ghcid_numeric: 9500557046495141050 valid_from: '2025-12-08T11:21:33.340922+00:00' @@ -219,3 +220,22 @@ location: postal_code: 517 71 street_address: Osvobození 188 normalization_timestamp: '2025-12-09T10:52:58.654965+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:27.345908+00:00' + source_url: https://rychnov.tritius.cz/library/cmezirici + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rychnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://rychnov.tritius.cz/library/cmezirici + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:46:27.345908+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-CES-L-OKCC.yaml b/data/custodian/CZ-52-CES-L-OKCC.yaml index 9340ef1728..6e63889771 100644 --- a/data/custodian/CZ-52-CES-L-OKCC.yaml +++ b/data/custodian/CZ-52-CES-L-OKCC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CES-L-OKCC - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CES-L-OKCC valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CES-L-OKCC ghcid_numeric: 2482027352530836329 valid_from: '2025-12-08T11:21:39.359979+00:00' @@ -215,3 +216,22 @@ location: postal_code: 549 21 street_address: Česká Čermná 128 normalization_timestamp: '2025-12-09T10:52:58.710480+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:37.353474+00:00' + source_url: https://ceskacermna.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ceskacermna.mknachod.cz/favicon.png?v=2.3.0-32021 + source_url: https://ceskacermna.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:46:37.353474+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CES-L-OKVCM.yaml b/data/custodian/CZ-52-CES-L-OKVCM.yaml index 1cc9d492ea..eaf5deee3a 100644 --- a/data/custodian/CZ-52-CES-L-OKVCM.yaml +++ b/data/custodian/CZ-52-CES-L-OKVCM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CES-L-OKVCM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CES-L-OKVCM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CES-L-OKVCM ghcid_numeric: 4867719674839446156 valid_from: '2025-12-08T11:21:31.417300+00:00' @@ -215,3 +216,22 @@ location: postal_code: 549 56 street_address: Česká Metuje 10 normalization_timestamp: '2025-12-09T10:52:58.766769+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:48.744601+00:00' + source_url: https://www.ceskametuje.cz/zivot-v-obci/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ceskametuje.cz/skins/ceskametuje_lego/favicons/safari-pinned-tab.svg + source_url: https://www.ceskametuje.cz/zivot-v-obci/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:46:48.744601+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-CES-L-OKVZ.yaml b/data/custodian/CZ-52-CES-L-OKVZ.yaml index bfdcce4842..d35ee65ffa 100644 --- a/data/custodian/CZ-52-CES-L-OKVZ.yaml +++ b/data/custodian/CZ-52-CES-L-OKVZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CES-L-OKVZ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CES-L-OKVZ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CES-L-OKVZ ghcid_numeric: 7079130626117640141 valid_from: '2025-12-08T11:21:38.226303+00:00' @@ -215,3 +216,22 @@ location: postal_code: 552 03 street_address: Žernov 112 normalization_timestamp: '2025-12-09T10:52:58.794416+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:55.050490+00:00' + source_url: https://knihovnack.tritius.cz/library/zernov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovnack.tritius.cz/apple-touch-icon-180x180.png + source_url: https://knihovnack.tritius.cz/library/zernov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:46:55.050490+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-CHL-L-OKP.yaml b/data/custodian/CZ-52-CHL-L-OKP.yaml index a6834ed324..be63875c9c 100644 --- a/data/custodian/CZ-52-CHL-L-OKP.yaml +++ b/data/custodian/CZ-52-CHL-L-OKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CHL-L-OKP - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CHL-L-OKP valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CHL-L-OKP ghcid_numeric: 3477880073623632148 valid_from: '2025-12-06T23:37:34.960122+00:00' @@ -207,3 +208,22 @@ location: postal_code: 503 51 street_address: Převýšov 89 normalization_timestamp: '2025-12-09T10:52:58.910074+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:07.978649+00:00' + source_url: https://www.prevysov.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.prevysov.cz/image.php?nid=576&oid=8156950&width=32 + source_url: https://www.prevysov.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:47:07.978649+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CHL-L-OKVK.yaml b/data/custodian/CZ-52-CHL-L-OKVK.yaml index fdadd98e22..c811960ccd 100644 --- a/data/custodian/CZ-52-CHL-L-OKVK.yaml +++ b/data/custodian/CZ-52-CHL-L-OKVK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CHL-L-OKVK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CHL-L-OKVK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CHL-L-OKVK ghcid_numeric: 757235367436209034 valid_from: '2025-12-06T23:37:34.945881+00:00' @@ -213,3 +214,22 @@ location: postal_code: 503 51 street_address: Klamoš 26 normalization_timestamp: '2025-12-09T10:52:58.944415+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:13.318635+00:00' + source_url: https://www.klamos.cz/obecni-knihovna/os-879 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.klamos.cz/html/images/favicon.ico + source_url: https://www.klamos.cz/obecni-knihovna/os-879 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:47:13.318635+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CHO-L-OKC.yaml b/data/custodian/CZ-52-CHO-L-OKC.yaml index 8ddb3e33b0..c00a1efec2 100644 --- a/data/custodian/CZ-52-CHO-L-OKC.yaml +++ b/data/custodian/CZ-52-CHO-L-OKC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CHO-L-OKC - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CHO-L-OKC valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CHO-L-OKC ghcid_numeric: 15465369916020328716 valid_from: '2025-12-06T23:37:35.148968+00:00' @@ -210,3 +211,22 @@ location: postal_code: 507 53 street_address: Chomutice 164 normalization_timestamp: '2025-12-09T10:52:58.976555+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:21.910064+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32021 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:47:21.910064+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CHV-L-MKVC.yaml b/data/custodian/CZ-52-CHV-L-MKVC.yaml index 243d608c79..f93e6005b0 100644 --- a/data/custodian/CZ-52-CHV-L-MKVC.yaml +++ b/data/custodian/CZ-52-CHV-L-MKVC.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CHV-L-MKVC - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CHV-L-MKVC valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CHV-L-MKVC ghcid_numeric: 12555325107828418377 valid_from: '2025-12-06T23:37:24.930124+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Místní knihovna ve Chvalkovicích @@ -225,3 +226,30 @@ location: geonames_id: 3077488 geonames_name: Chvalkovice feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:26.612574+00:00' + source_url: https://knihovnachvalkovice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnachvalkovice.files.webk.cz/logov.png + source_url: https://knihovnachvalkovice.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-24T22:47:26.612574+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnachvalkovice.webk.cz/themes/new/favicon.ico + source_url: https://knihovnachvalkovice.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T22:47:26.612574+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-CHV-L-MLKC.yaml b/data/custodian/CZ-52-CHV-L-MLKC.yaml index 9a61a1e853..12497af95a 100644 --- a/data/custodian/CZ-52-CHV-L-MLKC.yaml +++ b/data/custodian/CZ-52-CHV-L-MLKC.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-CHV-L-MLKC - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-CHV-L-MLKC valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-CHV-L-MLKC ghcid_numeric: 4370469850229363744 valid_from: '2025-12-06T23:37:35.643816+00:00' @@ -214,3 +215,22 @@ location: postal_code: 542 11 street_address: Chvaleč 231 normalization_timestamp: '2025-12-09T10:52:59.040429+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:34.151417+00:00' + source_url: https://trutnov.tritius.cz/library/chvalec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/chvalec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:47:34.151417+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-CIM-L-PNBLK.yaml b/data/custodian/CZ-52-CIM-L-PNBLK.yaml index d246c698ec..89d3eda4e8 100644 --- a/data/custodian/CZ-52-CIM-L-PNBLK.yaml +++ b/data/custodian/CZ-52-CIM-L-PNBLK.yaml @@ -222,3 +222,30 @@ location: youtube_status: NOT_FOUND youtube_search_query: Psychiatrická nemocnice Bohnice - Lékařská knihovna official youtube_search_timestamp: '2025-12-09T09:32:02.860157+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:40.264665+00:00' + source_url: https://bohnice.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://bohnice.cz/wp-content/uploads/2023/07/pnb-logo-negativ-2.svg + source_url: https://bohnice.cz + css_selector: '#masthead > div.inside-header > div.site-logo > a > img.header-image.is-logo-image' + retrieved_on: '2025-12-24T22:47:40.264665+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: PN Bohnice + - claim_type: favicon_url + claim_value: https://bohnice.cz/wp-content/uploads/cropped-favicon-180x180.webp + source_url: https://bohnice.cz + css_selector: '[document] > html > head > link:nth-of-type(22)' + retrieved_on: '2025-12-24T22:47:40.264665+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-CIM-L-UCPVSMVVSH.yaml b/data/custodian/CZ-52-CIM-L-UCPVSMVVSH.yaml index 13f06f9f01..ad250de532 100644 --- a/data/custodian/CZ-52-CIM-L-UCPVSMVVSH.yaml +++ b/data/custodian/CZ-52-CIM-L-UCPVSMVVSH.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1622062 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:46.085731+00:00' + source_url: https://www.ucp.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ucp.cz/files/responsive/152/0/1-34.png + source_url: https://www.ucp.cz + css_selector: '[document] > html.html.js > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:47:46.085731+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 152x152 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-DET-L-MKVD.yaml b/data/custodian/CZ-52-DET-L-MKVD.yaml index 09aa5f8f99..cb415ab172 100644 --- a/data/custodian/CZ-52-DET-L-MKVD.yaml +++ b/data/custodian/CZ-52-DET-L-MKVD.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DET-L-MKVD - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DET-L-MKVD valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DET-L-MKVD ghcid_numeric: 6656591791791985950 valid_from: '2025-12-06T23:37:35.112389+00:00' @@ -214,3 +215,22 @@ location: postal_code: 507 24 street_address: Dětenice 141 normalization_timestamp: '2025-12-09T10:52:59.086218+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:48:00.562238+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32021 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:48:00.562238+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-DLI-A-VHA.yaml b/data/custodian/CZ-52-DLI-A-VHA.yaml index 7dd5d07b4c..6d739af211 100644 --- a/data/custodian/CZ-52-DLI-A-VHA.yaml +++ b/data/custodian/CZ-52-DLI-A-VHA.yaml @@ -268,3 +268,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Vojenský historický archiv official youtube_search_timestamp: '2025-12-09T09:32:06.189477+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:48:07.851362+00:00' + source_url: http://www.vuapraha.cz/archiv-historicky + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vuapraha.cz/wp-content/themes/iq-theme/dist/img/safari-pinned-tab.svg + source_url: http://www.vuapraha.cz/archiv-historicky + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T22:48:07.851362+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 7 diff --git a/data/custodian/CZ-52-DOB-L-BZKB.yaml b/data/custodian/CZ-52-DOB-L-BZKB.yaml index 03fd3c609b..b2e6969a4d 100644 --- a/data/custodian/CZ-52-DOB-L-BZKB.yaml +++ b/data/custodian/CZ-52-DOB-L-BZKB.yaml @@ -177,3 +177,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q2326815 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:48:13.251271+00:00' + source_url: https://bacetin.cz/default/default/12538_knihovna-a-kultura + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bacetin.cz/files/bacetin/logo/apple-touch-icon.png + source_url: https://bacetin.cz/default/default/12538_knihovna-a-kultura + css_selector: '[document] > html.show--consent > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:48:13.251271+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-52-DOB-L-MKD.yaml b/data/custodian/CZ-52-DOB-L-MKD.yaml index 8cb8695907..0d607f8213 100644 --- a/data/custodian/CZ-52-DOB-L-MKD.yaml +++ b/data/custodian/CZ-52-DOB-L-MKD.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DOB-L-MKD - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DOB-L-MKD valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DOB-L-MKD ghcid_numeric: 7289360391635378741 valid_from: '2025-12-06T23:37:19.809849+00:00' @@ -241,3 +242,32 @@ location: postal_code: 518 01 street_address: Na Budíně 850 normalization_timestamp: '2025-12-09T10:52:59.248548+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:48:25.113295+00:00' + source_url: https://katalog.mestodobruska.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://katalog.mestodobruska.cz/custom/design/logo_knihovna.png + source_url: https://katalog.mestodobruska.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > div > img' + retrieved_on: '2025-12-24T22:48:25.113295+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://katalog.mestodobruska.cz/favicon.png?v=2.3.0-32021 + source_url: https://katalog.mestodobruska.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T22:48:25.113295+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-DOB-L-MKDVUH.yaml b/data/custodian/CZ-52-DOB-L-MKDVUH.yaml index 1ff6613053..75e1f8a1f9 100644 --- a/data/custodian/CZ-52-DOB-L-MKDVUH.yaml +++ b/data/custodian/CZ-52-DOB-L-MKDVUH.yaml @@ -215,3 +215,22 @@ location: postal_code: 507 73 street_address: Dobrá Voda u Hořic 131 normalization_timestamp: '2025-12-09T10:52:59.279740+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:48:30.999269+00:00' + source_url: https://knihovnadv.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnadv.webk.cz/themes/cbdb-klasicky/default/logo1.png + source_url: https://knihovnadv.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-24T22:48:30.999269+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-DOB-L-MKVB.yaml b/data/custodian/CZ-52-DOB-L-MKVB.yaml index 46d3f92c28..ab7078d244 100644 --- a/data/custodian/CZ-52-DOB-L-MKVB.yaml +++ b/data/custodian/CZ-52-DOB-L-MKVB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DOB-L-MKVB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DOB-L-MKVB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DOB-L-MKVB ghcid_numeric: 12864027692671220608 valid_from: '2025-12-06T23:37:35.474104+00:00' @@ -210,3 +211,22 @@ location: postal_code: 518 01 street_address: Bystré 88 normalization_timestamp: '2025-12-09T10:52:59.435459+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:48:46.750080+00:00' + source_url: https://www.obecbystre.cz/sluzby + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obecbystre.cz/file.php?nid=542&oid=6759242 + source_url: https://www.obecbystre.cz/sluzby + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:48:46.750080+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-DOB-L-OKD.yaml b/data/custodian/CZ-52-DOB-L-OKD.yaml index 5f15a82067..726f3f6250 100644 --- a/data/custodian/CZ-52-DOB-L-OKD.yaml +++ b/data/custodian/CZ-52-DOB-L-OKD.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DOB-L-OKD - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DOB-L-OKD valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DOB-L-OKD ghcid_numeric: 593588967283127274 valid_from: '2025-12-06T23:37:34.920585+00:00' @@ -210,3 +211,22 @@ location: postal_code: 503 25 street_address: Dobřenice 10 normalization_timestamp: '2025-12-09T10:52:59.461967+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:48:53.191063+00:00' + source_url: https://kmhk.tritius.cz/library/dobrenice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/dobrenice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:48:53.191063+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-DOH-L-OKVD.yaml b/data/custodian/CZ-52-DOH-L-OKVD.yaml index 4bf1738cec..eaf6e9eda1 100644 --- a/data/custodian/CZ-52-DOH-L-OKVD.yaml +++ b/data/custodian/CZ-52-DOH-L-OKVD.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DOH-L-OKVD - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DOH-L-OKVD valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DOH-L-OKVD ghcid_numeric: 18187858040999941381 valid_from: '2025-12-06T23:37:34.923594+00:00' @@ -207,3 +208,22 @@ location: postal_code: 503 13 street_address: Dohalice 17 normalization_timestamp: '2025-12-09T10:52:59.486676+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:01.474354+00:00' + source_url: https://kmhk.tritius.cz/library/dohalice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/dohalice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:49:01.474354+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-DOL-L-MLKDR.yaml b/data/custodian/CZ-52-DOL-L-MLKDR.yaml index 14d53b1910..6047920b55 100644 --- a/data/custodian/CZ-52-DOL-L-MLKDR.yaml +++ b/data/custodian/CZ-52-DOL-L-MLKDR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DOL-L-MLKDR - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DOL-L-MLKDR valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DOL-L-MLKDR ghcid_numeric: 10487984457392786360 valid_from: '2025-12-06T23:37:35.289663+00:00' @@ -207,3 +208,22 @@ location: postal_code: 549 11 street_address: Náchodská 240 normalization_timestamp: '2025-12-09T10:52:59.513009+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:07.213445+00:00' + source_url: https://knihovnadolniradechova.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnadolniradechova.files.webk.cz/logov.png + source_url: https://knihovnadolniradechova.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-24T22:49:07.213445+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-DOL-L-NCZPVVVK.yaml b/data/custodian/CZ-52-DOL-L-NCZPVVVK.yaml index 0dc0de07a0..56977d74b9 100644 --- a/data/custodian/CZ-52-DOL-L-NCZPVVVK.yaml +++ b/data/custodian/CZ-52-DOL-L-NCZPVVVK.yaml @@ -196,3 +196,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1438040 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:14.566672+00:00' + source_url: https://www.carc.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.carc.cz/favicon/favicon-32x32.png + source_url: https://www.carc.cz + css_selector: '[document] > html > head > link:nth-of-type(24)' + retrieved_on: '2025-12-24T22:49:14.566672+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-52-DOL-L-OKDL.yaml b/data/custodian/CZ-52-DOL-L-OKDL.yaml index ef12d7204b..1f0d97fb3a 100644 --- a/data/custodian/CZ-52-DOL-L-OKDL.yaml +++ b/data/custodian/CZ-52-DOL-L-OKDL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DOL-L-OKDL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DOL-L-OKDL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DOL-L-OKDL ghcid_numeric: 4239090280863650517 valid_from: '2025-12-06T23:37:35.660125+00:00' @@ -223,3 +224,22 @@ location: postal_code: 543 41 street_address: Dolní Lánov 132 normalization_timestamp: '2025-12-09T10:52:59.541001+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:27.657131+00:00' + source_url: https://trutnov.tritius.cz/library/dolnilanov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/dolnilanov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:49:27.657131+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-DOL-L-OKDP.yaml b/data/custodian/CZ-52-DOL-L-OKDP.yaml index 61e26e4615..4726bc770c 100644 --- a/data/custodian/CZ-52-DOL-L-OKDP.yaml +++ b/data/custodian/CZ-52-DOL-L-OKDP.yaml @@ -215,3 +215,31 @@ location: postal_code: 503 16 street_address: Dolní Přím 1 normalization_timestamp: '2025-12-09T10:52:59.567709+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:33.867231+00:00' + source_url: https://www.dolni-prim.cz/obecni-knihovna-dolni-prim-3375 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.dolni-prim.cz/images/web/logo.png + source_url: https://www.dolni-prim.cz/obecni-knihovna-dolni-prim-3375 + css_selector: '[document] > html > body.FrontDefault.menu_1 > header > div.container + > div.header-inner.clearfix > div.col-xs-12.col-sm-4 > a > img' + retrieved_on: '2025-12-24T22:49:33.867231+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo obce Dolní Přím + - claim_type: favicon_url + claim_value: https://www.dolni-prim.cz/favicon.ico + source_url: https://www.dolni-prim.cz/obecni-knihovna-dolni-prim-3375 + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:49:33.867231+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-DOL-L-OKP.yaml b/data/custodian/CZ-52-DOL-L-OKP.yaml index f5a9c48e7b..345c41da3d 100644 --- a/data/custodian/CZ-52-DOL-L-OKP.yaml +++ b/data/custodian/CZ-52-DOL-L-OKP.yaml @@ -212,3 +212,31 @@ location: postal_code: 503 16 street_address: Probluz normalization_timestamp: '2025-12-09T10:52:59.595927+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:39.946666+00:00' + source_url: https://www.dolni-prim.cz/obecni-knihovna-dolni-prim-3375 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.dolni-prim.cz/images/web/logo.png + source_url: https://www.dolni-prim.cz/obecni-knihovna-dolni-prim-3375 + css_selector: '[document] > html > body.FrontDefault.menu_1 > header > div.container + > div.header-inner.clearfix > div.col-xs-12.col-sm-4 > a > img' + retrieved_on: '2025-12-24T22:49:39.946666+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo obce Dolní Přím + - claim_type: favicon_url + claim_value: https://www.dolni-prim.cz/favicon.ico + source_url: https://www.dolni-prim.cz/obecni-knihovna-dolni-prim-3375 + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:49:39.946666+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-DOL-L-VUZTVVRPP.yaml b/data/custodian/CZ-52-DOL-L-VUZTVVRPP.yaml index d4145ae198..f702e3f036 100644 --- a/data/custodian/CZ-52-DOL-L-VUZTVVRPP.yaml +++ b/data/custodian/CZ-52-DOL-L-VUZTVVRPP.yaml @@ -239,3 +239,22 @@ youtube_status: NOT_FOUND youtube_search_query: Výzkumný ústav zemědělské techniky, v. v. i. - Referát projektové podpory official youtube_search_timestamp: '2025-12-09T09:32:08.852495+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:49.574617+00:00' + source_url: https://www.vuzt.cz/databaze-a-programy/databaze-nasich-publikaci + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vuzt.cz/databaze-a-programy/favicon.ico + source_url: https://www.vuzt.cz/databaze-a-programy/databaze-nasich-publikaci + css_selector: '[document] > html > head > link:nth-of-type(26)' + retrieved_on: '2025-12-24T22:49:49.574617+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-DOL-L-ZKSK.yaml b/data/custodian/CZ-52-DOL-L-ZKSK.yaml index 9a16c2fba2..450b215bd2 100644 --- a/data/custodian/CZ-52-DOL-L-ZKSK.yaml +++ b/data/custodian/CZ-52-DOL-L-ZKSK.yaml @@ -227,3 +227,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: ZENTIVA, k.s. - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:09.516187+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:58.267765+00:00' + source_url: https://www.zentiva.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zentiva.cz/assets/zentivacomv2/img/apple-touch-icon.png?v=20250512 + source_url: https://www.zentiva.cz + css_selector: '[document] > html.js.no-touchevents > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:49:58.267765+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-52-DOU-L-MKDNO.yaml b/data/custodian/CZ-52-DOU-L-MKDNO.yaml index 947a12df8b..ec96349cf0 100644 --- a/data/custodian/CZ-52-DOU-L-MKDNO.yaml +++ b/data/custodian/CZ-52-DOU-L-MKDNO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DOU-L-MKDNO - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DOU-L-MKDNO valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DOU-L-MKDNO ghcid_numeric: 14893353395121909234 valid_from: '2025-12-06T23:37:23.544820+00:00' @@ -216,3 +217,22 @@ location: postal_code: 517 42 street_address: Dukelská 68 normalization_timestamp: '2025-12-09T10:52:59.622420+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:50:04.850900+00:00' + source_url: https://www.knihovnadoudleby.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovnadoudleby.cz/file.php?nid=17633&oid=6888272 + source_url: https://www.knihovnadoudleby.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:50:04.850900+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-DUB-L-KD.yaml b/data/custodian/CZ-52-DUB-L-KD.yaml index 36c9c33d0b..142875b9fb 100644 --- a/data/custodian/CZ-52-DUB-L-KD.yaml +++ b/data/custodian/CZ-52-DUB-L-KD.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DUB-L-KD - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DUB-L-KD valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DUB-L-KD ghcid_numeric: 1432052903915652789 valid_from: '2025-12-06T23:37:22.419098+00:00' @@ -217,3 +218,22 @@ location: postal_code: 544 55 street_address: Dubenec 2 normalization_timestamp: '2025-12-09T10:52:59.651044+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:50:14.462596+00:00' + source_url: https://trutnov.tritius.cz/library/dubenec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/dubenec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:50:14.462596+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-DVU-L-OKVL.yaml b/data/custodian/CZ-52-DVU-L-OKVL.yaml index 57b1690672..42d4461b8c 100644 --- a/data/custodian/CZ-52-DVU-L-OKVL.yaml +++ b/data/custodian/CZ-52-DVU-L-OKVL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DVU-L-OKVL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DVU-L-OKVL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DVU-L-OKVL ghcid_numeric: 16985270867520465087 valid_from: '2025-12-06T23:37:35.627331+00:00' @@ -210,3 +211,22 @@ location: postal_code: 544 01 street_address: Lanžov 2 normalization_timestamp: '2025-12-09T10:52:59.739075+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:50:49.030853+00:00' + source_url: https://trutnov.tritius.cz/library/lanzov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/lanzov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:50:49.030853+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-DVU-M-MMVDKNLK.yaml b/data/custodian/CZ-52-DVU-M-MMVDKNLK.yaml index c85a7a5b83..db29fb284a 100644 --- a/data/custodian/CZ-52-DVU-M-MMVDKNLK.yaml +++ b/data/custodian/CZ-52-DVU-M-MMVDKNLK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-DVU-M-MMVDKNLK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-DVU-M-MMVDKNLK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-DVU-M-MMVDKNLK ghcid_numeric: 12283637869442356439 valid_from: '2025-12-06T23:37:26.298238+00:00' @@ -210,3 +211,22 @@ location: postal_code: 544 01 street_address: Sladkovského 530 normalization_timestamp: '2025-12-09T10:52:59.870858+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:04.294310+00:00' + source_url: https://muzeum.tritius.cz/library/muzeumdk + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeum.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeum.tritius.cz/library/muzeumdk + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:51:04.294310+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-DZA-L-UTAMACVVOK.yaml b/data/custodian/CZ-52-DZA-L-UTAMACVVOK.yaml index db2556bd02..0087747552 100644 --- a/data/custodian/CZ-52-DZA-L-UTAMACVVOK.yaml +++ b/data/custodian/CZ-52-DZA-L-UTAMACVVOK.yaml @@ -238,3 +238,22 @@ youtube_status: NOT_FOUND youtube_search_query: Ústav teoretické a aplikované mechaniky AV ČR, v. v. i. - Odborná knihovna official youtube_search_timestamp: '2025-12-09T09:32:11.502467+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:42.915669+00:00' + source_url: https://katalog.lib.cas.cz/UTAM + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/UTAM/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/UTAM + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T22:51:42.915669+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HAJ-L-MKH.yaml b/data/custodian/CZ-52-HAJ-L-MKH.yaml index 588f00fd04..fad4a631fb 100644 --- a/data/custodian/CZ-52-HAJ-L-MKH.yaml +++ b/data/custodian/CZ-52-HAJ-L-MKH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HAJ-L-MKH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HAJ-L-MKH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HAJ-L-MKH ghcid_numeric: 16018957039401359299 valid_from: '2025-12-06T23:37:35.630016+00:00' @@ -210,3 +211,22 @@ location: postal_code: 544 66 street_address: Hajnice 35 normalization_timestamp: '2025-12-09T10:52:59.895662+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:49.397274+00:00' + source_url: https://trutnov.tritius.cz/library/hajnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/hajnice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:51:49.397274+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-HAV-L-OKH.yaml b/data/custodian/CZ-52-HAV-L-OKH.yaml index 78b1bc51f7..01d16a8265 100644 --- a/data/custodian/CZ-52-HAV-L-OKH.yaml +++ b/data/custodian/CZ-52-HAV-L-OKH.yaml @@ -211,3 +211,22 @@ location: postal_code: 542 38 street_address: Havlovice 146 normalization_timestamp: '2025-12-09T10:52:59.922268+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:55.945190+00:00' + source_url: https://trutnov.tritius.cz/library/havlovice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/havlovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:51:55.945190+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-HER-L-OKH.yaml b/data/custodian/CZ-52-HER-L-OKH.yaml index e72a3b7e29..992868ae67 100644 --- a/data/custodian/CZ-52-HER-L-OKH.yaml +++ b/data/custodian/CZ-52-HER-L-OKH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HER-L-OKH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HER-L-OKH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HER-L-OKH ghcid_numeric: 8365410649487097573 valid_from: '2025-12-06T23:37:35.292685+00:00' @@ -210,3 +211,22 @@ location: postal_code: 552 12 street_address: Heřmanice 13 normalization_timestamp: '2025-12-09T10:52:59.947430+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:03.136180+00:00' + source_url: https://obecniknihovnahermanice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://obecniknihovnahermanice.files.webk.cz/logov.png + source_url: https://obecniknihovnahermanice.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-24T22:52:03.136180+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-HOL-M-NTM.yaml b/data/custodian/CZ-52-HOL-M-NTM.yaml index bbf3e81ae2..a11b98b93b 100644 --- a/data/custodian/CZ-52-HOL-M-NTM.yaml +++ b/data/custodian/CZ-52-HOL-M-NTM.yaml @@ -252,3 +252,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: National Technical Museum official youtube_search_timestamp: '2025-12-09T09:32:16.093536+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:20.772469+00:00' + source_url: https://ntm.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ntm.cz/file/30dc8e5fefba6ceba5d690d796c861ec/2220/favicon/NTM%20EN%20%C4%8Derven%C3%A1%20negativ.png + source_url: https://ntm.cz + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:52:20.772469+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOR-L-MKH.yaml b/data/custodian/CZ-52-HOR-L-MKH.yaml index 2aaa66121b..62aa49b0e7 100644 --- a/data/custodian/CZ-52-HOR-L-MKH.yaml +++ b/data/custodian/CZ-52-HOR-L-MKH.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-MKH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-MKH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-MKH ghcid_numeric: 177721685452865900 valid_from: '2025-12-06T23:37:17.899731+00:00' @@ -223,3 +224,22 @@ location: postal_code: 508 01 street_address: nám. Jiřího z Poděbrad 239 normalization_timestamp: '2025-12-09T10:53:00.032404+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:31.603720+00:00' + source_url: https://kpwin.horice.org/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kpwin.horice.org/html/images/favicon.ico + source_url: https://kpwin.horice.org/#! + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:52:31.603720+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOR-L-MKPUV.yaml b/data/custodian/CZ-52-HOR-L-MKPUV.yaml index 7a64f45377..cff4d4f118 100644 --- a/data/custodian/CZ-52-HOR-L-MKPUV.yaml +++ b/data/custodian/CZ-52-HOR-L-MKPUV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-MKPUV - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-MKPUV valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-MKPUV ghcid_numeric: 2777939366578941243 valid_from: '2025-12-08T11:21:40.583707+00:00' @@ -219,3 +220,22 @@ location: postal_code: 508 01 street_address: Vojice 141 normalization_timestamp: '2025-12-09T10:53:00.085779+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:42.235656+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32021 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:52:42.235656+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOR-L-MKS-mistni_knihovna_sobcice.yaml b/data/custodian/CZ-52-HOR-L-MKS-mistni_knihovna_sobcice.yaml index 2b1f20a29c..9d3fe5d710 100644 --- a/data/custodian/CZ-52-HOR-L-MKS-mistni_knihovna_sobcice.yaml +++ b/data/custodian/CZ-52-HOR-L-MKS-mistni_knihovna_sobcice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-MKS-mistni_knihovna_sobcice - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-MKS-mistni_knihovna_sobcice valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-MKS-mistni_knihovna_sobcice ghcid_numeric: 12405275995756833394 valid_from: '2025-12-06T23:37:35.131818+00:00' @@ -210,3 +211,22 @@ location: postal_code: 508 01 street_address: Sobčice 25 normalization_timestamp: '2025-12-09T10:53:00.112142+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:50.139944+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32021 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:52:50.139944+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOR-L-MKVJ.yaml b/data/custodian/CZ-52-HOR-L-MKVJ.yaml index d54b523c38..acf83ce963 100644 --- a/data/custodian/CZ-52-HOR-L-MKVJ.yaml +++ b/data/custodian/CZ-52-HOR-L-MKVJ.yaml @@ -216,3 +216,22 @@ location: postal_code: 508 01 street_address: Jeřice 21 normalization_timestamp: '2025-12-09T10:53:00.141252+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:57.067350+00:00' + source_url: https://www.jermanice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jermanice.cz/skins/jermanice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.jermanice.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:52:57.067350+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-HOR-L-MKVL.yaml b/data/custodian/CZ-52-HOR-L-MKVL.yaml index 16cc89dc21..7962810d47 100644 --- a/data/custodian/CZ-52-HOR-L-MKVL.yaml +++ b/data/custodian/CZ-52-HOR-L-MKVL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-MKVL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-MKVL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-MKVL ghcid_numeric: 2311746242962234235 valid_from: '2025-12-06T23:37:35.176258+00:00' @@ -214,3 +215,22 @@ location: postal_code: 508 01 street_address: Lískovice 72 normalization_timestamp: '2025-12-09T10:53:00.167133+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:53:07.976839+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32021 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:53:07.976839+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOR-L-OKH-obecni_knihovna_horineves.yaml b/data/custodian/CZ-52-HOR-L-OKH-obecni_knihovna_horineves.yaml index 57c9f0e00a..9126f88c0f 100644 --- a/data/custodian/CZ-52-HOR-L-OKH-obecni_knihovna_horineves.yaml +++ b/data/custodian/CZ-52-HOR-L-OKH-obecni_knihovna_horineves.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-OKH-obecni_knihovna_horineves - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-OKH-obecni_knihovna_horineves valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-OKH-obecni_knihovna_horineves ghcid_numeric: 6294392935089498707 valid_from: '2025-12-06T23:37:34.940398+00:00' @@ -216,3 +217,22 @@ location: postal_code: 503 06 street_address: Hořiněves 73 normalization_timestamp: '2025-12-09T10:53:00.222991+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:53:24.826117+00:00' + source_url: https://vck.tritius.cz/library/horineves + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vck.tritius.cz/apple-touch-icon-180x180.png + source_url: https://vck.tritius.cz/library/horineves + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:53:24.826117+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-HOR-L-OKH.yaml b/data/custodian/CZ-52-HOR-L-OKH.yaml index 1be35df9f2..6a4c13f856 100644 --- a/data/custodian/CZ-52-HOR-L-OKH.yaml +++ b/data/custodian/CZ-52-HOR-L-OKH.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-OKH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-OKH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-OKH ghcid_numeric: 965830316515187799 valid_from: '2025-12-06T23:37:18.803347+00:00' @@ -104,8 +105,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Obecní knihovna Hořičky @@ -215,3 +216,22 @@ location: geonames_id: 3075490 geonames_name: Hořičky feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:53:31.080189+00:00' + source_url: https://knihovnahoricky.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnahoricky.files.webk.cz/logov.png + source_url: https://knihovnahoricky.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-24T22:53:31.080189+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-HOR-L-OKVHB.yaml b/data/custodian/CZ-52-HOR-L-OKVHB.yaml index 22f99ac88c..4f259e51a6 100644 --- a/data/custodian/CZ-52-HOR-L-OKVHB.yaml +++ b/data/custodian/CZ-52-HOR-L-OKVHB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-OKVHB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-OKVHB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-OKVHB ghcid_numeric: 14190910587581998122 valid_from: '2025-12-06T23:37:35.635360+00:00' @@ -216,3 +217,22 @@ location: postal_code: 544 74 street_address: Horní Brusnice 284 normalization_timestamp: '2025-12-09T10:53:00.277421+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:53:41.882682+00:00' + source_url: https://trutnov.tritius.cz/library/hornibrusnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/hornibrusnice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:53:41.882682+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-HOR-L-OKVHM.yaml b/data/custodian/CZ-52-HOR-L-OKVHM.yaml index 86f5917fdb..2f9b32b8e3 100644 --- a/data/custodian/CZ-52-HOR-L-OKVHM.yaml +++ b/data/custodian/CZ-52-HOR-L-OKVHM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-OKVHM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-OKVHM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-OKVHM ghcid_numeric: 7767493808038604833 valid_from: '2025-12-06T23:37:35.638329+00:00' @@ -210,3 +211,22 @@ location: postal_code: 542 26 street_address: Bertholdovo nám. 102 normalization_timestamp: '2025-12-09T10:53:00.305404+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:53:52.293766+00:00' + source_url: https://trutnov.tritius.cz/library/hornimarsov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/hornimarsov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T22:53:52.293766+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-HOR-L-OKZ.yaml b/data/custodian/CZ-52-HOR-L-OKZ.yaml index c91f50ec91..4bfd0a7ab2 100644 --- a/data/custodian/CZ-52-HOR-L-OKZ.yaml +++ b/data/custodian/CZ-52-HOR-L-OKZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOR-L-OKZ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOR-L-OKZ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOR-L-OKZ ghcid_numeric: 15805122975421179886 valid_from: '2025-12-08T11:21:37.590989+00:00' @@ -215,3 +216,22 @@ location: postal_code: 503 06 street_address: Žíželeves 42 normalization_timestamp: '2025-12-09T10:53:00.399476+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:07.849359+00:00' + source_url: https://www.horineves.cz/knihovny + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.horineves.cz/favicon.ico + source_url: https://www.horineves.cz/knihovny + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:54:07.849359+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOR-L-UKLFFNVMOK.yaml b/data/custodian/CZ-52-HOR-L-UKLFFNVMOK.yaml index b4122749f1..a8cf6fb152 100644 --- a/data/custodian/CZ-52-HOR-L-UKLFFNVMOK.yaml +++ b/data/custodian/CZ-52-HOR-L-UKLFFNVMOK.yaml @@ -236,3 +236,37 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - 1.lékařská fakulta a Fakultní nemocnice v Motole - Ortopedická klinika official youtube_search_timestamp: '2025-12-09T09:32:16.762286+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:16.816701+00:00' + source_url: https://www.lf1.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lf1.cuni.cz/content/img/logo-cz.svg + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > body > header > div.logocz > a.lf1.logocz + > img' + retrieved_on: '2025-12-24T22:54:16.816701+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 1. lékařská fakulta Univerzity Karlovy + - claim_type: favicon_url + claim_value: https://www.lf1.cuni.cz/content/img/apple-icon.png + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:54:16.816701+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lf1.cuni.cz + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T22:54:16.816701+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/CZ-52-HOR-L-UKUK.yaml b/data/custodian/CZ-52-HOR-L-UKUK.yaml index a4edb1ce04..41dd30eca8 100644 --- a/data/custodian/CZ-52-HOR-L-UKUK.yaml +++ b/data/custodian/CZ-52-HOR-L-UKUK.yaml @@ -307,3 +307,36 @@ location: youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Ústřední knihovna official youtube_search_timestamp: '2025-12-09T09:32:17.498460+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:24.494144+00:00' + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#logoImage' + retrieved_on: '2025-12-24T22:54:24.494144+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo knihovny + - claim_type: favicon_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/favicon.ico + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#viewCustomerFavIcon' + retrieved_on: '2025-12-24T22:54:24.494144+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#ogImage' + retrieved_on: '2025-12-24T22:54:24.494144+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOR-L-UMCACVVK.yaml b/data/custodian/CZ-52-HOR-L-UMCACVVK.yaml index 837f81b5fa..ea343213ce 100644 --- a/data/custodian/CZ-52-HOR-L-UMCACVVK.yaml +++ b/data/custodian/CZ-52-HOR-L-UMCACVVK.yaml @@ -242,3 +242,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Ústav makromolekulární chemie AV ČR, v. v. i. - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:18.160460+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:29.939860+00:00' + source_url: https://katalog.lib.cas.cz/UMCH + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/UMCH/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/UMCH + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T22:54:29.939860+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HOS-L-MKH.yaml b/data/custodian/CZ-52-HOS-L-MKH.yaml index e452364911..1dc270eee5 100644 --- a/data/custodian/CZ-52-HOS-L-MKH.yaml +++ b/data/custodian/CZ-52-HOS-L-MKH.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HOS-L-MKH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HOS-L-MKH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HOS-L-MKH ghcid_numeric: 398686012031892450 valid_from: '2025-12-06T23:37:20.388056+00:00' @@ -215,3 +216,22 @@ location: postal_code: 543 71 street_address: Nádražní 119 normalization_timestamp: '2025-12-09T10:53:00.446429+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:39.390368+00:00' + source_url: https://www.klasterhostinne.cz/aktuality-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.klasterhostinne.cz/favicon.ico + source_url: https://www.klasterhostinne.cz/aktuality-knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:54:39.390368+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HRA-A-SOAHK.yaml b/data/custodian/CZ-52-HRA-A-SOAHK.yaml index 55663eda9b..d92ea8750d 100644 --- a/data/custodian/CZ-52-HRA-A-SOAHK.yaml +++ b/data/custodian/CZ-52-HRA-A-SOAHK.yaml @@ -44,13 +44,14 @@ ghcid: longitude: 13.12137 ghcid_history: - ghcid: CZ-52-HRA-A-SOAHK - valid_from: "2025-12-10T09:46:51Z" + valid_from: '2025-12-10T09:46:51Z' valid_to: null - reason: "Corrected region code from CZ-521 to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-521 to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-521-HRA-A-SOAHK valid_from: null - valid_to: "2025-12-10T09:46:51Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:46:51Z' + reason: Previous GHCID with incorrect region code - ghcid: XX-XX-XXX-A-SOAHK ghcid_numeric: 10042392007948660218 valid_from: '2025-12-06T23:37:44.433862+00:00' @@ -248,3 +249,33 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Hradec Králové official youtube_search_timestamp: '2025-12-09T09:34:07.808226+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:57.869922+00:00' + source_url: https://vychodoceskearchivy.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-1.png + source_url: https://vychodoceskearchivy.cz + css_selector: '#cb-row--header-main > div.header--row-inner.header-main-inner + > div.customify-container > div.customify-grid.cb-row--desktop > div.row-v2.row-v2-main + > div.col-v2.col-v2-left > div.item--inner.builder-item--logo > div.site-branding.logo-left + > a.logo-link > img.site-img-logo' + retrieved_on: '2025-12-24T22:54:57.869922+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Státní oblastní archiv v Hradci Králové + - claim_type: favicon_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-180x180.png + source_url: https://vychodoceskearchivy.cz + css_selector: '[document] > html > head > link:nth-of-type(31)' + retrieved_on: '2025-12-24T22:54:57.869922+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-HRA-E-VOSZSZSHKS.yaml b/data/custodian/CZ-52-HRA-E-VOSZSZSHKS.yaml index 3b66d7fce8..c88529fa60 100644 --- a/data/custodian/CZ-52-HRA-E-VOSZSZSHKS.yaml +++ b/data/custodian/CZ-52-HRA-E-VOSZSZSHKS.yaml @@ -218,3 +218,28 @@ location: postal_code: 500 03 street_address: Komenského 268 normalization_timestamp: '2025-12-09T10:53:00.474050+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:04.209970+00:00' + source_url: https://www.zshk.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.zshk.cz/wp-content/themes/zshk/dist/images/favicon/safari-pinned-tab.svg + source_url: https://www.zshk.cz + css_selector: '[document] > html.no-js.no-svg > head > link:nth-of-type(19)' + retrieved_on: '2025-12-24T22:55:04.209970+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.zshk.cz/wp-content/uploads/2019/11/zshk-FB-odkaz_na_web-1200x630px.png + source_url: https://www.zshk.cz + css_selector: '[document] > html.no-js.no-svg > head > meta:nth-of-type(17)' + retrieved_on: '2025-12-24T22:55:04.209970+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-52-HRA-G-GMUHK.yaml b/data/custodian/CZ-52-HRA-G-GMUHK.yaml index abc4397765..24daa07a51 100644 --- a/data/custodian/CZ-52-HRA-G-GMUHK.yaml +++ b/data/custodian/CZ-52-HRA-G-GMUHK.yaml @@ -39,18 +39,20 @@ ghcid: city_label: Hradec Kralove geonames_id: 3074967 ghcid_history: - - previous_ghcid_component: "HK" - new_ghcid_component: "HRA" - change_date: "2025-12-20T19:55:24Z" - reason: "Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Hradec Kralove" + - previous_ghcid_component: HK + new_ghcid_component: HRA + change_date: '2025-12-20T19:55:24Z' + reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: + Hradec Kralove' - ghcid: CZ-52-HK-G-GMUHK - valid_from: "2025-12-10T09:46:51Z" + valid_from: '2025-12-10T09:46:51Z' valid_to: null - reason: "Corrected region code from CZ-521 to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-521 to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-521-HK-G-GMUHK valid_from: null - valid_to: "2025-12-10T09:46:51Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:46:51Z' + reason: Previous GHCID with incorrect region code - ghcid: XX-XX-XXX-G-GMUHK ghcid_numeric: 12161302584764868726 valid_from: '2025-12-06T23:37:44.004115+00:00' @@ -92,8 +94,10 @@ provenance: notes: - 'Country resolved 2025-12-06T23:54:38Z: XX→CZ via Wikidata P17' - 'Region resolved 2025-12-07T00:01:02Z: XX->521 via Wikidata P131 (CZ-521)' - - 'City resolved 2025-12-07T00:33:21Z: XXX->HK via Wikidata Q1491909 coords (50.2092,15.8319) -> Hradec Kralove (GeoNames:3074967)' - - Removed incorrect wikidata_enrichment on 2025-12-08T08:18:45.594649+00:00. Re-enrichment required with proper matching. + - 'City resolved 2025-12-07T00:33:21Z: XXX->HK via Wikidata Q1491909 coords (50.2092,15.8319) + -> Hradec Kralove (GeoNames:3074967)' + - Removed incorrect wikidata_enrichment on 2025-12-08T08:18:45.594649+00:00. Re-enrichment + required with proper matching. - Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:19Z - Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:44Z - 'YouTube/Google Maps enrichment 2025-12-09T09:34:06Z: YouTube: not found' @@ -124,8 +128,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.85 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Galerie moderního umění, Hradec Králové @@ -217,8 +221,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance wikidata_instance_of: *id005 wikidata_location: country: &id007 @@ -259,3 +263,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Galerie moderního umění, Hradec Králové official youtube_search_timestamp: '2025-12-09T09:34:06.469105+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:10.524539+00:00' + source_url: http://www.galeriehk.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.galeriehk.cz/wp-content/uploads/2021/06/cropped-Snímek-obrazovky-2021-06-01-v-8.41.35-180x180.png + source_url: http://www.galeriehk.cz + css_selector: '[document] > html > head > link:nth-of-type(25)' + retrieved_on: '2025-12-24T22:55:10.524539+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.galeriehk.cz/wp-content/uploads/2023/09/Budova.jpg + source_url: http://www.galeriehk.cz + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:55:10.524539+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-52-HRA-H-BKBK.yaml b/data/custodian/CZ-52-HRA-H-BKBK.yaml index c936c9a202..9ae1878c07 100644 --- a/data/custodian/CZ-52-HRA-H-BKBK.yaml +++ b/data/custodian/CZ-52-HRA-H-BKBK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-H-BKBK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-H-BKBK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-H-BKBK ghcid_numeric: 11814175135645202497 valid_from: '2025-12-06T23:37:43.112074+00:00' @@ -213,3 +214,28 @@ location: postal_code: 501 01 street_address: Velké náměstí 35/44 normalization_timestamp: '2025-12-09T10:53:00.500505+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:16.359883+00:00' + source_url: https://www.bihk.cz/vzdelani-media/biskupska-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bihk.cz/themes/bihk/favicon.ico + source_url: https://www.bihk.cz/vzdelani-media/biskupska-knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:55:16.359883+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.bihk.cz/bihk-fb.png + source_url: https://www.bihk.cz/vzdelani-media/biskupska-knihovna + css_selector: '[document] > html.js > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-24T22:55:16.359883+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-CHI-L-CL.yaml b/data/custodian/JP-12-CHI-L-CL.yaml index 4930cce3b7..75a5802c49 100644 --- a/data/custodian/JP-12-CHI-L-CL.yaml +++ b/data/custodian/JP-12-CHI-L-CL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-CL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-CL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-CL ghcid_numeric: 4853573344257004245 valid_from: '2025-12-06T23:38:53.948199+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: CHIBAKENRITSUHOKENIRYODAIGAKUNITONAKYAMPASU Library @@ -206,3 +207,28 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:54:22.934362+00:00' + source_url: http://www.pref.chiba.lg.jp/hoidai/kyouiku/toshokan.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.pref.chiba.lg.jp/shared/site_hoidai/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.pref.chiba.lg.jp/hoidai/kyouiku/toshokan.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T11:54:22.934362+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.pref.chiba.lg.jp/shared/images/sns/logo.png + source_url: http://www.pref.chiba.lg.jp/hoidai/kyouiku/toshokan.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T11:54:22.934362+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-CLML.yaml b/data/custodian/JP-12-CHI-L-CLML.yaml index 39b772554a..fddea6b95f 100644 --- a/data/custodian/JP-12-CHI-L-CLML.yaml +++ b/data/custodian/JP-12-CHI-L-CLML.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-CLML - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-CLML valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-CLML ghcid_numeric: 4620073202338837812 valid_from: '2025-12-06T23:38:53.945592+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: CHIBAKENRITSUHOKENIRYODAIGAKU Library (MAKUHARIKYAMPASU Library ) @@ -164,7 +165,8 @@ wikidata_enrichment: wikidata_labels: en: CHIBAKENRITSUHOKENIRYODAIGAKU Library (MAKUHARIKYAMPASU Library ) ja: 千葉県立保健医療大学図書館(幕張キャンパス図書館) - wikidata_label_en: CHIBAKENRITSUHOKENIRYODAIGAKU Library (MAKUHARIKYAMPASU Library ) + wikidata_label_en: CHIBAKENRITSUHOKENIRYODAIGAKU Library (MAKUHARIKYAMPASU Library + ) wikidata_label_ja: 千葉県立保健医療大学図書館(幕張キャンパス図書館) wikidata_classification: instance_of: &id004 @@ -206,3 +208,28 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:54:34.105744+00:00' + source_url: http://www.pref.chiba.lg.jp/hoidai/kyouiku/toshokan.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.pref.chiba.lg.jp/shared/site_hoidai/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.pref.chiba.lg.jp/hoidai/kyouiku/toshokan.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T11:54:34.105744+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.pref.chiba.lg.jp/shared/images/sns/logo.png + source_url: http://www.pref.chiba.lg.jp/hoidai/kyouiku/toshokan.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T11:54:34.105744+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-CPAFRC.yaml b/data/custodian/JP-12-CHI-L-CPAFRC.yaml index b991186536..a15f403606 100644 --- a/data/custodian/JP-12-CHI-L-CPAFRC.yaml +++ b/data/custodian/JP-12-CHI-L-CPAFRC.yaml @@ -154,3 +154,30 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:54:45.430846+00:00' + source_url: https://www.pref.chiba.lg.jp/lab-nourin + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.chiba.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.pref.chiba.lg.jp/lab-nourin + css_selector: '[document] > html.wf-a-otf-ud-shin-go-pr6n-n3-active.wf-active + > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T11:54:45.430846+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.pref.chiba.lg.jp/shared/images/sns/logo.png + source_url: https://www.pref.chiba.lg.jp/lab-nourin + css_selector: '[document] > html.wf-a-otf-ud-shin-go-pr6n-n3-active.wf-active + > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T11:54:45.430846+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-CPAL.yaml b/data/custodian/JP-12-CHI-L-CPAL.yaml index db67d5b685..a424cd48e4 100644 --- a/data/custodian/JP-12-CHI-L-CPAL.yaml +++ b/data/custodian/JP-12-CHI-L-CPAL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-CPAL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-CPAL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-CPAL ghcid_numeric: 40237058141285491 valid_from: '2025-12-06T23:38:57.816160+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Chiba Prefectural Assembly Library @@ -153,3 +154,30 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:54:55.549728+00:00' + source_url: http://www.pref.chiba.lg.jp/gikai/tosho + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.pref.chiba.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.pref.chiba.lg.jp/gikai/tosho + css_selector: '[document] > html.wf-a-otf-ud-shin-go-pr6n-n3-active.wf-active + > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T11:54:55.549728+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.pref.chiba.lg.jp/shared/images/sns/logo.png + source_url: http://www.pref.chiba.lg.jp/gikai/tosho + css_selector: '[document] > html.wf-a-otf-ud-shin-go-pr6n-n3-active.wf-active + > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T11:54:55.549728+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-CPCL.yaml b/data/custodian/JP-12-CHI-L-CPCL.yaml index 435f20fee0..398d2bc4ea 100644 --- a/data/custodian/JP-12-CHI-L-CPCL.yaml +++ b/data/custodian/JP-12-CHI-L-CPCL.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-CPCL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-CPCL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-CPCL ghcid_numeric: 6590576095954798865 valid_from: '2025-12-06T23:38:42.752047+00:00' @@ -268,3 +269,22 @@ location: postal_code: 260-8660 street_address: 11-1 ICHIBACHO, Chiba Shi Chuo Ku, Chiba Ken, 260-8660 normalization_timestamp: '2025-12-09T10:55:27.860500+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:55:08.305239+00:00' + source_url: https://www.library.pref.chiba.lg.jp/guide/central/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.pref.chiba.lg.jp/apple-touch-icon.png + source_url: https://www.library.pref.chiba.lg.jp/guide/central/index.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T11:55:08.305239+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-CUL.yaml b/data/custodian/JP-12-CHI-L-CUL.yaml index 18179ec2d1..f92cdb2bb0 100644 --- a/data/custodian/JP-12-CHI-L-CUL.yaml +++ b/data/custodian/JP-12-CHI-L-CUL.yaml @@ -227,3 +227,28 @@ wikidata_enrichment: commons_category: Chiba University Library image: N Building, Chiba University Library, July 2023.jpg wikidata_image: N Building, Chiba University Library, July 2023.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:55:24.016235+00:00' + source_url: http://www.ll.chiba-u.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ll.chiba-u.jp/common/img/favicon.ico + source_url: http://www.ll.chiba-u.jp + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T11:55:24.016235+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://alc.chiba-u.jp/img/topImg.jpg + source_url: http://www.ll.chiba-u.jp + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T11:55:24.016235+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-CHI-L-K.yaml b/data/custodian/JP-12-CHI-L-K.yaml index ac4358f463..4d1264c923 100644 --- a/data/custodian/JP-12-CHI-L-K.yaml +++ b/data/custodian/JP-12-CHI-L-K.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-K - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-K valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-K ghcid_numeric: 17550809185709678942 valid_from: '2025-12-06T23:38:54.736369+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KEIAIDAIGAKUCHIBAKEIAITANKIDAIGAKUMEDEIASENTAINAGEKYAMPASU @@ -206,3 +207,28 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:55:38.922964+00:00' + source_url: http://www.u-keiai.ac.jp/kulir + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.u-keiai.ac.jp/common/image/app-icon.png + source_url: http://www.u-keiai.ac.jp/kulir + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T11:55:38.922964+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.u-keiai.ac.jp/common/image/sns-icon.jpg + source_url: http://www.u-keiai.ac.jp/kulir + css_selector: '[document] > html.js > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-24T11:55:38.922964+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-KUISL.yaml b/data/custodian/JP-12-CHI-L-KUISL.yaml index 764ea878bc..185f487695 100644 --- a/data/custodian/JP-12-CHI-L-KUISL.yaml +++ b/data/custodian/JP-12-CHI-L-KUISL.yaml @@ -216,3 +216,22 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:55:45.117615+00:00' + source_url: http://kuis.libguides.com/home + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://d329ms1y997xa5.cloudfront.net/apps/common/favicon/safari-pinned-tab.svg + source_url: http://kuis.libguides.com/home + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T11:55:45.117615+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-12-CHI-L-LIDEJETO.yaml b/data/custodian/JP-12-CHI-L-LIDEJETO.yaml index 43e852006a..a232e0cb94 100644 --- a/data/custodian/JP-12-CHI-L-LIDEJETO.yaml +++ b/data/custodian/JP-12-CHI-L-LIDEJETO.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-LIDEJETO - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-LIDEJETO valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-LIDEJETO ghcid_numeric: 15103486718490543440 valid_from: '2025-12-06T23:38:57.945320+00:00' @@ -96,11 +97,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Library, Institute of Developing Economies, Japan External Trade Organization + claim_value: Library, Institute of Developing Economies, Japan External Trade + Organization property_uri: skos:prefLabel provenance: namespace: glam @@ -153,3 +155,37 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T11:56:25.517827+00:00' + source_url: http://www.ide.go.jp/Japanese/Library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.ide.go.jp/library/rn23/common/images/mainlogo_jp.png + source_url: http://www.ide.go.jp/Japanese/Library + css_selector: '#headerJP > div.headerInner > div.headerLeft > div.headerLogo > + a > img' + retrieved_on: '2025-12-24T11:56:25.517827+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: IDE-JETRO ジェトロ・アジア経済研究所 + - claim_type: favicon_url + claim_value: http://www.ide.go.jp/favicon.ico?dummy=1705374019 + source_url: http://www.ide.go.jp/Japanese/Library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T11:56:25.517827+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ide.go.jp/library/common/images/twitter_card.jpg + source_url: http://www.ide.go.jp/Japanese/Library + css_selector: '[document] > html > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-24T11:56:25.517827+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-SUCL.yaml b/data/custodian/JP-12-CHI-L-SUCL.yaml index 8d5fd75e52..dfc3befb63 100644 --- a/data/custodian/JP-12-CHI-L-SUCL.yaml +++ b/data/custodian/JP-12-CHI-L-SUCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-SUCL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-SUCL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-SUCL ghcid_numeric: 4068697118272029170 valid_from: '2025-12-06T23:38:54.728744+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Shukutoku University C0hiba Library @@ -211,3 +212,22 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:13:37.312163+00:00' + source_url: http://www.shukutoku.ac.jp/library/chiba + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shukutoku.ac.jp/favicon.ico + source_url: http://www.shukutoku.ac.jp/library/chiba + css_selector: '[document] > html > body > link' + retrieved_on: '2025-12-24T12:13:37.312163+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-CHI-L-SUSNNL.yaml b/data/custodian/JP-12-CHI-L-SUSNNL.yaml index 46b22bf6fc..18d462cd33 100644 --- a/data/custodian/JP-12-CHI-L-SUSNNL.yaml +++ b/data/custodian/JP-12-CHI-L-SUSNNL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-SUSNNL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-SUSNNL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-SUSNNL ghcid_numeric: 8581960741897047383 valid_from: '2025-12-06T23:38:54.733841+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Shukutoku University School of Nursing and Nutrition Library @@ -206,3 +207,22 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:13:53.715061+00:00' + source_url: http://www.shukutoku.ac.jp/library/chiba2 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shukutoku.ac.jp/favicon.ico + source_url: http://www.shukutoku.ac.jp/library/chiba2 + css_selector: '[document] > html > body > link' + retrieved_on: '2025-12-24T12:13:53.715061+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-CHI-L-TUISISC.yaml b/data/custodian/JP-12-CHI-L-TUISISC.yaml index 9a71f89554..d3e22d06af 100644 --- a/data/custodian/JP-12-CHI-L-TUISISC.yaml +++ b/data/custodian/JP-12-CHI-L-TUISISC.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-TUISISC - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-TUISISC valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-TUISISC ghcid_numeric: 6104413471930075131 valid_from: '2025-12-06T23:38:54.770549+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo University of Information Sciences Information Support Center @@ -165,7 +166,8 @@ wikidata_enrichment: wikidata_labels: en: Tokyo University of Information Sciences Information Support Center ja: 東京情報大学情報サービスセンター - wikidata_label_en: Tokyo University of Information Sciences Information Support Center + wikidata_label_en: Tokyo University of Information Sciences Information Support + Center wikidata_label_ja: 東京情報大学情報サービスセンター wikidata_descriptions: en: academic library in Japan @@ -196,7 +198,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: https://tuis.repo.nii.ac.jp/ wikidata_official_website: https://tuis.repo.nii.ac.jp/ @@ -220,3 +223,22 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:13.647161+00:00' + source_url: https://tuis.repo.nii.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tuis.repo.nii.ac.jp/static/apple-touch-icon-144-precomposed.png + source_url: https://tuis.repo.nii.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:14:13.647161+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 144x144 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-12-CHI-L-TUML.yaml b/data/custodian/JP-12-CHI-L-TUML.yaml index da2088c270..b34173d623 100644 --- a/data/custodian/JP-12-CHI-L-TUML.yaml +++ b/data/custodian/JP-12-CHI-L-TUML.yaml @@ -154,3 +154,28 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:27.106118+00:00' + source_url: https://www.tohto.ac.jp/about/library2021 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tohto.ac.jp/wp-content/assets/img/icon/apple-touch-icon.png + source_url: https://www.tohto.ac.jp/about/library2021 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:14:27.106118+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.tohto.ac.jp/wp-content/assets/img/common/ogp.jpg + source_url: https://www.tohto.ac.jp/about/library2021 + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:14:27.106118+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-L-UGUL.yaml b/data/custodian/JP-12-CHI-L-UGUL.yaml index 6f3b1b0b6e..f27a995679 100644 --- a/data/custodian/JP-12-CHI-L-UGUL.yaml +++ b/data/custodian/JP-12-CHI-L-UGUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-L-UGUL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-L-UGUL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-L-UGUL ghcid_numeric: 4169090203973063324 valid_from: '2025-12-06T23:38:54.796024+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Uekusa Gakuen University Library @@ -206,3 +207,28 @@ location: geonames_id: 2113015 geonames_name: Chiba feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:37.373890+00:00' + source_url: http://www.uekusa.ac.jp/school_life/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.uekusa.ac.jp/uekusa_wp/wp-content/themes/uekusagakuen2022/images/apple-touch-icon.png + source_url: http://www.uekusa.ac.jp/school_life/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:14:37.373890+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.uekusa.ac.jp/uekusa_wp/wp-content/uploads/2010/11/2eddea690ad9270760f5087047edf23a.jpg + source_url: http://www.uekusa.ac.jp/school_life/library + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:14:37.373890+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-M-CCFM.yaml b/data/custodian/JP-12-CHI-M-CCFM.yaml index ec72356984..ad1aef47e7 100644 --- a/data/custodian/JP-12-CHI-M-CCFM.yaml +++ b/data/custodian/JP-12-CHI-M-CCFM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-M-CCFM - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-M-CCFM valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-M-CCFM ghcid_numeric: 17006564099960827931 valid_from: '2025-12-06T23:38:32.678842+00:00' @@ -268,3 +269,28 @@ location: postal_code: 260-0856 street_address: INOHANA, Chiba Shi Chuo Ku, Chiba Ken, 260-0856 normalization_timestamp: '2025-12-09T10:55:28.242558+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:45.479990+00:00' + source_url: https://www.city.chiba.jp/kyoiku/shogaigakushu/bunkazai/kyodo/kyodo_top.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.chiba.jp/shared/site_kyodo/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.chiba.jp/kyoiku/shogaigakushu/bunkazai/kyodo/kyodo_top.html + css_selector: '[document] > html > head.notranslate > link:nth-of-type(6)' + retrieved_on: '2025-12-24T12:14:45.479990+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.chiba.jp/shared/site_kyodo/images/sns/logo.png + source_url: https://www.city.chiba.jp/kyoiku/shogaigakushu/bunkazai/kyodo/kyodo_top.html + css_selector: '[document] > html > head.notranslate > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:14:45.479990+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHI-M-CCMS.yaml b/data/custodian/JP-12-CHI-M-CCMS.yaml index 6f9b7c9d9c..d1401f3665 100644 --- a/data/custodian/JP-12-CHI-M-CCMS.yaml +++ b/data/custodian/JP-12-CHI-M-CCMS.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-M-CCMS - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-M-CCMS valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-M-CCMS ghcid_numeric: 18387043141156484632 valid_from: '2025-12-06T23:38:32.670646+00:00' @@ -207,3 +208,22 @@ location: postal_code: 260-0013 street_address: CHUO, Chiba Shi Chuo Ku, Chiba Ken, 260-0013 normalization_timestamp: '2025-12-09T10:55:28.269785+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:14:54.899904+00:00' + source_url: https://www.kagakukanq.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kagakukanq.com/wp-content/uploads/2019/03/cropped-kagakukan_symbol_icon_512x512-180x180.png + source_url: https://www.kagakukanq.com + css_selector: '[document] > html.js.no-touch > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T12:14:54.899904+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/JP-12-CHI-M-CKUREM.yaml b/data/custodian/JP-12-CHI-M-CKUREM.yaml index b3e64fd437..e9c32fa42e 100644 --- a/data/custodian/JP-12-CHI-M-CKUREM.yaml +++ b/data/custodian/JP-12-CHI-M-CKUREM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHI-M-CKUREM - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHI-M-CKUREM valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHI-M-CKUREM ghcid_numeric: 14819272734637864465 valid_from: '2025-12-06T23:38:32.686488+00:00' @@ -212,3 +213,28 @@ location: postal_code: 263-0021 street_address: TODOROKICHO, Chiba Shi Inage Ku, Chiba Ken, 263-0021 normalization_timestamp: '2025-12-09T10:55:28.297728+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:02.932042+00:00' + source_url: https://www.cku.ac.jp/local/museum.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.cku.ac.jp/wp/wp-content/themes/cku/images/common/apple-touch-icon.png + source_url: https://www.cku.ac.jp/local/museum.html + css_selector: '[document] > html.js._device-pc > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:15:02.932042+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.cku.ac.jp/wp/wp-content/themes/cku/images/common/ogp.jpg + source_url: https://www.cku.ac.jp/local/museum.html + css_selector: '[document] > html.js._device-pc > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T12:15:02.932042+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 6 diff --git a/data/custodian/JP-12-CHI-M-CPMA.yaml b/data/custodian/JP-12-CHI-M-CPMA.yaml index 3c00ccd759..c01166e395 100644 --- a/data/custodian/JP-12-CHI-M-CPMA.yaml +++ b/data/custodian/JP-12-CHI-M-CPMA.yaml @@ -376,3 +376,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/ofHoZzdK5CI/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:13.631911+00:00' + source_url: http://www.chiba-muse.or.jp/ART + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chiba-muse.or.jp/ART/cms/wp-content/themes/chibamuse_art/img/common/favicon.ico + source_url: http://www.chiba-muse.or.jp/ART + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:15:13.631911+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-CHI-M-HM.yaml b/data/custodian/JP-12-CHI-M-HM.yaml index 9948fb9fa5..b8b8dac73d 100644 --- a/data/custodian/JP-12-CHI-M-HM.yaml +++ b/data/custodian/JP-12-CHI-M-HM.yaml @@ -286,3 +286,22 @@ wikidata_enrichment: - id: Q2804130 label: Nikken Sekkei description: Japanese architecture firm +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:28.485170+00:00' + source_url: https://www.hoki-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hoki-museum.jp/wp-content/uploads/2021/12/cropped-logo-180x180.jpg + source_url: https://www.hoki-museum.jp + css_selector: '[document] > html.pc > head > link:nth-of-type(22)' + retrieved_on: '2025-12-24T12:15:28.485170+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-CHI-M-NHMIC.yaml b/data/custodian/JP-12-CHI-M-NHMIC.yaml index 5d0005813a..837d079e0f 100644 --- a/data/custodian/JP-12-CHI-M-NHMIC.yaml +++ b/data/custodian/JP-12-CHI-M-NHMIC.yaml @@ -293,3 +293,22 @@ wikidata_enrichment: - id: Q11509101 label: Nihon Sekkei description: architectural firm in Japan +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:39.266743+00:00' + source_url: http://www.chiba-muse.or.jp/NATURAL + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chiba-muse.or.jp/NATURAL/cms/wp-content/themes/chibamuse_natural/img/common/favicon.ico + source_url: http://www.chiba-muse.or.jp/NATURAL + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:15:39.266743+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-CHO-L-CISL.yaml b/data/custodian/JP-12-CHO-L-CISL.yaml index fba11ad10c..6f63da84d0 100644 --- a/data/custodian/JP-12-CHO-L-CISL.yaml +++ b/data/custodian/JP-12-CHO-L-CISL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHO-L-CISL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHO-L-CISL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHO-L-CISL ghcid_numeric: 2015190895067931544 valid_from: '2025-12-06T23:38:54.791056+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Chiba Institute of Science Library @@ -196,7 +197,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.lib.cis.ac.jp wikidata_official_website: http://www.lib.cis.ac.jp @@ -218,3 +220,22 @@ location: geonames_id: 2112996 geonames_name: Choshi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:45.283172+00:00' + source_url: http://www.lib.cis.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.cis.ac.jp/opac/images/cyan/favicon.ico + source_url: http://www.lib.cis.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:15:45.283172+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-CHO-L-CL.yaml b/data/custodian/JP-12-CHO-L-CL.yaml index a98d78650d..b1dcea7303 100644 --- a/data/custodian/JP-12-CHO-L-CL.yaml +++ b/data/custodian/JP-12-CHO-L-CL.yaml @@ -208,3 +208,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.choshi.chiba.jp/edu/sg-guide/toshokan/toshokantop.html wikidata_official_website: http://www.city.choshi.chiba.jp/edu/sg-guide/toshokan/toshokantop.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:15:52.388703+00:00' + source_url: https://www.city.choshi.chiba.jp/kurashi/index0151.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.choshi.chiba.jp/favicon.svg + source_url: https://www.city.choshi.chiba.jp/kurashi/index0151.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:15:52.388703+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.choshi.chiba.jp/ogp.png + source_url: https://www.city.choshi.chiba.jp/kurashi/index0151.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:15:52.388703+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-CHO-L-N.yaml b/data/custodian/JP-12-CHO-L-N.yaml index a49b7af0e0..bd0cd84511 100644 --- a/data/custodian/JP-12-CHO-L-N.yaml +++ b/data/custodian/JP-12-CHO-L-N.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.nagara.chiba.jp/ngr/pf.html wikidata_official_website: http://www.town.nagara.chiba.jp/ngr/pf.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:00.709438+00:00' + source_url: https://www.town.nagara.chiba.jp/soshiki/9/117.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.nagara.chiba.jp/img/icon/apple-touch-icon.png + source_url: https://www.town.nagara.chiba.jp/soshiki/9/117.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:16:00.709438+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-CHO-L-S.yaml b/data/custodian/JP-12-CHO-L-S.yaml index f1de818aff..988a70b63f 100644 --- a/data/custodian/JP-12-CHO-L-S.yaml +++ b/data/custodian/JP-12-CHO-L-S.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.shirako.lg.jp/ wikidata_official_website: http://www.town.shirako.lg.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:09.789311+00:00' + source_url: http://www.town.shirako.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.shirako.lg.jp/css/img/apple-touch-icon.png + source_url: http://www.town.shirako.lg.jp + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:16:09.789311+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.town.shirako.lg.jp/design_img/og_image.png + source_url: http://www.town.shirako.lg.jp + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T12:16:09.789311+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-CHO-M-MMHF.yaml b/data/custodian/JP-12-CHO-M-MMHF.yaml index 8cd7eb06cf..84ebb30e43 100644 --- a/data/custodian/JP-12-CHO-M-MMHF.yaml +++ b/data/custodian/JP-12-CHO-M-MMHF.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHO-M-MMHF - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHO-M-MMHF valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHO-M-MMHF ghcid_numeric: 11210636333298136962 valid_from: '2025-12-06T23:38:32.914815+00:00' @@ -213,3 +214,22 @@ location: postal_code: 299-4413 street_address: KAMINOGO, Chosei Gun Mutsuzawa Machi, Chiba Ken, 299-4413 normalization_timestamp: '2025-12-09T10:55:28.537820+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:21.540910+00:00' + source_url: https://www.town.mutsuzawa.chiba.jp/shisetsu/rekishiminzoku/gaiyou-2.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.mutsuzawa.chiba.jp/wp-content/themes/mutsuzawa_new/assets/images/apple-touch-icon.png + source_url: https://www.town.mutsuzawa.chiba.jp/shisetsu/rekishiminzoku/gaiyou-2.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:16:21.540910+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-CHO-M-STMRHF.yaml b/data/custodian/JP-12-CHO-M-STMRHF.yaml index 7939cbd6ec..1aa1050016 100644 --- a/data/custodian/JP-12-CHO-M-STMRHF.yaml +++ b/data/custodian/JP-12-CHO-M-STMRHF.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-CHO-M-STMRHF - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-CHO-M-STMRHF valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-CHO-M-STMRHF ghcid_numeric: 14784800944487933367 valid_from: '2025-12-06T23:38:32.917535+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIRAKO TOWN MATERIAL ROOMS OF HISTORY AND FOLKLORE @@ -153,3 +154,28 @@ location: geonames_id: 1851898 geonames_name: Shirako feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:30.894072+00:00' + source_url: http://www.shirako.or.jp/3chiiki/html/chiiki11.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://shirako.or.jp/wp/wp-content/themes/shirako/images/common/apple-touch-icon-180x180.png + source_url: http://www.shirako.or.jp/3chiiki/html/chiiki11.html + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T12:16:30.894072+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://shirako.or.jp/wp/wp-content/themes/shirako/images/common/image_ogp.jpg + source_url: http://www.shirako.or.jp/3chiiki/html/chiiki11.html + css_selector: '[document] > html > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-24T12:16:30.894072+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-CHU-M-KKAK.yaml b/data/custodian/JP-12-CHU-M-KKAK.yaml index 7ad85f6af3..0dfa4be8d9 100644 --- a/data/custodian/JP-12-CHU-M-KKAK.yaml +++ b/data/custodian/JP-12-CHU-M-KKAK.yaml @@ -383,3 +383,20 @@ location: geonames_id: 8739698 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:32.414361+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:16:43.117238+00:00' + source_url: http://k-aynu-mh.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://k-aynu-mh.jp/bdflashinfo/thumbnail-large.png + source_url: http://k-aynu-mh.jp + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T12:16:43.117238+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-FUN-L-F-funabashishimiyamashiminsentatoshoshitsu.yaml b/data/custodian/JP-12-FUN-L-F-funabashishimiyamashiminsentatoshoshitsu.yaml index 5a50decefe..d7a809af7b 100644 --- a/data/custodian/JP-12-FUN-L-F-funabashishimiyamashiminsentatoshoshitsu.yaml +++ b/data/custodian/JP-12-FUN-L-F-funabashishimiyamashiminsentatoshoshitsu.yaml @@ -199,3 +199,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.funabashi.lg.jp/shisetsu/shiminkatsudo/0002/0002/0001/p011269.html wikidata_official_website: http://www.city.funabashi.lg.jp/shisetsu/shiminkatsudo/0002/0002/0001/p011269.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:17:04.708755+00:00' + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=43 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.funabashi.lg.jp/apple-touch-icon.png + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=43 + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T12:17:04.708755+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.lib.city.funabashi.lg.jp/manage/contents/upload/60125f41c4f4e.jpg + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=43 + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:17:04.708755+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-FUN-L-F-funabashishiseibukominkantoshoshitsu.yaml b/data/custodian/JP-12-FUN-L-F-funabashishiseibukominkantoshoshitsu.yaml index 2bff65d7a3..8cb3d0b68c 100644 --- a/data/custodian/JP-12-FUN-L-F-funabashishiseibukominkantoshoshitsu.yaml +++ b/data/custodian/JP-12-FUN-L-F-funabashishiseibukominkantoshoshitsu.yaml @@ -199,3 +199,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0002/0010/0002/p033235.html wikidata_official_website: http://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0002/0010/0002/p033235.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:17:14.336687+00:00' + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=41 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.funabashi.lg.jp/apple-touch-icon.png + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=41 + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T12:17:14.336687+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.lib.city.funabashi.lg.jp/manage/contents/upload/60125c90ce026.jpg + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=41 + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:17:14.336687+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-FUN-L-F.yaml b/data/custodian/JP-12-FUN-L-F.yaml index 60b0d2c31d..d29dff42fd 100644 --- a/data/custodian/JP-12-FUN-L-F.yaml +++ b/data/custodian/JP-12-FUN-L-F.yaml @@ -199,3 +199,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0002/0025/0001/p011044.html wikidata_official_website: http://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0002/0025/0001/p011044.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:17:23.333129+00:00' + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=42 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.funabashi.lg.jp/apple-touch-icon.png + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=42 + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T12:17:23.333129+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.lib.city.funabashi.lg.jp/manage/contents/upload/60125e4295b90.jpg + source_url: https://www.lib.city.funabashi.lg.jp/viewer/info.html?idSubTop=0&id=42 + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:17:23.333129+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-FUN-L-FL-funabashishichuo_library.yaml b/data/custodian/JP-12-FUN-L-FL-funabashishichuo_library.yaml index 5562286b0d..6b2414b4a8 100644 --- a/data/custodian/JP-12-FUN-L-FL-funabashishichuo_library.yaml +++ b/data/custodian/JP-12-FUN-L-FL-funabashishichuo_library.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0001/0001/p011016.html wikidata_official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0001/0001/p011016.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:17:31.779977+00:00' + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0001/0001/p011016.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/logo.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0001/0001/p011016.html + css_selector: '#header > div.l-header__inner > div.l-header__logo > a > img' + retrieved_on: '2025-12-24T12:17:31.779977+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 船橋市 + - claim_type: favicon_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-apple-touch-icon.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0001/0001/p011016.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:17:31.779977+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-ogimg.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0001/0001/p011016.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:17:31.779977+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-FUN-L-FL-funabashishihigashi_library.yaml b/data/custodian/JP-12-FUN-L-FL-funabashishihigashi_library.yaml index 2865523dc5..bc4099898c 100644 --- a/data/custodian/JP-12-FUN-L-FL-funabashishihigashi_library.yaml +++ b/data/custodian/JP-12-FUN-L-FL-funabashishihigashi_library.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0003/0001/p011018.html wikidata_official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0003/0001/p011018.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:18:48.670532+00:00' + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0003/0001/p011018.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/logo.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0003/0001/p011018.html + css_selector: '#header > div.l-header__inner > div.l-header__logo > a > img' + retrieved_on: '2025-12-24T12:18:48.670532+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 船橋市 + - claim_type: favicon_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-apple-touch-icon.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0003/0001/p011018.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:18:48.670532+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-ogimg.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0003/0001/p011018.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:18:48.670532+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-FUN-L-FL-funabashishikita_library.yaml b/data/custodian/JP-12-FUN-L-FL-funabashishikita_library.yaml index 669ea2834f..03b4211943 100644 --- a/data/custodian/JP-12-FUN-L-FL-funabashishikita_library.yaml +++ b/data/custodian/JP-12-FUN-L-FL-funabashishikita_library.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0004/0001/p011019.html wikidata_official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0004/0001/p011019.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:18:54.350495+00:00' + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0004/0001/p011019.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/logo.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0004/0001/p011019.html + css_selector: '#header > div.l-header__inner > div.l-header__logo > a > img' + retrieved_on: '2025-12-24T12:18:54.350495+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 船橋市 + - claim_type: favicon_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-apple-touch-icon.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0004/0001/p011019.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:18:54.350495+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-ogimg.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0004/0001/p011019.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:18:54.350495+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-FUN-L-FL.yaml b/data/custodian/JP-12-FUN-L-FL.yaml index 3cb7ecc374..557aa6d927 100644 --- a/data/custodian/JP-12-FUN-L-FL.yaml +++ b/data/custodian/JP-12-FUN-L-FL.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0002/0001/p011017.html wikidata_official_website: http://www.city.funabashi.chiba.jp/shisetsu/toshokankominkan/0001/0002/0001/p011017.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:18:59.936404+00:00' + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0002/0001/p011017.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/logo.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0002/0001/p011017.html + css_selector: '#header > div.l-header__inner > div.l-header__logo > a > img' + retrieved_on: '2025-12-24T12:18:59.936404+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 船橋市 + - claim_type: favicon_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-apple-touch-icon.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0002/0001/p011017.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:18:59.936404+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-ogimg.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/toshokankominkan/0001/0002/0001/p011017.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:18:59.936404+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-FUN-L-LSPNU.yaml b/data/custodian/JP-12-FUN-L-LSPNU.yaml index 59c90b8af6..f260e174d4 100644 --- a/data/custodian/JP-12-FUN-L-LSPNU.yaml +++ b/data/custodian/JP-12-FUN-L-LSPNU.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-FUN-L-LSPNU - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-FUN-L-LSPNU valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-FUN-L-LSPNU ghcid_numeric: 4162389473408197398 valid_from: '2025-12-06T23:38:54.713336+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Library, School of Pharmacy, Nihon University @@ -204,3 +205,37 @@ location: geonames_id: 1863904 geonames_name: Funabashi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:19:10.144403+00:00' + source_url: http://libinfo.pha.nihon-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.pha.nihon-u.ac.jp/common/image/header-logo001.gif + source_url: http://libinfo.pha.nihon-u.ac.jp + css_selector: '#header > div.header-area-in.clearfix > div.header-main > h1.logo + > a > picture > source > img' + retrieved_on: '2025-12-24T12:19:10.144403+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日本大学 薬学部 + - claim_type: favicon_url + claim_value: https://www.pha.nihon-u.ac.jp/common/image/app-icon.png + source_url: http://libinfo.pha.nihon-u.ac.jp + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:19:10.144403+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pha.nihon-u.ac.jp/common/image/sns-icon.jpg + source_url: http://libinfo.pha.nihon-u.ac.jp + css_selector: '[document] > html.js > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-24T12:19:10.144403+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-FUN-L-THUFL.yaml b/data/custodian/JP-12-FUN-L-THUFL.yaml index 6cdde4c0cf..3abdf52ca4 100644 --- a/data/custodian/JP-12-FUN-L-THUFL.yaml +++ b/data/custodian/JP-12-FUN-L-THUFL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-FUN-L-THUFL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-FUN-L-THUFL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-FUN-L-THUFL ghcid_numeric: 9401457961851364443 valid_from: '2025-12-06T23:38:59.995544+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Healthcare University Funabashi Library @@ -151,3 +152,20 @@ location: geonames_id: 1863904 geonames_name: Funabashi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:20:05.604968+00:00' + source_url: https://www.thcu.ac.jp/facilities/library + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://thcu.ac.jp/img/asset/ogp.png + source_url: https://www.thcu.ac.jp/facilities/library + css_selector: '[document] > html.other > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:20:05.604968+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-FUN-L-TUNMC.yaml b/data/custodian/JP-12-FUN-L-TUNMC.yaml index b7fe56ba2e..1878a25497 100644 --- a/data/custodian/JP-12-FUN-L-TUNMC.yaml +++ b/data/custodian/JP-12-FUN-L-TUNMC.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-FUN-L-TUNMC - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-FUN-L-TUNMC valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-FUN-L-TUNMC ghcid_numeric: 14630007751169126610 valid_from: '2025-12-06T23:38:55.152413+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Toho University Narashino Media Center @@ -204,3 +205,22 @@ location: geonames_id: 1863904 geonames_name: Funabashi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:20:14.001331+00:00' + source_url: http://www.mnc.toho-u.ac.jp/nmc + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mnc.toho-u.ac.jp/img/favicon.ico + source_url: http://www.mnc.toho-u.ac.jp/nmc + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:20:14.001331+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-FUN-M-FHM.yaml b/data/custodian/JP-12-FUN-M-FHM.yaml index e34408f21e..174361423e 100644 --- a/data/custodian/JP-12-FUN-M-FHM.yaml +++ b/data/custodian/JP-12-FUN-M-FHM.yaml @@ -250,3 +250,36 @@ location: postal_code: 274-0077 street_address: YAKUENDAI, Funabashi Shi, Chiba Ken, 274-0077 normalization_timestamp: '2025-12-09T10:55:28.918309+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:20:38.211130+00:00' + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0005/0001/p011081.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/logo.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0005/0001/p011081.html + css_selector: '#header > div.l-header__inner > div.l-header__logo > a > img' + retrieved_on: '2025-12-24T12:20:38.211130+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 船橋市 + - claim_type: favicon_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-apple-touch-icon.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0005/0001/p011081.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:20:38.211130+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-ogimg.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0005/0001/p011081.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:20:38.211130+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-FUN-M-FSCPK.yaml b/data/custodian/JP-12-FUN-M-FSCPK.yaml index 9579d6764e..22d5f00134 100644 --- a/data/custodian/JP-12-FUN-M-FSCPK.yaml +++ b/data/custodian/JP-12-FUN-M-FSCPK.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-FUN-M-FSCPK - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-FUN-M-FSCPK valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-FUN-M-FSCPK ghcid_numeric: 701266866228552704 valid_from: '2025-12-06T23:38:32.729051+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: FUNABASHISHI SOUGOUKYOUIKU CENTER PLANETARIUM KAN @@ -151,3 +152,36 @@ location: geonames_id: 1863904 geonames_name: Funabashi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:20:43.858008+00:00' + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0002/0002/0001/p011085.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/logo.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0002/0002/0001/p011085.html + css_selector: '#header > div.l-header__inner > div.l-header__logo > a > img' + retrieved_on: '2025-12-24T12:20:43.858008+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 船橋市 + - claim_type: favicon_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-apple-touch-icon.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0002/0002/0001/p011085.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:20:43.858008+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-ogimg.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0002/0002/0001/p011085.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:20:43.858008+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-FUN-M-MPGSPNU.yaml b/data/custodian/JP-12-FUN-M-MPGSPNU.yaml index 3e6a5215fd..ec85884442 100644 --- a/data/custodian/JP-12-FUN-M-MPGSPNU.yaml +++ b/data/custodian/JP-12-FUN-M-MPGSPNU.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-FUN-M-MPGSPNU - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-FUN-M-MPGSPNU valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-FUN-M-MPGSPNU ghcid_numeric: 4825331029011008508 valid_from: '2025-12-06T23:38:32.741802+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Medicinal Plant Garden, School of Pharmacy, Nihon University @@ -151,3 +152,30 @@ location: geonames_id: 1863904 geonames_name: Funabashi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:20:53.530948+00:00' + source_url: http://mpgarden.pha.nihon-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://mpgarden.pha.nihon-u.ac.jp/wp-content/themes/garden/images/common/logo.jpg + source_url: http://mpgarden.pha.nihon-u.ac.jp + css_selector: '#branding > div.inner > h1 > a > img' + retrieved_on: '2025-12-24T12:20:53.530948+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日本大学薬学部薬用植物園 + - claim_type: favicon_url + claim_value: https://mpgarden.pha.nihon-u.ac.jp/wp-content/themes/garden/images/favicon.ico + source_url: http://mpgarden.pha.nihon-u.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T12:20:53.530948+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-FUN-M-MPGTU.yaml b/data/custodian/JP-12-FUN-M-MPGTU.yaml index 736a0aec01..75f770a567 100644 --- a/data/custodian/JP-12-FUN-M-MPGTU.yaml +++ b/data/custodian/JP-12-FUN-M-MPGTU.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-FUN-M-MPGTU - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-FUN-M-MPGTU valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-FUN-M-MPGTU ghcid_numeric: 17014930735337284612 valid_from: '2025-12-06T23:38:32.739408+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Medical Plant Garden of Toho University @@ -151,3 +152,28 @@ location: geonames_id: 1863904 geonames_name: Funabashi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:21:08.534401+00:00' + source_url: https://www.lab.toho-u.ac.jp/phar/yakusou + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lab.toho-u.ac.jp/common/images/global/favicon.ico + source_url: https://www.lab.toho-u.ac.jp/phar/yakusou + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T12:21:08.534401+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lab.toho-u.ac.jp/phar/yakusou/common/ovohlk0000002spv-img/toho_logo_01.svg + source_url: https://www.lab.toho-u.ac.jp/phar/yakusou + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T12:21:08.534401+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-FUT-M-TZ.yaml b/data/custodian/JP-12-FUT-M-TZ.yaml index a0c234fea9..b38f42eefc 100644 --- a/data/custodian/JP-12-FUT-M-TZ.yaml +++ b/data/custodian/JP-12-FUT-M-TZ.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-FUT-M-TZ - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-FUT-M-TZ valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-FUT-M-TZ ghcid_numeric: 13735493843365589636 valid_from: '2025-12-06T23:38:32.865544+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAGOYAMA ZOO @@ -177,8 +178,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q43501 label: zoo - description: 'collection of assorted wild animal species kept for purposes like: study, conservation and, or, commercial - exhibition' + description: 'collection of assorted wild animal species kept for purposes like: + study, conservation and, or, commercial exhibition' wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -195,8 +196,8 @@ wikidata_enrichment: part_of: id: Q11271817 label: 100 Treasures of Chiba - description: sélection de traditions et culture, patrimoine culturel et patrimoine naturel de la préfecture de Chiba, - au Japon + description: sélection de traditions et culture, patrimoine culturel et patrimoine + naturel de la préfecture de Chiba, au Japon wikidata_web: official_website: https://www.city.futtsu.lg.jp/0000000348.html wikidata_official_website: https://www.city.futtsu.lg.jp/0000000348.html @@ -221,3 +222,28 @@ location: geonames_id: 1863713 geonames_name: Futtsu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:21:31.884218+00:00' + source_url: https://www.city.futtsu.lg.jp/0000000348.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.futtsu.lg.jp/design_img/favicon.ico + source_url: https://www.city.futtsu.lg.jp/0000000348.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T12:21:31.884218+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.futtsu.lg.jp/design_img/og_image.jpg + source_url: https://www.city.futtsu.lg.jp/0000000348.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T12:21:31.884218+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-GOR-L-HCCL.yaml b/data/custodian/JP-12-GOR-L-HCCL.yaml index cb471d43fa..e3ee5cccd3 100644 --- a/data/custodian/JP-12-GOR-L-HCCL.yaml +++ b/data/custodian/JP-12-GOR-L-HCCL.yaml @@ -428,3 +428,22 @@ location: geonames_id: 11865330 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:32.530881+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:21:40.203172+00:00' + source_url: https://hakodate-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hakodate-lib.jp/apple-touch-icon-180x180.png + source_url: https://hakodate-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:21:40.203172+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-GOR-M-GT.yaml b/data/custodian/JP-12-GOR-M-GT.yaml index 6b4f32dcc7..085b64bc1d 100644 --- a/data/custodian/JP-12-GOR-M-GT.yaml +++ b/data/custodian/JP-12-GOR-M-GT.yaml @@ -459,3 +459,36 @@ location: geonames_id: 11865330 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:32.576125+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:21:48.399430+00:00' + source_url: https://www.goryokaku-tower.co.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.goryokaku-tower.co.jp/cms/wp-content/themes/gt_2019/resource/img/common/logo_174x34.svgz + source_url: https://www.goryokaku-tower.co.jp + css_selector: '#js-logo-change' + retrieved_on: '2025-12-24T12:21:48.399430+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 五稜郭タワー + - claim_type: favicon_url + claim_value: https://www.goryokaku-tower.co.jp/cms/wp-content/themes/gt_2019/resource/favicons/safari-pinned-tab.svg + source_url: https://www.goryokaku-tower.co.jp + css_selector: '[document] > html.dsktp.win > head > link:nth-of-type(13)' + retrieved_on: '2025-12-24T12:21:48.399430+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.goryokaku-tower.co.jp/cms/wp-content/themes/gt_2019/resource/img/mainimg_1180_600.jpg + source_url: https://www.goryokaku-tower.co.jp + css_selector: '[document] > html.dsktp.win > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T12:21:48.399430+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-ICH-L-CUCL.yaml b/data/custodian/JP-12-ICH-L-CUCL.yaml index c00152e538..86b361fc8e 100644 --- a/data/custodian/JP-12-ICH-L-CUCL.yaml +++ b/data/custodian/JP-12-ICH-L-CUCL.yaml @@ -214,3 +214,22 @@ location: geonames_id: 11837657 geonames_name: Ichikawa feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:22:54.317143+00:00' + source_url: http://www.lib.cuc.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.cuc.ac.jp/net_commons/favicon.ico?1613715745 + source_url: http://www.lib.cuc.ac.jp + css_selector: '[document] > html.ng-scope > head > link' + retrieved_on: '2025-12-24T12:22:54.317143+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-ICH-L-IL-ichikawashigyotoku_library.yaml b/data/custodian/JP-12-ICH-L-IL-ichikawashigyotoku_library.yaml index 96bd82a877..8c1ac6f461 100644 --- a/data/custodian/JP-12-ICH-L-IL-ichikawashigyotoku_library.yaml +++ b/data/custodian/JP-12-ICH-L-IL-ichikawashigyotoku_library.yaml @@ -205,3 +205,29 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ichikawa.lg.jp/library/index.html wikidata_official_website: http://www.city.ichikawa.lg.jp/library/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:23:12.699385+00:00' + source_url: https://www.city.ichikawa.lg.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/library/assets/images/common/logo.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img' + retrieved_on: '2025-12-24T12:23:12.699385+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市川市立図書館 ICHIKAWA CITY PUBLIC LIBRARY + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:23:12.699385+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-L-IL-ichikawashiichikawaekiminamiguchi_library.yaml b/data/custodian/JP-12-ICH-L-IL-ichikawashiichikawaekiminamiguchi_library.yaml index fb3273c85f..5d53329c03 100644 --- a/data/custodian/JP-12-ICH-L-IL-ichikawashiichikawaekiminamiguchi_library.yaml +++ b/data/custodian/JP-12-ICH-L-IL-ichikawashiichikawaekiminamiguchi_library.yaml @@ -205,3 +205,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.ekinan-lib.jp/ wikidata_official_website: http://www.ekinan-lib.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:23:20.143489+00:00' + source_url: https://www.ekinan-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.ekinan-lib.jp/wp-content/themes/ekinan/img/common/default_2.jpg + source_url: https://www.ekinan-lib.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:23:20.143489+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-L-IL-ichikawashiminamigyotoku_library.yaml b/data/custodian/JP-12-ICH-L-IL-ichikawashiminamigyotoku_library.yaml index 142479abf5..7b863fbc3b 100644 --- a/data/custodian/JP-12-ICH-L-IL-ichikawashiminamigyotoku_library.yaml +++ b/data/custodian/JP-12-ICH-L-IL-ichikawashiminamigyotoku_library.yaml @@ -205,3 +205,29 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ichikawa.lg.jp/library/index.html wikidata_official_website: http://www.city.ichikawa.lg.jp/library/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:23:29.009662+00:00' + source_url: https://www.city.ichikawa.lg.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/library/assets/images/common/logo.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img' + retrieved_on: '2025-12-24T12:23:29.009662+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市川市立図書館 ICHIKAWA CITY PUBLIC LIBRARY + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:23:29.009662+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-L-IL-ichikawashishintoku_library.yaml b/data/custodian/JP-12-ICH-L-IL-ichikawashishintoku_library.yaml index 6803ea2fbd..b775087767 100644 --- a/data/custodian/JP-12-ICH-L-IL-ichikawashishintoku_library.yaml +++ b/data/custodian/JP-12-ICH-L-IL-ichikawashishintoku_library.yaml @@ -205,3 +205,29 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ichikawa.lg.jp/library/index.html wikidata_official_website: http://www.city.ichikawa.lg.jp/library/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:25:23.241400+00:00' + source_url: https://www.city.ichikawa.lg.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/library/assets/images/common/logo.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img' + retrieved_on: '2025-12-24T12:25:23.241400+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市川市立図書館 ICHIKAWA CITY PUBLIC LIBRARY + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:25:23.241400+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-L-IL.yaml b/data/custodian/JP-12-ICH-L-IL.yaml index 55d49f122b..8b02b416da 100644 --- a/data/custodian/JP-12-ICH-L-IL.yaml +++ b/data/custodian/JP-12-ICH-L-IL.yaml @@ -209,3 +209,29 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ichikawa.lg.jp/library/index.html wikidata_official_website: http://www.city.ichikawa.lg.jp/library/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:25:32.542937+00:00' + source_url: https://www.city.ichikawa.lg.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/library/assets/images/common/logo.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img' + retrieved_on: '2025-12-24T12:25:32.542937+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市川市立図書館 ICHIKAWA CITY PUBLIC LIBRARY + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:25:32.542937+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-L-ILH.yaml b/data/custodian/JP-12-ICH-L-ILH.yaml index 74989fba83..a4354fdb08 100644 --- a/data/custodian/JP-12-ICH-L-ILH.yaml +++ b/data/custodian/JP-12-ICH-L-ILH.yaml @@ -205,3 +205,29 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ichikawa.lg.jp/library/index.html wikidata_official_website: http://www.city.ichikawa.lg.jp/library/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:25:40.643110+00:00' + source_url: https://www.city.ichikawa.lg.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/library/assets/images/common/logo.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img' + retrieved_on: '2025-12-24T12:25:40.643110+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市川市立図書館 ICHIKAWA CITY PUBLIC LIBRARY + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:25:40.643110+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-L-SL.yaml b/data/custodian/JP-12-ICH-L-SL.yaml index da28c5ac1c..4a77e1126e 100644 --- a/data/custodian/JP-12-ICH-L-SL.yaml +++ b/data/custodian/JP-12-ICH-L-SL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-ICH-L-SL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-ICH-L-SL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-ICH-L-SL ghcid_numeric: 15696076233941056836 valid_from: '2025-12-06T23:38:56.905813+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHOWAGAKUINTANKIDAIGAKUFUZOKU Library @@ -204,3 +205,28 @@ location: geonames_id: 11837657 geonames_name: Ichikawa feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:25:59.043388+00:00' + source_url: http://www.showagakuin.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.showagakuin.ac.jp/web/wp-content/uploads/2024/05/cropped-Mark-180x180.png + source_url: http://www.showagakuin.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T12:25:59.043388+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.showagakuin.ac.jp/web/web/wp-content/themes/showa-junior-college2024/img/ogp.jpg + source_url: http://www.showagakuin.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T12:25:59.043388+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-12-ICH-L-TL-tokyokeieitankidaigaku_library.yaml b/data/custodian/JP-12-ICH-L-TL-tokyokeieitankidaigaku_library.yaml index 22ca585be5..5b77b2e8d0 100644 --- a/data/custodian/JP-12-ICH-L-TL-tokyokeieitankidaigaku_library.yaml +++ b/data/custodian/JP-12-ICH-L-TL-tokyokeieitankidaigaku_library.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-ICH-L-TL-tokyokeieitankidaigaku_library - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-ICH-L-TL-tokyokeieitankidaigaku_library valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-ICH-L-TL-tokyokeieitankidaigaku_library ghcid_numeric: 6807510655355291202 valid_from: '2025-12-06T23:38:56.903304+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOKYOKEIEITANKIDAIGAKU Library @@ -204,3 +205,28 @@ location: geonames_id: 11837657 geonames_name: Ichikawa feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:26:19.768639+00:00' + source_url: http://www.tokyo-keitan.ac.jp/wp-keitan/guide/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tokyo-keitan.ac.jp/assets/images/apple-touch-icon.png + source_url: http://www.tokyo-keitan.ac.jp/wp-keitan/guide/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:26:19.768639+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tokyo-keitan.ac.jp/wp-content/uploads/2018/11/facebook-ogpsd.png + source_url: http://www.tokyo-keitan.ac.jp/wp-keitan/guide/library + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:26:19.768639+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-ICH-L-WWSUMC.yaml b/data/custodian/JP-12-ICH-L-WWSUMC.yaml index 4db796e8f4..9930e3f2cc 100644 --- a/data/custodian/JP-12-ICH-L-WWSUMC.yaml +++ b/data/custodian/JP-12-ICH-L-WWSUMC.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-ICH-L-WWSUMC - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-ICH-L-WWSUMC valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-ICH-L-WWSUMC ghcid_numeric: 2583104628380917165 valid_from: '2025-12-06T23:38:54.751593+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Wayo Women's University Media Center @@ -204,3 +205,31 @@ location: geonames_id: 11837657 geonames_name: Ichikawa feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:26:40.679274+00:00' + source_url: http://www.wayo.ac.jp/facilities_campus/media_center/tabid/565/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://data-univ.wayo.ac.jp/9516/8023/7150/site-logo_at_2x.png + source_url: http://www.wayo.ac.jp/facilities_campus/media_center/tabid/565/Default.aspx + css_selector: '[document] > html.chrome.is-visitor-nav-active > body > div.global-wrapper.ccm-page + > header.header > p.site-logo > a > img.site-logo__img' + retrieved_on: '2025-12-24T12:26:40.679274+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 和洋女子大学 + - claim_type: favicon_url + claim_value: https://data-univ.wayo.ac.jp/9216/8023/6459/apple-touch-icon-57x57.png + source_url: http://www.wayo.ac.jp/facilities_campus/media_center/tabid/565/Default.aspx + css_selector: '[document] > html.chrome.is-visitor-nav-active > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:26:40.679274+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-ICH-M-CMSI.yaml b/data/custodian/JP-12-ICH-M-CMSI.yaml index a61abd485e..a6ec3b9ed5 100644 --- a/data/custodian/JP-12-ICH-M-CMSI.yaml +++ b/data/custodian/JP-12-ICH-M-CMSI.yaml @@ -238,3 +238,22 @@ wikidata_enrichment: commons_category: Chiba Museum of Science and Industry image: Chiba Museum of Science and Industry.jpg wikidata_image: Chiba Museum of Science and Industry.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:26:56.007582+00:00' + source_url: http://www2.chiba-muse.or.jp/SCIENCE + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chiba-muse.or.jp/SCIENCE/cms/wp-content/themes/chibamuse_science/img/common/favicon.ico + source_url: http://www2.chiba-muse.or.jp/SCIENCE + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:26:56.007582+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-ICH-M-MKKHS.yaml b/data/custodian/JP-12-ICH-M-MKKHS.yaml index 22f3bc311d..b656f08034 100644 --- a/data/custodian/JP-12-ICH-M-MKKHS.yaml +++ b/data/custodian/JP-12-ICH-M-MKKHS.yaml @@ -152,3 +152,28 @@ location: geonames_id: 2112664 geonames_name: Ichihara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:27:04.986351+00:00' + source_url: https://www.city.ichihara.chiba.jp/article?articleId=60237754ece4651c88c1873d + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.ichihara.chiba.jp/assets/images/city-logo-image/favicon.png + source_url: https://www.city.ichihara.chiba.jp/article?articleId=60237754ece4651c88c1873d + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:27:04.986351+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ichihara.chiba.jp/assets/images/city-logo-image/Ichihara_OGP.png + source_url: https://www.city.ichihara.chiba.jp/article?articleId=60237754ece4651c88c1873d + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T12:27:04.986351+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-ICH-M-MMAI.yaml b/data/custodian/JP-12-ICH-M-MMAI.yaml index b33b45661a..7ff79a0008 100644 --- a/data/custodian/JP-12-ICH-M-MMAI.yaml +++ b/data/custodian/JP-12-ICH-M-MMAI.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-ICH-M-MMAI - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-ICH-M-MMAI valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-ICH-M-MMAI ghcid_numeric: 13309816969244768438 valid_from: '2025-12-06T23:38:32.714704+00:00' @@ -253,3 +254,29 @@ location: postal_code: 272-0837 street_address: HORINOCHI, Ichikawa Shi, Chiba Ken, 272-0837 normalization_timestamp: '2025-12-09T10:55:29.512113+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:27:13.685237+00:00' + source_url: https://www.city.ichikawa.lg.jp/edu14 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/edu14/assets/images/common/logo.png + source_url: https://www.city.ichikawa.lg.jp/edu14 + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img.pcOnly' + retrieved_on: '2025-12-24T12:27:13.685237+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市立市川考古博物館 市立市川歴史博物館 + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/edu14 + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:27:13.685237+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-M-MMHI.yaml b/data/custodian/JP-12-ICH-M-MMHI.yaml index ffb11da1f0..69cfc2a524 100644 --- a/data/custodian/JP-12-ICH-M-MMHI.yaml +++ b/data/custodian/JP-12-ICH-M-MMHI.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-ICH-M-MMHI - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-ICH-M-MMHI valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-ICH-M-MMHI ghcid_numeric: 15582144512423808698 valid_from: '2025-12-06T23:38:32.717354+00:00' @@ -250,3 +251,29 @@ location: postal_code: 272-0837 street_address: HORINOCHI, Ichikawa Shi, Chiba Ken, 272-0837 normalization_timestamp: '2025-12-09T10:55:29.552244+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:27:21.653439+00:00' + source_url: https://www.city.ichikawa.lg.jp/edu14 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/edu14/assets/images/common/logo.png + source_url: https://www.city.ichikawa.lg.jp/edu14 + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img.pcOnly' + retrieved_on: '2025-12-24T12:27:21.653439+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市立市川考古博物館 市立市川歴史博物館 + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/edu14 + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:27:21.653439+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-M-MMNHI.yaml b/data/custodian/JP-12-ICH-M-MMNHI.yaml index dd20b69821..550bf23d48 100644 --- a/data/custodian/JP-12-ICH-M-MMNHI.yaml +++ b/data/custodian/JP-12-ICH-M-MMNHI.yaml @@ -221,3 +221,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.city.ichikawa.lg.jp/edu16/ wikidata_official_website: https://www.city.ichikawa.lg.jp/edu16/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:27:28.723118+00:00' + source_url: https://www.city.ichikawa.lg.jp/catpage/cat_00000191.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/catpage/cat_00000191.html + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T12:27:28.723118+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ICH-M-WWSUM.yaml b/data/custodian/JP-12-ICH-M-WWSUM.yaml index 6d719e7777..6adb2a0d57 100644 --- a/data/custodian/JP-12-ICH-M-WWSUM.yaml +++ b/data/custodian/JP-12-ICH-M-WWSUM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-ICH-M-WWSUM - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-ICH-M-WWSUM valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-ICH-M-WWSUM ghcid_numeric: 12720384172065284959 valid_from: '2025-12-06T23:38:32.720052+00:00' @@ -238,3 +239,31 @@ location: postal_code: 272-8533 street_address: KONODAI, Ichikawa Shi, Chiba Ken, 272-8533 normalization_timestamp: '2025-12-09T10:55:29.613331+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:27:37.321085+00:00' + source_url: https://www.wayo.ac.jp/facilities_campus/museum + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://data-univ.wayo.ac.jp/9516/8023/7150/site-logo_at_2x.png + source_url: https://www.wayo.ac.jp/facilities_campus/museum + css_selector: '[document] > html.chrome.is-visitor-nav-active > body > div.global-wrapper.ccm-page + > header.header > p.site-logo > a > img.site-logo__img' + retrieved_on: '2025-12-24T12:27:37.321085+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 和洋女子大学 + - claim_type: favicon_url + claim_value: https://data-univ.wayo.ac.jp/9216/8023/6459/apple-touch-icon-57x57.png + source_url: https://www.wayo.ac.jp/facilities_campus/museum + css_selector: '[document] > html.chrome.is-visitor-nav-active > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:27:37.321085+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-IKU-M-MCM.yaml b/data/custodian/JP-12-IKU-M-MCM.yaml index 8f200a56e5..9ffa716d28 100644 --- a/data/custodian/JP-12-IKU-M-MCM.yaml +++ b/data/custodian/JP-12-IKU-M-MCM.yaml @@ -442,3 +442,28 @@ location: geonames_id: 2129942 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:32.765927+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:27:59.903824+00:00' + source_url: https://www.city.mikasa.hokkaido.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.mikasa.hokkaido.jp/museum/images/logo.gif + source_url: https://www.city.mikasa.hokkaido.jp/museum + css_selector: '#header > h1 > a > img' + retrieved_on: '2025-12-24T12:27:59.903824+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 三笠市立博物館 + - claim_type: og_image_url + claim_value: https://www.city.mikasa.hokkaido.jp/images/museum_og.jpg + source_url: https://www.city.mikasa.hokkaido.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T12:27:59.903824+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-IMB-L-F.yaml b/data/custodian/JP-12-IMB-L-F.yaml index 97c83318a2..a77f194a51 100644 --- a/data/custodian/JP-12-IMB-L-F.yaml +++ b/data/custodian/JP-12-IMB-L-F.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.sakae.chiba.jp/dir.php?code=1052 wikidata_official_website: http://www.town.sakae.chiba.jp/dir.php?code=1052 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:28:07.237326+00:00' + source_url: http://www.town.sakae.chiba.jp/dir.php?code=1052 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.sakae.chiba.jp/web_clip_icon.png + source_url: http://www.town.sakae.chiba.jp/dir.php?code=1052 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:28:07.237326+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-IMB-L-SL.yaml b/data/custodian/JP-12-IMB-L-SL.yaml index d6b6ad46fc..50ef17b08c 100644 --- a/data/custodian/JP-12-IMB-L-SL.yaml +++ b/data/custodian/JP-12-IMB-L-SL.yaml @@ -201,3 +201,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.tosyokan.town.shisui.chiba.jp/ wikidata_official_website: http://www.tosyokan.town.shisui.chiba.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:28:23.231334+00:00' + source_url: https://www.tosyokan.town.shisui.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.tosyokan.town.shisui.chiba.jp/TOSHOW/asp/shared/img/snsThumbnail.png + source_url: https://www.tosyokan.town.shisui.chiba.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:28:23.231334+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-IMB-M-BM.yaml b/data/custodian/JP-12-IMB-M-BM.yaml index 2fa28a67a3..2e9e2dce48 100644 --- a/data/custodian/JP-12-IMB-M-BM.yaml +++ b/data/custodian/JP-12-IMB-M-BM.yaml @@ -494,3 +494,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/y7e1AxuVgu8/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:28:36.934040+00:00' + source_url: http://www2.chiba-muse.or.jp/MURA + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chiba-muse.or.jp/MURA/cms/wp-content/themes/chibamuse_mura/img/common/favicon.ico + source_url: http://www2.chiba-muse.or.jp/MURA + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:28:36.934040+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-INZ-L-J.yaml b/data/custodian/JP-12-INZ-L-J.yaml index 5638761df6..4f743a3d99 100644 --- a/data/custodian/JP-12-INZ-L-J.yaml +++ b/data/custodian/JP-12-INZ-L-J.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-INZ-L-J - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-INZ-L-J valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-INZ-L-J ghcid_numeric: 17183413886399903179 valid_from: '2025-12-06T23:38:54.940392+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JUNTENDODAIGAKUSAKURAKYAMPASUGAKUJUTSUMEDEIASENTA @@ -215,3 +216,29 @@ location: geonames_id: 6822179 geonames_name: Inzai feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:29:47.528675+00:00' + source_url: http://www.juntendo.ac.jp/hss/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: '[inline-svg]' + source_url: http://www.juntendo.ac.jp/hss/library + css_selector: '#logo' + retrieved_on: '2025-12-24T12:29:47.528675+00:00' + extraction_method: crawl4ai_svg_detection + detection_confidence: high + is_inline_svg: true + aria_label: '' + - claim_type: og_image_url + claim_value: https://www.juntendo.ac.jp/ogp.png + source_url: http://www.juntendo.ac.jp/hss/library + css_selector: '[document] > html.js_domload.js_imgload > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T12:29:47.528675+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-INZ-L-NMSLK.yaml b/data/custodian/JP-12-INZ-L-NMSLK.yaml index 69d94e9215..bd3539620d 100644 --- a/data/custodian/JP-12-INZ-L-NMSLK.yaml +++ b/data/custodian/JP-12-INZ-L-NMSLK.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-INZ-L-NMSLK - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-INZ-L-NMSLK valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-INZ-L-NMSLK ghcid_numeric: 7742774003331333719 valid_from: '2025-12-06T23:39:00.015838+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nippon Medical School Library KANGOSENMONGAKKOTOSHOSHITSU @@ -151,3 +152,31 @@ location: geonames_id: 6822179 geonames_name: Inzai feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:30:09.873225+00:00' + source_url: https://www.nms.ac.jp/nursing-s/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://nursing-s.nms.ac.jp/wp-content/themes/nursing-s_glodia/images/img_logo01.png + source_url: https://www.nms.ac.jp/nursing-s/library + css_selector: '#header_inner01 > h1.site-title.h1_logo > a > div.logo_img > img.object-fit-img.img-fluid' + retrieved_on: '2025-12-24T12:30:09.873225+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 写真:日本医科大学看護専門学校 + - claim_type: favicon_url + claim_value: https://nursing-s.nms.ac.jp/wp-content/uploads/2023/10/cropped-cropped-img_logo02-180x180.png + source_url: https://www.nms.ac.jp/nursing-s/library + css_selector: '[document] > html.fontawesome-i2svg-active.fontawesome-i2svg-complete + > head > link:nth-of-type(53)' + retrieved_on: '2025-12-24T12:30:09.873225+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-INZ-L-T.yaml b/data/custodian/JP-12-INZ-L-T.yaml index e2ffac13e1..ed548ae6bb 100644 --- a/data/custodian/JP-12-INZ-L-T.yaml +++ b/data/custodian/JP-12-INZ-L-T.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-INZ-L-T - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-INZ-L-T valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-INZ-L-T ghcid_numeric: 10545010169339393604 valid_from: '2025-12-06T23:38:55.125315+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOKYODENKIDAIGAKUSOGOMEDEIASENTACHIBASATERAITOSENTA @@ -204,3 +205,22 @@ location: geonames_id: 6822179 geonames_name: Inzai feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:33:00.713999+00:00' + source_url: http://www.mrcl.dendai.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mrcl.dendai.ac.jp/mrcl/wp-content/uploads/2020/05/cropped-TDU-ICON-180x180.png + source_url: http://www.mrcl.dendai.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(35)' + retrieved_on: '2025-12-24T12:33:00.713999+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-INZ-L-TL.yaml b/data/custodian/JP-12-INZ-L-TL.yaml index 329bac52ac..a891f0e38a 100644 --- a/data/custodian/JP-12-INZ-L-TL.yaml +++ b/data/custodian/JP-12-INZ-L-TL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-INZ-L-TL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-INZ-L-TL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-INZ-L-TL ghcid_numeric: 4504934057343473876 valid_from: '2025-12-06T23:38:54.773198+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOKYOKIRISUTOKYODAIGAKU Library @@ -204,3 +205,28 @@ location: geonames_id: 6822179 geonames_name: Inzai feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:33:11.568817+00:00' + source_url: http://www.tci.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tci.ac.jp/icon.svg + source_url: http://www.tci.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:33:11.568817+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tci.ac.jp/img/common/ogp_tci.png + source_url: http://www.tci.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:33:11.568817+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 6 diff --git a/data/custodian/JP-12-INZ-M-ISIHMMD.yaml b/data/custodian/JP-12-INZ-M-ISIHMMD.yaml index e7e9feecf6..4a2ca98d47 100644 --- a/data/custodian/JP-12-INZ-M-ISIHMMD.yaml +++ b/data/custodian/JP-12-INZ-M-ISIHMMD.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-INZ-M-ISIHMMD - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-INZ-M-ISIHMMD valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-INZ-M-ISIHMMD ghcid_numeric: 6337308671263275052 valid_from: '2025-12-06T23:38:32.874316+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: INZAI SHIRITSU INBA HISTORICAL MUSEUM OF MEDICAL DEVICES @@ -189,8 +190,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q3329663 label: medical museum - description: institutions that store and exhibit objects of historical, scientific, artistic, or cultural interest that - have a link to medicine or health + description: institutions that store and exhibit objects of historical, scientific, + artistic, or cultural interest that have a link to medicine or health main_subject: - id: Q6554101 label: medical device @@ -231,3 +232,29 @@ location: geonames_id: 6822179 geonames_name: Inzai feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:33:23.068600+00:00' + source_url: https://ikakikai-hozon.org + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://ikakikai-hozon.org/wp/wp-content/themes/shiryoukan/assets/img/base/logo.png + source_url: https://ikakikai-hozon.org + css_selector: '[document] > html.no-js > body.home.page-template-default > header + > div.header-inner > div.header-logo > span > a > img' + retrieved_on: '2025-12-24T12:33:23.068600+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 印西市立印旛医科器械歴史資料館 + - claim_type: og_image_url + claim_value: https://ikakikai-hozon.org/wp/wp-content/themes/shiryoukan/assets/img/base/logo.png + source_url: https://ikakikai-hozon.org + css_selector: '[document] > html.no-js > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:33:23.068600+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-ISU-L-GLF.yaml b/data/custodian/JP-12-ISU-L-GLF.yaml index f5c9ddf02c..586146892b 100644 --- a/data/custodian/JP-12-ISU-L-GLF.yaml +++ b/data/custodian/JP-12-ISU-L-GLF.yaml @@ -154,3 +154,22 @@ location: geonames_id: 11112562 geonames_name: Onjukudai feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:33:30.576905+00:00' + source_url: http://www.town.onjuku.chiba.jp/sub6/7/minzoku_shiryoukan_01/gorinbunko_01 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.onjuku.chiba.jp/sub6/7/minzoku_shiryoukan_01/images/apple-touch-icon.png + source_url: http://www.town.onjuku.chiba.jp/sub6/7/minzoku_shiryoukan_01/gorinbunko_01 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:33:30.576905+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-ISU-L-OLT.yaml b/data/custodian/JP-12-ISU-L-OLT.yaml index 74a62b47f8..f2caa14bc0 100644 --- a/data/custodian/JP-12-ISU-L-OLT.yaml +++ b/data/custodian/JP-12-ISU-L-OLT.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.otaki.chiba.jp/index.cfm/6 wikidata_official_website: http://www.town.otaki.chiba.jp/index.cfm/6 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:33:39.303363+00:00' + source_url: https://www.town.otaki.chiba.jp/soshiki/shougaigakusyu/3/1/2/492.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.otaki.chiba.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.town.otaki.chiba.jp/soshiki/shougaigakusyu/3/1/2/492.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-24T12:33:39.303363+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 千葉県 大多喜町 OTAKI TOWN + - claim_type: favicon_url + claim_value: https://www.town.otaki.chiba.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.otaki.chiba.jp/soshiki/shougaigakusyu/3/1/2/492.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:33:39.303363+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.otaki.chiba.jp/material/images/group/38/20150627-200901.JPG + source_url: https://www.town.otaki.chiba.jp/soshiki/shougaigakusyu/3/1/2/492.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T12:33:39.303363+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-IWA-M-ICAHMMH.yaml b/data/custodian/JP-12-IWA-M-ICAHMMH.yaml index 8e92675e7f..a762e7d219 100644 --- a/data/custodian/JP-12-IWA-M-ICAHMMH.yaml +++ b/data/custodian/JP-12-IWA-M-ICAHMMH.yaml @@ -411,3 +411,36 @@ location: geonames_id: 2129870 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:32.809774+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:33:53.669304+00:00' + source_url: https://www.city.iwamizawa.hokkaido.jp/content/detail/1506246 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.iwamizawa.hokkaido.jp/theme/base/img_common/sub_heaeder_logo.png + source_url: https://www.city.iwamizawa.hokkaido.jp/content/detail/1506246 + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-24T12:33:53.669304+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩見沢市 IWAMIZAWA CITY + - claim_type: favicon_url + claim_value: https://www.city.iwamizawa.hokkaido.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.iwamizawa.hokkaido.jp/content/detail/1506246 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:33:53.669304+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.iwamizawa.hokkaido.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.iwamizawa.hokkaido.jp/content/detail/1506246 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T12:33:53.669304+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-KAG-M-ACM.yaml b/data/custodian/JP-12-KAG-M-ACM.yaml index c579b0c640..a9e1d57e3e 100644 --- a/data/custodian/JP-12-KAG-M-ACM.yaml +++ b/data/custodian/JP-12-KAG-M-ACM.yaml @@ -490,3 +490,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/gfOq1qy4LDc/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:34:03.429228+00:00' + source_url: https://www.city.asahikawa.hokkaido.jp/hakubutukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.asahikawa.hokkaido.jp/share/imgs/favicon.ico + source_url: https://www.city.asahikawa.hokkaido.jp/hakubutukan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:34:03.429228+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-KAG-M-MALM.yaml b/data/custodian/JP-12-KAG-M-MALM.yaml index 3dc53fe3e2..3e5268599b 100644 --- a/data/custodian/JP-12-KAG-M-MALM.yaml +++ b/data/custodian/JP-12-KAG-M-MALM.yaml @@ -1111,3 +1111,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/rqyRY5IDDUA/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:34:12.494974+00:00' + source_url: https://www.hyouten.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hyouten.com/wp/wp-content/uploads/2020/06/cropped-dea8b9ad799b9905770f09d90fe2cf7a-180x180.png + source_url: https://www.hyouten.com + css_selector: '[document] > html > body > link:nth-of-type(45)' + retrieved_on: '2025-12-24T12:34:12.494974+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.hyouten.com/wp/wp-content/uploads/2024/03/68895a1d6a025cfb9406e30b5331cb8a.jpg + source_url: https://www.hyouten.com + css_selector: '[document] > html > body > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:34:12.494974+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-KAM-L-KL.yaml b/data/custodian/JP-12-KAM-L-KL.yaml index 3daf08f64e..734bf1c523 100644 --- a/data/custodian/JP-12-KAM-L-KL.yaml +++ b/data/custodian/JP-12-KAM-L-KL.yaml @@ -206,3 +206,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.kamogawa.lg.jp/gyoseijoho/shisetsuichiran/toshokan/index.html wikidata_official_website: http://www.city.kamogawa.lg.jp/gyoseijoho/shisetsuichiran/toshokan/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:34:20.153223+00:00' + source_url: https://www.city.kamogawa.lg.jp/site/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.kamogawa.lg.jp/apple-touch-icon.png + source_url: https://www.city.kamogawa.lg.jp/site/library + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:34:20.153223+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-KAM-L-KPL.yaml b/data/custodian/JP-12-KAM-L-KPL.yaml index 1feada22f1..68b64e6dd0 100644 --- a/data/custodian/JP-12-KAM-L-KPL.yaml +++ b/data/custodian/JP-12-KAM-L-KPL.yaml @@ -199,3 +199,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-kamagaya-chiba.jp wikidata_official_website: http://www.library-kamagaya-chiba.jp +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:34:34.021823+00:00' + source_url: https://www.library-kamagaya-chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://localhost/TOSHOW/asp/shared/img/snsThumbnail.png + source_url: https://www.library-kamagaya-chiba.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T12:34:34.021823+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-KAM-M-KCLM.yaml b/data/custodian/JP-12-KAM-M-KCLM.yaml index aa5e8de9a0..fce78c4580 100644 --- a/data/custodian/JP-12-KAM-M-KCLM.yaml +++ b/data/custodian/JP-12-KAM-M-KCLM.yaml @@ -248,3 +248,36 @@ location: geonames_id: 2129770 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:32.926807+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:34:43.612963+00:00' + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=1107 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.kamifurano.hokkaido.jp/images/mainlogo.jpg + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=1107 + css_selector: '#logo > div:nth-of-type(2) > img' + retrieved_on: '2025-12-24T12:34:43.612963+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 北海道上富良野町公式(行政)ホームページ + - claim_type: favicon_url + claim_value: http://www.town.kamifurano.hokkaido.jp/icon.svg?t=2402230900 + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=1107 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T12:34:43.612963+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.kamifurano.hokkaido.jp/images/mainlogo_fbv1.png + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=1107 + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:34:43.612963+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-KAM-M-KK.yaml b/data/custodian/JP-12-KAM-M-KK.yaml index 884d8a37f6..396b7fd7f3 100644 --- a/data/custodian/JP-12-KAM-M-KK.yaml +++ b/data/custodian/JP-12-KAM-M-KK.yaml @@ -234,3 +234,22 @@ location: geonames_id: 2129696 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:32.957868+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:35:01.604219+00:00' + source_url: https://www.vill.kamoenai.hokkaido.jp/hotnews/detail/00000481.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vill.kamoenai.hokkaido.jp/icon.png + source_url: https://www.vill.kamoenai.hokkaido.jp/hotnews/detail/00000481.html + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T12:35:01.604219+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-KAM-M-KSW.yaml b/data/custodian/JP-12-KAM-M-KSW.yaml index d231add698..f7edb6c193 100644 --- a/data/custodian/JP-12-KAM-M-KSW.yaml +++ b/data/custodian/JP-12-KAM-M-KSW.yaml @@ -255,3 +255,22 @@ wikidata_enrichment: commons_category: Kamogawa Seaworld image: 南総 2013122110350000.jpg wikidata_image: 南総 2013122110350000.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:35:11.430217+00:00' + source_url: https://www.kamogawa-seaworld.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kamogawa-seaworld.jp/resources/images/apple-icon.png + source_url: https://www.kamogawa-seaworld.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:35:11.430217+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-KAM-M-MFMKC.yaml b/data/custodian/JP-12-KAM-M-MFMKC.yaml index e6c4e7babf..c36fdfcfeb 100644 --- a/data/custodian/JP-12-KAM-M-MFMKC.yaml +++ b/data/custodian/JP-12-KAM-M-MFMKC.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAM-M-MFMKC - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAM-M-MFMKC valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAM-M-MFMKC ghcid_numeric: 13445450303445295904 valid_from: '2025-12-06T23:38:32.846837+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MUNICIPAL FOLK MUSEUM,KAMOGAWA CITY @@ -151,3 +152,22 @@ location: geonames_id: 2112297 geonames_name: Kamogawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:35:19.204869+00:00' + source_url: https://www.city.kamogawa.lg.jp/site/shiryoukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.kamogawa.lg.jp/apple-touch-icon.png + source_url: https://www.city.kamogawa.lg.jp/site/shiryoukan + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:35:19.204869+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-KAM-M-THTJT.yaml b/data/custodian/JP-12-KAM-M-THTJT.yaml index 011d238122..5dec348a44 100644 --- a/data/custodian/JP-12-KAM-M-THTJT.yaml +++ b/data/custodian/JP-12-KAM-M-THTJT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAM-M-THTJT - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAM-M-THTJT valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAM-M-THTJT ghcid_numeric: 4938911857044641367 valid_from: '2025-12-06T23:38:32.851378+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TREASURE HOUSE OF THE TANJO-JI TEMPLE @@ -151,3 +152,36 @@ location: geonames_id: 2112297 geonames_name: Kamogawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:35:36.008543+00:00' + source_url: http://www.tanjoh-ji.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.tanjoh-ji.jp/images/common/header_logo01.svg + source_url: http://www.tanjoh-ji.jp + css_selector: '#home > header > h1.h-logo > a > img' + retrieved_on: '2025-12-24T12:35:36.008543+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 誕生寺 + - claim_type: favicon_url + claim_value: http://www.tanjoh-ji.jp/apple-touch-icon.png + source_url: http://www.tanjoh-ji.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:35:36.008543+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tanjoh-ji.jp/images/common/ogp.jpg + source_url: http://www.tanjoh-ji.jp + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T12:35:36.008543+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-12-KAS-L-ISUKCL.yaml b/data/custodian/JP-12-KAS-L-ISUKCL.yaml index 141003f18f..9eb3bc27b4 100644 --- a/data/custodian/JP-12-KAS-L-ISUKCL.yaml +++ b/data/custodian/JP-12-KAS-L-ISUKCL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAS-L-ISUKCL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAS-L-ISUKCL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAS-L-ISUKCL ghcid_numeric: 6400827690544950906 valid_from: '2025-12-06T23:38:59.977403+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Iryo Sosei University Kashiwa Campus Library @@ -151,3 +152,28 @@ location: geonames_id: 1859924 geonames_name: Kashiwa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:37:33.647976+00:00' + source_url: https://kn.isu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kn.isu.ac.jp/library/wp-content/themes/tm_isuLib_kashiwa/apple-touch-icon-180x180.png + source_url: https://kn.isu.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:37:33.647976+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://kn.isu.ac.jp/library/wp-content/themes/tm_isuLib_kashiwa/img/ogp.png + source_url: https://kn.isu.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:37:33.647976+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-KAS-L-KCL.yaml b/data/custodian/JP-12-KAS-L-KCL.yaml index 415123c44f..55d76f6253 100644 --- a/data/custodian/JP-12-KAS-L-KCL.yaml +++ b/data/custodian/JP-12-KAS-L-KCL.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/00_honkan.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/00_honkan.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:37:39.923081+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/honkan.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/honkan.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:37:39.923081+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KIUL.yaml b/data/custodian/JP-12-KAS-L-KIUL.yaml index 00d16c3c0d..d26e671d57 100644 --- a/data/custodian/JP-12-KAS-L-KIUL.yaml +++ b/data/custodian/JP-12-KAS-L-KIUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAS-L-KIUL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAS-L-KIUL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAS-L-KIUL ghcid_numeric: 7973978164235577319 valid_from: '2025-12-06T23:38:54.788582+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Kaichi International University Library @@ -204,3 +205,28 @@ location: geonames_id: 1859924 geonames_name: Kashiwa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:37:49.454809+00:00' + source_url: http://www.kaichi.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.kaichi.ac.jp/contents/wp-content/uploads/fbrfg/safari-pinned-tab.svg + source_url: http://www.kaichi.ac.jp/library + css_selector: '[document] > html.js > head > link:nth-of-type(32)' + retrieved_on: '2025-12-24T12:37:49.454809+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.kaichi.ac.jp/contents/wp-content/uploads/2017/06/image002.jpg + source_url: http://www.kaichi.ac.jp/library + css_selector: '[document] > html.js > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T12:37:49.454809+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/JP-12-KAS-L-KLE.yaml b/data/custodian/JP-12-KAS-L-KLE.yaml index bc711e9717..f662b063a3 100644 --- a/data/custodian/JP-12-KAS-L-KLE.yaml +++ b/data/custodian/JP-12-KAS-L-KLE.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/06_eirakudai.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/06_eirakudai.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:37:55.620774+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/eirakudai.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/eirakudai.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:37:55.620774+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLF-kashiwashiritsu_library_fujigokorobunkan.yaml b/data/custodian/JP-12-KAS-L-KLF-kashiwashiritsu_library_fujigokorobunkan.yaml index b6c108efd7..d418f755cf 100644 --- a/data/custodian/JP-12-KAS-L-KLF-kashiwashiritsu_library_fujigokorobunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLF-kashiwashiritsu_library_fujigokorobunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/14_hujigokoro.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/14_hujigokoro.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:01.956781+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/hujigokoro.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/hujigokoro.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:01.956781+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLF.yaml b/data/custodian/JP-12-KAS-L-KLF.yaml index b5922097d0..412c2b9edc 100644 --- a/data/custodian/JP-12-KAS-L-KLF.yaml +++ b/data/custodian/JP-12-KAS-L-KLF.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/05_huse.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/05_huse.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:07.374671+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/huse.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/huse.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:07.374671+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLH.yaml b/data/custodian/JP-12-KAS-L-KLH.yaml index cf288400b7..7cdc68427b 100644 --- a/data/custodian/JP-12-KAS-L-KLH.yaml +++ b/data/custodian/JP-12-KAS-L-KLH.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/08_hikarigaoka.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/08_hikarigaoka.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:13.847992+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/hikarigaoka.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/hikarigaoka.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:13.847992+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLKL.yaml b/data/custodian/JP-12-KAS-L-KLKL.yaml index 2f444d6830..e21d04a558 100644 --- a/data/custodian/JP-12-KAS-L-KLKL.yaml +++ b/data/custodian/JP-12-KAS-L-KLKL.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/17_kodomo.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/17_kodomo.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:20.168734+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/kodomo.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/kodomo.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:20.168734+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLM-kashiwashiritsu_library_matsubabunkan.yaml b/data/custodian/JP-12-KAS-L-KLM-kashiwashiritsu_library_matsubabunkan.yaml index 85148e61a5..348068aaa7 100644 --- a/data/custodian/JP-12-KAS-L-KLM-kashiwashiritsu_library_matsubabunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLM-kashiwashiritsu_library_matsubabunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/13_matuba.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/13_matuba.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:25.245992+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/matuba.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/matuba.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:25.245992+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLM.yaml b/data/custodian/JP-12-KAS-L-KLM.yaml index f146b8057d..0e52b58b63 100644 --- a/data/custodian/JP-12-KAS-L-KLM.yaml +++ b/data/custodian/JP-12-KAS-L-KLM.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/07_masuo.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/07_masuo.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:31.389864+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/masuo.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/masuo.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:31.389864+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nedobunkan.yaml b/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nedobunkan.yaml index 1894b50396..4f4a52cc7e 100644 --- a/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nedobunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nedobunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/11_nedo.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/11_nedo.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:37.587660+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/nedo.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/nedo.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:37.587660+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nishiharabunkan.yaml b/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nishiharabunkan.yaml index a23a9986ef..ebe83a6407 100644 --- a/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nishiharabunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLN-kashiwashiritsu_library_nishiharabunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/03_nishihara.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/03_nishihara.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:43.767425+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/nishihara.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/nishihara.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:43.767425+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLN.yaml b/data/custodian/JP-12-KAS-L-KLN.yaml index 240a87cc7f..200b0f47f0 100644 --- a/data/custodian/JP-12-KAS-L-KLN.yaml +++ b/data/custodian/JP-12-KAS-L-KLN.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/04_nanbu.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/04_nanbu.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:50.752275+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/nanbu.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/nanbu.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:50.752275+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shindembarabunkan.yaml b/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shindembarabunkan.yaml index 0fcc76ab41..30f3ffad81 100644 --- a/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shindembarabunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shindembarabunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/12_shindenhara.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/12_shindenhara.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:38:56.858797+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/shindenhara.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/shindenhara.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:38:56.858797+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shonambunkan.yaml b/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shonambunkan.yaml index 074de9a334..abd281c0fc 100644 --- a/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shonambunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLS-kashiwashiritsu_library_shonambunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/15_shonan.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/15_shonan.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:03.322262+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/shonan.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/shonan.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:39:03.322262+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLS.yaml b/data/custodian/JP-12-KAS-L-KLS.yaml index 6f24ecbd25..742cf330bf 100644 --- a/data/custodian/JP-12-KAS-L-KLS.yaml +++ b/data/custodian/JP-12-KAS-L-KLS.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/09_shintomi.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/09_shintomi.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:09.669963+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/shintomi.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/shintomi.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:39:09.669963+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takadabunkan.yaml b/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takadabunkan.yaml index 0ae877cdfb..4f5fa20edc 100644 --- a/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takadabunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takadabunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/10_takata.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/10_takata.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:15.987867+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/takata.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/takata.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:39:15.987867+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takayanagibunkan.yaml b/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takayanagibunkan.yaml index 827af4cd3d..9846acfc34 100644 --- a/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takayanagibunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_takayanagibunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/16_takayanagi.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/16_takayanagi.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:22.062780+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/takayanagi.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/takayanagi.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:39:22.062780+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_toyoshikidaibunkan.yaml b/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_toyoshikidaibunkan.yaml index ac85cb4b05..a94cfba868 100644 --- a/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_toyoshikidaibunkan.yaml +++ b/data/custodian/JP-12-KAS-L-KLT-kashiwashiritsu_library_toyoshikidaibunkan.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/01_toyosikidai.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/01_toyosikidai.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:28.237385+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/toyosikidai.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/toyosikidai.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:39:28.237385+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLT.yaml b/data/custodian/JP-12-KAS-L-KLT.yaml index dbd2f47d7d..72c149058d 100644 --- a/data/custodian/JP-12-KAS-L-KLT.yaml +++ b/data/custodian/JP-12-KAS-L-KLT.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/02_tanaka.html wikidata_official_website: http://tosho.city.kashiwa.lg.jp/homepage/html/02_tanaka.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:33.737460+00:00' + source_url: https://tosho.city.kashiwa.lg.jp/access/tanaka.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tosho.city.kashiwa.lg.jp/img/common/logo.png + source_url: https://tosho.city.kashiwa.lg.jp/access/tanaka.html + css_selector: '#header_logo' + retrieved_on: '2025-12-24T12:39:33.737460+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-KAS-L-KLUT.yaml b/data/custodian/JP-12-KAS-L-KLUT.yaml index 0945ae73bb..a791707c45 100644 --- a/data/custodian/JP-12-KAS-L-KLUT.yaml +++ b/data/custodian/JP-12-KAS-L-KLUT.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAS-L-KLUT - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAS-L-KLUT valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAS-L-KLUT ghcid_numeric: 13843521785978273114 valid_from: '2025-12-06T23:38:53.338452+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Kashiwa Library, the University of Tokyo @@ -204,3 +205,22 @@ location: geonames_id: 1859924 geonames_name: Kashiwa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:47.912619+00:00' + source_url: http://www.lib.u-tokyo.ac.jp/kashiwa + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.u-tokyo.ac.jp/themes/custom/tokyolib/dest/images/favicon/safari-pinned-tab.svg + source_url: http://www.lib.u-tokyo.ac.jp/kashiwa + css_selector: '[document] > html.js > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T12:39:47.912619+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 6 diff --git a/data/custodian/JP-12-KAS-L-LAORIUT.yaml b/data/custodian/JP-12-KAS-L-LAORIUT.yaml index 8944b9f90d..675272f430 100644 --- a/data/custodian/JP-12-KAS-L-LAORIUT.yaml +++ b/data/custodian/JP-12-KAS-L-LAORIUT.yaml @@ -37,20 +37,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAS-L-LAORIUT - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAS-L-LAORIUT valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAS-L-LAORIUT ghcid_numeric: 12010471015594511036 valid_from: '2025-12-06T23:38:53.322868+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Library, Atmosphere and Ocean Research Institute,The University of Tokyo + claim_value: Library, Atmosphere and Ocean Research Institute,The University of + Tokyo source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -101,11 +103,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Library, Atmosphere and Ocean Research Institute,The University of Tokyo + claim_value: Library, Atmosphere and Ocean Research Institute,The University of + Tokyo property_uri: skos:prefLabel provenance: namespace: glam @@ -164,7 +167,8 @@ wikidata_enrichment: wikidata_labels: en: Library, Atmosphere and Ocean Research Institute,The University of Tokyo ja: 東京大学大気海洋研究所図書室 - wikidata_label_en: Library, Atmosphere and Ocean Research Institute,The University of Tokyo + wikidata_label_en: Library, Atmosphere and Ocean Research Institute,The University + of Tokyo wikidata_label_ja: 東京大学大気海洋研究所図書室 wikidata_classification: instance_of: &id004 @@ -204,3 +208,22 @@ location: geonames_id: 1859924 geonames_name: Kashiwa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:39:55.603505+00:00' + source_url: http://www.library.aori.u-tokyo.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.aori.u-tokyo.ac.jp/images/icon/favicon.ico + source_url: http://www.library.aori.u-tokyo.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T12:39:55.603505+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-KAS-L-RUL.yaml b/data/custodian/JP-12-KAS-L-RUL.yaml index bcab5c6ae5..0b98295f5c 100644 --- a/data/custodian/JP-12-KAS-L-RUL.yaml +++ b/data/custodian/JP-12-KAS-L-RUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAS-L-RUL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAS-L-RUL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAS-L-RUL ghcid_numeric: 15935055753999402135 valid_from: '2025-12-06T23:38:54.749125+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Reitaku University Library @@ -190,7 +191,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: https://library.reitaku-u.ac.jp/library/ wikidata_official_website: https://library.reitaku-u.ac.jp/library/ @@ -212,3 +214,22 @@ location: geonames_id: 1859924 geonames_name: Kashiwa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:40:17.177245+00:00' + source_url: https://library.reitaku-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.reitaku-u.ac.jp/opac/images/cyan/favicon.ico + source_url: https://library.reitaku-u.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:40:17.177245+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-KAT-L-IBUL.yaml b/data/custodian/JP-12-KAT-L-IBUL.yaml index 27a6f4fdb9..09304fc779 100644 --- a/data/custodian/JP-12-KAT-L-IBUL.yaml +++ b/data/custodian/JP-12-KAT-L-IBUL.yaml @@ -214,3 +214,28 @@ location: geonames_id: 1859797 geonames_name: Katsura feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:40:23.642110+00:00' + source_url: http://www.budo-u.ac.jp/campuslife/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.budo-u.ac.jp/common/img/apple-touch-icon.png + source_url: http://www.budo-u.ac.jp/campuslife/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:40:23.642110+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.budo-u.ac.jp/common/img/img_ogimg.jpg + source_url: http://www.budo-u.ac.jp/campuslife/library + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T12:40:23.642110+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-KAT-L-KL-katorishiritsuomigawa_library.yaml b/data/custodian/JP-12-KAT-L-KL-katorishiritsuomigawa_library.yaml index a0f3a34883..cc7cc4202f 100644 --- a/data/custodian/JP-12-KAT-L-KL-katorishiritsuomigawa_library.yaml +++ b/data/custodian/JP-12-KAT-L-KL-katorishiritsuomigawa_library.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-katori-chiba.jp/index.html wikidata_official_website: http://www.library-katori-chiba.jp/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:41:01.664447+00:00' + source_url: https://www.katori-kompas.net/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.katori-kompas.net/wp-content/uploads/2022/11/cropped-siteicon-180x180.png + source_url: https://www.katori-kompas.net/library + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-24T12:41:01.664447+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-KAT-L-KL-katorishiritsusawarachuo_library.yaml b/data/custodian/JP-12-KAT-L-KL-katorishiritsusawarachuo_library.yaml index a7e78b8a34..8dfe1dad23 100644 --- a/data/custodian/JP-12-KAT-L-KL-katorishiritsusawarachuo_library.yaml +++ b/data/custodian/JP-12-KAT-L-KL-katorishiritsusawarachuo_library.yaml @@ -199,3 +199,30 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-katori-chiba.jp/index.html wikidata_official_website: http://www.library-katori-chiba.jp/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:41:11.229498+00:00' + source_url: https://www.katori-kompas.net/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.katori-kompas.net/wp-content/themes/kompas/images/mainlogo.svg + source_url: https://www.katori-kompas.net/library + css_selector: '#site-navigation > a.fix-logo > h1.site-title > img' + retrieved_on: '2025-12-24T12:41:11.229498+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: みんなの賑わい交流拠点KOMPAS + - claim_type: favicon_url + claim_value: https://www.katori-kompas.net/wp-content/uploads/2022/11/cropped-siteicon-180x180.png + source_url: https://www.katori-kompas.net/library + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-24T12:41:11.229498+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-KAT-L-KL.yaml b/data/custodian/JP-12-KAT-L-KL.yaml index ef6f62a3c4..b49b95231e 100644 --- a/data/custodian/JP-12-KAT-L-KL.yaml +++ b/data/custodian/JP-12-KAT-L-KL.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: https://www.city.katsuura.lg.jp/forms/info/info.aspx?info_id=29401 wikidata_official_website: https://www.city.katsuura.lg.jp/forms/info/info.aspx?info_id=29401 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:41:19.842240+00:00' + source_url: https://www.city.katsuura.lg.jp/site/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.katsuura.lg.jp/apple-touch-icon.png + source_url: https://www.city.katsuura.lg.jp/site/library + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:41:19.842240+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-KAT-L-TL.yaml b/data/custodian/JP-12-KAT-L-TL.yaml index 5b14538bcd..9dcda15a5c 100644 --- a/data/custodian/JP-12-KAT-L-TL.yaml +++ b/data/custodian/JP-12-KAT-L-TL.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.tohnosho.chiba.jp/003profile/c005/010.html wikidata_official_website: http://www.town.tohnosho.chiba.jp/003profile/c005/010.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:41:27.595848+00:00' + source_url: https://www.town.tohnosho.chiba.jp/soshiki/machitoshokan/gyomu/tonoshomachinoshisetsu/684.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.tohnosho.chiba.jp/theme/base/img_common/pc_header_logo_sub.png + source_url: https://www.town.tohnosho.chiba.jp/soshiki/machitoshokan/gyomu/tonoshomachinoshisetsu/684.html + css_selector: '#header > div.header-subnav-area > p.header-logo > a > img' + retrieved_on: '2025-12-24T12:41:27.595848+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東庄町 Tonosho Town + - claim_type: favicon_url + claim_value: https://www.town.tohnosho.chiba.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.tohnosho.chiba.jp/soshiki/machitoshokan/gyomu/tonoshomachinoshisetsu/684.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:41:27.595848+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.tohnosho.chiba.jp/material/images/group/15/toshokan01.JPG + source_url: https://www.town.tohnosho.chiba.jp/soshiki/machitoshokan/gyomu/tonoshomachinoshisetsu/684.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T12:41:27.595848+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-KAT-M-JCM.yaml b/data/custodian/JP-12-KAT-M-JCM.yaml index 3aee8c8286..e8c0f2e20a 100644 --- a/data/custodian/JP-12-KAT-M-JCM.yaml +++ b/data/custodian/JP-12-KAT-M-JCM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAT-M-JCM - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAT-M-JCM valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAT-M-JCM ghcid_numeric: 16477727423913844558 valid_from: '2025-12-06T23:38:32.825681+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JAPAN CURRENT MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 1859797 geonames_name: Katsura feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:41:51.051518+00:00' + source_url: http://www.rinkaisou.com/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.rinkaisou.com/images/common/favicon.ico + source_url: http://www.rinkaisou.com/museum + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T12:41:51.051518+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-KAT-M-KJT.yaml b/data/custodian/JP-12-KAT-M-KJT.yaml index 300bd207e2..ef885f4600 100644 --- a/data/custodian/JP-12-KAT-M-KJT.yaml +++ b/data/custodian/JP-12-KAT-M-KJT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KAT-M-KJT - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KAT-M-KJT valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KAT-M-KJT ghcid_numeric: 4199667637240736122 valid_from: '2025-12-06T23:38:32.895990+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KATORI-JINGU TREASURY @@ -151,3 +152,28 @@ location: geonames_id: 2112319 geonames_name: Katori-shi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:41:59.585106+00:00' + source_url: https://katori-jingu.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katori-jingu.or.jp/wp/wp-content/uploads/2017/05/cropped-site-icon-180x180.png + source_url: https://katori-jingu.or.jp + css_selector: '[document] > html > head > link:nth-of-type(20)' + retrieved_on: '2025-12-24T12:41:59.585106+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://katori-jingu.or.jp/wp/wp-content/uploads/2017/04/ogimage.jpg + source_url: https://katori-jingu.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T12:41:59.585106+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-KIM-M-KJMK.yaml b/data/custodian/JP-12-KIM-M-KJMK.yaml index 9c7a518351..f43603e1cd 100644 --- a/data/custodian/JP-12-KIM-M-KJMK.yaml +++ b/data/custodian/JP-12-KIM-M-KJMK.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KIM-M-KJMK - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KIM-M-KJMK valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KIM-M-KJMK ghcid_numeric: 1141839505394412503 valid_from: '2025-12-06T23:38:32.858508+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KURURI-JOSHI MUSEUM, KIMITSU @@ -151,3 +152,22 @@ location: geonames_id: 1907307 geonames_name: Kimitsu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:42:46.745431+00:00' + source_url: https://www.city.kimitsu.lg.jp/soshiki/54 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.kimitsu.lg.jp/apple-touch-icon.png + source_url: https://www.city.kimitsu.lg.jp/soshiki/54 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:42:46.745431+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-KIS-L-KL.yaml b/data/custodian/JP-12-KIS-L-KL.yaml index e0da1c848d..0983d7f2b9 100644 --- a/data/custodian/JP-12-KIS-L-KL.yaml +++ b/data/custodian/JP-12-KIS-L-KL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KIS-L-KL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KIS-L-KL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KIS-L-KL ghcid_numeric: 5964095423345742936 valid_from: '2025-12-06T23:38:57.391811+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KISARAZUKOGYOKOTOSEMMONGAKKO Library @@ -151,3 +152,31 @@ location: geonames_id: 1859393 geonames_name: Kisarazu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:42:59.673160+00:00' + source_url: http://www.kisarazu.ac.jp/lib.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.kisarazu.ac.jp/wp-content/themes/2023_kisarazu/img/share/menu_arrow.png + source_url: http://www.kisarazu.ac.jp/lib.html + css_selector: '#header_wrap > nav.hb-menu > div > div.toggle-switch.gaiyo:nth-of-type(2) + > img.menu-logo' + retrieved_on: '2025-12-24T12:42:59.673160+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.kisarazu.ac.jp/wp-content/uploads/2021/01/cropped-symbol-180x180.png + source_url: http://www.kisarazu.ac.jp/lib.html + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-24T12:42:59.673160+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-KIS-L-KPL.yaml b/data/custodian/JP-12-KIS-L-KPL.yaml index a7d197010c..6b1174822c 100644 --- a/data/custodian/JP-12-KIS-L-KPL.yaml +++ b/data/custodian/JP-12-KIS-L-KPL.yaml @@ -202,3 +202,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.kisarazu.chiba.jp/ wikidata_official_website: http://www.lib.kisarazu.chiba.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:43:09.915613+00:00' + source_url: https://www.city.kisarazu.lg.jp/soshiki/kyoikuiinkai/toshokan/1/3957.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.kisarazu.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.kisarazu.lg.jp/soshiki/kyoikuiinkai/toshokan/1/3957.html + css_selector: '#header > div.header-subnav-area > p.header-logo > a > img' + retrieved_on: '2025-12-24T12:43:09.915613+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 木更津市 Kisarazu City + - claim_type: favicon_url + claim_value: https://www.city.kisarazu.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.kisarazu.lg.jp/soshiki/kyoikuiinkai/toshokan/1/3957.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:43:09.915613+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.kisarazu.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.kisarazu.lg.jp/soshiki/kyoikuiinkai/toshokan/1/3957.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T12:43:09.915613+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-KIS-L-SL.yaml b/data/custodian/JP-12-KIS-L-SL.yaml index db7cd8eebc..d817fd3698 100644 --- a/data/custodian/JP-12-KIS-L-SL.yaml +++ b/data/custodian/JP-12-KIS-L-SL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KIS-L-SL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KIS-L-SL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KIS-L-SL ghcid_numeric: 17208127100982548367 valid_from: '2025-12-06T23:38:56.908626+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SEIWADAIGAKUTANKIDAIGAKUBU Library @@ -204,3 +205,31 @@ location: geonames_id: 1859393 geonames_name: Kisarazu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:43:22.541042+00:00' + source_url: http://www.seiwa-jc.ac.jp/about/library.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://seiwa-jc.ac.jp/official/wp-content/themes/seiwa-jc/common/img/logo.png + source_url: http://www.seiwa-jc.ac.jp/about/library.html + css_selector: '[document] > html.no-js > body > div.g-nav:nth-of-type(3) > header.l-header + > div.l-header__inner > h2 > a > img' + retrieved_on: '2025-12-24T12:43:22.541042+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 清和大学短期大学部 + - claim_type: favicon_url + claim_value: https://seiwa-jc.ac.jp/official/wp-content/uploads/2022/11/cropped-favicon-180x180.png + source_url: http://www.seiwa-jc.ac.jp/about/library.html + css_selector: '[document] > html.no-js > head > link:nth-of-type(15)' + retrieved_on: '2025-12-24T12:43:22.541042+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/JP-12-KIS-L-SUL.yaml b/data/custodian/JP-12-KIS-L-SUL.yaml index bd12e1617b..c30689c6b8 100644 --- a/data/custodian/JP-12-KIS-L-SUL.yaml +++ b/data/custodian/JP-12-KIS-L-SUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-KIS-L-SUL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-KIS-L-SUL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-KIS-L-SUL ghcid_numeric: 12870418701374333125 valid_from: '2025-12-06T23:38:54.783634+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Seiwa University Library @@ -204,3 +205,37 @@ location: geonames_id: 1859393 geonames_name: Kisarazu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:43:31.270675+00:00' + source_url: http://www.seiwa-univ.ac.jp/campus/library.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.seiwa-univ.ac.jp/common/img/seiwa_logo_top.png + source_url: http://www.seiwa-univ.ac.jp/campus/library.html + css_selector: '#top > header > div.header > div.header_box > div.seiwa_logo > + a > img' + retrieved_on: '2025-12-24T12:43:31.270675+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 清和大学 + - claim_type: favicon_url + claim_value: http://www.seiwa-univ.ac.jp/common/img/favicon.ico + source_url: http://www.seiwa-univ.ac.jp/campus/library.html + css_selector: '[document] > html.no-js > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T12:43:31.270675+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.seiwa-univ.ac.jp/common/img/sitelogo.png + source_url: http://www.seiwa-univ.ac.jp/campus/library.html + css_selector: '[document] > html.no-js > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T12:43:31.270675+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-KIS-M-KHMKS.yaml b/data/custodian/JP-12-KIS-M-KHMKS.yaml index d11369bc72..359906e670 100644 --- a/data/custodian/JP-12-KIS-M-KHMKS.yaml +++ b/data/custodian/JP-12-KIS-M-KHMKS.yaml @@ -234,3 +234,36 @@ wikidata_enrichment: image: Kisarazu city folk museum Kin no Suzu.jpg commons_category: Kisarazu Hometown Museum Kin-no-Suzu wikidata_image: Kisarazu city folk museum Kin no Suzu.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:43:38.177753+00:00' + source_url: https://www.city.kisarazu.lg.jp/shokai/rekishi/hakubutsukan/1002106.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.kisarazu.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.kisarazu.lg.jp/shokai/rekishi/hakubutsukan/1002106.html + css_selector: '#header > div.header-subnav-area > p.header-logo > a > img' + retrieved_on: '2025-12-24T12:43:38.177753+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 木更津市 Kisarazu City + - claim_type: favicon_url + claim_value: https://www.city.kisarazu.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.kisarazu.lg.jp/shokai/rekishi/hakubutsukan/1002106.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T12:43:38.177753+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.kisarazu.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.kisarazu.lg.jp/shokai/rekishi/hakubutsukan/1002106.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T12:43:38.177753+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-KIT-M-MKMAH.yaml b/data/custodian/JP-12-KIT-M-MKMAH.yaml index 772b835efd..11bae62314 100644 --- a/data/custodian/JP-12-KIT-M-MKMAH.yaml +++ b/data/custodian/JP-12-KIT-M-MKMAH.yaml @@ -422,3 +422,28 @@ location: geonames_id: 11998265 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:32.999818+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:43:48.702485+00:00' + source_url: https://artmuseum.pref.hokkaido.lg.jp/mkb + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://artmuseum.pref.hokkaido.lg.jp/assets/mkb/img/favicon.ico + source_url: https://artmuseum.pref.hokkaido.lg.jp/mkb + css_selector: '[document] > html.js-focus-visible.set-font-s > head > link' + retrieved_on: '2025-12-24T12:43:48.702485+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://artmuseum.pref.hokkaido.lg.jp/assets/mkb/img/ogp.jpg + source_url: https://artmuseum.pref.hokkaido.lg.jp/mkb + css_selector: '[document] > html.js-focus-visible.set-font-s > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T12:43:48.702485+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-KIT-M-NFM.yaml b/data/custodian/JP-12-KIT-M-NFM.yaml index a8ce742675..fbd2684a70 100644 --- a/data/custodian/JP-12-KIT-M-NFM.yaml +++ b/data/custodian/JP-12-KIT-M-NFM.yaml @@ -250,3 +250,22 @@ location: geonames_id: 11762249 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.035938+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:43:56.513257+00:00' + source_url: https://www.nakashibetsu.jp/kyoudokan_web/index.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nakashibetsu.jp/image/favicon.ico + source_url: https://www.nakashibetsu.jp/kyoudokan_web/index.htm + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:43:56.513257+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-MAT-L-CPWL.yaml b/data/custodian/JP-12-MAT-L-CPWL.yaml index 2d9e986aff..d25131702a 100644 --- a/data/custodian/JP-12-MAT-L-CPWL.yaml +++ b/data/custodian/JP-12-MAT-L-CPWL.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-MAT-L-CPWL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-MAT-L-CPWL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-MAT-L-CPWL ghcid_numeric: 5960678338951155084 valid_from: '2025-12-06T23:38:42.754571+00:00' @@ -265,3 +266,22 @@ location: postal_code: 270-2252 street_address: 657-7 SENDABORI, Matsudo Shi, Chiba Ken, 270-2252 normalization_timestamp: '2025-12-09T10:55:31.321132+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:44:08.385759+00:00' + source_url: https://www.library.pref.chiba.lg.jp/guide/west/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.pref.chiba.lg.jp/apple-touch-icon.png + source_url: https://www.library.pref.chiba.lg.jp/guide/west/index.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T12:44:08.385759+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-MAT-L-KHCLRICTSU.yaml b/data/custodian/JP-12-MAT-L-KHCLRICTSU.yaml index 08d4afd0b2..e297a600f9 100644 --- a/data/custodian/JP-12-MAT-L-KHCLRICTSU.yaml +++ b/data/custodian/JP-12-MAT-L-KHCLRICTSU.yaml @@ -225,3 +225,22 @@ location: geonames_id: 1857553 geonames_name: Matsudo feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T12:44:16.637387+00:00' + source_url: http://www.seitoku.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.seitoku.jp/favicon.ico + source_url: http://www.seitoku.jp/lib + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T12:44:16.637387+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-MAT-L-RL.yaml b/data/custodian/JP-12-MAT-L-RL.yaml index 6e567eaf83..6ffd920744 100644 --- a/data/custodian/JP-12-MAT-L-RL.yaml +++ b/data/custodian/JP-12-MAT-L-RL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-MAT-L-RL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-MAT-L-RL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-MAT-L-RL ghcid_numeric: 7583295114507096408 valid_from: '2025-12-06T23:38:54.517602+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: RYUTSUKEIZAIDAIGAKUSHIMMATSUDO Library @@ -204,3 +205,28 @@ location: geonames_id: 1857553 geonames_name: Matsudo feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:11:55.975374+00:00' + source_url: http://www.rku.ac.jp/campuslife/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rku.ac.jp/favicon.ico + source_url: http://www.rku.ac.jp/campuslife/library + css_selector: '[document] > html > body > div.wrapper > link:nth-of-type(21)' + retrieved_on: '2025-12-24T13:11:55.975374+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.rku.ac.jp/assets/img/ogp_img.png + source_url: http://www.rku.ac.jp/campuslife/library + css_selector: '[document] > html > body > div.wrapper > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T13:11:55.975374+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-MIN-L-ECL.yaml b/data/custodian/JP-12-MIN-L-ECL.yaml index ce1df0b88e..bce2ba399d 100644 --- a/data/custodian/JP-12-MIN-L-ECL.yaml +++ b/data/custodian/JP-12-MIN-L-ECL.yaml @@ -374,3 +374,22 @@ location: geonames_id: 9100951 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.077878+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:38:39.726294+00:00' + source_url: https://eniwa-library.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://eniwa-library.jp/wp/wp-content/themes/eniwalib/images/favicon.ico + source_url: https://eniwa-library.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T13:38:39.726294+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-MIN-L-ML.yaml b/data/custodian/JP-12-MIN-L-ML.yaml index a42a97dcb4..f4cdadeef5 100644 --- a/data/custodian/JP-12-MIN-L-ML.yaml +++ b/data/custodian/JP-12-MIN-L-ML.yaml @@ -204,3 +204,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.minamiboso.chiba.jp/0000000999.html wikidata_official_website: http://www.city.minamiboso.chiba.jp/0000000999.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:38:47.753444+00:00' + source_url: https://www.city.minamiboso.chiba.jp/0000007208.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.minamiboso.chiba.jp/design_img/favicon.ico + source_url: https://www.city.minamiboso.chiba.jp/0000007208.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T13:38:47.753444+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.minamiboso.chiba.jp/design_img/ + source_url: https://www.city.minamiboso.chiba.jp/0000007208.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T13:38:47.753444+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-MIN-M-ACDM.yaml b/data/custodian/JP-12-MIN-M-ACDM.yaml index 135a153154..41483d9b58 100644 --- a/data/custodian/JP-12-MIN-M-ACDM.yaml +++ b/data/custodian/JP-12-MIN-M-ACDM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-MIN-M-ACDM - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-MIN-M-ACDM valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-MIN-M-ACDM ghcid_numeric: 11973276659324304716 valid_from: '2025-12-06T23:38:32.889143+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ADMINISTRATION CENTER OF DAILY MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 11612454 geonames_name: Minamibōsō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:38:58.460650+00:00' + source_url: https://www.e-makiba.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.e-makiba.jp/favicon.ico + source_url: https://www.e-makiba.jp + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T13:38:58.460650+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-MIN-M-AMA.yaml b/data/custodian/JP-12-MIN-M-AMA.yaml index 1893efa3a2..2cb1882448 100644 --- a/data/custodian/JP-12-MIN-M-AMA.yaml +++ b/data/custodian/JP-12-MIN-M-AMA.yaml @@ -280,3 +280,22 @@ location: geonames_id: 11708936 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.114905+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:39:06.729717+00:00' + source_url: https://www.city.abashiri.hokkaido.jp/270kyoiku/040bizyutukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.abashiri.hokkaido.jp/apple-touch-icon.png + source_url: https://www.city.abashiri.hokkaido.jp/270kyoiku/040bizyutukan + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T13:39:06.729717+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-MOB-L-MPL.yaml b/data/custodian/JP-12-MOB-L-MPL.yaml index fb91cac651..97e7604acd 100644 --- a/data/custodian/JP-12-MOB-L-MPL.yaml +++ b/data/custodian/JP-12-MOB-L-MPL.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-MOB-L-MPL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-MOB-L-MPL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-MOB-L-MPL ghcid_numeric: 8522062983134635212 valid_from: '2025-12-06T23:38:42.879742+00:00' @@ -243,3 +244,22 @@ location: postal_code: 297-0023 street_address: 1-6-1 CHIYODACHO, Mobara Shi, Chiba Ken, 297-0023 normalization_timestamp: '2025-12-09T10:55:31.972369+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T13:40:06.711160+00:00' + source_url: https://opac.library-mobara.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://opac.library-mobara.jp/favicon.ico + source_url: https://opac.library-mobara.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T13:40:06.711160+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-MOB-M-MCMALH.yaml b/data/custodian/JP-12-MOB-M-MCMALH.yaml index ba0d704efd..1745cf8788 100644 --- a/data/custodian/JP-12-MOB-M-MCMALH.yaml +++ b/data/custodian/JP-12-MOB-M-MCMALH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-MOB-M-MCMALH - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-MOB-M-MCMALH valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-MOB-M-MCMALH ghcid_numeric: 1415989521839558788 valid_from: '2025-12-06T23:38:32.775730+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MOBARA CITY MUSEUM OF ART&LOCAL HISTORY @@ -151,3 +152,37 @@ location: geonames_id: 2111855 geonames_name: Mobara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:03:11.725650+00:00' + source_url: https://www.city.mobara.chiba.jp/soshiki/13-10-0-0-0_1.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.mobara.chiba.jp/css/img/head_logo_cach.png + source_url: https://www.city.mobara.chiba.jp/soshiki/13-10-0-0-0_1.html + css_selector: '#body > div.all:nth-of-type(2) > div.design > header.main_header + > div.head > div.h_top_wrap > div.head_in > div.h_main > p.h1_catch > img' + retrieved_on: '2025-12-24T14:03:11.725650+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 未来へつながる 交流拠点都市 もばら + - claim_type: favicon_url + claim_value: https://www.city.mobara.chiba.jp/soshiki/css/img/apple-touch-icon.png + source_url: https://www.city.mobara.chiba.jp/soshiki/13-10-0-0-0_1.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T14:03:11.725650+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.city.mobara.chiba.jp/design_img/og_image.jpeg + source_url: https://www.city.mobara.chiba.jp/soshiki/13-10-0-0-0_1.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T14:03:11.725650+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-MOI-M-SSM.yaml b/data/custodian/JP-12-MOI-M-SSM.yaml index ff3101882b..801bcd8938 100644 --- a/data/custodian/JP-12-MOI-M-SSM.yaml +++ b/data/custodian/JP-12-MOI-M-SSM.yaml @@ -425,3 +425,22 @@ location: geonames_id: 2129176 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.240635+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:03:19.710649+00:00' + source_url: https://salmon-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://salmon-museum.jp/apple-touch-icon-180x180.png + source_url: https://salmon-museum.jp + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T14:03:19.710649+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-12-MOM-M-MMM.yaml b/data/custodian/JP-12-MOM-M-MMM.yaml index 03e2d3005f..5ee4d40b78 100644 --- a/data/custodian/JP-12-MOM-M-MMM.yaml +++ b/data/custodian/JP-12-MOM-M-MMM.yaml @@ -414,3 +414,28 @@ location: geonames_id: 2129163 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.287105+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:03:27.871735+00:00' + source_url: https://mombetsu.jp/sisetu/bunkasisetu/hakubutukan/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mombetsu.jp/sisetu/bunkasisetu/apple-touch-icon.png + source_url: https://mombetsu.jp/sisetu/bunkasisetu/hakubutukan/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T14:03:27.871735+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://mombetsu.jp/assets/images/og-image.jpg + source_url: https://mombetsu.jp/sisetu/bunkasisetu/hakubutukan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T14:03:27.871735+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-NAG-L-EL.yaml b/data/custodian/JP-12-NAG-L-EL.yaml index e9c4cfeea1..2d3e863d89 100644 --- a/data/custodian/JP-12-NAG-L-EL.yaml +++ b/data/custodian/JP-12-NAG-L-EL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-NAG-L-EL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-NAG-L-EL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-NAG-L-EL ghcid_numeric: 668460323840982243 valid_from: '2025-12-06T23:38:54.778561+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: EDOGAWADAIGAKUSOGOJOHO Library @@ -196,7 +197,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.edogawa-u.ac.jp/facility/library/ wikidata_official_website: http://www.edogawa-u.ac.jp/facility/library/ @@ -218,3 +220,36 @@ location: geonames_id: 1856184 geonames_name: Nagareyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:03:38.022932+00:00' + source_url: http://www.edogawa-u.ac.jp/facility/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.edogawa-u.ac.jp/img/head/logo2021.svg + source_url: http://www.edogawa-u.ac.jp/facility/library + css_selector: '#header-pc-2021 > div > a.logo > img' + retrieved_on: '2025-12-24T14:03:38.022932+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 江戸川大学 + - claim_type: favicon_url + claim_value: http://www.edogawa-u.ac.jp/img/icon/152.png + source_url: http://www.edogawa-u.ac.jp/facility/library + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T14:03:38.022932+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 152x152 + - claim_type: og_image_url + claim_value: https://www.edogawa-u.ac.jp/img/icon/OGP.png + source_url: http://www.edogawa-u.ac.jp/facility/library + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T14:03:38.022932+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 8 diff --git a/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsukino_library.yaml b/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsukino_library.yaml index 7619189193..ab81e0d0b8 100644 --- a/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsukino_library.yaml +++ b/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsukino_library.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.subaru-shoten.co.jp/tosho/ki/index.html wikidata_official_website: http://www.subaru-shoten.co.jp/tosho/ki/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:03:46.221517+00:00' + source_url: https://www.subaru-shoten.co.jp/tosho/ki/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.subaru-shoten.co.jp/tosho/ki/favicon.ico + source_url: https://www.subaru-shoten.co.jp/tosho/ki/index.html + css_selector: '[document] > html.bg-img-ki > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T14:03:46.221517+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsuminaminagareyamachiiki_library.yaml b/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsuminaminagareyamachiiki_library.yaml index 3d3ea32f74..20d5e81f77 100644 --- a/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsuminaminagareyamachiiki_library.yaml +++ b/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsuminaminagareyamachiiki_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-city-nagareyama.jp/ wikidata_official_website: http://www.library-city-nagareyama.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:03:54.391511+00:00' + source_url: https://www.subaru-shoten.co.jp/tosho/minami + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.subaru-shoten.co.jp/tosho/minami/favicon.ico + source_url: https://www.subaru-shoten.co.jp/tosho/minami + css_selector: '[document] > html.bg-img-minami > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T14:03:54.391511+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsumorino_library.yaml b/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsumorino_library.yaml index 35fd02b8c7..e18a2ff001 100644 --- a/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsumorino_library.yaml +++ b/data/custodian/JP-12-NAG-L-NL-nagareyamashiritsumorino_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.subaru-shoten.co.jp/tosho/mori/ wikidata_official_website: http://www.subaru-shoten.co.jp/tosho/mori/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:04:02.244749+00:00' + source_url: https://www.subaru-shoten.co.jp/tosho/mori + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.subaru-shoten.co.jp/tosho/mori/favicon.ico + source_url: https://www.subaru-shoten.co.jp/tosho/mori + css_selector: '[document] > html.bg-img-mori > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T14:04:02.244749+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NAG-L-NL.yaml b/data/custodian/JP-12-NAG-L-NL.yaml index bb57147084..ae0d597ed6 100644 --- a/data/custodian/JP-12-NAG-L-NL.yaml +++ b/data/custodian/JP-12-NAG-L-NL.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-city-nagareyama.jp/index.html wikidata_official_website: http://www.library-city-nagareyama.jp/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:04:10.622126+00:00' + source_url: https://www.library-city-nagareyama.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library-city-nagareyama.jp/contents/wp-content/uploads/2023/09/favicon.png + source_url: https://www.library-city-nagareyama.jp + css_selector: '[document] > html > body > link:nth-of-type(8)' + retrieved_on: '2025-12-24T14:04:10.622126+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NAG-L-NLH-nagareyamashiritsuchuo_library_hokububunkan.yaml b/data/custodian/JP-12-NAG-L-NLH-nagareyamashiritsuchuo_library_hokububunkan.yaml index 748156cda9..66ee2e321e 100644 --- a/data/custodian/JP-12-NAG-L-NLH-nagareyamashiritsuchuo_library_hokububunkan.yaml +++ b/data/custodian/JP-12-NAG-L-NLH-nagareyamashiritsuchuo_library_hokububunkan.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-city-nagareyama.jp/ wikidata_official_website: http://www.library-city-nagareyama.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:04:17.804125+00:00' + source_url: https://www.library-city-nagareyama.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library-city-nagareyama.jp/contents/wp-content/uploads/2023/09/favicon.png + source_url: https://www.library-city-nagareyama.jp + css_selector: '[document] > html > body > link:nth-of-type(8)' + retrieved_on: '2025-12-24T14:04:17.804125+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NAG-L-NLH.yaml b/data/custodian/JP-12-NAG-L-NLH.yaml index c22457c3ce..dfa76a2645 100644 --- a/data/custodian/JP-12-NAG-L-NLH.yaml +++ b/data/custodian/JP-12-NAG-L-NLH.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-city-nagareyama.jp/ wikidata_official_website: http://www.library-city-nagareyama.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T14:04:25.868441+00:00' + source_url: https://www.library-city-nagareyama.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library-city-nagareyama.jp/contents/wp-content/uploads/2023/09/favicon.png + source_url: https://www.library-city-nagareyama.jp + css_selector: '[document] > html > body > link:nth-of-type(8)' + retrieved_on: '2025-12-24T14:04:25.868441+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NAR-L-CLSL.yaml b/data/custodian/JP-12-NAR-L-CLSL.yaml index 07b21b55c3..54bbdf148a 100644 --- a/data/custodian/JP-12-NAR-L-CLSL.yaml +++ b/data/custodian/JP-12-NAR-L-CLSL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-NAR-L-CLSL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-NAR-L-CLSL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-NAR-L-CLSL ghcid_numeric: 9482632451819839239 valid_from: '2025-12-06T23:38:54.741629+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: CHIBAKOGYODAIGAKUFUZOKU Library SHINNARASHINO Library @@ -204,3 +205,28 @@ location: geonames_id: 11612347 geonames_name: Narashino feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T16:57:41.402000+00:00' + source_url: http://www.it-chiba.ac.jp/library/shinnarashino + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.it-chiba.ac.jp/favicon.ico + source_url: http://www.it-chiba.ac.jp/library/shinnarashino + css_selector: '[document] > html.lenis > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T16:57:41.402000+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: any + - claim_type: og_image_url + claim_value: https://chibatech.jp/dl53f300000000fd-img/dl53f300000000fk.png + source_url: http://www.it-chiba.ac.jp/library/shinnarashino + css_selector: '[document] > html.lenis > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T16:57:41.402000+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-NAR-L-CLTL.yaml b/data/custodian/JP-12-NAR-L-CLTL.yaml index 28f3eb6e4f..ee5e9b713e 100644 --- a/data/custodian/JP-12-NAR-L-CLTL.yaml +++ b/data/custodian/JP-12-NAR-L-CLTL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-NAR-L-CLTL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-NAR-L-CLTL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-NAR-L-CLTL ghcid_numeric: 13675224082747507244 valid_from: '2025-12-06T23:38:59.733177+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: CHIBAKOGYODAIGAKUFUZOKU Library TSUDANUMA Library @@ -204,3 +205,28 @@ location: geonames_id: 11612347 geonames_name: Narashino feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T16:57:50.865907+00:00' + source_url: http://www.it-chiba.ac.jp/library/tsudanuma + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.it-chiba.ac.jp/favicon.ico + source_url: http://www.it-chiba.ac.jp/library/tsudanuma + css_selector: '[document] > html.lenis > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T16:57:50.865907+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: any + - claim_type: og_image_url + claim_value: https://chibatech.jp/dl53f300000000fd-img/dl53f300000000fk.png + source_url: http://www.it-chiba.ac.jp/library/tsudanuma + css_selector: '[document] > html.lenis > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T16:57:50.865907+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-NAR-L-NL-narashinoshiritsuhigashinarashino_library.yaml b/data/custodian/JP-12-NAR-L-NL-narashinoshiritsuhigashinarashino_library.yaml index 7716ffe93a..e0af5841a6 100644 --- a/data/custodian/JP-12-NAR-L-NL-narashinoshiritsuhigashinarashino_library.yaml +++ b/data/custodian/JP-12-NAR-L-NL-narashinoshiritsuhigashinarashino_library.yaml @@ -204,3 +204,36 @@ wikidata_enrichment: wikidata_web: official_website: https://www.city.narashino.lg.jp/shisetu/toshokan/higashinarashino.html wikidata_official_website: https://www.city.narashino.lg.jp/shisetu/toshokan/higashinarashino.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T20:17:05.129769+00:00' + source_url: https://www.city.narashino.lg.jp/shisetu/toshokan/higashinarashino.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.narashino.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.narashino.lg.jp/shisetu/toshokan/higashinarashino.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-24T20:17:05.129769+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 習志野市 Narashino City + - claim_type: favicon_url + claim_value: https://www.city.narashino.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.narashino.lg.jp/shisetu/toshokan/higashinarashino.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T20:17:05.129769+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.narashino.lg.jp/material/images/group/10/tounara-gaikan.JPG + source_url: https://www.city.narashino.lg.jp/shisetu/toshokan/higashinarashino.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T20:17:05.129769+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-NAR-M-NRM.yaml b/data/custodian/JP-12-NAR-M-NRM.yaml index 8710de6abe..6d842e5877 100644 --- a/data/custodian/JP-12-NAR-M-NRM.yaml +++ b/data/custodian/JP-12-NAR-M-NRM.yaml @@ -231,3 +231,28 @@ location: postal_code: 286-0021 street_address: TSUCHIYA, Narita Shi, Chiba Ken, 286-0021 normalization_timestamp: '2025-12-09T10:55:32.841913+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:18.580005+00:00' + source_url: https://maruchiba.jp/sys/data/index/page/id/8938 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://maruchiba.jp/common/images/favicon.svg + source_url: https://maruchiba.jp/sys/data/index/page/id/8938 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:08:18.580005+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://maruchiba.jp/common/images/ogImg.png + source_url: https://maruchiba.jp/sys/data/index/page/id/8938 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T21:08:18.580005+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-NAR-M-NYM.yaml b/data/custodian/JP-12-NAR-M-NYM.yaml index df0deeaed5..93fcb396d7 100644 --- a/data/custodian/JP-12-NAR-M-NYM.yaml +++ b/data/custodian/JP-12-NAR-M-NYM.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-NAR-M-NYM - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-NAR-M-NYM valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-NAR-M-NYM ghcid_numeric: 17061860748203315824 valid_from: '2025-12-06T23:38:32.786952+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NARITA YOUKAN MUSEUM @@ -233,3 +234,22 @@ location: geonames_id: 2111684 geonames_name: Narita feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:28.633161+00:00' + source_url: https://nagomi-yoneya.co.jp/youkanshiryoukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nagomi-yoneya.co.jp/wp2021/wp-content/themes/yoneya2021-themes/img/favicon-sp.png + source_url: https://nagomi-yoneya.co.jp/youkanshiryoukan + css_selector: '[document] > html > head > link:nth-of-type(31)' + retrieved_on: '2025-12-24T21:08:28.633161+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-NAY-M-NO.yaml b/data/custodian/JP-12-NAY-M-NO.yaml index ce82017709..77159de2c2 100644 --- a/data/custodian/JP-12-NAY-M-NO.yaml +++ b/data/custodian/JP-12-NAY-M-NO.yaml @@ -1390,3 +1390,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/R5suQ0Mw8UQ/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:37.692450+00:00' + source_url: https://www.nayoro-star.jp/kitasubaru + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nayoro-star.jp/images/favicon.ico + source_url: https://www.nayoro-star.jp/kitasubaru + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:08:37.692450+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://nayoro-star.jp/kitasubaru/slider/toppic.jpg + source_url: https://www.nayoro-star.jp/kitasubaru + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T21:08:37.692450+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-NOB-M-NBP.yaml b/data/custodian/JP-12-NOB-M-NBP.yaml index f470b87a91..87be9d39fd 100644 --- a/data/custodian/JP-12-NOB-M-NBP.yaml +++ b/data/custodian/JP-12-NOB-M-NBP.yaml @@ -2252,3 +2252,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/iT-cW8oBJdE/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:08:51.450364+00:00' + source_url: https://bearpark.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bearpark.jp/favicon.ico + source_url: https://bearpark.jp + css_selector: '#arve > head > link' + retrieved_on: '2025-12-24T21:08:51.450364+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NOD-L-NL-nodashiritsukita_library.yaml b/data/custodian/JP-12-NOD-L-NL-nodashiritsukita_library.yaml index a5467e453c..8469c2b017 100644 --- a/data/custodian/JP-12-NOD-L-NL-nodashiritsukita_library.yaml +++ b/data/custodian/JP-12-NOD-L-NL-nodashiritsukita_library.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-noda.jp/ wikidata_official_website: http://www.library-noda.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:02.318105+00:00' + source_url: https://www.library-noda.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library-noda.jp/favicon.ico + source_url: https://www.library-noda.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:09:02.318105+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NOD-L-NL-nodashiritsuminami_library.yaml b/data/custodian/JP-12-NOD-L-NL-nodashiritsuminami_library.yaml index 8a0d722419..faf40d59e0 100644 --- a/data/custodian/JP-12-NOD-L-NL-nodashiritsuminami_library.yaml +++ b/data/custodian/JP-12-NOD-L-NL-nodashiritsuminami_library.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-noda.jp/ wikidata_official_website: http://www.library-noda.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:08.739750+00:00' + source_url: https://www.library-noda.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library-noda.jp/favicon.ico + source_url: https://www.library-noda.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:09:08.739750+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NOD-L-NL-nodashiritsusekiyado_library.yaml b/data/custodian/JP-12-NOD-L-NL-nodashiritsusekiyado_library.yaml index dfd59dd27f..ccabf8480f 100644 --- a/data/custodian/JP-12-NOD-L-NL-nodashiritsusekiyado_library.yaml +++ b/data/custodian/JP-12-NOD-L-NL-nodashiritsusekiyado_library.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-noda.jp wikidata_official_website: http://www.library-noda.jp +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:16.627352+00:00' + source_url: https://www.library-noda.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library-noda.jp/favicon.ico + source_url: https://www.library-noda.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:09:16.627352+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NOD-L-NL.yaml b/data/custodian/JP-12-NOD-L-NL.yaml index 1eb2abc921..e2dc7c405f 100644 --- a/data/custodian/JP-12-NOD-L-NL.yaml +++ b/data/custodian/JP-12-NOD-L-NL.yaml @@ -210,3 +210,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library-noda.jp/ wikidata_official_website: http://www.library-noda.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:23.475828+00:00' + source_url: https://www.library-noda.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library-noda.jp/favicon.ico + source_url: https://www.library-noda.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:09:23.475828+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NOD-M-CPSJM.yaml b/data/custodian/JP-12-NOD-M-CPSJM.yaml index 1176921ed9..a539058eaf 100644 --- a/data/custodian/JP-12-NOD-M-CPSJM.yaml +++ b/data/custodian/JP-12-NOD-M-CPSJM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-NOD-M-CPSJM - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-NOD-M-CPSJM valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-NOD-M-CPSJM ghcid_numeric: 2726450885275010481 valid_from: '2025-12-06T23:38:32.759478+00:00' @@ -263,3 +264,22 @@ location: postal_code: 270-0201 street_address: SEKIYADO SANGENYA, Noda Shi, Chiba Ken, 270-0201 normalization_timestamp: '2025-12-09T10:55:33.030069+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:36.554098+00:00' + source_url: http://www2.chiba-muse.or.jp/www/SEKIYADO + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.chiba-muse.or.jp/cms/wp-content/themes/chibamuse_portal/img/common/favicon.ico + source_url: http://www2.chiba-muse.or.jp/www/SEKIYADO + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:09:36.554098+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-NOD-M-IKM.yaml b/data/custodian/JP-12-NOD-M-IKM.yaml index aebde72864..d270f17e15 100644 --- a/data/custodian/JP-12-NOD-M-IKM.yaml +++ b/data/custodian/JP-12-NOD-M-IKM.yaml @@ -247,3 +247,28 @@ location: postal_code: 278-0033 street_address: KAMIHANAWA, Noda Shi, Chiba Ken, 278-0033 normalization_timestamp: '2025-12-09T10:55:33.056807+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:45.178346+00:00' + source_url: https://kamihanawa.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kamihanawa.jp/wp-content/uploads/2018/04/cropped-Logo-180x180.jpg + source_url: https://kamihanawa.jp + css_selector: '[document] > html > head > link:nth-of-type(28)' + retrieved_on: '2025-12-24T21:09:45.178346+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://kamihanawa.jp/wp-content/themes/xwrite/assets/img/ogp.png + source_url: https://kamihanawa.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:09:45.178346+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-12-NOD-M-MHMA.yaml b/data/custodian/JP-12-NOD-M-MHMA.yaml index 9a73bd6d1a..75ded8b273 100644 --- a/data/custodian/JP-12-NOD-M-MHMA.yaml +++ b/data/custodian/JP-12-NOD-M-MHMA.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-NOD-M-MHMA - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-NOD-M-MHMA valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-NOD-M-MHMA ghcid_numeric: 14043069007085043925 valid_from: '2025-12-06T23:38:32.770742+00:00' @@ -243,3 +244,28 @@ location: postal_code: 278-0037 street_address: NODA, Noda Shi, Chiba Ken, 278-0037 normalization_timestamp: '2025-12-09T10:55:33.095798+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:09:55.224167+00:00' + source_url: https://www.momoa.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.momoa.jp/momoa_wp/wp-content/themes/mogihonkebijutukan/assets/img/common/apple-touch-icon.png + source_url: https://www.momoa.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:09:55.224167+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.momoa.jp/momoa_wp/wp-content/themes/mogihonkebijutukan/assets/img/common/og_img.jpg + source_url: https://www.momoa.jp + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T21:09:55.224167+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-NOD-M-NCM.yaml b/data/custodian/JP-12-NOD-M-NCM.yaml index 854047a1b2..ec50688c6e 100644 --- a/data/custodian/JP-12-NOD-M-NCM.yaml +++ b/data/custodian/JP-12-NOD-M-NCM.yaml @@ -267,3 +267,22 @@ location: postal_code: 278-0037 street_address: NODA, Noda Shi, Chiba Ken, 278-0037 normalization_timestamp: '2025-12-09T10:55:33.127975+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:10:04.097209+00:00' + source_url: https://www.noda-muse.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://noda-muse.jp/sys22/wp-content/uploads/2020/04/cropped-icon-180x180.png + source_url: https://www.noda-muse.jp + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:10:04.097209+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-NOP-L-HROEGRDIES.yaml b/data/custodian/JP-12-NOP-L-HROEGRDIES.yaml index 46df3e5ed0..e616f75320 100644 --- a/data/custodian/JP-12-NOP-L-HROEGRDIES.yaml +++ b/data/custodian/JP-12-NOP-L-HROEGRDIES.yaml @@ -243,3 +243,29 @@ location: geonames_id: 2128871 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.433774+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:10:21.086790+00:00' + source_url: http://www.hro.or.jp/list/environmental/research/ies/katsudo/kankyo_joho/jouhoushiryou.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.hro.or.jp/images/logo@0.5x.png + source_url: http://www.hro.or.jp/list/environmental/research/ies/katsudo/kankyo_joho/jouhoushiryou.html + css_selector: '#corp-hq > header > div.header-content.container:nth-of-type(2) + > a.header-logo > h1 > img' + retrieved_on: '2025-12-24T21:10:21.086790+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 地方独立行政法人 北海道立総合研究機構(道総研) + - claim_type: og_image_url + claim_value: https://www.hro.or.jp/logo_ogp.png + source_url: http://www.hro.or.jp/list/environmental/research/ies/katsudo/kankyo_joho/jouhoushiryou.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T21:10:21.086790+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-NOP-M-ECAC.yaml b/data/custodian/JP-12-NOP-M-ECAC.yaml index 476c5dd115..9f6ad6dc19 100644 --- a/data/custodian/JP-12-NOP-M-ECAC.yaml +++ b/data/custodian/JP-12-NOP-M-ECAC.yaml @@ -243,3 +243,22 @@ location: geonames_id: 2128871 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.456114+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:10:33.893640+00:00' + source_url: https://www.city.ebetsu.hokkaido.jp/site/ceramic + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.ebetsu.hokkaido.jp/favicon.png + source_url: https://www.city.ebetsu.hokkaido.jp/site/ceramic + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:10:33.893640+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-OHM-M-APM.yaml b/data/custodian/JP-12-OHM-M-APM.yaml index 1259e797ce..9793a2c282 100644 --- a/data/custodian/JP-12-OHM-M-APM.yaml +++ b/data/custodian/JP-12-OHM-M-APM.yaml @@ -294,3 +294,22 @@ location: geonames_id: 2128689 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.512063+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:12:40.520284+00:00' + source_url: https://www.kangoku.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kangoku.jp/images/favicons/apple-touch-icon-144x144.png + source_url: https://www.kangoku.jp + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-24T21:12:40.520284+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 144x144 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 6 diff --git a/data/custodian/JP-12-OTA-M-OCMA.yaml b/data/custodian/JP-12-OTA-M-OCMA.yaml index 6b1da393f8..b0546de777 100644 --- a/data/custodian/JP-12-OTA-M-OCMA.yaml +++ b/data/custodian/JP-12-OTA-M-OCMA.yaml @@ -266,3 +266,28 @@ location: geonames_id: 2128574 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:33.541067+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:22:59.299752+00:00' + source_url: https://www.city.otaru.lg.jp/soshiki/kyoiku/bijutukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.otaru.lg.jp/_themes/images/favicon.ico + source_url: https://www.city.otaru.lg.jp/soshiki/kyoiku/bijutukan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:22:59.299752+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.otaru.lg.jp/banner/top-20210322.jpg + source_url: https://www.city.otaru.lg.jp/soshiki/kyoiku/bijutukan + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T21:22:59.299752+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-SAI-M-PMH.yaml b/data/custodian/JP-12-SAI-M-PMH.yaml index 3a5fbbfe54..5e084b0f40 100644 --- a/data/custodian/JP-12-SAI-M-PMH.yaml +++ b/data/custodian/JP-12-SAI-M-PMH.yaml @@ -261,3 +261,20 @@ location: geonames_id: 11681103 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.563724+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:23:23.719236+00:00' + source_url: http://www.npo-pierson.org + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://bdflashinfo/thumbnail.png + source_url: http://www.npo-pierson.org + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T21:23:23.719236+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-SAK-L-K.yaml b/data/custodian/JP-12-SAK-L-K.yaml index 6cf59c17ce..977bd6819c 100644 --- a/data/custodian/JP-12-SAK-L-K.yaml +++ b/data/custodian/JP-12-SAK-L-K.yaml @@ -205,3 +205,28 @@ location: geonames_id: 2111220 geonames_name: Sakura feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:23:38.208543+00:00' + source_url: http://www.u-keiai.ac.jp/kulir + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.u-keiai.ac.jp/common/image/app-icon.png + source_url: http://www.u-keiai.ac.jp/kulir + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:23:38.208543+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.u-keiai.ac.jp/common/image/sns-icon.jpg + source_url: http://www.u-keiai.ac.jp/kulir + css_selector: '[document] > html.js > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-24T21:23:38.208543+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SAK-M-HSFR.yaml b/data/custodian/JP-12-SAK-M-HSFR.yaml index 7f4eb8ae68..cc7aca6fb7 100644 --- a/data/custodian/JP-12-SAK-M-HSFR.yaml +++ b/data/custodian/JP-12-SAK-M-HSFR.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-SAK-M-HSFR - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-SAK-M-HSFR valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-SAK-M-HSFR ghcid_numeric: 8753106592756896249 valid_from: '2025-12-06T23:38:32.803928+00:00' @@ -245,3 +246,28 @@ location: postal_code: 285-0025 street_address: KABURAGIMACHI, Sakura Shi, Chiba Ken, 285-0025 normalization_timestamp: '2025-12-09T10:55:33.388047+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:11.235513+00:00' + source_url: http://www.city.sakura.lg.jp/0000000627.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sakura.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.sakura.lg.jp/0000000627.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:24:11.235513+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.sakura.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.sakura.lg.jp/0000000627.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T21:24:11.235513+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SAK-M-KMDMA.yaml b/data/custodian/JP-12-SAK-M-KMDMA.yaml index 06f7f8a6bc..b29f0d3d3b 100644 --- a/data/custodian/JP-12-SAK-M-KMDMA.yaml +++ b/data/custodian/JP-12-SAK-M-KMDMA.yaml @@ -286,3 +286,28 @@ wikidata_enrichment: - id: Q11559121 label: Ichirō Ebihara description: Japanese architect (1905-1990) +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:18.013354+00:00' + source_url: https://kawamura-museum.dic.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kawamura-museum.dic.co.jp/application/files/5515/4886/2181/apple-touch-icon.png + source_url: https://kawamura-museum.dic.co.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:24:18.013354+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://kawamura-museum.dic.co.jp/application/files/2215/4886/1377/ogp.png + source_url: https://kawamura-museum.dic.co.jp + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T21:24:18.013354+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SAK-M-NMJH.yaml b/data/custodian/JP-12-SAK-M-NMJH.yaml index a53e9a215a..41395b4323 100644 --- a/data/custodian/JP-12-SAK-M-NMJH.yaml +++ b/data/custodian/JP-12-SAK-M-NMJH.yaml @@ -343,3 +343,28 @@ wikidata_enrichment: - id: Q3572675 label: Yoshinobu Ashihara description: Japanese architect (1918-2003) +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:34.101853+00:00' + source_url: https://www.rekihaku.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rekihaku.ac.jp/favicon.ico?v=76310c28a8aa0818e27f6508f1a0ead3 + source_url: https://www.rekihaku.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T21:24:34.101853+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.rekihaku.ac.jp/og.png + source_url: https://www.rekihaku.ac.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:24:34.101853+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-SAK-M-TMA.yaml b/data/custodian/JP-12-SAK-M-TMA.yaml index fe659470fa..d732030509 100644 --- a/data/custodian/JP-12-SAK-M-TMA.yaml +++ b/data/custodian/JP-12-SAK-M-TMA.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-SAK-M-TMA - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-SAK-M-TMA valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-SAK-M-TMA ghcid_numeric: 5040344671766080787 valid_from: '2025-12-06T23:38:32.800236+00:00' @@ -217,3 +218,28 @@ location: postal_code: 285-0024 street_address: URASHIMMACHI, Sakura Shi, Chiba Ken, 285-0024 normalization_timestamp: '2025-12-09T10:55:33.462678+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:44.812180+00:00' + source_url: https://www.city.sakura.lg.jp/soshiki/sakuranomiryoku/1/3036.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sakura.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.sakura.lg.jp/soshiki/sakuranomiryoku/1/3036.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:24:44.812180+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.sakura.lg.jp/material/images/group/114/horikawakunihiro.jpg + source_url: https://www.city.sakura.lg.jp/soshiki/sakuranomiryoku/1/3036.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T21:24:44.812180+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SAK-M-WFMRHF.yaml b/data/custodian/JP-12-SAK-M-WFMRHF.yaml index d546a11063..2cf6fdb87c 100644 --- a/data/custodian/JP-12-SAK-M-WFMRHF.yaml +++ b/data/custodian/JP-12-SAK-M-WFMRHF.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-SAK-M-WFMRHF - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-SAK-M-WFMRHF valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-SAK-M-WFMRHF ghcid_numeric: 16009246077734452744 valid_from: '2025-12-06T23:38:32.808795+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: WADA FURUSATOKAN MATERIAL ROOM OF HISTORY AND FOLKLORE @@ -151,3 +152,28 @@ location: geonames_id: 2111220 geonames_name: Sakura feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:24:55.193975+00:00' + source_url: http://www.city.sakura.lg.jp/0000000073.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sakura.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.sakura.lg.jp/0000000073.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:24:55.193975+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.sakura.lg.jp/material/images/group/64/top-image.jpg + source_url: http://www.city.sakura.lg.jp/0000000073.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T21:24:55.193975+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SAM-L-YLY.yaml b/data/custodian/JP-12-SAM-L-YLY.yaml index a972bc2da8..e1b4897d0b 100644 --- a/data/custodian/JP-12-SAM-L-YLY.yaml +++ b/data/custodian/JP-12-SAM-L-YLY.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.yokoshibahikari.chiba.jp/shisetsu/toshokan/02.html wikidata_official_website: http://www.town.yokoshibahikari.chiba.jp/shisetsu/toshokan/02.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:24.772945+00:00' + source_url: https://www.library.yokoshibahikari.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.yokoshibahikari.chiba.jp/favicon.ico + source_url: https://www.library.yokoshibahikari.chiba.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:25:24.772945+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-SAM-L-YPL.yaml b/data/custodian/JP-12-SAM-L-YPL.yaml index 570f0052cb..8ea60cf73f 100644 --- a/data/custodian/JP-12-SAM-L-YPL.yaml +++ b/data/custodian/JP-12-SAM-L-YPL.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.yokoshibahikari.chiba.jp/ wikidata_official_website: http://www.library.yokoshibahikari.chiba.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:31.089514+00:00' + source_url: https://www.library.yokoshibahikari.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.yokoshibahikari.chiba.jp/favicon.ico + source_url: https://www.library.yokoshibahikari.chiba.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:25:31.089514+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-SAM-M-MAS.yaml b/data/custodian/JP-12-SAM-M-MAS.yaml index 8eb2a965db..1a93fb08e4 100644 --- a/data/custodian/JP-12-SAM-M-MAS.yaml +++ b/data/custodian/JP-12-SAM-M-MAS.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-SAM-M-MAS - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-SAM-M-MAS valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-SAM-M-MAS ghcid_numeric: 12941807462934527384 valid_from: '2025-12-06T23:38:32.909295+00:00' @@ -266,3 +267,22 @@ location: postal_code: 289-1608 street_address: IWAYAMA, Sambu Gun Shibayama Machi, Chiba Ken, 289-1608 normalization_timestamp: '2025-12-09T10:55:33.629539+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:50.953120+00:00' + source_url: http://www.aeromuseum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.aeromuseum.or.jp/wp-content/uploads/2024/03/cropped-aviationmuseum-fav-180x180.jpg + source_url: http://www.aeromuseum.or.jp + css_selector: '[document] > html.pc > head > link:nth-of-type(24)' + retrieved_on: '2025-12-24T21:25:50.953120+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-SAM-M-SCMHF.yaml b/data/custodian/JP-12-SAM-M-SCMHF.yaml index 3eb2ab4cff..aba1d566aa 100644 --- a/data/custodian/JP-12-SAM-M-SCMHF.yaml +++ b/data/custodian/JP-12-SAM-M-SCMHF.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-SAM-M-SCMHF - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-SAM-M-SCMHF valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-SAM-M-SCMHF ghcid_numeric: 4735982603541145144 valid_from: '2025-12-06T23:38:32.901680+00:00' @@ -220,3 +221,28 @@ geocoding: resolved_place: Tonodai resolved_city: Sammu Shi timestamp: '2025-12-09T23:13:16.724777+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:25:56.683355+00:00' + source_url: https://www.city.sammu.lg.jp/page/dir000115.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sammu.lg.jp/web_clip_icon.png + source_url: https://www.city.sammu.lg.jp/page/dir000115.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:25:56.683355+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sammu.lg.jp/web_clip_icon.png + source_url: https://www.city.sammu.lg.jp/page/dir000115.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T21:25:56.683355+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SHI-L-SL.yaml b/data/custodian/JP-12-SHI-L-SL.yaml index 196ca100be..835d6d0083 100644 --- a/data/custodian/JP-12-SHI-L-SL.yaml +++ b/data/custodian/JP-12-SHI-L-SL.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.center.shiroi.chiba.jp/library/aatosyo2.htm wikidata_official_website: http://www.center.shiroi.chiba.jp/library/aatosyo2.htm +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:26:08.652999+00:00' + source_url: https://www.center.shiroi.chiba.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.center.shiroi.chiba.jp/img/common/logo.png + source_url: https://www.center.shiroi.chiba.jp/library + css_selector: '#wrap > header > div.inner > ul.wrap > li.logo > h1 > a > img.back-logo' + retrieved_on: '2025-12-24T21:26:08.652999+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: しろい市立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-SHI-M-ETMMKF.yaml b/data/custodian/JP-12-SHI-M-ETMMKF.yaml index e39f21e1c2..432a25e86e 100644 --- a/data/custodian/JP-12-SHI-M-ETMMKF.yaml +++ b/data/custodian/JP-12-SHI-M-ETMMKF.yaml @@ -223,3 +223,28 @@ location: geonames_id: 11525872 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.607281+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:26:18.662012+00:00' + source_url: https://www.town.erimo.lg.jp/horoizumi + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.erimo.lg.jp/horoizumi/mpdu1g0000000050-att/favicon.ico + source_url: https://www.town.erimo.lg.jp/horoizumi + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:26:18.662012+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.erimo.lg.jp/horoizumi/mpdu1g0000000050-img/mpdu1g0000000073.jpg + source_url: https://www.town.erimo.lg.jp/horoizumi + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T21:26:18.662012+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-SHI-M-ICSC.yaml b/data/custodian/JP-12-SHI-M-ICSC.yaml index 1256ab458d..8a435c8d1a 100644 --- a/data/custodian/JP-12-SHI-M-ICSC.yaml +++ b/data/custodian/JP-12-SHI-M-ICSC.yaml @@ -253,3 +253,36 @@ location: geonames_id: 2128196 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.633160+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:26:26.898753+00:00' + source_url: https://www.city.iwamizawa.hokkaido.jp/soshiki/shogaigakushu_bunka_sportshinkoka/iwamizawashi_shokai/1/5/3148.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.iwamizawa.hokkaido.jp/theme/base/img_common/sub_heaeder_logo.png + source_url: https://www.city.iwamizawa.hokkaido.jp/soshiki/shogaigakushu_bunka_sportshinkoka/iwamizawashi_shokai/1/5/3148.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-24T21:26:26.898753+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩見沢市 IWAMIZAWA CITY + - claim_type: favicon_url + claim_value: https://www.city.iwamizawa.hokkaido.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.iwamizawa.hokkaido.jp/soshiki/shogaigakushu_bunka_sportshinkoka/iwamizawashi_shokai/1/5/3148.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:26:26.898753+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.iwamizawa.hokkaido.jp/material/images/group/49/content_20170719_130252.gif + source_url: https://www.city.iwamizawa.hokkaido.jp/soshiki/shogaigakushu_bunka_sportshinkoka/iwamizawashi_shokai/1/5/3148.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T21:26:26.898753+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SHI-M-NAM.yaml b/data/custodian/JP-12-SHI-M-NAM.yaml index 8d02657e01..91b02f7b36 100644 --- a/data/custodian/JP-12-SHI-M-NAM.yaml +++ b/data/custodian/JP-12-SHI-M-NAM.yaml @@ -287,3 +287,28 @@ location: geonames_id: 2128072 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.660716+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:26:38.070939+00:00' + source_url: https://nam.go.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nam.go.jp/wp/wp-content/uploads/2020/03/apple-touch-icon.png?v=2003190500 + source_url: https://nam.go.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:26:38.070939+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://nam.go.jp/wp/wp-content/uploads/2020/03/DSC0756-2.jpg + source_url: https://nam.go.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:26:38.070939+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SHI-M-SCSMHM.yaml b/data/custodian/JP-12-SHI-M-SCSMHM.yaml index 53f33fc08c..433f35e2bc 100644 --- a/data/custodian/JP-12-SHI-M-SCSMHM.yaml +++ b/data/custodian/JP-12-SHI-M-SCSMHM.yaml @@ -247,3 +247,28 @@ location: geonames_id: 2128072 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.688361+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:13.689670+00:00' + source_url: http://www.town.shiraoi.hokkaido.jp/bunya/jinya + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.shiraoi.hokkaido.jp/common/images/apple-touch-icon.png + source_url: http://www.town.shiraoi.hokkaido.jp/bunya/jinya + css_selector: '[document] > html.history.no-touchevents > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T21:28:13.689670+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.shiraoi.hokkaido.jp/common/images/ogp.jpg + source_url: http://www.town.shiraoi.hokkaido.jp/bunya/jinya + css_selector: '[document] > html.history.no-touchevents > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T21:28:13.689670+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-SHI-M-STM.yaml b/data/custodian/JP-12-SHI-M-STM.yaml index 1035ec2910..a13540f7a4 100644 --- a/data/custodian/JP-12-SHI-M-STM.yaml +++ b/data/custodian/JP-12-SHI-M-STM.yaml @@ -233,3 +233,30 @@ location: geonames_id: 2128025 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.714837+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:26.828444+00:00' + source_url: http://www.shinhidaka-hokkaido.jp/hotnews/category/180.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.shinhidaka-hokkaido.jp/images/logo.png + source_url: http://www.shinhidaka-hokkaido.jp/hotnews/category/180.html + css_selector: '#headerLogo > a > img' + retrieved_on: '2025-12-24T21:28:26.828444+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新ひだか町 + - claim_type: favicon_url + claim_value: http://www.shinhidaka-hokkaido.jp/images/logo_mark_ios.png + source_url: http://www.shinhidaka-hokkaido.jp/hotnews/category/180.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:28:26.828444+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsuhirakawa_library.yaml b/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsuhirakawa_library.yaml index 12c9b250a4..0c5c9f6394 100644 --- a/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsuhirakawa_library.yaml +++ b/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsuhirakawa_library.yaml @@ -204,3 +204,30 @@ wikidata_enrichment: wikidata_web: official_website: http://lib.sodegaura.ed.jp/shisetsu/hirakawa.html wikidata_official_website: http://lib.sodegaura.ed.jp/shisetsu/hirakawa.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:37.241061+00:00' + source_url: https://sodelib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sodelib.jp/themes/lib_theme/images/logo.png + source_url: https://sodelib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-24T21:28:37.241061+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 袖ケ浦市立図書館 + - claim_type: favicon_url + claim_value: https://sodelib.jp/themes/lib_theme/favicon.ico + source_url: https://sodelib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-24T21:28:37.241061+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsunagauraokanoue_library.yaml b/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsunagauraokanoue_library.yaml index 54c36c4db1..09ac06d769 100644 --- a/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsunagauraokanoue_library.yaml +++ b/data/custodian/JP-12-SOD-L-SL-sodegaurashiritsunagauraokanoue_library.yaml @@ -204,3 +204,30 @@ wikidata_enrichment: wikidata_web: official_website: http://lib.sodegaura.ed.jp/shisetsu/nagaura.html wikidata_official_website: http://lib.sodegaura.ed.jp/shisetsu/nagaura.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:45.948737+00:00' + source_url: https://sodelib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sodelib.jp/themes/lib_theme/images/logo.png + source_url: https://sodelib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-24T21:28:45.948737+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 袖ケ浦市立図書館 + - claim_type: favicon_url + claim_value: https://sodelib.jp/themes/lib_theme/favicon.ico + source_url: https://sodelib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-24T21:28:45.948737+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-SOD-L-SL.yaml b/data/custodian/JP-12-SOD-L-SL.yaml index b4c9451355..4b90a09586 100644 --- a/data/custodian/JP-12-SOD-L-SL.yaml +++ b/data/custodian/JP-12-SOD-L-SL.yaml @@ -205,3 +205,30 @@ wikidata_enrichment: wikidata_web: official_website: http://lib.sodegaura.ed.jp/shisetsu/chuo.html wikidata_official_website: http://lib.sodegaura.ed.jp/shisetsu/chuo.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:28:58.537609+00:00' + source_url: https://sodelib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sodelib.jp/themes/lib_theme/images/logo.png + source_url: https://sodelib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-24T21:28:58.537609+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 袖ケ浦市立図書館 + - claim_type: favicon_url + claim_value: https://sodelib.jp/themes/lib_theme/favicon.ico + source_url: https://sodelib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-24T21:28:58.537609+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-SOD-M-SCLM.yaml b/data/custodian/JP-12-SOD-M-SCLM.yaml index 65ca3e2721..71bd963547 100644 --- a/data/custodian/JP-12-SOD-M-SCLM.yaml +++ b/data/custodian/JP-12-SOD-M-SCLM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-SOD-M-SCLM - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-SOD-M-SCLM valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-SOD-M-SCLM ghcid_numeric: 5954029527638220853 valid_from: '2025-12-06T23:38:32.871715+00:00' @@ -221,3 +222,22 @@ location: postal_code: 299-0255 street_address: SHIMONITTA, Sodegaura Shi, Chiba Ken, 299-0255 normalization_timestamp: '2025-12-09T10:55:33.864794+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:29:07.063624+00:00' + source_url: https://www.city.sodegaura.lg.jp/soshiki/hakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sodegaura.lg.jp/favicon.png + source_url: https://www.city.sodegaura.lg.jp/soshiki/hakubutsukan + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:29:07.063624+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-TAK-L-TCL.yaml b/data/custodian/JP-12-TAK-L-TCL.yaml index 2d81d19098..a188afec86 100644 --- a/data/custodian/JP-12-TAK-L-TCL.yaml +++ b/data/custodian/JP-12-TAK-L-TCL.yaml @@ -238,3 +238,22 @@ location: geonames_id: 2127896 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:33.767661+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:29:42.747223+00:00' + source_url: https://lib.city.takikawa.hokkaido.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lib.city.takikawa.hokkaido.jp/wp-content/uploads/2020/09/cropped-takikawacity_logo-180x180.png + source_url: https://lib.city.takikawa.hokkaido.jp + css_selector: '[document] > html > head > link:nth-of-type(21)' + retrieved_on: '2025-12-24T21:29:42.747223+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-TOG-L-TL.yaml b/data/custodian/JP-12-TOG-L-TL.yaml index 58ee5194da..cca140cda1 100644 --- a/data/custodian/JP-12-TOG-L-TL.yaml +++ b/data/custodian/JP-12-TOG-L-TL.yaml @@ -199,3 +199,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.togane.chiba.jp/category/1-8-6-0-0.html wikidata_official_website: http://www.city.togane.chiba.jp/category/1-8-6-0-0.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:41:33.414151+00:00' + source_url: https://www.city.togane.chiba.jp/category/12-2-0-0-0-0-0-0-0-0.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.togane.chiba.jp/category/css/img/apple-touch-icon.png + source_url: https://www.city.togane.chiba.jp/category/12-2-0-0-0-0-0-0-0-0.html + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T21:41:33.414151+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.city.togane.chiba.jp/design_img/og_image.png + source_url: https://www.city.togane.chiba.jp/category/12-2-0-0-0-0-0-0-0-0.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T21:41:33.414151+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-TOG-M-MMAJIU.yaml b/data/custodian/JP-12-TOG-M-MMAJIU.yaml index c1fb996909..459b6c592e 100644 --- a/data/custodian/JP-12-TOG-M-MMAJIU.yaml +++ b/data/custodian/JP-12-TOG-M-MMAJIU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-TOG-M-MMAJIU - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-TOG-M-MMAJIU valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-TOG-M-MMAJIU ghcid_numeric: 15280237612139080685 valid_from: '2025-12-06T23:38:32.818252+00:00' @@ -106,8 +107,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MIZUTA MUSEUM OF ART, JOSAI INTERNATIONAL UNIVERSITY @@ -181,7 +182,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) - id: Q866133 label: university museum description: museum run within a university @@ -218,3 +220,22 @@ location: geonames_id: 2110774 geonames_name: Tōgane feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:41:45.864437+00:00' + source_url: https://www.jiu.ac.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jiu.ac.jp/files/user/images/apple-touch-icon.png?v=1509065559 + source_url: https://www.jiu.ac.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:41:45.864437+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-TOM-M-TCM.yaml b/data/custodian/JP-12-TOM-M-TCM.yaml index 0f8ddfc01a..72184e8233 100644 --- a/data/custodian/JP-12-TOM-M-TCM.yaml +++ b/data/custodian/JP-12-TOM-M-TCM.yaml @@ -288,3 +288,22 @@ location: geonames_id: 2127733 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:33.818693+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:42:13.668648+00:00' + source_url: https://www.city.tomakomai.hokkaido.jp/hakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.tomakomai.hokkaido.jp/hakubutsukan/icon.png + source_url: https://www.city.tomakomai.hokkaido.jp/hakubutsukan + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:42:13.668648+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-URA-L-JL.yaml b/data/custodian/JP-12-URA-L-JL.yaml index de8a9639fc..f98a3223bb 100644 --- a/data/custodian/JP-12-URA-L-JL.yaml +++ b/data/custodian/JP-12-URA-L-JL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-URA-L-JL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-URA-L-JL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-URA-L-JL ghcid_numeric: 10062793142697859824 valid_from: '2025-12-06T23:38:54.943043+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JUNTENDODAIGAKURAYASUKYAMPASU Library @@ -204,3 +205,20 @@ location: geonames_id: 1849186 geonames_name: Urayasu feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:42:30.563688+00:00' + source_url: http://www.nurs.juntendo.ac.jp/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.juntendo.ac.jp/ogp.png + source_url: http://www.nurs.juntendo.ac.jp/library/index.html + css_selector: '[document] > html.js_domload.js_ajaxload > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T21:42:30.563688+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-12-URA-L-MUUCMC.yaml b/data/custodian/JP-12-URA-L-MUUCMC.yaml index 6aed56c0a9..c0220e4b77 100644 --- a/data/custodian/JP-12-URA-L-MUUCMC.yaml +++ b/data/custodian/JP-12-URA-L-MUUCMC.yaml @@ -217,3 +217,22 @@ location: geonames_id: 1849186 geonames_name: Urayasu feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:42:40.442350+00:00' + source_url: https://opac-ura.meikai.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://opac-ura.meikai.ac.jp/favicon.ico + source_url: https://opac-ura.meikai.ac.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:42:40.442350+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-URA-L-RUL.yaml b/data/custodian/JP-12-URA-L-RUL.yaml index aece7b58af..f7f3a24e5b 100644 --- a/data/custodian/JP-12-URA-L-RUL.yaml +++ b/data/custodian/JP-12-URA-L-RUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-URA-L-RUL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-URA-L-RUL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-URA-L-RUL ghcid_numeric: 4103306030274997733 valid_from: '2025-12-06T23:38:54.793555+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ryotokuji University Library @@ -204,3 +205,28 @@ location: geonames_id: 1849186 geonames_name: Urayasu feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:42:52.259601+00:00' + source_url: http://www.ryotokuji-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ryotokuji-u.ac.jp/favicon.ico?v=e2678523db8ddaf6548307144e6cd858 + source_url: http://www.ryotokuji-u.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:42:52.259601+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sbctmu.ac.jp/ogp.png + source_url: http://www.ryotokuji-u.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:42:52.259601+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-12-URA-M-UCFM.yaml b/data/custodian/JP-12-URA-M-UCFM.yaml index 50e7c42dc9..92dbf8e95a 100644 --- a/data/custodian/JP-12-URA-M-UCFM.yaml +++ b/data/custodian/JP-12-URA-M-UCFM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-URA-M-UCFM - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-URA-M-UCFM valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-URA-M-UCFM ghcid_numeric: 8273184828355050895 valid_from: '2025-12-06T23:38:32.868197+00:00' @@ -244,3 +245,36 @@ location: postal_code: 279-0004 street_address: NEKOZANE, Urayasu Shi, Chiba Ken, 279-0004 normalization_timestamp: '2025-12-09T10:55:34.395957+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:43:59.105415+00:00' + source_url: https://www.city.urayasu.lg.jp/kanko/kyodo/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.urayasu.lg.jp/_template_/_site_/_default_/_res/images/header/tlogo.svg + source_url: https://www.city.urayasu.lg.jp/kanko/kyodo/index.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-24T21:43:59.105415+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 浦安市トップページ + - claim_type: favicon_url + claim_value: https://www.city.urayasu.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.urayasu.lg.jp/kanko/kyodo/index.html + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-24T21:43:59.105415+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.urayasu.lg.jp//_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.urayasu.lg.jp/kanko/kyodo/index.html + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T21:43:59.105415+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-YAC-L-SL.yaml b/data/custodian/JP-12-YAC-L-SL.yaml index 7dae733b1c..8064faa6fb 100644 --- a/data/custodian/JP-12-YAC-L-SL.yaml +++ b/data/custodian/JP-12-YAC-L-SL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-YAC-L-SL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-YAC-L-SL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-YAC-L-SL ghcid_numeric: 9122650001631312646 valid_from: '2025-12-06T23:38:54.765248+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHUMEIDAIGAKU Library @@ -215,3 +216,22 @@ location: geonames_id: 6822182 geonames_name: Yachiyo feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:44:19.047697+00:00' + source_url: http://www.shumei-u.ac.jp/campuslife/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.shumei-u.ac.jp/campuslife/img/logo.gif + source_url: http://www.shumei-u.ac.jp/campuslife/library + css_selector: '[document] > html > body > header > div.inner > h1 > a > img' + retrieved_on: '2025-12-24T21:44:19.047697+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秀明大学図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-12-YAC-L-TYL.yaml b/data/custodian/JP-12-YAC-L-TYL.yaml index b39b44426c..f7affe6fe2 100644 --- a/data/custodian/JP-12-YAC-L-TYL.yaml +++ b/data/custodian/JP-12-YAC-L-TYL.yaml @@ -213,3 +213,22 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.yachiyo.chiba.jp/KAKUKAN/CHUO.HTML wikidata_official_website: https://www.library.yachiyo.chiba.jp/KAKUKAN/CHUO.HTML +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:44:29.893163+00:00' + source_url: https://www.library.yachiyo.chiba.jp/KAKUKAN/CHUO.HTML + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.yachiyo.chiba.jp/favicon/favicon.ico + source_url: https://www.library.yachiyo.chiba.jp/KAKUKAN/CHUO.HTML + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:44:29.893163+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsukatsutadai_library.yaml b/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsukatsutadai_library.yaml index 0d8c1bad9e..557e1cff7f 100644 --- a/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsukatsutadai_library.yaml +++ b/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsukatsutadai_library.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=2 wikidata_official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:44:40.923794+00:00' + source_url: https://www.library.yachiyo.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.yachiyo.chiba.jp/favicon/favicon.ico + source_url: https://www.library.yachiyo.chiba.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:44:40.923794+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsumidorigaoka_library.yaml b/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsumidorigaoka_library.yaml index 3f4b3f7e6f..3911fd4623 100644 --- a/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsumidorigaoka_library.yaml +++ b/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsumidorigaoka_library.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=10 wikidata_official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=10 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:44:50.950768+00:00' + source_url: https://www.library.yachiyo.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.yachiyo.chiba.jp/favicon/favicon.ico + source_url: https://www.library.yachiyo.chiba.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:44:50.950768+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsuyachiyodai_library.yaml b/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsuyachiyodai_library.yaml index bf78ec299d..df26e538b1 100644 --- a/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsuyachiyodai_library.yaml +++ b/data/custodian/JP-12-YAC-L-YL-yachiyoshiritsuyachiyodai_library.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=6 wikidata_official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=6 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:45:01.357865+00:00' + source_url: https://www.library.yachiyo.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.yachiyo.chiba.jp/favicon/favicon.ico + source_url: https://www.library.yachiyo.chiba.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:45:01.357865+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-YAC-L-YL.yaml b/data/custodian/JP-12-YAC-L-YL.yaml index 4431d06751..f53223ce50 100644 --- a/data/custodian/JP-12-YAC-L-YL.yaml +++ b/data/custodian/JP-12-YAC-L-YL.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=7 wikidata_official_website: http://www.library.yachiyo.chiba.jp/modules/tinyd3/index.php?id=7 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:45:11.180142+00:00' + source_url: https://www.library.yachiyo.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.yachiyo.chiba.jp/favicon/favicon.ico + source_url: https://www.library.yachiyo.chiba.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:45:11.180142+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-12-YAK-M-YTM.yaml b/data/custodian/JP-12-YAK-M-YTM.yaml index 54434cd748..0c86056740 100644 --- a/data/custodian/JP-12-YAK-M-YTM.yaml +++ b/data/custodian/JP-12-YAK-M-YTM.yaml @@ -246,3 +246,28 @@ location: geonames_id: 2127478 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.873233+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:45:59.339830+00:00' + source_url: https://www.town.yakumo.lg.jp/soshiki/kyoudo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.yakumo.lg.jp/apple-touch-icon.png + source_url: https://www.town.yakumo.lg.jp/soshiki/kyoudo + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T21:45:59.339830+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.yakumo.lg.jp/img/top/top_background.png + source_url: https://www.town.yakumo.lg.jp/soshiki/kyoudo + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T21:45:59.339830+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-YOD-M-MCVH.yaml b/data/custodian/JP-12-YOD-M-MCVH.yaml index 89945ceca9..adb0d6fa24 100644 --- a/data/custodian/JP-12-YOD-M-MCVH.yaml +++ b/data/custodian/JP-12-YOD-M-MCVH.yaml @@ -220,3 +220,28 @@ location: geonames_id: 11559501 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.898142+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:10.465915+00:00' + source_url: https://www.town.makubetsu.lg.jp/kyouiku/matikadogallery/furusatokan/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.makubetsu.lg.jp/touchicon.jpg + source_url: https://www.town.makubetsu.lg.jp/kyouiku/matikadogallery/furusatokan/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:46:10.465915+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 512x512 + - claim_type: og_image_url + claim_value: https://www.town.makubetsu.lg.jp/assets/images/makubetsu/og-image.jpg + source_url: https://www.town.makubetsu.lg.jp/kyouiku/matikadogallery/furusatokan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:46:10.465915+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-12-YOT-L-AL.yaml b/data/custodian/JP-12-YOT-L-AL.yaml index 9641e5d29a..26f9f2e496 100644 --- a/data/custodian/JP-12-YOT-L-AL.yaml +++ b/data/custodian/JP-12-YOT-L-AL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-YOT-L-AL - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-YOT-L-AL valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-YOT-L-AL ghcid_numeric: 7991393305642214140 valid_from: '2025-12-06T23:38:54.786115+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: AIKOKUGAKUENDAIGAKUFUZOKU Library @@ -204,3 +205,22 @@ location: geonames_id: 2110480 geonames_name: Yotsukaidō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:17.774277+00:00' + source_url: https://www.aikoku-u.ac.jp/jp/campus/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://aikoku-u.ac.jp/application/files/3116/8964/9048/iphone.png + source_url: https://www.aikoku-u.ac.jp/jp/campus/library + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:46:17.774277+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-12-YOT-L-LCPEFCPC.yaml b/data/custodian/JP-12-YOT-L-LCPEFCPC.yaml index 38fa0b7790..29ead685bb 100644 --- a/data/custodian/JP-12-YOT-L-LCPEFCPC.yaml +++ b/data/custodian/JP-12-YOT-L-LCPEFCPC.yaml @@ -32,20 +32,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-12-YOT-L-LCPEFCPC - valid_from: "2025-12-10T09:43:30Z" + valid_from: '2025-12-10T09:43:30Z' valid_to: null - reason: "Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO 3166-2:JP" + reason: Corrected region code from JP-CH (abbreviation) to JP-12 (Chiba) per ISO + 3166-2:JP - ghcid: JP-CH-YOT-L-LCPEFCPC valid_from: null - valid_to: "2025-12-10T09:43:30Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:30Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-CH-YOT-L-LCPEFCPC ghcid_numeric: 6708570746393802240 valid_from: '2025-12-06T23:38:58.674439+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Library, Chiba Prefectural Education Foundation Cultural Properties Center + claim_value: Library, Chiba Prefectural Education Foundation Cultural Properties + Center source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +98,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Library, Chiba Prefectural Education Foundation Cultural Properties Center + claim_value: Library, Chiba Prefectural Education Foundation Cultural Properties + Center property_uri: skos:prefLabel provenance: namespace: glam @@ -151,3 +154,30 @@ location: geonames_id: 2110480 geonames_name: Yotsukaidō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:30.299303+00:00' + source_url: http://www.echiba.org/bunkazai_top.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.echiba.org/img/hd_logo.svg + source_url: http://www.echiba.org/bunkazai_top.html + css_selector: '#masthead > div.ap_menu_box.bunkazai > a.logo > h1 > img.ap_menu_box__logo' + retrieved_on: '2025-12-24T21:46:30.299303+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: トップページ + - claim_type: favicon_url + claim_value: https://www.echiba.org/wp-content/uploads/2022/12/cropped-logo-180x180.png + source_url: http://www.echiba.org/bunkazai_top.html + css_selector: '[document] > html.js.svg > head > link:nth-of-type(21)' + retrieved_on: '2025-12-24T21:46:30.299303+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-YOT-L-YPL.yaml b/data/custodian/JP-12-YOT-L-YPL.yaml index acb9965411..842417a32b 100644 --- a/data/custodian/JP-12-YOT-L-YPL.yaml +++ b/data/custodian/JP-12-YOT-L-YPL.yaml @@ -226,3 +226,31 @@ location: postal_code: 284-0001 street_address: 396 DAINICHI, Yotsukaido Shi, Chiba Ken, 284-0001 normalization_timestamp: '2025-12-09T10:55:34.688600+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:49.739480+00:00' + source_url: https://www.library.yotsukaido.chiba.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.yotsukaido.chiba.jp/wp-content/themes/yotsukaido/images/site-logo.png + source_url: https://www.library.yotsukaido.chiba.jp + css_selector: '#top > header.l-header.no-print > div.l-header__container > div.l-header__2column + > div.l-header__2column--left > h1.l-header__logo > a > img' + retrieved_on: '2025-12-24T21:46:49.739480+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 四街道市立図書館 + - claim_type: favicon_url + claim_value: https://www.library.yotsukaido.chiba.jp/wp-content/uploads/2024/04/cropped-4495bed8051fcc9fd4ac4bababda36e3-180x180.png + source_url: https://www.library.yotsukaido.chiba.jp + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:46:49.739480+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-12-YUB-M-YR.yaml b/data/custodian/JP-12-YUB-M-YR.yaml index 8eb86057f7..1ccb29c3eb 100644 --- a/data/custodian/JP-12-YUB-M-YR.yaml +++ b/data/custodian/JP-12-YUB-M-YR.yaml @@ -233,3 +233,22 @@ location: geonames_id: 2127419 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:33.925061+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:46:58.779496+00:00' + source_url: https://www.city.yubari.lg.jp/kanko/miruasobutaiken/rokumeikan.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.yubari.lg.jp/apple-touch-icon.png + source_url: https://www.city.yubari.lg.jp/kanko/miruasobutaiken/rokumeikan.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:46:58.779496+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-ADA-L-BUTAL.yaml b/data/custodian/JP-13-ADA-L-BUTAL.yaml index eac319dc76..d6c4e5606f 100644 --- a/data/custodian/JP-13-ADA-L-BUTAL.yaml +++ b/data/custodian/JP-13-ADA-L-BUTAL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ADA-L-BUTAL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ADA-L-BUTAL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ADA-L-BUTAL ghcid_numeric: 1336213663327806769 valid_from: '2025-12-06T23:38:59.958021+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Bunkyo University Tokyo-Adachi Library @@ -151,3 +152,28 @@ location: geonames_id: 10987897 geonames_name: Adachi feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:49:35.147699+00:00' + source_url: https://www.bunkyo.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bunkyo.ac.jp/library/favicon.ico + source_url: https://www.bunkyo.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:49:35.147699+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.bunkyo.ac.jp/library/ogp.jpg + source_url: https://www.bunkyo.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:49:35.147699+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-ADA-L-TDUMRCL.yaml b/data/custodian/JP-13-ADA-L-TDUMRCL.yaml index 92d5259f92..acb8120f46 100644 --- a/data/custodian/JP-13-ADA-L-TDUMRCL.yaml +++ b/data/custodian/JP-13-ADA-L-TDUMRCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ADA-L-TDUMRCL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ADA-L-TDUMRCL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ADA-L-TDUMRCL ghcid_numeric: 3002202271858061378 valid_from: '2025-12-06T23:38:55.120085+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Denki University Multimedia Resource Center and Library @@ -196,7 +197,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.mrcl.dendai.ac.jp/ wikidata_official_website: http://www.mrcl.dendai.ac.jp/ @@ -218,3 +220,22 @@ location: geonames_id: 10987897 geonames_name: Adachi feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:49:55.886674+00:00' + source_url: http://www.mrcl.dendai.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mrcl.dendai.ac.jp/mrcl/wp-content/uploads/2020/05/cropped-TDU-ICON-180x180.png + source_url: http://www.mrcl.dendai.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(35)' + retrieved_on: '2025-12-24T21:49:55.886674+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-ADA-L-TLSL.yaml b/data/custodian/JP-13-ADA-L-TLSL.yaml index 4a706285cb..a3b4908866 100644 --- a/data/custodian/JP-13-ADA-L-TLSL.yaml +++ b/data/custodian/JP-13-ADA-L-TLSL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ADA-L-TLSL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ADA-L-TLSL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ADA-L-TLSL ghcid_numeric: 8667057192654961032 valid_from: '2025-12-06T23:38:55.472941+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TEIKYOKAGAKUDAIGAKUFUZOKU Library SENJU Library @@ -204,3 +205,28 @@ location: geonames_id: 10987897 geonames_name: Adachi feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:09.499334+00:00' + source_url: http://www.ntu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ntu.ac.jp/common/image/app-icon.png + source_url: http://www.ntu.ac.jp/library + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T21:50:09.499334+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ntu.ac.jp/common/image/sns-icon.jpg + source_url: http://www.ntu.ac.jp/library + css_selector: '[document] > html.js > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T21:50:09.499334+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-ADA-L-TWSMULA.yaml b/data/custodian/JP-13-ADA-L-TWSMULA.yaml index b44f799277..9761f22e1d 100644 --- a/data/custodian/JP-13-ADA-L-TWSMULA.yaml +++ b/data/custodian/JP-13-ADA-L-TWSMULA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ADA-L-TWSMULA - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ADA-L-TWSMULA valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ADA-L-TWSMULA ghcid_numeric: 4435714941808014896 valid_from: '2025-12-06T23:39:00.013415+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Women's Medical University Library ADACHITOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 10987897 geonames_name: Adachi feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:17.509802+00:00' + source_url: http://www.twmu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.twmu.ac.jp/images/favicon.ico + source_url: http://www.twmu.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T21:50:17.509802+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-ADA-M-G.yaml b/data/custodian/JP-13-ADA-M-G.yaml index 4ed819742e..1eb1650cfc 100644 --- a/data/custodian/JP-13-ADA-M-G.yaml +++ b/data/custodian/JP-13-ADA-M-G.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ADA-M-G - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ADA-M-G valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ADA-M-G ghcid_numeric: 6697732684646435709 valid_from: '2025-12-06T23:38:33.527288+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: GALAXCITY @@ -221,3 +222,22 @@ location: postal_code: 123-0842 street_address: KURIHARA, Adachi Ku, Tokyo To, 123-0842 normalization_timestamp: '2025-12-09T12:21:16.611690+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:38.031013+00:00' + source_url: https://www.galaxcity.jp/facilities/multi-experience-dome.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.galaxcity.jp/assets/img/common/apple-touch-icon.png + source_url: https://www.galaxcity.jp/facilities/multi-experience-dome.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T21:50:38.031013+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-AIO-L-LMSKU.yaml b/data/custodian/JP-13-AIO-L-LMSKU.yaml index af607537af..afd2bcdec7 100644 --- a/data/custodian/JP-13-AIO-L-LMSKU.yaml +++ b/data/custodian/JP-13-AIO-L-LMSKU.yaml @@ -226,3 +226,28 @@ location: geonames_id: 9290162 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:33.951814+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:50:48.549489+00:00' + source_url: http://lib.kobe-u.ac.jp/www/modules/igaku + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://lib.kobe-u.ac.jp/media/common/apple-touch-icon.png + source_url: http://lib.kobe-u.ac.jp/www/modules/igaku + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T21:50:48.549489+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://lib.kobe-u.ac.jp/media/sites/2/img-uriko02j.jpg + source_url: http://lib.kobe-u.ac.jp/www/modules/igaku + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T21:50:48.549489+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-AKA-M-AMP.yaml b/data/custodian/JP-13-AKA-M-AMP.yaml index cecf330112..3b48485918 100644 --- a/data/custodian/JP-13-AKA-M-AMP.yaml +++ b/data/custodian/JP-13-AKA-M-AMP.yaml @@ -1187,3 +1187,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/muE1heinVcM/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:51:05.268698+00:00' + source_url: https://www.am12.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.am12.jp/WPDATA/wp-content/uploads/2022/04/favicon.png + source_url: https://www.am12.jp + css_selector: '[document] > html.pc > head > link:nth-of-type(14)' + retrieved_on: '2025-12-24T21:51:05.268698+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-AKI-L-AL-akirunoshichuo_library.yaml b/data/custodian/JP-13-AKI-L-AL-akirunoshichuo_library.yaml index ecfb7c5959..f6b84e557d 100644 --- a/data/custodian/JP-13-AKI-L-AL-akirunoshichuo_library.yaml +++ b/data/custodian/JP-13-AKI-L-AL-akirunoshichuo_library.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.akiruno.tokyo.jp/index.asp wikidata_official_website: https://www.library.akiruno.tokyo.jp/index.asp +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:52:18.087037+00:00' + source_url: https://www.library.akiruno.tokyo.jp/TOSHOW/asp/index.aspx + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.akiruno.tokyo.jp/TOSHOW/asp/shared/img/snsThumbnail.png + source_url: https://www.library.akiruno.tokyo.jp/TOSHOW/asp/index.aspx + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T21:52:18.087037+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-AKI-L-ALE.yaml b/data/custodian/JP-13-AKI-L-ALE.yaml index 1ac1f2a233..64aad21885 100644 --- a/data/custodian/JP-13-AKI-L-ALE.yaml +++ b/data/custodian/JP-13-AKI-L-ALE.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.akiruno.tokyo.jp/index.asp wikidata_official_website: https://www.library.akiruno.tokyo.jp/index.asp +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:55:16.185434+00:00' + source_url: https://www.library.akiruno.tokyo.jp/toshow/asp/index.aspx + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.akiruno.tokyo.jp/TOSHOW/asp/shared/img/snsThumbnail.png + source_url: https://www.library.akiruno.tokyo.jp/toshow/asp/index.aspx + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T21:55:16.185434+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-AKI-L-ALM-akirunoshichuo_library_masukobunshitsu.yaml b/data/custodian/JP-13-AKI-L-ALM-akirunoshichuo_library_masukobunshitsu.yaml index 009817fd26..c56f6610fd 100644 --- a/data/custodian/JP-13-AKI-L-ALM-akirunoshichuo_library_masukobunshitsu.yaml +++ b/data/custodian/JP-13-AKI-L-ALM-akirunoshichuo_library_masukobunshitsu.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.akiruno.tokyo.jp/index.asp wikidata_official_website: http://www.library.akiruno.tokyo.jp/index.asp +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:56:10.868910+00:00' + source_url: https://www.library.akiruno.tokyo.jp/toshow/asp/index.aspx + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.akiruno.tokyo.jp/TOSHOW/asp/shared/img/snsThumbnail.png + source_url: https://www.library.akiruno.tokyo.jp/toshow/asp/index.aspx + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T21:56:10.868910+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-AKI-L-ALM.yaml b/data/custodian/JP-13-AKI-L-ALM.yaml index 178f2b1799..d056848bdb 100644 --- a/data/custodian/JP-13-AKI-L-ALM.yaml +++ b/data/custodian/JP-13-AKI-L-ALM.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.akishima.tokyo.jp wikidata_official_website: http://www.library.akishima.tokyo.jp +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:56:21.789006+00:00' + source_url: https://www.library.akishima.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.akishima.tokyo.jp/favicon.ico + source_url: https://www.library.akishima.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:56:21.789006+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-AKI-L-ALS.yaml b/data/custodian/JP-13-AKI-L-ALS.yaml index 37d0e6b4ba..4f9658ff00 100644 --- a/data/custodian/JP-13-AKI-L-ALS.yaml +++ b/data/custodian/JP-13-AKI-L-ALS.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.akishima.tokyo.jp wikidata_official_website: http://www.library.akishima.tokyo.jp +logo_enrichment: + enrichment_timestamp: '2025-12-24T21:56:32.285830+00:00' + source_url: https://www.library.akishima.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.akishima.tokyo.jp/favicon.ico + source_url: https://www.library.akishima.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T21:56:32.285830+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-AKI-L-ALY.yaml b/data/custodian/JP-13-AKI-L-ALY.yaml index 030e8f95de..fa525b8e17 100644 --- a/data/custodian/JP-13-AKI-L-ALY.yaml +++ b/data/custodian/JP-13-AKI-L-ALY.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.akishima.tokyo.jp wikidata_official_website: http://www.library.akishima.tokyo.jp +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:12:29.167805+00:00' + source_url: https://www.library.akishima.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.akishima.tokyo.jp/favicon.ico + source_url: https://www.library.akishima.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:12:29.167805+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-AKI-M-ILM.yaml b/data/custodian/JP-13-AKI-M-ILM.yaml index 07e2b72722..a06b020576 100644 --- a/data/custodian/JP-13-AKI-M-ILM.yaml +++ b/data/custodian/JP-13-AKI-M-ILM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-AKI-M-ILM - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-AKI-M-ILM valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-AKI-M-ILM ghcid_numeric: 7614442736994532511 valid_from: '2025-12-06T23:38:33.733560+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ITSUKAICHI LOCAL MUSEUM @@ -151,3 +152,37 @@ location: geonames_id: 11612343 geonames_name: Akiruno feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:12:42.113571+00:00' + source_url: https://www.city.akiruno.tokyo.jp/0000001285.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.akiruno.tokyo.jp/css/img/logo30th.png + source_url: https://www.city.akiruno.tokyo.jp/0000001285.html + css_selector: '#body > div.all > div.design > header.main_header > div.head > + div.head_in:nth-of-type(2) > div.h_main > div.h1-img > img' + retrieved_on: '2025-12-24T22:12:42.113571+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: あきる野市30年 未来へ繋ごうトカイナカ + - claim_type: favicon_url + claim_value: https://www.city.akiruno.tokyo.jp/design_img/favicon.ico + source_url: https://www.city.akiruno.tokyo.jp/0000001285.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:12:42.113571+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.akiruno.tokyo.jp/design_img/og_image.png + source_url: https://www.city.akiruno.tokyo.jp/0000001285.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T22:12:42.113571+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-AKI-M-NK.yaml b/data/custodian/JP-13-AKI-M-NK.yaml index a6502ddae7..bd8b3f5500 100644 --- a/data/custodian/JP-13-AKI-M-NK.yaml +++ b/data/custodian/JP-13-AKI-M-NK.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-AKI-M-NK - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-AKI-M-NK valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-AKI-M-NK ghcid_numeric: 17264738522886827990 valid_from: '2025-12-06T23:38:33.735822+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NINOMIYA KOUKOKAN @@ -225,3 +226,37 @@ location: postal_code: 197-0814 street_address: NINOMIYA, Akiruno Shi, Tokyo To, 197-0814 normalization_timestamp: '2025-12-09T12:21:17.042906+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:12:49.348220+00:00' + source_url: https://www.city.akiruno.tokyo.jp/0000001066.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.akiruno.tokyo.jp/css/img/logo30th.png + source_url: https://www.city.akiruno.tokyo.jp/0000001066.html + css_selector: '#body > div.all > div.design > header.main_header > div.head > + div.head_in:nth-of-type(2) > div.h_main > div.h1-img > img' + retrieved_on: '2025-12-24T22:12:49.348220+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: あきる野市30年 未来へ繋ごうトカイナカ + - claim_type: favicon_url + claim_value: https://www.city.akiruno.tokyo.jp/design_img/favicon.ico + source_url: https://www.city.akiruno.tokyo.jp/0000001066.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:12:49.348220+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.akiruno.tokyo.jp/design_img/og_image.png + source_url: https://www.city.akiruno.tokyo.jp/0000001066.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T22:12:49.348220+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-AMA-M-ASBWMBM.yaml b/data/custodian/JP-13-AMA-M-ASBWMBM.yaml index 210329aa2b..ee6817c848 100644 --- a/data/custodian/JP-13-AMA-M-ASBWMBM.yaml +++ b/data/custodian/JP-13-AMA-M-ASBWMBM.yaml @@ -251,3 +251,28 @@ location: geonames_id: 1865387 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:34.029931+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:12:59.288891+00:00' + source_url: https://www.amashin.co.jp/sekai/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.amashin.co.jp/common_v2/images/favicon.ico + source_url: https://www.amashin.co.jp/sekai/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:12:59.288891+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.amashin.co.jp/common_v2/images/og.png + source_url: https://www.amashin.co.jp/sekai/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T22:12:59.288891+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-ANA-L-AL.yaml b/data/custodian/JP-13-ANA-L-AL.yaml index 9d6c5cd993..2b39e2c534 100644 --- a/data/custodian/JP-13-ANA-L-AL.yaml +++ b/data/custodian/JP-13-ANA-L-AL.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ANA-L-AL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ANA-L-AL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ANA-L-AL ghcid_numeric: 8757128924731063006 valid_from: '2025-12-06T23:38:47.344531+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ANANSHIRITSUANAN Library @@ -195,8 +196,9 @@ wikidata_enrichment: instance_of: &id004 - id: Q7075 label: library - description: institution charged with the care of a collection of literary, musical, artistic, or reference materials, - such as books, manuscripts, recordings, or films + description: institution charged with the care of a collection of literary, + musical, artistic, or reference materials, such as books, manuscripts, recordings, + or films wikidata_instance_of: *id004 wikidata_location: coordinates: &id007 @@ -231,3 +233,22 @@ location: postal_code: 774-0011 street_address: 121 RYOKECHO HONSONOUCHI, Anan Shi, Tokushima Ken, 774-0011 normalization_timestamp: '2025-12-09T12:21:17.096436+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:13:14.098134+00:00' + source_url: http://anan-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.anan-lib.jp/wp-content/themes/anan-lib/commons/images/apple-touch-icon180.png + source_url: http://anan-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:13:14.098134+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-ANA-L-ANCT.yaml b/data/custodian/JP-13-ANA-L-ANCT.yaml index 032bf505dc..c7356e6f9e 100644 --- a/data/custodian/JP-13-ANA-L-ANCT.yaml +++ b/data/custodian/JP-13-ANA-L-ANCT.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ANA-L-ANCT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ANA-L-ANCT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ANA-L-ANCT ghcid_numeric: 12383456444648493926 valid_from: '2025-12-06T23:38:57.449959+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Anan National College of Technology @@ -252,3 +253,28 @@ location: postal_code: 774-0017 street_address: 265 MINOBAYASHICHO AOKI, Anan Shi, Tokushima Ken, 774-0017 normalization_timestamp: '2025-12-09T12:21:17.152704+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:13:25.887443+00:00' + source_url: https://www.anan-nct.ac.jp/facility/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.anan-nct.ac.jp/wp-content/uploads/2019/10/icon-150x150.jpg + source_url: https://www.anan-nct.ac.jp/facility/library + css_selector: '[document] > html > head > link:nth-of-type(28)' + retrieved_on: '2025-12-24T22:13:25.887443+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://www.anan-nct.ac.jp/wp-content/uploads/2020/01/Library2.png + source_url: https://www.anan-nct.ac.jp/facility/library + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:13:25.887443+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-ARA-L-A.yaml b/data/custodian/JP-13-ARA-L-A.yaml index e70d3d3f1e..5b9b8c9e98 100644 --- a/data/custodian/JP-13-ARA-L-A.yaml +++ b/data/custodian/JP-13-ARA-L-A.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: https://www.city.arakawa.tokyo.jp/shisetsu/toshokan/shioiri.html wikidata_official_website: https://www.city.arakawa.tokyo.jp/shisetsu/toshokan/shioiri.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:29:52.114272+00:00' + source_url: https://www.city.arakawa.tokyo.jp/shisetsu/toshokan/shioiri.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.arakawa.tokyo.jp/shared/site_rn2025/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.arakawa.tokyo.jp/shisetsu/toshokan/shioiri.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:29:52.114272+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-ARA-L-ACPLCL.yaml b/data/custodian/JP-13-ARA-L-ACPLCL.yaml index febbe5b723..769be46abd 100644 --- a/data/custodian/JP-13-ARA-L-ACPLCL.yaml +++ b/data/custodian/JP-13-ARA-L-ACPLCL.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=773&idSubTop=1 wikidata_official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=773&idSubTop=1 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:30:00.372303+00:00' + source_url: https://www.library.city.arakawa.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.arakawa.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.arakawa.tokyo.jp + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:30:00.372303+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-ARA-L-ACPLML.yaml b/data/custodian/JP-13-ARA-L-ACPLML.yaml index 66c891fa09..95226b0727 100644 --- a/data/custodian/JP-13-ARA-L-ACPLML.yaml +++ b/data/custodian/JP-13-ARA-L-ACPLML.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=384&idSubTop=1 wikidata_official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=384&idSubTop=1 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:30:08.816023+00:00' + source_url: https://www.library.city.arakawa.tokyo.jp/contents?8&pid=89 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.arakawa.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.arakawa.tokyo.jp/contents?8&pid=89 + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:30:08.816023+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-ARA-L-ACPLMSL.yaml b/data/custodian/JP-13-ARA-L-ACPLMSL.yaml index 0ed1bc8d9e..3a3f112322 100644 --- a/data/custodian/JP-13-ARA-L-ACPLMSL.yaml +++ b/data/custodian/JP-13-ARA-L-ACPLMSL.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=376&idSubTop=1 wikidata_official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=376&idSubTop=1 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:30:17.561554+00:00' + source_url: https://www.library.city.arakawa.tokyo.jp/contents?9&pid=87 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.arakawa.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.arakawa.tokyo.jp/contents?9&pid=87 + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:30:17.561554+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-ARA-L-ACPLNL.yaml b/data/custodian/JP-13-ARA-L-ACPLNL.yaml index 179262ec46..941bc46bf6 100644 --- a/data/custodian/JP-13-ARA-L-ACPLNL.yaml +++ b/data/custodian/JP-13-ARA-L-ACPLNL.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=388&idSubTop=1 wikidata_official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=388&idSubTop=1 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:30:25.480704+00:00' + source_url: https://www.library.city.arakawa.tokyo.jp/contents?6&pid=90 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.arakawa.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.arakawa.tokyo.jp/contents?6&pid=90 + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:30:25.480704+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-ARA-L-ACPLOL.yaml b/data/custodian/JP-13-ARA-L-ACPLOL.yaml index 5f866b32bd..4cb9bdf552 100644 --- a/data/custodian/JP-13-ARA-L-ACPLOL.yaml +++ b/data/custodian/JP-13-ARA-L-ACPLOL.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=380&idSubTop=1 wikidata_official_website: https://www.library.city.arakawa.tokyo.jp/viewer/info.html?id=380&idSubTop=1 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:30:34.201662+00:00' + source_url: https://www.library.city.arakawa.tokyo.jp/contents?4&pid=88 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.arakawa.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.arakawa.tokyo.jp/contents?4&pid=88 + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:30:34.201662+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-ARA-L-TLH.yaml b/data/custodian/JP-13-ARA-L-TLH.yaml index 9c0041a654..ab4652d314 100644 --- a/data/custodian/JP-13-ARA-L-TLH.yaml +++ b/data/custodian/JP-13-ARA-L-TLH.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ARA-L-TLH - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ARA-L-TLH valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ARA-L-TLH ghcid_numeric: 16151895645676832796 valid_from: '2025-12-06T23:38:55.101667+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOKYOJOSHIIKADAIGAKU Library HIGASHIIRYOSENTATOSHOSHITSU @@ -204,3 +205,22 @@ location: geonames_id: 10968247 geonames_name: Arakawa feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:30:56.480661+00:00' + source_url: http://www.twmu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.twmu.ac.jp/images/favicon.ico + source_url: http://www.twmu.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:30:56.480661+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-ARA-M-AFM.yaml b/data/custodian/JP-13-ARA-M-AFM.yaml index 4f549fce23..f4934f6319 100644 --- a/data/custodian/JP-13-ARA-M-AFM.yaml +++ b/data/custodian/JP-13-ARA-M-AFM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ARA-M-AFM - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ARA-M-AFM valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ARA-M-AFM ghcid_numeric: 2096677626445783099 valid_from: '2025-12-06T23:38:33.482538+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ARAKAWA FURUSATO MUSEUM @@ -256,3 +257,28 @@ location: postal_code: 116-0003 street_address: MINAMISENJU, Arakawa Ku, Tokyo To, 116-0003 normalization_timestamp: '2025-12-09T12:21:17.710540+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:31:08.100492+00:00' + source_url: https://www.city.arakawa.tokyo.jp/a016/bunkageijutsu/furusato/furusato.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.arakawa.tokyo.jp/shared/site_rn2025/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.arakawa.tokyo.jp/a016/bunkageijutsu/furusato/furusato.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T22:31:08.100492+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.arakawa.tokyo.jp/shared/site_rn2025/images/sns/logo.jpg + source_url: https://www.city.arakawa.tokyo.jp/a016/bunkageijutsu/furusato/furusato.html + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T22:31:08.100492+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-ARA-M-YALM.yaml b/data/custodian/JP-13-ARA-M-YALM.yaml index 67b214fa87..d7451d2069 100644 --- a/data/custodian/JP-13-ARA-M-YALM.yaml +++ b/data/custodian/JP-13-ARA-M-YALM.yaml @@ -225,3 +225,28 @@ wikidata_enrichment: wikidata_media: image: Yuinomori Arakawa.jpg wikidata_image: Yuinomori Arakawa.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:31:15.509303+00:00' + source_url: https://www.yoshimurabungakukan.city.arakawa.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.yoshimurabungakukan.city.arakawa.tokyo.jp/images/bun_favicon.ico + source_url: https://www.yoshimurabungakukan.city.arakawa.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:31:15.509303+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.yoshimurabungakukan.city.arakawa.tokyo.jp/images/ogimageBun.png + source_url: https://www.yoshimurabungakukan.city.arakawa.tokyo.jp + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:31:15.509303+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-ASH-L-AL.yaml b/data/custodian/JP-13-ASH-L-AL.yaml index 9064d087dd..1821077aaa 100644 --- a/data/custodian/JP-13-ASH-L-AL.yaml +++ b/data/custodian/JP-13-ASH-L-AL.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ASH-L-AL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ASH-L-AL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ASH-L-AL ghcid_numeric: 10331776063175676371 valid_from: '2025-12-06T23:38:42.159506+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ASHIKAGASHIRITSU Library @@ -254,3 +255,22 @@ location: postal_code: 326-0801 street_address: 832 YURAKUCHO, Ashikaga Shi, Tochigi Ken, 326-0801 normalization_timestamp: '2025-12-09T12:21:17.848188+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:31:26.241897+00:00' + source_url: https://www.city.ashikaga.tochigi.jp/education/000030/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.ashikaga.tochigi.jp/apple-touch-icon.png + source_url: https://www.city.ashikaga.tochigi.jp/education/000030/index.html + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T22:31:26.241897+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-ASH-M-HSAG.yaml b/data/custodian/JP-13-ASH-M-HSAG.yaml index e096445852..142bc257dd 100644 --- a/data/custodian/JP-13-ASH-M-HSAG.yaml +++ b/data/custodian/JP-13-ASH-M-HSAG.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-ASH-M-HSAG - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-ASH-M-HSAG valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-ASH-M-HSAG ghcid_numeric: 9419309563151087020 valid_from: '2025-12-06T23:38:31.786328+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HISTORIC SITE ASHIKAGA GAKKO @@ -151,3 +152,22 @@ location: geonames_id: 1865005 geonames_name: Ashikaga feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:31:54.127384+00:00' + source_url: https://www.city.ashikaga.tochigi.jp/site/ashikagagakko + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.ashikaga.tochigi.jp/apple-touch-icon.png + source_url: https://www.city.ashikaga.tochigi.jp/site/ashikagagakko + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-24T22:31:54.127384+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-ASH-M-SM.yaml b/data/custodian/JP-13-ASH-M-SM.yaml index a68a71fcf2..46ec88b808 100644 --- a/data/custodian/JP-13-ASH-M-SM.yaml +++ b/data/custodian/JP-13-ASH-M-SM.yaml @@ -241,3 +241,22 @@ location: postal_code: 326-0816 street_address: MIDORICHO, Ashikaga Shi, Tochigi Ken, 326-0816 normalization_timestamp: '2025-12-09T12:21:17.987539+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:32:04.426131+00:00' + source_url: http://www.city.ashikaga.tochigi.jp/site/soun + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.ashikaga.tochigi.jp/apple-touch-icon.png + source_url: http://www.city.ashikaga.tochigi.jp/site/soun + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-24T22:32:04.426131+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-A-UTA-university_of_tokyo_archives.yaml b/data/custodian/JP-13-BUN-A-UTA-university_of_tokyo_archives.yaml index a37e7c1ac2..212b68a37b 100644 --- a/data/custodian/JP-13-BUN-A-UTA-university_of_tokyo_archives.yaml +++ b/data/custodian/JP-13-BUN-A-UTA-university_of_tokyo_archives.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:33:06.395016+00:00' + source_url: https://www.u-tokyo.ac.jp/adm/history/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.u-tokyo.ac.jp/content/400130668.png + source_url: https://www.u-tokyo.ac.jp/adm/history/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:33:06.395016+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.u-tokyo.ac.jp/content/400276511.jpg + source_url: https://www.u-tokyo.ac.jp/adm/history/index.html + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T22:33:06.395016+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-A-UTA.yaml b/data/custodian/JP-13-BUN-A-UTA.yaml index c14b515adf..81227fb670 100644 --- a/data/custodian/JP-13-BUN-A-UTA.yaml +++ b/data/custodian/JP-13-BUN-A-UTA.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:33:16.332109+00:00' + source_url: https://www.u-tokyo.ac.jp/adm/history/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.u-tokyo.ac.jp/content/400130668.png + source_url: https://www.u-tokyo.ac.jp/adm/history/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:33:16.332109+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.u-tokyo.ac.jp/content/400276511.jpg + source_url: https://www.u-tokyo.ac.jp/adm/history/index.html + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T22:33:16.332109+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-L-B-bunkyokuritsuotsukakoemmidorinotoshoshitsu.yaml b/data/custodian/JP-13-BUN-L-B-bunkyokuritsuotsukakoemmidorinotoshoshitsu.yaml index 4d67c6986e..0d672b0d51 100644 --- a/data/custodian/JP-13-BUN-L-B-bunkyokuritsuotsukakoemmidorinotoshoshitsu.yaml +++ b/data/custodian/JP-13-BUN-L-B-bunkyokuritsuotsukakoemmidorinotoshoshitsu.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib10-otsuka.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib10-otsuka.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:33:39.528064+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib10-otsuka.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib10-otsuka.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:33:39.528064+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-B.yaml b/data/custodian/JP-13-BUN-L-B.yaml index cb931be9d0..d124ef842b 100644 --- a/data/custodian/JP-13-BUN-L-B.yaml +++ b/data/custodian/JP-13-BUN-L-B.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib09-nedu.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib09-nedu.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:33:52.352007+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib09-nedu.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib09-nedu.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:33:52.352007+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BCMCL.yaml b/data/custodian/JP-13-BUN-L-BCMCL.yaml index 767b6d54c0..867ad9c5a5 100644 --- a/data/custodian/JP-13-BUN-L-BCMCL.yaml +++ b/data/custodian/JP-13-BUN-L-BCMCL.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-BCMCL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-BCMCL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-BCMCL ghcid_numeric: 18279062335509658914 valid_from: '2025-12-06T23:38:43.164818+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Bunkyo City Masago Central Library @@ -203,8 +204,9 @@ wikidata_enrichment: instance_of: &id005 - id: Q7075 label: library - description: institution charged with the care of a collection of literary, musical, artistic, or reference materials, - such as books, manuscripts, recordings, or films + description: institution charged with the care of a collection of literary, + musical, artistic, or reference materials, such as books, manuscripts, recordings, + or films wikidata_instance_of: *id005 wikidata_location: coordinates: &id008 @@ -250,3 +252,22 @@ location: postal_code: 113-0033 street_address: 4-8-15 HONGO, Bunkyo Ku, Tokyo To, 113-0033 normalization_timestamp: '2025-12-09T12:21:18.459167+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:04.367585+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib01-masago.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib01-masago.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:34:04.367585+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL-bunkyogakuindaigakuhongo_library.yaml b/data/custodian/JP-13-BUN-L-BL-bunkyogakuindaigakuhongo_library.yaml index 2bf7276c73..54012ff7c0 100644 --- a/data/custodian/JP-13-BUN-L-BL-bunkyogakuindaigakuhongo_library.yaml +++ b/data/custodian/JP-13-BUN-L-BL-bunkyogakuindaigakuhongo_library.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-BL-bunkyogakuindaigakuhongo_library - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-BL-bunkyogakuindaigakuhongo_library valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-BL-bunkyogakuindaigakuhongo_library ghcid_numeric: 1637206662760771834 valid_from: '2025-12-06T23:38:54.801040+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: BUNKYOGAKUINDAIGAKUHONGO Library @@ -204,3 +205,20 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:12.939830+00:00' + source_url: http://www.u-bunkyo.ac.jp/center/library/hongo.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.bgu.ac.jp/bgu_sys/wp-content/uploads/sites/11/2022/08/ogp.png + source_url: http://www.u-bunkyo.ac.jp/center/library/hongo.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T22:34:12.939830+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuhonkomagome_library.yaml b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuhonkomagome_library.yaml index 2d88c55000..1817170e57 100644 --- a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuhonkomagome_library.yaml +++ b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuhonkomagome_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib04-honkoma.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib04-honkoma.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:25.542721+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib04-honkoma.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib04-honkoma.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:34:25.542721+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsukoishikawa_library.yaml b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsukoishikawa_library.yaml index 73a9a71d63..6677f81eaa 100644 --- a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsukoishikawa_library.yaml +++ b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsukoishikawa_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib03-koishi.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib03-koishi.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:39.014148+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib03-koishi.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib03-koishi.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:34:39.014148+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsumejirodai_library.yaml b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsumejirodai_library.yaml index adacfa0288..1e80fa6d73 100644 --- a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsumejirodai_library.yaml +++ b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsumejirodai_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib06-mejiro.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib06-mejiro.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:34:52.375021+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib06-mejiro.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib06-mejiro.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:34:52.375021+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusengoku_library.yaml b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusengoku_library.yaml index 98e90d07bf..1867153bd7 100644 --- a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusengoku_library.yaml +++ b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusengoku_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib07-sengoku.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib07-sengoku.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:04.975473+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib07-sengoku.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib07-sengoku.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:35:04.975473+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusuidobata_library.yaml b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusuidobata_library.yaml index ec7e0066cd..b680f16d57 100644 --- a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusuidobata_library.yaml +++ b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsusuidobata_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib05-suido.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib05-suido.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:18.082839+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib05-suido.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib05-suido.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:35:18.082839+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuyushima_library.yaml b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuyushima_library.yaml index 904a476b02..c30635ceb7 100644 --- a/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuyushima_library.yaml +++ b/data/custodian/JP-13-BUN-L-BL-bunkyokuritsuyushima_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.lib.city.bunkyo.tokyo.jp/lib08-yushima.html wikidata_official_website: http://www.lib.city.bunkyo.tokyo.jp/lib08-yushima.html +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:31.563583+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib08-yushima.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib08-yushima.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:35:31.563583+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-BL.yaml b/data/custodian/JP-13-BUN-L-BL.yaml index bbf41e2dec..0903893cee 100644 --- a/data/custodian/JP-13-BUN-L-BL.yaml +++ b/data/custodian/JP-13-BUN-L-BL.yaml @@ -224,3 +224,22 @@ wikidata_enrichment: wikidata_media: image: 文京区立本郷図書館.jpg wikidata_image: 文京区立本郷図書館.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:35:45.053090+00:00' + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib02-hongo.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.city.bunkyo.tokyo.jp/Portals/0/logo.png + source_url: https://www.lib.city.bunkyo.tokyo.jp/lib02-hongo.html + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-24T22:35:45.053090+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文京区立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-CUSEL.yaml b/data/custodian/JP-13-BUN-L-CUSEL.yaml index 0beaa4ac94..59c5b10c24 100644 --- a/data/custodian/JP-13-BUN-L-CUSEL.yaml +++ b/data/custodian/JP-13-BUN-L-CUSEL.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-CUSEL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-CUSEL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-CUSEL ghcid_numeric: 3522252936207928234 valid_from: '2025-12-06T23:38:55.028169+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Chuo University Science and Engineering Library @@ -224,3 +225,28 @@ location: postal_code: 112-8551 street_address: 1-13-27 KASUGA, Bunkyo Ku, Tokyo To, 112-8551 normalization_timestamp: '2025-12-09T12:21:18.853564+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:36:04.960555+00:00' + source_url: http://www.chuo-u.ac.jp/library/library_service/kourakuencampus + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chuo-u.ac.jp/favicon-16x16.ico + source_url: http://www.chuo-u.ac.jp/library/library_service/kourakuencampus + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T22:36:04.960555+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 16x16 + - claim_type: og_image_url + claim_value: https://www.chuo-u.ac.jp/media/images/common/ogp.png + source_url: http://www.chuo-u.ac.jp/library/library_service/kourakuencampus + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T22:36:04.960555+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-L-FPS.yaml b/data/custodian/JP-13-BUN-L-FPS.yaml index d44cefa2a5..ba3044a760 100644 --- a/data/custodian/JP-13-BUN-L-FPS.yaml +++ b/data/custodian/JP-13-BUN-L-FPS.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-FPS - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-FPS valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-FPS ghcid_numeric: 969363865930520552 valid_from: '2025-12-06T23:38:58.692654+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Film Preservation Society @@ -151,3 +152,22 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:36:33.739027+00:00' + source_url: http://filmpres.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://filmpres.org/wp2/wp-content/uploads/fbrfg/apple-touch-icon-180x180.png + source_url: http://filmpres.org + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-24T22:36:33.739027+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 15 diff --git a/data/custodian/JP-13-BUN-L-GLUT.yaml b/data/custodian/JP-13-BUN-L-GLUT.yaml index 2fd5310269..eb51beda71 100644 --- a/data/custodian/JP-13-BUN-L-GLUT.yaml +++ b/data/custodian/JP-13-BUN-L-GLUT.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-GLUT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-GLUT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-GLUT ghcid_numeric: 5841965110009721815 valid_from: '2025-12-06T23:38:53.259890+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: General Library, The University of Tokyo @@ -279,3 +280,22 @@ location: postal_code: 113-0033 street_address: 7-3-1 HONGO, Bunkyo Ku, Tokyo To, 113-0033 normalization_timestamp: '2025-12-09T12:21:19.081609+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:36:45.285288+00:00' + source_url: http://www.lib.u-tokyo.ac.jp/sogoto + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.u-tokyo.ac.jp/themes/custom/tokyolib/dest/images/favicon/safari-pinned-tab.svg + source_url: http://www.lib.u-tokyo.ac.jp/sogoto + css_selector: '[document] > html.js > head > link:nth-of-type(9)' + retrieved_on: '2025-12-24T22:36:45.285288+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 6 diff --git a/data/custodian/JP-13-BUN-L-ISSLUT.yaml b/data/custodian/JP-13-BUN-L-ISSLUT.yaml index 18d6cf104c..637f9f3d15 100644 --- a/data/custodian/JP-13-BUN-L-ISSLUT.yaml +++ b/data/custodian/JP-13-BUN-L-ISSLUT.yaml @@ -205,3 +205,28 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:37:09.932497+00:00' + source_url: http://library.iss.u-tokyo.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.iss.u-tokyo.ac.jp/favicon.svg + source_url: http://library.iss.u-tokyo.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T22:37:09.932497+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://library.iss.u-tokyo.ac.jp/img/photo2.jpeg + source_url: http://library.iss.u-tokyo.ac.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T22:37:09.932497+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-L-JL.yaml b/data/custodian/JP-13-BUN-L-JL.yaml index b075663b34..c65e799a23 100644 --- a/data/custodian/JP-13-BUN-L-JL.yaml +++ b/data/custodian/JP-13-BUN-L-JL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-JL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-JL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-JL ghcid_numeric: 17739316846271197306 valid_from: '2025-12-06T23:38:54.937743+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JUNTENDODAIGAKU Library @@ -204,3 +205,20 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:37:31.688844+00:00' + source_url: http://www.juntendo.ac.jp/facility/library + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.juntendo.ac.jp/ogp.png + source_url: http://www.juntendo.ac.jp/facility/library + css_selector: '[document] > html.js_domload.js_imgload > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T22:37:31.688844+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-KL.yaml b/data/custodian/JP-13-BUN-L-KL.yaml index 79601fab2a..defbf87e8f 100644 --- a/data/custodian/JP-13-BUN-L-KL.yaml +++ b/data/custodian/JP-13-BUN-L-KL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-KL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-KL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-KL ghcid_numeric: 5018267937538479238 valid_from: '2025-12-06T23:38:55.415347+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KOKUSAIBUKKYOGAKUDAIGAKUINDAIGAKUFUZOKU Library @@ -196,7 +197,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.icabs.ac.jp/library wikidata_official_website: http://www.icabs.ac.jp/library @@ -218,3 +220,30 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:37:57.909740+00:00' + source_url: http://www.icabs.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.icabs.ac.jp/wp/wp-content/themes/codiaCMS/apple-touch-icon.png + source_url: http://www.icabs.ac.jp/library + css_selector: '[document] > html.wf-a-otf-ud-reimin-pr6n-n3-active.wf-source-han-serif-tc-n7-active + > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:37:57.909740+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.icabs.ac.jp/wp/wp-content/themes/codiaCMS/apple-touch-icon.png + source_url: http://www.icabs.ac.jp/library + css_selector: '[document] > html.wf-a-otf-ud-reimin-pr6n-n3-active.wf-source-han-serif-tc-n7-active + > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T22:37:57.909740+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 6 diff --git a/data/custodian/JP-13-BUN-L-LEUT.yaml b/data/custodian/JP-13-BUN-L-LEUT.yaml index d019914632..181ecd40ce 100644 --- a/data/custodian/JP-13-BUN-L-LEUT.yaml +++ b/data/custodian/JP-13-BUN-L-LEUT.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-LEUT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-LEUT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-LEUT ghcid_numeric: 13266920833408850264 valid_from: '2025-12-06T23:38:53.282365+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Library of Economics, the University of Tokyo @@ -238,3 +239,22 @@ location: postal_code: 113-0033 street_address: 7-3-1 HONGO, Bunkyo Ku, Tokyo To, 113-0033 normalization_timestamp: '2025-12-09T12:21:19.668558+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:38:15.465387+00:00' + source_url: http://www.lib.e.u-tokyo.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.e.u-tokyo.ac.jp/wp-content/uploads/2024/04/cropped-book_logo_01_wh-180x180.png + source_url: http://www.lib.e.u-tokyo.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-24T22:38:15.465387+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-L-LHIUT.yaml b/data/custodian/JP-13-BUN-L-LHIUT.yaml index 727bb3f62d..95e750b2e5 100644 --- a/data/custodian/JP-13-BUN-L-LHIUT.yaml +++ b/data/custodian/JP-13-BUN-L-LHIUT.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-LHIUT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-LHIUT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-LHIUT ghcid_numeric: 3024109091627641492 valid_from: '2025-12-06T23:38:53.311669+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Library, Historiograhical Institute, The University of Tokyo @@ -217,3 +218,28 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:38:23.279543+00:00' + source_url: http://www.hi.u-tokyo.ac.jp/tosho/tosho.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.hi.u-tokyo.ac.jp/assets/img/common/hilogo.jpg + source_url: http://www.hi.u-tokyo.ac.jp/tosho/tosho.html + css_selector: '#header > div.header-inner > div.header-logo > h1 > a > img' + retrieved_on: '2025-12-24T22:38:23.279543+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東京大学史料編纂所 Historiographical Institute The University of Tokyo + - claim_type: og_image_url + claim_value: https://www.hi.u-tokyo.ac.jp/icon.png + source_url: http://www.hi.u-tokyo.ac.jp/tosho/tosho.html + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T22:38:23.279543+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-MERIL.yaml b/data/custodian/JP-13-BUN-L-MERIL.yaml index db9ec91410..2eb179fe93 100644 --- a/data/custodian/JP-13-BUN-L-MERIL.yaml +++ b/data/custodian/JP-13-BUN-L-MERIL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-MERIL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-MERIL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-MERIL ghcid_numeric: 10431471195705856625 valid_from: '2025-12-06T23:38:57.987631+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Mitsubishi Economic Research Institute Library @@ -151,3 +152,22 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:38:39.376362+00:00' + source_url: http://www.meri.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.meri.or.jp/apple-touch-icon-180x180.png + source_url: http://www.meri.or.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:38:39.376362+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-BUN-L-MLJMA.yaml b/data/custodian/JP-13-BUN-L-MLJMA.yaml index 902c3cbd06..c029d1009f 100644 --- a/data/custodian/JP-13-BUN-L-MLJMA.yaml +++ b/data/custodian/JP-13-BUN-L-MLJMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-MLJMA - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-MLJMA valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-MLJMA ghcid_numeric: 16677917985155692671 valid_from: '2025-12-06T23:38:58.050470+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Medical Library of the Japan Medical Association @@ -151,3 +152,37 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:38:48.393823+00:00' + source_url: https://www.med.or.jp/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.med.or.jp/n_common/images/logo_01.png + source_url: https://www.med.or.jp/index.html + css_selector: '#header > div.header_contents:nth-of-type(2) > div.header_inner.clearfix + > h1 > a > img' + retrieved_on: '2025-12-24T22:38:48.393823+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日本医師会 Japan Medical Association + - claim_type: favicon_url + claim_value: https://www.med.or.jp/favicon.ico + source_url: https://www.med.or.jp/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:38:48.393823+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.med.or.jp/n_common/images/ogpimage.jpg + source_url: https://www.med.or.jp/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T22:38:48.393823+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-BUN-L-MMSISAUT.yaml b/data/custodian/JP-13-BUN-L-MMSISAUT.yaml index a8d3d4db09..3e7713a45c 100644 --- a/data/custodian/JP-13-BUN-L-MMSISAUT.yaml +++ b/data/custodian/JP-13-BUN-L-MMSISAUT.yaml @@ -37,20 +37,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-MMSISAUT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-MMSISAUT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-MMSISAUT ghcid_numeric: 14743111381293375015 valid_from: '2025-12-06T23:38:53.306155+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Multi-media and Socio-information Studies Archive, the University of Tokyo + claim_value: Multi-media and Socio-information Studies Archive, the University of + Tokyo source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -101,11 +103,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Multi-media and Socio-information Studies Archive, the University of Tokyo + claim_value: Multi-media and Socio-information Studies Archive, the University + of Tokyo property_uri: skos:prefLabel provenance: namespace: glam @@ -164,7 +167,8 @@ wikidata_enrichment: wikidata_labels: en: Multi-media and Socio-information Studies Archive, the University of Tokyo ja: 東京大学大学院情報学環附属社会情報研究資料センター - wikidata_label_en: Multi-media and Socio-information Studies Archive, the University of Tokyo + wikidata_label_en: Multi-media and Socio-information Studies Archive, the University + of Tokyo wikidata_label_ja: 東京大学大学院情報学環附属社会情報研究資料センター wikidata_classification: instance_of: &id004 @@ -206,3 +210,31 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:39:05.435802+00:00' + source_url: http://www.center.iii.u-tokyo.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.center.iii.u-tokyo.ac.jp/wp-content/uploads/2019/10/cropped-maintitle-bg.png + source_url: http://www.center.iii.u-tokyo.ac.jp + css_selector: '#masthead > div.site-header-wrapper > div.site-identity > a.custom-logo-link + > img.custom-logo' + retrieved_on: '2025-12-24T22:39:05.435802+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 社会情報研究資料センター + - claim_type: favicon_url + claim_value: https://www.center.iii.u-tokyo.ac.jp/wp-content/uploads/2019/10/cropped-maintitle-bg.png + source_url: http://www.center.iii.u-tokyo.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-24T22:39:05.435802+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-BUN-L-OUL.yaml b/data/custodian/JP-13-BUN-L-OUL.yaml index 2cf597bfd9..d369efdcb8 100644 --- a/data/custodian/JP-13-BUN-L-OUL.yaml +++ b/data/custodian/JP-13-BUN-L-OUL.yaml @@ -209,3 +209,28 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.ocha.ac.jp/ wikidata_official_website: https://www.lib.ocha.ac.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:39:24.870209+00:00' + source_url: https://www.lib.ocha.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.ocha.ac.jp/share/imgs/icon-512.png + source_url: https://www.lib.ocha.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:39:24.870209+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.ocha.ac.jp//share/imgs/og-image-default.png + source_url: https://www.lib.ocha.ac.jp + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:39:24.870209+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-BUN-L-TL-teiseigakuentankidaigakufuzoku_library.yaml b/data/custodian/JP-13-BUN-L-TL-teiseigakuentankidaigakufuzoku_library.yaml index 7c4ab73e71..921b675687 100644 --- a/data/custodian/JP-13-BUN-L-TL-teiseigakuentankidaigakufuzoku_library.yaml +++ b/data/custodian/JP-13-BUN-L-TL-teiseigakuentankidaigakufuzoku_library.yaml @@ -205,3 +205,28 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:40:57.632025+00:00' + source_url: http://www.teisei.ac.jp/about/affiliated + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://teisei.ac.jp/wp-content/uploads/2023/02/cropped-favicon-180x180.png + source_url: http://www.teisei.ac.jp/about/affiliated + css_selector: '[document] > html > head > link:nth-of-type(38)' + retrieved_on: '2025-12-24T22:40:57.632025+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://teisei.ac.jp/wp-content/uploads/2023/04/defalt_thumbnail.png + source_url: http://www.teisei.ac.jp/about/affiliated + css_selector: '[document] > html > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-24T22:40:57.632025+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-L-TUL-toyo_university_library.yaml b/data/custodian/JP-13-BUN-L-TUL-toyo_university_library.yaml index f8d5cc8c52..8ba56e6c38 100644 --- a/data/custodian/JP-13-BUN-L-TUL-toyo_university_library.yaml +++ b/data/custodian/JP-13-BUN-L-TUL-toyo_university_library.yaml @@ -214,3 +214,37 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:19.854646+00:00' + source_url: http://www.toyo.ac.jp/site/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.toyo.ac.jp/img/common/img_logo.svg + source_url: http://www.toyo.ac.jp/site/library/index.html + css_selector: '#gheader > div.gnav__frm > h1.gnav__logo > a.gnav__logo-link > + img.gnav__logo-img' + retrieved_on: '2025-12-24T22:41:19.854646+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東洋大学 + - claim_type: favicon_url + claim_value: http://www.toyo.ac.jp/img/common/favicon.ico + source_url: http://www.toyo.ac.jp/site/library/index.html + css_selector: '[document] > html.js_domload.js_ajax_load > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:41:19.854646+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.toyo.ac.jp/site/library/ogp.jpg + source_url: http://www.toyo.ac.jp/site/library/index.html + css_selector: '[document] > html.js_domload.js_ajax_load > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T22:41:19.854646+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-BUN-L-TUL.yaml b/data/custodian/JP-13-BUN-L-TUL.yaml index e4478651d7..665c9d667a 100644 --- a/data/custodian/JP-13-BUN-L-TUL.yaml +++ b/data/custodian/JP-13-BUN-L-TUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-TUL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-TUL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-TUL ghcid_numeric: 7764332448549412777 valid_from: '2025-12-06T23:38:55.012479+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Takushoku University Library @@ -209,3 +210,20 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:28.118934+00:00' + source_url: http://www.takushoku-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.takushoku-u.ac.jp/images/standard_photo_takudai_logo.gif + source_url: http://www.takushoku-u.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T22:41:28.118934+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-BUN-L-ULALSUT.yaml b/data/custodian/JP-13-BUN-L-ULALSUT.yaml index 35e867cffd..42b08c1be2 100644 --- a/data/custodian/JP-13-BUN-L-ULALSUT.yaml +++ b/data/custodian/JP-13-BUN-L-ULALSUT.yaml @@ -37,20 +37,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-ULALSUT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-ULALSUT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-ULALSUT ghcid_numeric: 6324488349032818885 valid_from: '2025-12-06T23:38:53.279025+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: University Library for Agricultural and Life Sciences, the University of Tokyo + claim_value: University Library for Agricultural and Life Sciences, the University + of Tokyo source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -101,11 +103,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: University Library for Agricultural and Life Sciences, the University of Tokyo + claim_value: University Library for Agricultural and Life Sciences, the University + of Tokyo property_uri: skos:prefLabel provenance: namespace: glam @@ -164,7 +167,8 @@ wikidata_enrichment: wikidata_labels: en: University Library for Agricultural and Life Sciences, the University of Tokyo ja: 東京大学農学生命科学図書館 - wikidata_label_en: University Library for Agricultural and Life Sciences, the University of Tokyo + wikidata_label_en: University Library for Agricultural and Life Sciences, the University + of Tokyo wikidata_label_ja: 東京大学農学生命科学図書館 wikidata_classification: instance_of: &id004 @@ -204,3 +208,37 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:43.061892+00:00' + source_url: http://www.lib.a.u-tokyo.ac.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.a.u-tokyo.ac.jp/website2022/wp-content/uploads/2022/12/header-logo.png + source_url: http://www.lib.a.u-tokyo.ac.jp/lib + css_selector: '#header-in > div.logo.logo-header > a.site-name.site-name-text-link + > span.site-name-text > img.site-logo-image.header-site-logo-image' + retrieved_on: '2025-12-24T22:41:43.061892+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東京大学農学生命科学図書館 + - claim_type: favicon_url + claim_value: https://www.lib.a.u-tokyo.ac.jp/website2022/wp-content/uploads/2022/11/aglib-favicon-200x200.png + source_url: http://www.lib.a.u-tokyo.ac.jp/lib + css_selector: '[document] > html > head > link:nth-of-type(37)' + retrieved_on: '2025-12-24T22:41:43.061892+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://www.lib.a.u-tokyo.ac.jp/website2022/wp-content/uploads/2022/12/thumbnail.png + source_url: http://www.lib.a.u-tokyo.ac.jp/lib + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T22:41:43.061892+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-BUN-L-UTGSHSFLL.yaml b/data/custodian/JP-13-BUN-L-UTGSHSFLL.yaml index a45369e0ff..a768b66298 100644 --- a/data/custodian/JP-13-BUN-L-UTGSHSFLL.yaml +++ b/data/custodian/JP-13-BUN-L-UTGSHSFLL.yaml @@ -1,5 +1,6 @@ original_entry: - name: The University of Tokyo, Graduate school of Humanities and Sociology, Faculty of Letters, Library + name: The University of Tokyo, Graduate school of Humanities and Sociology, Faculty + of Letters, Library institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -37,20 +38,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-UTGSHSFLL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-UTGSHSFLL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-UTGSHSFLL ghcid_numeric: 8069117655326473909 valid_from: '2025-12-06T23:38:53.273715+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: The University of Tokyo, Graduate school of Humanities and Sociology, Faculty of Letters, Library + claim_value: The University of Tokyo, Graduate school of Humanities and Sociology, + Faculty of Letters, Library source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -101,11 +104,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: The University of Tokyo, Graduate school of Humanities and Sociology, Faculty of Letters, Library + claim_value: The University of Tokyo, Graduate school of Humanities and Sociology, + Faculty of Letters, Library property_uri: skos:prefLabel provenance: namespace: glam @@ -162,9 +166,11 @@ wikidata_enrichment: - P791 - P856 wikidata_labels: - en: The University of Tokyo, Graduate school of Humanities and Sociology, Faculty of Letters, Library + en: The University of Tokyo, Graduate school of Humanities and Sociology, Faculty + of Letters, Library ja: 東京大学大学院人文社会系研究科・文学部図書室 - wikidata_label_en: The University of Tokyo, Graduate school of Humanities and Sociology, Faculty of Letters, Library + wikidata_label_en: The University of Tokyo, Graduate school of Humanities and Sociology, + Faculty of Letters, Library wikidata_label_ja: 東京大学大学院人文社会系研究科・文学部図書室 wikidata_classification: instance_of: &id004 @@ -204,3 +210,22 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:41:54.164177+00:00' + source_url: http://www.l.u-tokyo.ac.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.l.u-tokyo.ac.jp/lib/content/000008099.png + source_url: http://www.l.u-tokyo.ac.jp/lib + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:41:54.164177+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-L-UTIIISGSII.yaml b/data/custodian/JP-13-BUN-L-UTIIISGSII.yaml index d8ed0a3118..7c5c2ee4b2 100644 --- a/data/custodian/JP-13-BUN-L-UTIIISGSII.yaml +++ b/data/custodian/JP-13-BUN-L-UTIIISGSII.yaml @@ -210,3 +210,31 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:42:04.111817+00:00' + source_url: http://www.lib.iii.u-tokyo.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.lib.iii.u-tokyo.ac.jp/img/logo.png + source_url: http://www.lib.iii.u-tokyo.ac.jp + css_selector: '[document] > html > body > nav.navbar.navbar-expand-md > div.container + > div.header-box.d-flex > div.header-logo.col-10 > a > img.w-100' + retrieved_on: '2025-12-24T22:42:04.111817+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東京大学大学院 情報学環・学際情報学府図書室 + - claim_type: favicon_url + claim_value: http://www.lib.iii.u-tokyo.ac.jp/img/apple-touch-icon-180x180.png + source_url: http://www.lib.iii.u-tokyo.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T22:42:04.111817+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-BUN-L-UTLOL.yaml b/data/custodian/JP-13-BUN-L-UTLOL.yaml index 1f1bbb4aa9..75ead9ef41 100644 --- a/data/custodian/JP-13-BUN-L-UTLOL.yaml +++ b/data/custodian/JP-13-BUN-L-UTLOL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-L-UTLOL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-L-UTLOL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-L-UTLOL ghcid_numeric: 16328616350112674380 valid_from: '2025-12-06T23:38:53.226940+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: University of Tsukuba Library Otsuka Library @@ -209,3 +210,22 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:42:12.935482+00:00' + source_url: http://www.tulips.tsukuba.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tulips.tsukuba.ac.jp/lib/sites/default/files/favicon-tulips.ico + source_url: http://www.tulips.tsukuba.ac.jp + css_selector: '[document] > html.front.js > head > link' + retrieved_on: '2025-12-24T22:42:12.935482+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-BUN-M-BHFM.yaml b/data/custodian/JP-13-BUN-M-BHFM.yaml index 2608a9c911..bc15f5f08b 100644 --- a/data/custodian/JP-13-BUN-M-BHFM.yaml +++ b/data/custodian/JP-13-BUN-M-BHFM.yaml @@ -1543,3 +1543,30 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/OSQJnYR98No/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:42:35.808250+00:00' + source_url: https://baseball-museum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://baseball-museum.or.jp/img/logo.png + source_url: https://baseball-museum.or.jp + css_selector: '#header > h1 > a > img.pc_only' + retrieved_on: '2025-12-24T22:42:35.808250+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 野球殿堂博物館 + - claim_type: favicon_url + claim_value: https://baseball-museum.or.jp/wp-content/uploads/2020/12/cropped-ydh_fab-180x180.png + source_url: https://baseball-museum.or.jp + css_selector: '[document] > html.sr > head > link:nth-of-type(23)' + retrieved_on: '2025-12-24T22:42:35.808250+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-BUN-M-IEMMTU.yaml b/data/custodian/JP-13-BUN-M-IEMMTU.yaml index 3a421d50f5..fc2c9a5be4 100644 --- a/data/custodian/JP-13-BUN-M-IEMMTU.yaml +++ b/data/custodian/JP-13-BUN-M-IEMMTU.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-M-IEMMTU - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-M-IEMMTU valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-M-IEMMTU ghcid_numeric: 3652819334513971197 valid_from: '2025-12-06T23:38:33.148706+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Inoue Enryo Memorial Museum,Toyo University @@ -263,3 +264,37 @@ location: postal_code: 112-8606 street_address: HAKUSAN, Bunkyo Ku, Tokyo To, 112-8606 normalization_timestamp: '2025-12-09T12:21:20.812212+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:42:50.064628+00:00' + source_url: https://www.toyo.ac.jp/about/founder/iecp/museum + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.toyo.ac.jp/img/common/img_logo.svg + source_url: https://www.toyo.ac.jp/about/founder/iecp/museum + css_selector: '#gheader > div.gnav__frm > h1.gnav__logo > a.gnav__logo-link > + img.gnav__logo-img' + retrieved_on: '2025-12-24T22:42:50.064628+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東洋大学 + - claim_type: favicon_url + claim_value: https://www.toyo.ac.jp/img/common/favicon.ico + source_url: https://www.toyo.ac.jp/about/founder/iecp/museum + css_selector: '[document] > html.js_domload.js_ajax_load > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:42:50.064628+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.toyo.ac.jp/ogp.jpg + source_url: https://www.toyo.ac.jp/about/founder/iecp/museum + css_selector: '[document] > html.js_domload.js_ajax_load > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T22:42:50.064628+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-BUN-M-JWSUNMH.yaml b/data/custodian/JP-13-BUN-M-JWSUNMH.yaml index 1592136497..68d799fdf6 100644 --- a/data/custodian/JP-13-BUN-M-JWSUNMH.yaml +++ b/data/custodian/JP-13-BUN-M-JWSUNMH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-M-JWSUNMH - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-M-JWSUNMH valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-M-JWSUNMH ghcid_numeric: 15569226067062859614 valid_from: '2025-12-06T23:38:33.153265+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JAPAN WOMEN'S UNIVERSITY NARUSE MEMORIAL HALL @@ -151,3 +152,28 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:42:59.234076+00:00' + source_url: https://www.jwu.ac.jp/unv/about/naruse_memorial/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jwu.ac.jp/unv/assets/img/common/favicon.ico + source_url: https://www.jwu.ac.jp/unv/about/naruse_memorial/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:42:59.234076+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.jwu.ac.jp/unv/assets/img/common/og_img.png + source_url: https://www.jwu.ac.jp/unv/about/naruse_memorial/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T22:42:59.234076+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-BUN-M-PMT.yaml b/data/custodian/JP-13-BUN-M-PMT.yaml index 5ec60b71b1..c37faa5b23 100644 --- a/data/custodian/JP-13-BUN-M-PMT.yaml +++ b/data/custodian/JP-13-BUN-M-PMT.yaml @@ -261,3 +261,28 @@ wikidata_enrichment: image: Printing-museum.jpg commons_category: Printing Museum, Tokyo wikidata_image: Printing-museum.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:14.814311+00:00' + source_url: https://www.printing-museum.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.printing-museum.org/assets/img/favicon/safari-pinned-tab.svg + source_url: https://www.printing-museum.org + css_selector: '[document] > html.device-others.browser-chrome > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:43:14.814311+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.printing-museum.org/assets/img/common/ogp.jpg + source_url: https://www.printing-museum.org + css_selector: '[document] > html.device-others.browser-chrome > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T22:43:14.814311+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-BUN-M-TBM.yaml b/data/custodian/JP-13-BUN-M-TBM.yaml index 1f73efa579..7d94dda866 100644 --- a/data/custodian/JP-13-BUN-M-TBM.yaml +++ b/data/custodian/JP-13-BUN-M-TBM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-M-TBM - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-M-TBM valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-M-TBM ghcid_numeric: 7650504946999099453 valid_from: '2025-12-06T23:38:33.158237+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Toyo Bunko Museum @@ -151,3 +152,28 @@ location: geonames_id: 11790632 geonames_name: Bunkyo feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:38.122573+00:00' + source_url: http://www.toyo-bunko.or.jp/museum/museum_index.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.toyo-bunko.or.jp/favicon.ico + source_url: http://www.toyo-bunko.or.jp/museum/museum_index.php + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:43:38.122573+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://toyo-bunko.or.jp/wp-content/uploads/2024/04/og.png + source_url: http://www.toyo-bunko.or.jp/museum/museum_index.php + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T22:43:38.122573+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-BUN-M-YMTYM.yaml b/data/custodian/JP-13-BUN-M-YMTYM.yaml index da7f22a507..b090997a57 100644 --- a/data/custodian/JP-13-BUN-M-YMTYM.yaml +++ b/data/custodian/JP-13-BUN-M-YMTYM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-BUN-M-YMTYM - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-BUN-M-YMTYM valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-BUN-M-YMTYM ghcid_numeric: 2251221687400712028 valid_from: '2025-12-06T23:38:33.166507+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAYOI MUSEUM TAKEHISA YUMEJI MUSEUM @@ -210,7 +211,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) wikidata_instance_of: *id005 wikidata_location: coordinates: &id008 @@ -264,3 +266,22 @@ location: postal_code: 113-0032 street_address: YAYOI, Bunkyo Ku, Tokyo To, 113-0032 normalization_timestamp: '2025-12-09T12:21:21.014777+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:45.405927+00:00' + source_url: https://www.yayoi-yumeji-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.yayoi-yumeji-museum.jp/images/common/logo.svg + source_url: https://www.yayoi-yumeji-museum.jp + css_selector: '#logo > h1 > a > img' + retrieved_on: '2025-12-24T22:43:45.405927+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 弥生美術館・竹久夢二美術館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-A-IHA-the_imperial_household_archives.yaml b/data/custodian/JP-13-CHI-A-IHA-the_imperial_household_archives.yaml index 55d3e0bc39..129540056f 100644 --- a/data/custodian/JP-13-CHI-A-IHA-the_imperial_household_archives.yaml +++ b/data/custodian/JP-13-CHI-A-IHA-the_imperial_household_archives.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-A-IHA-the_imperial_household_archives - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-A-IHA-the_imperial_household_archives valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-A-IHA-the_imperial_household_archives ghcid_numeric: 16389212483929872181 valid_from: '2025-12-06T23:38:29.471728+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Imperial Household Archives @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:52.376011+00:00' + source_url: https://www.kunaicho.go.jp/kunaicho/shinsei/kobunshokan.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kunaicho.go.jp/apple-touch-icon.png + source_url: https://www.kunaicho.go.jp/kunaicho/shinsei/kobunshokan.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:43:52.376011+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kunaicho.go.jp/common/images/ogp.png + source_url: https://www.kunaicho.go.jp/kunaicho/shinsei/kobunshokan.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T22:43:52.376011+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-A-IHA.yaml b/data/custodian/JP-13-CHI-A-IHA.yaml index c6d4efc5a1..62463367ed 100644 --- a/data/custodian/JP-13-CHI-A-IHA.yaml +++ b/data/custodian/JP-13-CHI-A-IHA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-A-IHA - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-A-IHA valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-A-IHA ghcid_numeric: 4113999193984011551 valid_from: '2025-12-06T23:35:50.025714+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Imperial Household Archives @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:43:58.277418+00:00' + source_url: https://www.kunaicho.go.jp/kunaicho/shinsei/kobunshokan.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kunaicho.go.jp/apple-touch-icon.png + source_url: https://www.kunaicho.go.jp/kunaicho/shinsei/kobunshokan.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:43:58.277418+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kunaicho.go.jp/common/images/ogp.png + source_url: https://www.kunaicho.go.jp/kunaicho/shinsei/kobunshokan.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T22:43:58.277418+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-ADTHOMN.yaml b/data/custodian/JP-13-CHI-L-ADTHOMN.yaml index 05b199ea00..26e3e6a11d 100644 --- a/data/custodian/JP-13-CHI-L-ADTHOMN.yaml +++ b/data/custodian/JP-13-CHI-L-ADTHOMN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-ADTHOMN - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-ADTHOMN valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-ADTHOMN ghcid_numeric: 1022651440433882140 valid_from: '2025-12-06T23:38:58.355678+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Archive Department, Tokyo Head Office, The Mainichi Newspapers @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:31.278327+00:00' + source_url: http://mainichi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://cdn.mainichi.jp/vol1/images/icon/mainichi/apple-touch.png + source_url: http://mainichi.jp + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T22:44:31.278327+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cdn.mainichi.jp/vol1/images/icon/mainichi/ogp.png + source_url: http://mainichi.jp + css_selector: '[document] > html > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-24T22:44:31.278327+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-AHL.yaml b/data/custodian/JP-13-CHI-L-AHL.yaml index 20bb295503..e515f5f62c 100644 --- a/data/custodian/JP-13-CHI-L-AHL.yaml +++ b/data/custodian/JP-13-CHI-L-AHL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-AHL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-AHL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-AHL ghcid_numeric: 7407637982809079317 valid_from: '2025-12-06T23:38:59.689262+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Academyhills Hirakawacho Library @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:42.802345+00:00' + source_url: http://www.academyhills.com/library/hirakawa + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.academyhills.com/favicon.ico + source_url: http://www.academyhills.com/library/hirakawa + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-24T22:44:42.802345+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.academyhills.com/prefs/tqe2it00000000oc-img/tqe2it00000o4rdr.jpg + source_url: http://www.academyhills.com/library/hirakawa + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T22:44:42.802345+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-ALNMMAT.yaml b/data/custodian/JP-13-CHI-L-ALNMMAT.yaml index cd62dc7f86..4ba30b0cb4 100644 --- a/data/custodian/JP-13-CHI-L-ALNMMAT.yaml +++ b/data/custodian/JP-13-CHI-L-ALNMMAT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-ALNMMAT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-ALNMMAT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-ALNMMAT ghcid_numeric: 14787767787898249378 valid_from: '2025-12-06T23:38:58.048045+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Art Library, The National Museum of Modern Art, Tokyo @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:49.215572+00:00' + source_url: http://www.momat.go.jp/am/visit/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.momat.go.jp/wp-content/themes/momat/images/favicon/favicon.svg + source_url: http://www.momat.go.jp/am/visit/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:44:49.215572+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.momat.go.jp/wp-content/uploads/2022/12/og-momat.png + source_url: http://www.momat.go.jp/am/visit/library + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T22:44:49.215572+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-L-APC.yaml b/data/custodian/JP-13-CHI-L-APC.yaml index 7a18036bdd..bad50479bd 100644 --- a/data/custodian/JP-13-CHI-L-APC.yaml +++ b/data/custodian/JP-13-CHI-L-APC.yaml @@ -152,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:44:57.102112+00:00' + source_url: https://www.asahikasei-pharma.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.asahikasei-pharma.co.jp/pharma/favicon.ico + source_url: https://www.asahikasei-pharma.co.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:44:57.102112+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-BFGLINS.yaml b/data/custodian/JP-13-CHI-L-BFGLINS.yaml index 102a1fce70..da2f62b594 100644 --- a/data/custodian/JP-13-CHI-L-BFGLINS.yaml +++ b/data/custodian/JP-13-CHI-L-BFGLINS.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-BFGLINS - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-BFGLINS valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-BFGLINS ghcid_numeric: 18328713894454643533 valid_from: '2025-12-06T23:38:58.957668+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Biblioteca Federico García Lorca (Institution name in Spanish) @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:07.925888+00:00' + source_url: http://tokio.cervantes.es/jp/library_spanish/general_information_library_spanish.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://comunes.cervantes.es/1_STYLE/imagenes/favico.ico + source_url: http://tokio.cervantes.es/jp/library_spanish/general_information_library_spanish.htm + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T22:45:07.925888+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-BLJBA.yaml b/data/custodian/JP-13-CHI-L-BLJBA.yaml index 5f98fc6ab4..33059f6866 100644 --- a/data/custodian/JP-13-CHI-L-BLJBA.yaml +++ b/data/custodian/JP-13-CHI-L-BLJBA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-BLJBA - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-BLJBA valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-BLJBA ghcid_numeric: 16517168585320783012 valid_from: '2025-12-06T23:38:57.847564+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Bankers Library, Japanese Bankers Association @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:13.494938+00:00' + source_url: http://www.zenginkyo.or.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.zenginkyo.or.jp/_common/img/logo/logo.png + source_url: http://www.zenginkyo.or.jp/library + css_selector: '[document] > html > body > header.header-global > img' + retrieved_on: '2025-12-24T22:45:13.494938+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-CL-chiyodakuritsukandamachikado_library.yaml b/data/custodian/JP-13-CHI-L-CL-chiyodakuritsukandamachikado_library.yaml index f2a38d98fa..5f440538d8 100644 --- a/data/custodian/JP-13-CHI-L-CL-chiyodakuritsukandamachikado_library.yaml +++ b/data/custodian/JP-13-CHI-L-CL-chiyodakuritsukandamachikado_library.yaml @@ -210,3 +210,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.chiyoda.tokyo.jp/facilities/kanda/ wikidata_official_website: http://www.library.chiyoda.tokyo.jp/facilities/kanda/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:25.556984+00:00' + source_url: https://www.library.chiyoda.tokyo.jp/kanda + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.chiyoda.tokyo.jp/kanda + css_selector: '[document] > html > body.information.lib_top > div.wrapper > header.header + > div.header__inner > h1.header__logo > a > img' + retrieved_on: '2025-12-24T22:45:25.556984+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 千代田区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.library.chiyoda.tokyo.jp/kanda + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:45:25.556984+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-CL-chiyodakuritsushoheimachikado_library.yaml b/data/custodian/JP-13-CHI-L-CL-chiyodakuritsushoheimachikado_library.yaml index b889e02b14..ad87fbcce6 100644 --- a/data/custodian/JP-13-CHI-L-CL-chiyodakuritsushoheimachikado_library.yaml +++ b/data/custodian/JP-13-CHI-L-CL-chiyodakuritsushoheimachikado_library.yaml @@ -210,3 +210,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.chiyoda.tokyo.jp/facilities/shohei/ wikidata_official_website: http://www.library.chiyoda.tokyo.jp/facilities/shohei/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:35.006356+00:00' + source_url: https://www.library.chiyoda.tokyo.jp/shohei + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.chiyoda.tokyo.jp/shohei + css_selector: '[document] > html > body.information.lib_top > div.wrapper > header.header + > div.header__inner > h1.header__logo > a > img' + retrieved_on: '2025-12-24T22:45:35.006356+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 千代田区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.library.chiyoda.tokyo.jp/shohei + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:45:35.006356+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-CL-chiyodakuritsuyombancho_library.yaml b/data/custodian/JP-13-CHI-L-CL-chiyodakuritsuyombancho_library.yaml index 488f2069da..03fdf5aceb 100644 --- a/data/custodian/JP-13-CHI-L-CL-chiyodakuritsuyombancho_library.yaml +++ b/data/custodian/JP-13-CHI-L-CL-chiyodakuritsuyombancho_library.yaml @@ -210,3 +210,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.chiyoda.tokyo.jp/facilities/yonbancho/ wikidata_official_website: http://www.library.chiyoda.tokyo.jp/facilities/yonbancho/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:43.384746+00:00' + source_url: https://www.library.chiyoda.tokyo.jp/yonbancho + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.chiyoda.tokyo.jp/yonbancho + css_selector: '[document] > html > body.information.lib_top > div.wrapper > header.header + > div.header__inner > h1.header__logo > a > img' + retrieved_on: '2025-12-24T22:45:43.384746+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 千代田区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.library.chiyoda.tokyo.jp/yonbancho + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:45:43.384746+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-CL-the_chemistry_library.yaml b/data/custodian/JP-13-CHI-L-CL-the_chemistry_library.yaml index cd7cca445a..b97f6efc8a 100644 --- a/data/custodian/JP-13-CHI-L-CL-the_chemistry_library.yaml +++ b/data/custodian/JP-13-CHI-L-CL-the_chemistry_library.yaml @@ -261,3 +261,22 @@ wikidata_enrichment: commons_category: Foreign Correspondents' Club of Japan image: Fccj.jpg wikidata_image: Fccj.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:45:51.281022+00:00' + source_url: http://www.chemistry.or.jp/societyguide/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chemistry.or.jp/favicon.ico + source_url: http://www.chemistry.or.jp/societyguide/library + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:45:51.281022+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-CL.yaml b/data/custodian/JP-13-CHI-L-CL.yaml index 9ab91acf23..e2b4da524e 100644 --- a/data/custodian/JP-13-CHI-L-CL.yaml +++ b/data/custodian/JP-13-CHI-L-CL.yaml @@ -211,3 +211,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.chiyoda.tokyo.jp/facilities/chiyoda/ wikidata_official_website: http://www.library.chiyoda.tokyo.jp/facilities/chiyoda/ +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:01.970846+00:00' + source_url: https://www.library.chiyoda.tokyo.jp/chiyoda + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.chiyoda.tokyo.jp/chiyoda + css_selector: '[document] > html > body.information.lib_top > div.wrapper > header.header + > div.header__inner > h1.header__logo > a > img' + retrieved_on: '2025-12-24T22:46:01.970846+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 千代田区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.library.chiyoda.tokyo.jp/chiyoda + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:46:01.970846+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-DHUML.yaml b/data/custodian/JP-13-CHI-L-DHUML.yaml index d3fa7decb0..71ab3d0ca5 100644 --- a/data/custodian/JP-13-CHI-L-DHUML.yaml +++ b/data/custodian/JP-13-CHI-L-DHUML.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-DHUML - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-DHUML valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-DHUML ghcid_numeric: 9355610799816315440 valid_from: '2025-12-06T23:38:55.434708+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Digital Hollywood University Media Library @@ -209,3 +210,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:33.616753+00:00' + source_url: http://www.dhw.ac.jp/profile/facility/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.dhw.ac.jp/wp/wp-content/uploads/2023/08/cropped-touch-icon-180x180-1-180x180.png + source_url: http://www.dhw.ac.jp/profile/facility/library + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-24T22:46:33.616753+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.dhw.ac.jp/wp/wp-content/uploads/2023/08/DHU_og-image.png + source_url: http://www.dhw.ac.jp/profile/facility/library + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T22:46:33.616753+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-L-EISU.yaml b/data/custodian/JP-13-CHI-L-EISU.yaml index c9f60dae42..6914ff18ba 100644 --- a/data/custodian/JP-13-CHI-L-EISU.yaml +++ b/data/custodian/JP-13-CHI-L-EISU.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-EISU - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-EISU valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-EISU ghcid_numeric: 5610257200220596424 valid_from: '2025-12-06T23:38:54.958919+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: European Institute, Sophia University @@ -204,3 +205,30 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:43.811956+00:00' + source_url: http://dept.sophia.ac.jp/is/ei/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://dept.sophia.ac.jp/is/ei/wp-content/themes/ei/img/logo.png + source_url: http://dept.sophia.ac.jp/is/ei/library + css_selector: '#headerCenter > h1.pt15 > a > img' + retrieved_on: '2025-12-24T22:46:43.811956+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://dept.sophia.ac.jp/is/ei/favicon.ico + source_url: http://dept.sophia.ac.jp/is/ei/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:46:43.811956+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-FALBN.yaml b/data/custodian/JP-13-CHI-L-FALBN.yaml index 7bd0957916..170b86c394 100644 --- a/data/custodian/JP-13-CHI-L-FALBN.yaml +++ b/data/custodian/JP-13-CHI-L-FALBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-FALBN - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-FALBN valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-FALBN ghcid_numeric: 15782392644445871777 valid_from: '2025-12-06T23:38:53.038637+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Forestry Agency Library, Branch of the NDL @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:46:57.228499+00:00' + source_url: https://www.rinya.maff.go.jp/j/tosyo/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rinya.maff.go.jp/j/shared_new/shared/images/rinya.ico + source_url: https://www.rinya.maff.go.jp/j/tosyo/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:46:57.228499+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-FCCJ.yaml b/data/custodian/JP-13-CHI-L-FCCJ.yaml index e0fc958c00..7617a6ff3c 100644 --- a/data/custodian/JP-13-CHI-L-FCCJ.yaml +++ b/data/custodian/JP-13-CHI-L-FCCJ.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-FCCJ - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-FCCJ valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-FCCJ ghcid_numeric: 18271439986589307927 valid_from: '2025-12-06T23:38:58.895601+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Foreign Correspondents' Club of Japan @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:04.367906+00:00' + source_url: http://www.fccj.or.jp/facilities/library-and-workroom.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.fccj.or.jp/themes/fccj/favicon.ico + source_url: http://www.fccj.or.jp/facilities/library-and-workroom.html + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:47:04.367906+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-GS.yaml b/data/custodian/JP-13-CHI-L-GS.yaml index 89dc0d00a4..a52bfc8142 100644 --- a/data/custodian/JP-13-CHI-L-GS.yaml +++ b/data/custodian/JP-13-CHI-L-GS.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-GS - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-GS valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-GS ghcid_numeric: 11547479803518545714 valid_from: '2025-12-06T23:38:58.730894+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: GALLERY SATSU @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:16.436824+00:00' + source_url: http://www.satsu.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kajabi-storefronts-production.kajabi-cdn.com/kajabi-storefronts-production/themes/1171771/settings_images/x5YB3Y7xSgC8MJ2my6JC_favi-01.png?v=2 + source_url: http://www.satsu.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:47:16.436824+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://kajabi-storefronts-production.kajabi-cdn.com/kajabi-storefronts-production/sites/65914/images/yceMhXrQju9J0Jgyq1gT_satsu01_new.jpg + source_url: http://www.satsu.jp + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-24T22:47:16.436824+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-GSMGUL.yaml b/data/custodian/JP-13-CHI-L-GSMGUL.yaml index bed4b95f65..838d17cd2d 100644 --- a/data/custodian/JP-13-CHI-L-GSMGUL.yaml +++ b/data/custodian/JP-13-CHI-L-GSMGUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-GSMGUL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-GSMGUL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-GSMGUL ghcid_numeric: 1400298189421866434 valid_from: '2025-12-06T23:38:55.452497+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Graduate School of Management, Globis University Library @@ -204,3 +205,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:47:26.544661+00:00' + source_url: http://mba.globis.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://mba.globis.ac.jp/favicon_02.ico + source_url: http://mba.globis.ac.jp + css_selector: '[document] > html > body > link' + retrieved_on: '2025-12-24T22:47:26.544661+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mba.globis.ac.jp/assets/img/og/like.jpg + source_url: http://mba.globis.ac.jp + css_selector: '[document] > html > body > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:47:26.544661+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-HURCIJSH.yaml b/data/custodian/JP-13-CHI-L-HURCIJSH.yaml index c74792e599..922c0a0d9f 100644 --- a/data/custodian/JP-13-CHI-L-HURCIJSH.yaml +++ b/data/custodian/JP-13-CHI-L-HURCIJSH.yaml @@ -210,3 +210,30 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:01.198419+00:00' + source_url: http://hijas.hosei.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://hijas.hosei.ac.jp/wp/wp-content/themes/hijas/images/en/logo_en.png + source_url: http://hijas.hosei.ac.jp + css_selector: '#logo > a > img' + retrieved_on: '2025-12-24T22:49:01.198419+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Hosei University Research Center for International Japanese Studies + - claim_type: favicon_url + claim_value: https://hijas.hosei.ac.jp/wp/wp-content/themes/hijas/apple-touch-icon.png + source_url: http://hijas.hosei.ac.jp + css_selector: '[document] > html.no-js > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:49:01.198419+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 6 diff --git a/data/custodian/JP-13-CHI-L-ICCSU.yaml b/data/custodian/JP-13-CHI-L-ICCSU.yaml index 03eaff1b65..09a009aa81 100644 --- a/data/custodian/JP-13-CHI-L-ICCSU.yaml +++ b/data/custodian/JP-13-CHI-L-ICCSU.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-ICCSU - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-ICCSU valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-ICCSU ghcid_numeric: 674800594831971326 valid_from: '2025-12-06T23:38:54.966974+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Institute for Christian Culture, Sophia University @@ -204,3 +205,30 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:36.145227+00:00' + source_url: http://dept.sophia.ac.jp/is/icc/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://dept.sophia.ac.jp/is/icc/wp-content/themes/ibero/img/logo.png + source_url: http://dept.sophia.ac.jp/is/icc/library + css_selector: '#headerCenter > h1.pt15 > a > img' + retrieved_on: '2025-12-24T22:49:36.145227+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://dept.sophia.ac.jp/is/icc/favicon.ico + source_url: http://dept.sophia.ac.jp/is/icc/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:49:36.145227+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-IEIJ.yaml b/data/custodian/JP-13-CHI-L-IEIJ.yaml index 8670a69421..eb5749de18 100644 --- a/data/custodian/JP-13-CHI-L-IEIJ.yaml +++ b/data/custodian/JP-13-CHI-L-IEIJ.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-IEIJ - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-IEIJ valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-IEIJ ghcid_numeric: 3166522519853916217 valid_from: '2025-12-06T23:38:58.792242+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Illuminating Engineering Institute of Japan @@ -151,3 +152,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:49:54.338870+00:00' + source_url: http://www.ieij.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.ieij.or.jp/images/common/logo.png + source_url: http://www.ieij.or.jp + css_selector: '[document] > html > body > div.wrapper.pg_top > header.header > + div.container > div.colWrap.mdl > h1.logo > a > img' + retrieved_on: '2025-12-24T22:49:54.338870+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 一般社団法人 照明学会 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-IIPL.yaml b/data/custodian/JP-13-CHI-L-IIPL.yaml index aaa655a825..eca0a435a4 100644 --- a/data/custodian/JP-13-CHI-L-IIPL.yaml +++ b/data/custodian/JP-13-CHI-L-IIPL.yaml @@ -152,3 +152,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:50:05.417637+00:00' + source_url: https://www.iip.or.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.iip.or.jp/toppage/images/logo.png + source_url: https://www.iip.or.jp/library + css_selector: '[document] > html > body > header > div.container-fluid.bg-light + > div.container > div.row.px-0 > div.col-sm-12.col-md-6 > a > img.img-fluid' + retrieved_on: '2025-12-24T22:50:05.417637+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 一般財団法人知的財産研究教育財団 知的財産研究所 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-IMTSU.yaml b/data/custodian/JP-13-CHI-L-IMTSU.yaml index 25a4dc0e9b..715a379436 100644 --- a/data/custodian/JP-13-CHI-L-IMTSU.yaml +++ b/data/custodian/JP-13-CHI-L-IMTSU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-IMTSU - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-IMTSU valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-IMTSU ghcid_numeric: 2670654303220386089 valid_from: '2025-12-06T23:38:54.956282+00:00' @@ -106,8 +107,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Institute of Medieval Thought, Sophia University @@ -212,3 +213,30 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:50:15.575197+00:00' + source_url: http://dept.sophia.ac.jp/is/imdthght + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://dept.sophia.ac.jp/is/imdthght/wp-content/themes/imdthght/img/logo.png + source_url: http://dept.sophia.ac.jp/is/imdthght + css_selector: '#headerCenter > h1.pt15 > a > img' + retrieved_on: '2025-12-24T22:50:15.575197+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://dept.sophia.ac.jp/is/imdthght/favicon.ico + source_url: http://dept.sophia.ac.jp/is/imdthght + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:50:15.575197+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-J.yaml b/data/custodian/JP-13-CHI-L-J.yaml index d111135178..16ce4bef9b 100644 --- a/data/custodian/JP-13-CHI-L-J.yaml +++ b/data/custodian/JP-13-CHI-L-J.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-J - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-J valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-J ghcid_numeric: 15107103654714959533 valid_from: '2025-12-06T23:38:54.961569+00:00' @@ -106,8 +107,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JOCHIDAIGAKUIBEROAMERIKAKENKYUSHO @@ -232,3 +233,30 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:50:36.466353+00:00' + source_url: http://dept.sophia.ac.jp/is/ibero/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://dept.sophia.ac.jp/is/ibero/wp-content/themes/ibero/img/logo.png + source_url: http://dept.sophia.ac.jp/is/ibero/library + css_selector: '#headerCenter > h1.pt15 > a > img' + retrieved_on: '2025-12-24T22:50:36.466353+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://dept.sophia.ac.jp/is/ibero/favicon.ico + source_url: http://dept.sophia.ac.jp/is/ibero/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:50:36.466353+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-JACNTL.yaml b/data/custodian/JP-13-CHI-L-JACNTL.yaml index 1f95ed9894..cc6d23cdbe 100644 --- a/data/custodian/JP-13-CHI-L-JACNTL.yaml +++ b/data/custodian/JP-13-CHI-L-JACNTL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-JACNTL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-JACNTL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-JACNTL ghcid_numeric: 14263762937976832661 valid_from: '2025-12-06T23:38:58.915639+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Japan Arts Council National Theatre Library @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:50:50.244763+00:00' + source_url: http://www.ntj.jac.go.jp/tradition/lib.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ntj.jac.go.jp/assets/images/shared/apple-touch-icon.png + source_url: http://www.ntj.jac.go.jp/tradition/lib.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T22:50:50.244763+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ntj.jac.go.jp/assets/images/shared/ogimage.png + source_url: http://www.ntj.jac.go.jp/tradition/lib.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T22:50:50.244763+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-JCMJL.yaml b/data/custodian/JP-13-CHI-L-JCMJL.yaml index a1733ef0ac..38b5467571 100644 --- a/data/custodian/JP-13-CHI-L-JCMJL.yaml +++ b/data/custodian/JP-13-CHI-L-JCMJL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-JCMJL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-JCMJL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-JCMJL ghcid_numeric: 7767387612961845669 valid_from: '2025-12-06T23:38:58.904613+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JCII Camera Museum JCII LIBRARY @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:08.457811+00:00' + source_url: http://www.jcii-cameramuseum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jcii-cameramuseum.jp/wp-content/uploads/2024/04/jciicameramuseumlogo2-336x336.png + source_url: http://www.jcii-cameramuseum.jp + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T22:51:08.457811+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-JIIAL.yaml b/data/custodian/JP-13-CHI-L-JIIAL.yaml index 64a90a5631..386a1d2ead 100644 --- a/data/custodian/JP-13-CHI-L-JIIAL.yaml +++ b/data/custodian/JP-13-CHI-L-JIIAL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-JIIAL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-JIIAL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-JIIAL ghcid_numeric: 10042058632967127972 valid_from: '2025-12-06T23:38:57.919007+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Japan Institute of Internatioal Affairs Library @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:25.178730+00:00' + source_url: https://www2.jiia.or.jp/library/lib_annai.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www2.jiia.or.jp/apple-touch-icon.png + source_url: https://www2.jiia.or.jp/library/lib_annai.php + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:51:25.178730+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.jiia.or.jp/jpn/assets/images/ogp.png + source_url: https://www2.jiia.or.jp/library/lib_annai.php + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T22:51:25.178730+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-JIIMA.yaml b/data/custodian/JP-13-CHI-L-JIIMA.yaml index 08767877bf..2360de9db5 100644 --- a/data/custodian/JP-13-CHI-L-JIIMA.yaml +++ b/data/custodian/JP-13-CHI-L-JIIMA.yaml @@ -152,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:34.440109+00:00' + source_url: http://www.jiima.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jiima.or.jp/wp-content/uploads/site-img/cropped-fav-180x180.png + source_url: http://www.jiima.or.jp + css_selector: '[document] > html > head > link:nth-of-type(30)' + retrieved_on: '2025-12-24T22:51:34.440109+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-L-JMCML.yaml b/data/custodian/JP-13-CHI-L-JMCML.yaml index e2ad1f198b..c6217b316e 100644 --- a/data/custodian/JP-13-CHI-L-JMCML.yaml +++ b/data/custodian/JP-13-CHI-L-JMCML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-JMCML - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-JMCML valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-JMCML ghcid_numeric: 1404412948482758724 valid_from: '2025-12-06T23:38:57.648814+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Japan Maritime Center, Maritime Library @@ -151,3 +152,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:51:45.366277+00:00' + source_url: https://www.jpmac.or.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.jpmac.or.jp/img/img_logo01.png + source_url: https://www.jpmac.or.jp/library + css_selector: '#header > div.drawer:nth-of-type(2) > div.drawer_inner > p.m_logo + > a > img' + retrieved_on: '2025-12-24T22:51:45.366277+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: JMC(Japan Maritime Center) 公益財団法人 日本海事センター + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-JRIIMDB.yaml b/data/custodian/JP-13-CHI-L-JRIIMDB.yaml index 586c908602..f105b09c0f 100644 --- a/data/custodian/JP-13-CHI-L-JRIIMDB.yaml +++ b/data/custodian/JP-13-CHI-L-JRIIMDB.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-JRIIMDB - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-JRIIMDB valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-JRIIMDB ghcid_numeric: 13558025664281300432 valid_from: '2025-12-06T23:38:57.937571+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JMA Research Institute Inc., Marketing Data Bank @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:31.976668+00:00' + source_url: https://mdb-biz.jmar.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ferret-one.akamaized.net/images/603dafb372de783344e165d2/original.png?utime=1614655411 + source_url: https://mdb-biz.jmar.co.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:52:31.976668+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://ferret-one.akamaized.net/images/604076261ca1c754235fa854/large.png?utime=1614837286 + source_url: https://mdb-biz.jmar.co.jp + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T22:52:31.976668+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-JTA.yaml b/data/custodian/JP-13-CHI-L-JTA.yaml index ea9b6b1f36..acb5963317 100644 --- a/data/custodian/JP-13-CHI-L-JTA.yaml +++ b/data/custodian/JP-13-CHI-L-JTA.yaml @@ -152,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:52:41.327589+00:00' + source_url: http://www.kanzei.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.kanzei.or.jp/wp-content/themes/kanzei/img/favicon.ico + source_url: http://www.kanzei.or.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:52:41.327589+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu.yaml b/data/custodian/JP-13-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu.yaml index 85bb1d2918..41ede82d8f 100644 --- a/data/custodian/JP-13-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu.yaml +++ b/data/custodian/JP-13-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-K-koekishadanhojinnihondorokyokaitoshoshitsu ghcid_numeric: 10396019744585775251 valid_from: '2025-12-06T23:38:58.945952+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KOEKISHADANHOJINNIHONDOROKYOKAITOSHOSHITSU @@ -151,3 +152,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:53:32.130192+00:00' + source_url: http://www.road.or.jp/profile/library.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.road.or.jp/img/logo_h.png + source_url: http://www.road.or.jp/profile/library.html + css_selector: '#header > div.header-top > div.header-wrapper > div.header-logo + > a > img' + retrieved_on: '2025-12-24T22:53:32.130192+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu.yaml b/data/custodian/JP-13-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu.yaml index e9124fab2c..453abd96b0 100644 --- a/data/custodian/JP-13-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu.yaml +++ b/data/custodian/JP-13-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-K-koekizaidanhojintetsudokosaikaifukushishiryoshitsu ghcid_numeric: 11674169774709001963 valid_from: '2025-12-06T23:38:58.846050+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KOEKIZAIDANHOJINTETSUDOKOSAIKAIFUKUSHISHIRYOSHITSU @@ -151,3 +152,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:53:53.969442+00:00' + source_url: http://www.kousaikai.or.jp/document + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.kousaikai.or.jp/wp-content/themes/kousai/images/kousaikai_top_logo.png + source_url: http://www.kousaikai.or.jp/document + css_selector: '#main-header > section.top-menu-bar > div.container.clearfix > + div.logo > h1 > a > img' + retrieved_on: '2025-12-24T22:53:53.969442+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 公益財団法人鉄道弘済会 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-KG.yaml b/data/custodian/JP-13-CHI-L-KG.yaml index e5c30861ce..63ec357ef1 100644 --- a/data/custodian/JP-13-CHI-L-KG.yaml +++ b/data/custodian/JP-13-CHI-L-KG.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-KG - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-KG valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-KG ghcid_numeric: 902451208046548854 valid_from: '2025-12-06T23:38:59.948666+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KADOKAWA genponshitsu @@ -151,3 +152,37 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:17.276833+00:00' + source_url: https://www.kadokawa.co.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://static.kadokawa.co.jp/common/img/logo_kadokawa.png + source_url: https://www.kadokawa.co.jp + css_selector: '#header > div.inner > div.header-logo:nth-of-type(2) > h2.kadokawa-logo + > a > img' + retrieved_on: '2025-12-24T22:54:17.276833+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: KADOKAWA + - claim_type: favicon_url + claim_value: https://static.kadokawa.co.jp/apple-touch-icon.png?20251126 + source_url: https://www.kadokawa.co.jp + css_selector: '[document] > html.js.no-touch > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:54:17.276833+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://static.kadokawa.co.jp/assets/img/ogp.png + source_url: https://www.kadokawa.co.jp + css_selector: '[document] > html.js.no-touch > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T22:54:17.276833+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-KLCL.yaml b/data/custodian/JP-13-CHI-L-KLCL.yaml index f41bb31c27..a11d8b7b61 100644 --- a/data/custodian/JP-13-CHI-L-KLCL.yaml +++ b/data/custodian/JP-13-CHI-L-KLCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-KLCL - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-KLCL valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-KLCL ghcid_numeric: 12587665989560351041 valid_from: '2025-12-06T23:38:54.852342+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KYORITSUJOSHIDAIGAKU Library (CHUO Library ) @@ -204,3 +205,38 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:34.282762+00:00' + source_url: http://www.kyoritsu-wu.ac.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.kyoritsu-wu.ac.jp/lib/img/common/ft_logo.png + source_url: http://www.kyoritsu-wu.ac.jp/lib + css_selector: '[document] > html.lib.noTouchDevice > body > div.wrapper.top > + footer.footBlock.borderDecoration > div.footBlock__inner > nav.footLocalNav + > div.footLocalNav__inner > div.footLocalNav__left > h5 > a > img' + retrieved_on: '2025-12-24T22:54:34.282762+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: http://www.kyoritsu-wu.ac.jp/favicon.ico + source_url: http://www.kyoritsu-wu.ac.jp/lib + css_selector: '[document] > html.lib.noTouchDevice > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T22:54:34.282762+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.kyoritsu-wu.ac.jp/lib/img/ogimg.jpg + source_url: http://www.kyoritsu-wu.ac.jp/lib + css_selector: '[document] > html.lib.noTouchDevice > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T22:54:34.282762+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-LCGNMMAT.yaml b/data/custodian/JP-13-CHI-L-LCGNMMAT.yaml index f77a45aea6..1db3e21b2b 100644 --- a/data/custodian/JP-13-CHI-L-LCGNMMAT.yaml +++ b/data/custodian/JP-13-CHI-L-LCGNMMAT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-LCGNMMAT - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-LCGNMMAT valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-LCGNMMAT ghcid_numeric: 9126685869246435153 valid_from: '2025-12-06T23:38:58.855911+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Library, Crafts Gallery, The National Museum of Modern Art, Tokyo @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:51.145210+00:00' + source_url: http://www.momat.go.jp/cg/visit/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.momat.go.jp/craft-museum/wp-content/themes/craft-museum/images/favicon/favicon.svg + source_url: http://www.momat.go.jp/cg/visit/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T22:54:51.145210+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.momat.go.jp/craft-museum/wp-content/themes/craft-museum/images/access/car_ja.webp + source_url: http://www.momat.go.jp/cg/visit/library + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T22:54:51.145210+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-L-LDDPPPRIMA.yaml b/data/custodian/JP-13-CHI-L-LDDPPPRIMA.yaml index b14984cf59..494e24bf6a 100644 --- a/data/custodian/JP-13-CHI-L-LDDPPPRIMA.yaml +++ b/data/custodian/JP-13-CHI-L-LDDPPPRIMA.yaml @@ -1,6 +1,6 @@ original_entry: - name: Library Division, Department of Planning and Publicity, Policy Research Institute, Ministry of Agriculture, Forestry - and Fisheries + name: Library Division, Department of Planning and Publicity, Policy Research Institute, + Ministry of Agriculture, Forestry and Fisheries institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -33,21 +33,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-LDDPPPRIMA - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-LDDPPPRIMA valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-LDDPPPRIMA ghcid_numeric: 7474069751013863301 valid_from: '2025-12-06T23:38:57.567606+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Library Division, Department of Planning and Publicity, Policy Research Institute, Ministry of Agriculture, - Forestry and Fisheries + claim_value: Library Division, Department of Planning and Publicity, Policy Research + Institute, Ministry of Agriculture, Forestry and Fisheries source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -98,12 +99,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Library Division, Department of Planning and Publicity, Policy Research Institute, Ministry of Agriculture, - Forestry and Fisheries + claim_value: Library Division, Department of Planning and Publicity, Policy Research + Institute, Ministry of Agriculture, Forestry and Fisheries property_uri: skos:prefLabel provenance: namespace: glam @@ -154,3 +155,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:54:58.581095+00:00' + source_url: http://www.maff.go.jp/primaff/about/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.maff.go.jp/primaff/shared_new/shared/images/affrc.ico + source_url: http://www.maff.go.jp/primaff/about/library/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:54:58.581095+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-LEERRCNIEP.yaml b/data/custodian/JP-13-CHI-L-LEERRCNIEP.yaml index 0a447f9e7c..d2ccf417e1 100644 --- a/data/custodian/JP-13-CHI-L-LEERRCNIEP.yaml +++ b/data/custodian/JP-13-CHI-L-LEERRCNIEP.yaml @@ -155,3 +155,20 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:07.814934+00:00' + source_url: http://www.nier.go.jp/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.nier.go.jp/assets/common/img/ogp.png + source_url: http://www.nier.go.jp/library/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T22:55:07.814934+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-LGIIJ.yaml b/data/custodian/JP-13-CHI-L-LGIIJ.yaml index 7daade3963..4f016d0456 100644 --- a/data/custodian/JP-13-CHI-L-LGIIJ.yaml +++ b/data/custodian/JP-13-CHI-L-LGIIJ.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-LGIIJ - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-LGIIJ valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-LGIIJ ghcid_numeric: 11211911224130625350 valid_from: '2025-12-06T23:38:57.794621+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Library, The General Insurance Institute of Japan @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:16.317630+00:00' + source_url: http://www.sonposoken.or.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sonposoken.or.jp/wp-content/themes/sonposoken2016j/images/sonposoken.png + source_url: http://www.sonposoken.or.jp/library + css_selector: '[document] > html.w-mod-js.w-mod-no-touch > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T22:55:16.317630+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-LIICSU.yaml b/data/custodian/JP-13-CHI-L-LIICSU.yaml index b1d0814938..7b59aa754f 100644 --- a/data/custodian/JP-13-CHI-L-LIICSU.yaml +++ b/data/custodian/JP-13-CHI-L-LIICSU.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-LIICSU - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-LIICSU valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-LIICSU ghcid_numeric: 3619219278795466414 valid_from: '2025-12-06T23:38:54.969609+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Linguistic Institute for International Communication, Sophia University @@ -165,7 +166,8 @@ wikidata_enrichment: wikidata_labels: en: Linguistic Institute for International Communication, Sophia University ja: 上智大学国際言語情報研究所 - wikidata_label_en: Linguistic Institute for International Communication, Sophia University + wikidata_label_en: Linguistic Institute for International Communication, Sophia + University wikidata_label_ja: 上智大学国際言語情報研究所 wikidata_classification: instance_of: &id004 @@ -205,3 +207,30 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:25.863523+00:00' + source_url: http://dept.sophia.ac.jp/is/solific/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://dept.sophia.ac.jp/is/solific/wp-content/themes/solific/img/logo.png + source_url: http://dept.sophia.ac.jp/is/solific/library + css_selector: '#headerCenter > h1.pt15 > a > img' + retrieved_on: '2025-12-24T22:55:25.863523+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://dept.sophia.ac.jp/is/solific/favicon.ico + source_url: http://dept.sophia.ac.jp/is/solific/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:55:25.863523+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-MAFFLBN.yaml b/data/custodian/JP-13-CHI-L-MAFFLBN.yaml index d858b405fc..e9d65dd5ac 100644 --- a/data/custodian/JP-13-CHI-L-MAFFLBN.yaml +++ b/data/custodian/JP-13-CHI-L-MAFFLBN.yaml @@ -32,20 +32,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-MAFFLBN - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-MAFFLBN valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-MAFFLBN ghcid_numeric: 4757097962481343333 valid_from: '2025-12-06T23:38:53.036319+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Ministry of Agriculture, Forestry and Fisheries Library, Branch of the NDL + claim_value: Ministry of Agriculture, Forestry and Fisheries Library, Branch of + the NDL source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +98,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Ministry of Agriculture, Forestry and Fisheries Library, Branch of the NDL + claim_value: Ministry of Agriculture, Forestry and Fisheries Library, Branch of + the NDL property_uri: skos:prefLabel provenance: namespace: glam @@ -151,3 +154,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:51.146247+00:00' + source_url: https://www.maff.go.jp/j/library/portal/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.maff.go.jp/j/shared_new/shared/images/maff.ico + source_url: https://www.maff.go.jp/j/library/portal/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:55:51.146247+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-MELBN.yaml b/data/custodian/JP-13-CHI-L-MELBN.yaml index 492ff266cc..705878b114 100644 --- a/data/custodian/JP-13-CHI-L-MELBN.yaml +++ b/data/custodian/JP-13-CHI-L-MELBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-MELBN - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-MELBN valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-MELBN ghcid_numeric: 15318445346574188828 valid_from: '2025-12-06T23:38:53.052675+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ministry of the Environment Library, Branch of the NDL @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:55:59.792737+00:00' + source_url: https://www.env.go.jp/guide/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.env.go.jp/guide/library + source_url: https://www.env.go.jp/guide/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:55:59.792737+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.env.go.jp/content/000078974.jpg + source_url: https://www.env.go.jp/guide/library + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T22:55:59.792737+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-METILBN.yaml b/data/custodian/JP-13-CHI-L-METILBN.yaml index c7094a580d..778f715c88 100644 --- a/data/custodian/JP-13-CHI-L-METILBN.yaml +++ b/data/custodian/JP-13-CHI-L-METILBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-METILBN - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-METILBN valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-METILBN ghcid_numeric: 17144851229793699082 valid_from: '2025-12-06T23:38:53.040878+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ministry of Economy, Trade and Industry Library, Branch of the NDL @@ -151,3 +152,31 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:56:07.058654+00:00' + source_url: https://www.meti.go.jp/topic/data/e70621aj.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.meti.go.jp/img_2017/logo.png + source_url: https://www.meti.go.jp/topic/data/e70621aj.html + css_selector: '#pagetop > header > div.top.clearfix:nth-of-type(2) > h1.left.top_logo + > a > img' + retrieved_on: '2025-12-24T22:56:07.058654+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 経済産業省 + - claim_type: favicon_url + claim_value: https://www.meti.go.jp/favicon.ico + source_url: https://www.meti.go.jp/topic/data/e70621aj.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:56:07.058654+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-MHLWLBN.yaml b/data/custodian/JP-13-CHI-L-MHLWLBN.yaml index 0837b70069..0177c39819 100644 --- a/data/custodian/JP-13-CHI-L-MHLWLBN.yaml +++ b/data/custodian/JP-13-CHI-L-MHLWLBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-MHLWLBN - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-MHLWLBN valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-MHLWLBN ghcid_numeric: 5161214271223178292 valid_from: '2025-12-06T23:38:53.034034+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ministry of Health, Labour and Welfare Library, Branch of the NDL @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:56:15.315975+00:00' + source_url: https://www.mhlw.go.jp/library/opac4/opac/Top + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mhlw.go.jp/library/opac4/common/images/op4-favicon.ico + source_url: https://www.mhlw.go.jp/library/opac4/opac/Top + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:56:15.315975+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-MJLBN.yaml b/data/custodian/JP-13-CHI-L-MJLBN.yaml index 5c07011359..13f2cbe3a1 100644 --- a/data/custodian/JP-13-CHI-L-MJLBN.yaml +++ b/data/custodian/JP-13-CHI-L-MJLBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-MJLBN - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-MJLBN valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-MJLBN ghcid_numeric: 14086556635146070077 valid_from: '2025-12-06T23:38:53.026804+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ministry of Justice Library, Branch of the NDL @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T22:56:24.982763+00:00' + source_url: https://www.moj.go.jp/housei/tosho-tenji/kanbou_library_library01_00001.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.moj.go.jp/content/001428634.ico + source_url: https://www.moj.go.jp/housei/tosho-tenji/kanbou_library_library01_00001.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T22:56:24.982763+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-MMLNC.yaml b/data/custodian/JP-13-CHI-L-MMLNC.yaml index ddbd802aee..1064ff57b1 100644 --- a/data/custodian/JP-13-CHI-L-MMLNC.yaml +++ b/data/custodian/JP-13-CHI-L-MMLNC.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-MMLNC - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-MMLNC valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-MMLNC ghcid_numeric: 10440810638807977995 valid_from: '2025-12-06T23:38:58.752779+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Modern Manga Library @@ -270,3 +271,28 @@ location: postal_code: 101-8301 street_address: 1-7-1 SARUGAKUCHO, Chiyoda Ku, Tokyo To, 101-8301 normalization_timestamp: '2025-12-09T12:21:25.245169+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:12:56.617051+00:00' + source_url: https://www.naiki-collection.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ssl.gstatic.com/atari/images/public/favicon.ico + source_url: https://www.naiki-collection.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:12:56.617051+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://lh3.googleusercontent.com/sitesv/AAzXCkcKgZJxvXUJMvsxjh2OnIys75IvX32eytgaMKUpsV5ARjMYRSs35DujTLo8bQdMKsLjq78qB9WEHxm9OPk7z0rc9UNkA_XUGpa3mN1j2hpjmB-9YaJfCax30CK1yGUcydL71_Qbq1yqPy1XIUQe2AVjJEkW6wx2F20=w16383 + source_url: https://www.naiki-collection.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T23:12:56.617051+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-MRII.yaml b/data/custodian/JP-13-CHI-L-MRII.yaml index 4925e8db8d..4e7b8367b9 100644 --- a/data/custodian/JP-13-CHI-L-MRII.yaml +++ b/data/custodian/JP-13-CHI-L-MRII.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-MRII - valid_from: "2025-12-10T09:44:00Z" + valid_from: '2025-12-10T09:44:00Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-MRII valid_from: null - valid_to: "2025-12-10T09:44:00Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:00Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-MRII ghcid_numeric: 15006376640109674576 valid_from: '2025-12-06T23:38:58.360319+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Mitsubishi Research Institute,Inc. @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:29:11.833731+00:00' + source_url: http://www.mri.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mri.co.jp/dia6ou0000016csk-att/favicon.ico + source_url: http://www.mri.co.jp + css_selector: '[document] > html > head > link:nth-of-type(22)' + retrieved_on: '2025-12-24T23:29:11.833731+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.mri.co.jp/frontline/i5inlu000002q8op-img/24_expo_ogimage.jpg + source_url: http://www.mri.co.jp + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T23:29:11.833731+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-NAMAMPDRLD.yaml b/data/custodian/JP-13-CHI-L-NAMAMPDRLD.yaml index 0de7bedc33..6b474580e2 100644 --- a/data/custodian/JP-13-CHI-L-NAMAMPDRLD.yaml +++ b/data/custodian/JP-13-CHI-L-NAMAMPDRLD.yaml @@ -1,5 +1,6 @@ original_entry: - name: National Association of Mutual Aid for Municipal Property Damages, Reference Library for Disasters + name: National Association of Mutual Aid for Municipal Property Damages, Reference + Library for Disasters institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -32,20 +33,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-NAMAMPDRLD - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-NAMAMPDRLD valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-NAMAMPDRLD ghcid_numeric: 6930893228653149088 valid_from: '2025-12-06T23:38:57.791911+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: National Association of Mutual Aid for Municipal Property Damages, Reference Library for Disasters + claim_value: National Association of Mutual Aid for Municipal Property Damages, + Reference Library for Disasters source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +99,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: National Association of Mutual Aid for Municipal Property Damages, Reference Library for Disasters + claim_value: National Association of Mutual Aid for Municipal Property Damages, + Reference Library for Disasters property_uri: skos:prefLabel provenance: namespace: glam @@ -151,3 +155,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:39:22.575100+00:00' + source_url: http://www.city-net.or.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://city-net.or.jp/wp-content/uploads/2022/07/city-net-favicon.gif + source_url: http://www.city-net.or.jp/library + css_selector: '[document] > html.fontawesome-i2svg-active.fontawesome-i2svg-complete + > head > link:nth-of-type(66)' + retrieved_on: '2025-12-24T23:39:22.575100+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-NB.yaml b/data/custodian/JP-13-CHI-L-NB.yaml index 3f1cad5893..c3dcf3c7db 100644 --- a/data/custodian/JP-13-CHI-L-NB.yaml +++ b/data/custodian/JP-13-CHI-L-NB.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-NB - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-NB valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-NB ghcid_numeric: 14592636645130995078 valid_from: '2025-12-06T23:38:54.718618+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NIHONDAIGAKUDAIGAKUINGUROBARU・BIJINESUKENKYUKATOSHOETSURANSHITSU @@ -204,3 +205,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:39:32.639166+00:00' + source_url: http://www.gsb.nihon-u.ac.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.gsb.nihon-u.ac.jp/assets/img/favicon.ico + source_url: http://www.gsb.nihon-u.ac.jp/lib + css_selector: '[document] > html.js_ajaxload > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T23:39:32.639166+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://www.nihon-u.ac.jp/assets/img/ogp.png + source_url: http://www.gsb.nihon-u.ac.jp/lib + css_selector: '[document] > html.js_ajaxload > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T23:39:32.639166+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-NCIPIT.yaml b/data/custodian/JP-13-CHI-L-NCIPIT.yaml index a5f9491979..6276c42b8c 100644 --- a/data/custodian/JP-13-CHI-L-NCIPIT.yaml +++ b/data/custodian/JP-13-CHI-L-NCIPIT.yaml @@ -208,3 +208,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.khk.or.jp/english wikidata_official_website: http://www.khk.or.jp/english +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:39:43.765321+00:00' + source_url: http://www.inpit.go.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.inpit.go.jp/content/100879549.png + source_url: http://www.inpit.go.jp + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T23:39:43.765321+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-NDL.yaml b/data/custodian/JP-13-CHI-L-NDL.yaml index 9961ee8340..dfd89e5fae 100644 --- a/data/custodian/JP-13-CHI-L-NDL.yaml +++ b/data/custodian/JP-13-CHI-L-NDL.yaml @@ -533,3 +533,39 @@ wikidata_enrichment: - id: Q85877124 label: Maekawa Associates, Architects & Engineers description: '' +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:39:51.442012+00:00' + source_url: https://www.ndl.go.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: '[inline-svg]' + source_url: https://www.ndl.go.jp + css_selector: '#__nuxt > div.layouts-global.is-light > header.global-header > + div.base-layout-row.is-hidden-mobile > div.global-header-left > a.router-link-active.router-link-exact-active + > h1.base-heading.is-image > svg.ui-parts-logo-service.global-header-brand' + retrieved_on: '2025-12-24T23:39:51.442012+00:00' + extraction_method: crawl4ai_svg_detection + detection_confidence: high + is_inline_svg: true + aria_label: '' + - claim_type: favicon_url + claim_value: https://www.ndl.go.jp/assets/hp/favicon/favicon.ico + source_url: https://www.ndl.go.jp + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-24T23:39:51.442012+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ndl.go.jp/assets/hp/og.png + source_url: https://www.ndl.go.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T23:39:51.442012+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-NL.yaml b/data/custodian/JP-13-CHI-L-NL.yaml index a8f97726e1..105f2e256c 100644 --- a/data/custodian/JP-13-CHI-L-NL.yaml +++ b/data/custodian/JP-13-CHI-L-NL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-NL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-NL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-NL ghcid_numeric: 14956102753454082963 valid_from: '2025-12-06T23:38:54.673201+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NIHONDAIGAKUHOGAKUBU Library @@ -204,3 +205,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:40:08.119771+00:00' + source_url: http://www.law.nihon-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.law.nihon-u.ac.jp/common/img/apple-touch-icon.png + source_url: http://www.law.nihon-u.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T23:40:08.119771+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.law.nihon-u.ac.jp/common/img/ogp.png + source_url: http://www.law.nihon-u.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T23:40:08.119771+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-L-NSMM.yaml b/data/custodian/JP-13-CHI-L-NSMM.yaml index 9c5945233b..665e69affb 100644 --- a/data/custodian/JP-13-CHI-L-NSMM.yaml +++ b/data/custodian/JP-13-CHI-L-NSMM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-NSMM - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-NSMM valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-NSMM ghcid_numeric: 16097795781507964750 valid_from: '2025-12-06T23:38:58.796673+00:00' @@ -106,8 +107,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: National Showa Memorial Museum @@ -233,3 +234,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:40:42.374946+00:00' + source_url: http://www.showakan.go.jp/floor/4f/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.showakan.go.jp/main/wp-content/uploads/2023/03/cropped-logo144-180x180.png + source_url: http://www.showakan.go.jp/floor/4f/index.html + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-24T23:40:42.374946+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.showakan.go.jp/main/wp-content/uploads/2023/02/サムネイル用画像(昭和館ロゴ).png + source_url: http://www.showakan.go.jp/floor/4f/index.html + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T23:40:42.374946+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-L-NUCEL.yaml b/data/custodian/JP-13-CHI-L-NUCEL.yaml index 14f14f5e0f..5745ed183e 100644 --- a/data/custodian/JP-13-CHI-L-NUCEL.yaml +++ b/data/custodian/JP-13-CHI-L-NUCEL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-NUCEL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-NUCEL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-NUCEL ghcid_numeric: 11119633111392618146 valid_from: '2025-12-06T23:38:54.678222+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nihon University College of Economics Library @@ -204,3 +205,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:40:51.515191+00:00' + source_url: http://www.eco.nihon-u.ac.jp/eco_kyouin/nueco-library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.eco.nihon-u.ac.jp/wp-content/themes/eco/img/shared/favicon.ico + source_url: http://www.eco.nihon-u.ac.jp/eco_kyouin/nueco-library + css_selector: '[document] > html.ghostkit-effects-enabled > head > link' + retrieved_on: '2025-12-24T23:40:51.515191+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.eco.nihon-u.ac.jp/wp-content/themes/eco/img/shared/ogp.jpg + source_url: http://www.eco.nihon-u.ac.jp/eco_kyouin/nueco-library + css_selector: '[document] > html.ghostkit-effects-enabled > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-24T23:40:51.515191+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-NULSL.yaml b/data/custodian/JP-13-CHI-L-NULSL.yaml index fd88d213c3..b932a5b6e0 100644 --- a/data/custodian/JP-13-CHI-L-NULSL.yaml +++ b/data/custodian/JP-13-CHI-L-NULSL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-NULSL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-NULSL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-NULSL ghcid_numeric: 2311197936824065810 valid_from: '2025-12-06T23:38:54.715981+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nihon University Law School Library @@ -204,3 +205,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:41:31.612606+00:00' + source_url: http://www.nihon-u.ac.jp/lawschool/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.nihon-u.ac.jp/assets/img/favicon.ico + source_url: http://www.nihon-u.ac.jp/lawschool/library + css_selector: '[document] > html.js_ajaxload > head > link:nth-of-type(7)' + retrieved_on: '2025-12-24T23:41:31.612606+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://www.nihon-u.ac.jp/assets/img/ogp.png + source_url: http://www.nihon-u.ac.jp/lawschool/library + css_selector: '[document] > html.js_ajaxload > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T23:41:31.612606+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-OGSAL.yaml b/data/custodian/JP-13-CHI-L-OGSAL.yaml index 2ced280da0..8a61d0b3a4 100644 --- a/data/custodian/JP-13-CHI-L-OGSAL.yaml +++ b/data/custodian/JP-13-CHI-L-OGSAL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-OGSAL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-OGSAL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-OGSAL ghcid_numeric: 4543668248223193835 valid_from: '2025-12-06T23:38:55.457520+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ohara Graduate School of Accounting Library @@ -204,3 +205,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:41:39.733204+00:00' + source_url: http://www.o-hara.ac.jp/grad + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.o-hara.ac.jp/grad/web/images/favicon.png + source_url: http://www.o-hara.ac.jp/grad + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:41:39.733204+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 16x16 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-OWSUL.yaml b/data/custodian/JP-13-CHI-L-OWSUL.yaml index 70c35932a0..29786d93f8 100644 --- a/data/custodian/JP-13-CHI-L-OWSUL.yaml +++ b/data/custodian/JP-13-CHI-L-OWSUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-OWSUL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-OWSUL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-OWSUL ghcid_numeric: 10633850874388853661 valid_from: '2025-12-06T23:38:54.829355+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Otsuma Women's University Library @@ -204,3 +205,31 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:41:54.071540+00:00' + source_url: https://www.sjc.otsuma.ac.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.sjc.otsuma.ac.jp/lib/wp-content/themes/otsuma-lib/assets/image/logo.png?ver=1.0.2 + source_url: https://www.sjc.otsuma.ac.jp/lib + css_selector: '[document] > html > body.home.page-template-default > header.l-header.p-header + > div.p-header__row > h1.p-header__logo > a > img' + retrieved_on: '2025-12-24T23:41:54.071540+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大妻女子大学図書館 + - claim_type: favicon_url + claim_value: https://www.sjc.otsuma.ac.jp/lib/wp-content/uploads/sites/3/2021/03/favicon.png + source_url: https://www.sjc.otsuma.ac.jp/lib + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-24T23:41:54.071540+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-POLBN.yaml b/data/custodian/JP-13-CHI-L-POLBN.yaml index 1de78be347..72b1807279 100644 --- a/data/custodian/JP-13-CHI-L-POLBN.yaml +++ b/data/custodian/JP-13-CHI-L-POLBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-POLBN - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-POLBN valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-POLBN ghcid_numeric: 8688067834880036680 valid_from: '2025-12-06T23:38:53.043165+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Patent Office Library, Branch of the NDL @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:42:03.051817+00:00' + source_url: https://www.jpo.go.jp/news/koho/info/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jpo.go.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.jpo.go.jp/news/koho/info/library/index.html + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-24T23:42:03.051817+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-L-RIIMHU.yaml b/data/custodian/JP-13-CHI-L-RIIMHU.yaml index a5cf4a84cd..8a2fadd34e 100644 --- a/data/custodian/JP-13-CHI-L-RIIMHU.yaml +++ b/data/custodian/JP-13-CHI-L-RIIMHU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-RIIMHU - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-RIIMHU valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-RIIMHU ghcid_numeric: 8041168835256226997 valid_from: '2025-12-06T23:38:55.250824+00:00' @@ -106,8 +107,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Research Institute for Innovation Management, Hosei University @@ -212,3 +213,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:42:18.455379+00:00' + source_url: http://riim.ws.hosei.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://riim.ws.hosei.ac.jp/favicon.ico + source_url: http://riim.ws.hosei.ac.jp + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-24T23:42:18.455379+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-RL.yaml b/data/custodian/JP-13-CHI-L-RL.yaml index 98375cb8e2..93bd40a7dc 100644 --- a/data/custodian/JP-13-CHI-L-RL.yaml +++ b/data/custodian/JP-13-CHI-L-RL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-RL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-RL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-RL ghcid_numeric: 17468054717514438379 valid_from: '2025-12-06T23:38:55.432104+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: REKKUTOKYORIGARUMAINDODAIGAKUINDAIGAKUFUZOKU Library @@ -215,3 +216,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:42:26.643513+00:00' + source_url: http://www.lec.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lec.ac.jp/apple-touch-icon.png + source_url: http://www.lec.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:42:26.643513+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-ROISNIIL.yaml b/data/custodian/JP-13-CHI-L-ROISNIIL.yaml index 582b007fe3..4870a0f0bc 100644 --- a/data/custodian/JP-13-CHI-L-ROISNIIL.yaml +++ b/data/custodian/JP-13-CHI-L-ROISNIIL.yaml @@ -1,5 +1,6 @@ original_entry: - name: Research Organization of Information and Systems National Institute of Informatics Library + name: Research Organization of Information and Systems National Institute of Informatics + Library institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -32,20 +33,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-ROISNIIL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-ROISNIIL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-ROISNIIL ghcid_numeric: 7095812405784557070 valid_from: '2025-12-06T23:38:57.524310+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Research Organization of Information and Systems National Institute of Informatics Library + claim_value: Research Organization of Information and Systems National Institute + of Informatics Library source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +99,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Research Organization of Information and Systems National Institute of Informatics Library + claim_value: Research Organization of Information and Systems National Institute + of Informatics Library property_uri: skos:prefLabel provenance: namespace: glam @@ -151,3 +155,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:42:34.716991+00:00' + source_url: http://www.nii.ac.jp/about/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nii.ac.jp/_img/common/favicon.ico + source_url: http://www.nii.ac.jp/about/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T23:42:34.716991+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.nii.ac.jp/_img/ogp.jpg + source_url: http://www.nii.ac.jp/about/library + css_selector: '[document] > html > head > meta:nth-of-type(19)' + retrieved_on: '2025-12-24T23:42:34.716991+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-SCLBN.yaml b/data/custodian/JP-13-CHI-L-SCLBN.yaml index da637293f2..e209678ee7 100644 --- a/data/custodian/JP-13-CHI-L-SCLBN.yaml +++ b/data/custodian/JP-13-CHI-L-SCLBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-SCLBN - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-SCLBN valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-SCLBN ghcid_numeric: 2763743021626350244 valid_from: '2025-12-06T23:38:53.057366+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Supreme Court Library, Branch of the NDL @@ -151,3 +152,31 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:42:44.573663+00:00' + source_url: https://www.courts.go.jp/saikosai/tosyokan + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.courts.go.jp/assets/images/common/logo.svg + source_url: https://www.courts.go.jp/saikosai/tosyokan + css_selector: '[document] > html > body.black > header.c-header > div.c-header-container + > div.c-header-inner > div.c-header-logo-area > h1.c-header-logo > a > img' + retrieved_on: '2025-12-24T23:42:44.573663+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 裁判所 - Courts in Japan + - claim_type: favicon_url + claim_value: https://www.courts.go.jp/assets/images/common/favicon.ico + source_url: https://www.courts.go.jp/saikosai/tosyokan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:42:44.573663+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-SUIACS.yaml b/data/custodian/JP-13-CHI-L-SUIACS.yaml index f703547397..396161ab4d 100644 --- a/data/custodian/JP-13-CHI-L-SUIACS.yaml +++ b/data/custodian/JP-13-CHI-L-SUIACS.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-SUIACS - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-SUIACS valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-SUIACS ghcid_numeric: 7882661888818412540 valid_from: '2025-12-06T23:38:54.953355+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Sophia University Institute of American and Canadian Studies @@ -204,3 +205,30 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:43:23.493259+00:00' + source_url: http://dept.sophia.ac.jp/is/amecana/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://dept.sophia.ac.jp/is/amecana/wp-content/themes/amecana/img/logo.png + source_url: http://dept.sophia.ac.jp/is/amecana/library + css_selector: '#headerCenter > h1.pt15 > a > img' + retrieved_on: '2025-12-24T23:43:23.493259+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://dept.sophia.ac.jp/is/amecana/favicon.ico + source_url: http://dept.sophia.ac.jp/is/amecana/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:43:23.493259+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-SUIGC.yaml b/data/custodian/JP-13-CHI-L-SUIGC.yaml index fa7efab8d7..ce19ff6a87 100644 --- a/data/custodian/JP-13-CHI-L-SUIGC.yaml +++ b/data/custodian/JP-13-CHI-L-SUIGC.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-SUIGC - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-SUIGC valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-SUIGC ghcid_numeric: 5370347338076573874 valid_from: '2025-12-06T23:38:54.972369+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Sophia University Institute of Global Concern @@ -235,3 +236,20 @@ location: postal_code: 102-8554 street_address: 7-1 KIOICHO, Chiyoda Ku, Tokyo To, 102-8554 normalization_timestamp: '2025-12-09T12:21:26.905864+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:43:34.093477+00:00' + source_url: http://dept.sophia.ac.jp/is/igc + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://dept.sophia.ac.jp/is/igc/images/mainimg00.jpg + source_url: http://dept.sophia.ac.jp/is/igc + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T23:43:34.093477+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-SULKB.yaml b/data/custodian/JP-13-CHI-L-SULKB.yaml index 32ccf35d64..492a76b738 100644 --- a/data/custodian/JP-13-CHI-L-SULKB.yaml +++ b/data/custodian/JP-13-CHI-L-SULKB.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-SULKB - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-SULKB valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-SULKB ghcid_numeric: 17015606134352323387 valid_from: '2025-12-06T23:38:55.498415+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Senshu University Library Kanda Branch @@ -204,3 +205,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:43:44.547717+00:00' + source_url: http://www.senshu-u.ac.jp/libif/lib/introfalib/libkanda.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.senshu-u.ac.jp/favicon.ico + source_url: http://www.senshu-u.ac.jp/libif/lib/introfalib/libkanda.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:43:44.547717+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-SULL.yaml b/data/custodian/JP-13-CHI-L-SULL.yaml index 7b56aa18c9..8c3442fa22 100644 --- a/data/custodian/JP-13-CHI-L-SULL.yaml +++ b/data/custodian/JP-13-CHI-L-SULL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-SULL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-SULL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-SULL ghcid_numeric: 4016340944550252676 valid_from: '2025-12-06T23:38:55.503753+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Senshu University Law Library @@ -204,3 +205,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:44:01.343299+00:00' + source_url: http://www.senshu-u.ac.jp/libif/lib/introfalib/libhouka.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.senshu-u.ac.jp/favicon.ico + source_url: http://www.senshu-u.ac.jp/libif/lib/introfalib/libhouka.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:44:01.343299+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-SULSL.yaml b/data/custodian/JP-13-CHI-L-SULSL.yaml index f5aacbdc7f..131441a1f5 100644 --- a/data/custodian/JP-13-CHI-L-SULSL.yaml +++ b/data/custodian/JP-13-CHI-L-SULSL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-SULSL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-SULSL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-SULSL ghcid_numeric: 7300338137111101182 valid_from: '2025-12-06T23:38:54.979648+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SOPHIA UNIVERSITY LAW SCHOOL LIBRARY @@ -204,3 +205,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:44:08.114513+00:00' + source_url: http://www.sophia.ac.jp/jpn/research/lib/l-s + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sophia.ac.jp/assets/themes/sophia-university/img/safari-pinned-tab.svg + source_url: http://www.sophia.ac.jp/jpn/research/lib/l-s + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T23:44:08.114513+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sophia.ac.jp/assets/themes/sophia-university/img/ogimage.png + source_url: http://www.sophia.ac.jp/jpn/research/lib/l-s + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T23:44:08.114513+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-CHI-L-TCAJTLC.yaml b/data/custodian/JP-13-CHI-L-TCAJTLC.yaml index ae2a1d4ed1..e15dd76cf8 100644 --- a/data/custodian/JP-13-CHI-L-TCAJTLC.yaml +++ b/data/custodian/JP-13-CHI-L-TCAJTLC.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-TCAJTLC - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-TCAJTLC valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-TCAJTLC ghcid_numeric: 12469924818019212134 valid_from: '2025-12-06T23:38:58.806640+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Trust Companies Association of Japan Trust Library Center @@ -151,3 +152,32 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:44:25.976242+00:00' + source_url: http://www.shintaku-kyokai.or.jp/profile/profile05.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shintaku-kyokai.or.jp/themes/shintaku/assets/icon/safari-pinned-tab.svg + source_url: http://www.shintaku-kyokai.or.jp/profile/profile05.html + css_selector: '[document] > html.mac.puma > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T23:44:25.976242+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: ' + + https://www.shintaku-kyokai.or.jp/archives/001/201801/053eb42540e5ba7e26cffbd499e64a40.png + + ' + source_url: http://www.shintaku-kyokai.or.jp/profile/profile05.html + css_selector: '[document] > html.mac.puma > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:44:25.976242+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-CHI-L-TCCICSG.yaml b/data/custodian/JP-13-CHI-L-TCCICSG.yaml index faf967e1d4..ebfc3bd75d 100644 --- a/data/custodian/JP-13-CHI-L-TCCICSG.yaml +++ b/data/custodian/JP-13-CHI-L-TCCICSG.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-TCCICSG - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-TCCICSG valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-TCCICSG ghcid_numeric: 3355582994715961979 valid_from: '2025-12-06T23:38:57.852711+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Tokyo Chamber of Commerce and Industry, Chamber’s Gallery @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:44:56.795558+00:00' + source_url: https://www.tokyo-cci.or.jp/about/gallery + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tokyo-cci.or.jp/favicon.ico + source_url: https://www.tokyo-cci.or.jp/about/gallery + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-24T23:44:56.795558+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-L-TKGULOMSL.yaml b/data/custodian/JP-13-CHI-L-TKGULOMSL.yaml index dcc9b4fdec..6c40a54d0c 100644 --- a/data/custodian/JP-13-CHI-L-TKGULOMSL.yaml +++ b/data/custodian/JP-13-CHI-L-TKGULOMSL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-TKGULOMSL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-TKGULOMSL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-TKGULOMSL ghcid_numeric: 5098275507202508387 valid_from: '2025-12-06T23:38:55.085509+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Kasei Gakuin University Library, Oe Memorial Sanbancho Library @@ -164,7 +165,8 @@ wikidata_enrichment: wikidata_labels: en: Tokyo Kasei Gakuin University Library, Oe Memorial Sanbancho Library ja: 東京家政学院大学附属図書館大江記念三番町図書館 - wikidata_label_en: Tokyo Kasei Gakuin University Library, Oe Memorial Sanbancho Library + wikidata_label_en: Tokyo Kasei Gakuin University Library, Oe Memorial Sanbancho + Library wikidata_label_ja: 東京家政学院大学附属図書館大江記念三番町図書館 wikidata_classification: instance_of: &id004 @@ -204,3 +206,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:45:17.460131+00:00' + source_url: http://www.kasei-gakuin.ac.jp/library/lib-top.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kasei-gakuin.ac.jp/tkgu_cms/wp-content/uploads/2022/04/cropped-favicon-512x512-1-180x180.png + source_url: http://www.kasei-gakuin.ac.jp/library/lib-top.htm + css_selector: '[document] > html.fontawesome-i2svg-active.fontawesome-i2svg-complete + > head > link:nth-of-type(30)' + retrieved_on: '2025-12-24T23:45:17.460131+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-L-YKBYA.yaml b/data/custodian/JP-13-CHI-L-YKBYA.yaml index d2c9c8fcdd..5c344e9801 100644 --- a/data/custodian/JP-13-CHI-L-YKBYA.yaml +++ b/data/custodian/JP-13-CHI-L-YKBYA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-L-YKBYA - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-L-YKBYA valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-L-YKBYA ghcid_numeric: 12639396625788160526 valid_from: '2025-12-06T23:38:58.072275+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Yasukuni Kaiko Bunko (Yasukuni Archives) @@ -151,3 +152,23 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:45:36.147747+00:00' + source_url: http://www.yasukuni.or.jp/archives/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.yasukuni.or.jp/img/header/header_logo.png + source_url: http://www.yasukuni.or.jp/archives/index.html + css_selector: '#top > header > div.nav_sp:nth-of-type(3) > div.nav_sp_box > div.inner:nth-of-type(2) + > div.nav_sp_top > a > img' + retrieved_on: '2025-12-24T23:45:36.147747+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: header logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-L-YYMLMS.yaml b/data/custodian/JP-13-CHI-L-YYMLMS.yaml index 515c315737..d7991d0c79 100644 --- a/data/custodian/JP-13-CHI-L-YYMLMS.yaml +++ b/data/custodian/JP-13-CHI-L-YYMLMS.yaml @@ -205,3 +205,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:45:44.472271+00:00' + source_url: http://www.meiji.ac.jp/manga/yonezawa_lib/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.meiji.ac.jp/wr_common-v2/images/favicon.ico + source_url: http://www.meiji.ac.jp/manga/yonezawa_lib/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:45:44.472271+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.meiji.ac.jp/wr_common-v2/images/common/og.jpg + source_url: http://www.meiji.ac.jp/manga/yonezawa_lib/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T23:45:44.472271+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-M-CCSHLM.yaml b/data/custodian/JP-13-CHI-M-CCSHLM.yaml index 42923b2c34..e95afce873 100644 --- a/data/custodian/JP-13-CHI-M-CCSHLM.yaml +++ b/data/custodian/JP-13-CHI-M-CCSHLM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-M-CCSHLM - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-M-CCSHLM valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-M-CCSHLM ghcid_numeric: 2143554483630486913 valid_from: '2025-12-06T23:38:32.944072+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: CHIYODA CITY'S HIBIYA LIBRARY & MUSEUM @@ -229,12 +230,12 @@ wikidata_enrichment: description: 都道府県が設置する図書館 - id: Q28564 label: public library - description: free community resource offering access to books, media, and information, promoting literacy and education - for all ages + description: free community resource offering access to books, media, and information, + promoting literacy and education for all ages - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance - id: Q48085397 label: municipal library of Japan description: a generic name for libraries established by municipalities in Japan @@ -299,3 +300,31 @@ location: postal_code: 100-0012 street_address: HIBIYAKOEN, Chiyoda Ku, Tokyo To, 100-0012 normalization_timestamp: '2025-12-09T12:21:27.544338+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:45:57.573945+00:00' + source_url: https://www.library.chiyoda.tokyo.jp/hibiya + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.chiyoda.tokyo.jp/hibiya + css_selector: '[document] > html > body.information.lib_top > div.wrapper > header.header + > div.header__inner > h1.header__logo > a > img' + retrieved_on: '2025-12-24T23:45:57.573945+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 千代田区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.chiyoda.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.library.chiyoda.tokyo.jp/hibiya + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T23:45:57.573945+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-M-IMA.yaml b/data/custodian/JP-13-CHI-M-IMA.yaml index d40cb006e3..1284489158 100644 --- a/data/custodian/JP-13-CHI-M-IMA.yaml +++ b/data/custodian/JP-13-CHI-M-IMA.yaml @@ -271,3 +271,22 @@ wikidata_enrichment: commons_category: Idemitsu Museum of Arts image: Imperial Garden Theater, Tokyo.jpg wikidata_image: Imperial Garden Theater, Tokyo.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:46:06.311260+00:00' + source_url: http://idemitsu-museum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://idemitsu-museum.or.jp/favicon.ico + source_url: http://idemitsu-museum.or.jp + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-24T23:46:06.311260+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-M-JCM.yaml b/data/custodian/JP-13-CHI-M-JCM.yaml index 982cf68f65..8a66e369f8 100644 --- a/data/custodian/JP-13-CHI-M-JCM.yaml +++ b/data/custodian/JP-13-CHI-M-JCM.yaml @@ -1441,3 +1441,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/5WIn0AHid7A/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:46:15.156543+00:00' + source_url: https://www.jcii-cameramuseum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jcii-cameramuseum.jp/wp-content/uploads/2024/04/jciicameramuseumlogo2-336x336.png + source_url: https://www.jcii-cameramuseum.jp + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-24T23:46:15.156543+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-M-KWSUM.yaml b/data/custodian/JP-13-CHI-M-KWSUM.yaml index 4e04ddc534..34f4eec3e3 100644 --- a/data/custodian/JP-13-CHI-M-KWSUM.yaml +++ b/data/custodian/JP-13-CHI-M-KWSUM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-M-KWSUM - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-M-KWSUM valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-M-KWSUM ghcid_numeric: 5684231646800746147 valid_from: '2025-12-06T23:38:32.955681+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KYORITSU WOMEN'S UNIVERSITY MUSEUM @@ -151,3 +152,38 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:46:24.001186+00:00' + source_url: https://www.kyoritsu-wu.ac.jp/muse + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.kyoritsu-wu.ac.jp/muse/img/common/head_logo_s_w.png + source_url: https://www.kyoritsu-wu.ac.jp/muse + css_selector: '[document] > html.muse.noTouchDevice > body > div.wrapper.top > + footer.footBlock.borderDecoration > div.footBlock__inner > nav.footLocalNav + > div.footLocalNav__inner > div.footLocalNav__left > h5 > a > img' + retrieved_on: '2025-12-24T23:46:24.001186+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.kyoritsu-wu.ac.jp/favicon.ico + source_url: https://www.kyoritsu-wu.ac.jp/muse + css_selector: '[document] > html.muse.noTouchDevice > head > link:nth-of-type(5)' + retrieved_on: '2025-12-24T23:46:24.001186+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kyoritsu-wu.ac.jp/muse/img/ogimg.jpg + source_url: https://www.kyoritsu-wu.ac.jp/muse + css_selector: '[document] > html.muse.noTouchDevice > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T23:46:24.001186+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-M-MIMT.yaml b/data/custodian/JP-13-CHI-M-MIMT.yaml index 3e14c3226d..2ab8d519e5 100644 --- a/data/custodian/JP-13-CHI-M-MIMT.yaml +++ b/data/custodian/JP-13-CHI-M-MIMT.yaml @@ -279,3 +279,28 @@ wikidata_enrichment: commons_category: Mitsubishi Ichigokan Museum image: Mitsubishi Ichigokan Museum.JPG wikidata_image: Mitsubishi Ichigokan Museum.JPG +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:46:33.041315+00:00' + source_url: https://mimt.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mimt.jp/wp-content/themes/mimt/assets/img/common/favicon.ico + source_url: https://mimt.jp + css_selector: '[document] > html > body > link:nth-of-type(12)' + retrieved_on: '2025-12-24T23:46:33.041315+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mimt.jp/wp-content/themes/mimt/assets/img/common/mimt_OGP.png + source_url: https://mimt.jp + css_selector: '[document] > html > body > meta:nth-of-type(7)' + retrieved_on: '2025-12-24T23:46:33.041315+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-M-MUM.yaml b/data/custodian/JP-13-CHI-M-MUM.yaml index 0814516145..d3bf0ff3c7 100644 --- a/data/custodian/JP-13-CHI-M-MUM.yaml +++ b/data/custodian/JP-13-CHI-M-MUM.yaml @@ -239,3 +239,28 @@ wikidata_enrichment: facebook_id: meijimuseum wikidata_media: commons_category: Meiji University Museum +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:46:41.838862+00:00' + source_url: https://www.meiji.ac.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.meiji.ac.jp/wr_common-v2/images/favicon.ico + source_url: https://www.meiji.ac.jp/museum + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:46:41.838862+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.meiji.ac.jp/wr_common-v2/images/common/og.jpg + source_url: https://www.meiji.ac.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T23:46:41.838862+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-M-OWSUM.yaml b/data/custodian/JP-13-CHI-M-OWSUM.yaml index c2c353bbf0..4a620018d3 100644 --- a/data/custodian/JP-13-CHI-M-OWSUM.yaml +++ b/data/custodian/JP-13-CHI-M-OWSUM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-M-OWSUM - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-M-OWSUM valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-M-OWSUM ghcid_numeric: 7119765562522459607 valid_from: '2025-12-06T23:38:32.981244+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTSUMA WOMEN'S UNIVERSITY MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:46:55.602572+00:00' + source_url: https://www.museum.otsuma.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.museum.otsuma.ac.jp/sites/default/files/favicon.ico + source_url: https://www.museum.otsuma.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T23:46:55.602572+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-CHI-M-SBAM.yaml b/data/custodian/JP-13-CHI-M-SBAM.yaml index bcfc255956..77cb26bff1 100644 --- a/data/custodian/JP-13-CHI-M-SBAM.yaml +++ b/data/custodian/JP-13-CHI-M-SBAM.yaml @@ -263,3 +263,36 @@ wikidata_enrichment: - id: Q11537804 label: Sakurai Kotarō description: Japanese architect (1870-1953) +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:47:13.015179+00:00' + source_url: https://www.seikado.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.seikado.or.jp/file/wp-content/themes/seikado/images/common/x_logo.svg + source_url: https://www.seikado.or.jp + css_selector: '#sns-iconlist > li > a > noscript > img' + retrieved_on: '2025-12-24T23:47:13.015179+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: X@静嘉堂文庫美術館 + - claim_type: favicon_url + claim_value: https://www.seikado.or.jp/file/wp-content/uploads/2022/06/cropped-favicon-180x180.png + source_url: https://www.seikado.or.jp + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-24T23:47:13.015179+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.seikado.or.jp/file/wp-content/uploads/2024/08/ogp_img.jpg + source_url: https://www.seikado.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:47:13.015179+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHI-M-SKNSMM.yaml b/data/custodian/JP-13-CHI-M-SKNSMM.yaml index 59636a8dba..78aeddcd21 100644 --- a/data/custodian/JP-13-CHI-M-SKNSMM.yaml +++ b/data/custodian/JP-13-CHI-M-SKNSMM.yaml @@ -267,3 +267,20 @@ wikidata_enrichment: - id: Q1352623 label: Kiyonori Kikutake description: Japanese architect (1928-2011) +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:47:21.104729+00:00' + source_url: https://www.showakan.go.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.showakan.go.jp/special/asset/image/main/og.png + source_url: https://www.showakan.go.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-24T23:47:21.104729+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHI-M-SM.yaml b/data/custodian/JP-13-CHI-M-SM.yaml index 9e1c801910..ca88000a61 100644 --- a/data/custodian/JP-13-CHI-M-SM.yaml +++ b/data/custodian/JP-13-CHI-M-SM.yaml @@ -1036,3 +1036,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/943Sjgd6q0o/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:47:31.932580+00:00' + source_url: http://www.jsf.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jsf.or.jp/wp-content/uploads/2022/02/cropped-favicon-512x512-1-180x180.png + source_url: http://www.jsf.or.jp + css_selector: '[document] > html.no-js > head > link:nth-of-type(12)' + retrieved_on: '2025-12-24T23:47:31.932580+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.jsf.or.jp/image/ogp.jpg + source_url: http://www.jsf.or.jp + css_selector: '[document] > html.no-js > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:47:31.932580+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-CHI-M-TG.yaml b/data/custodian/JP-13-CHI-M-TG.yaml index f0ff6d40c4..ed43d2e249 100644 --- a/data/custodian/JP-13-CHI-M-TG.yaml +++ b/data/custodian/JP-13-CHI-M-TG.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-M-TG - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-M-TG valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-M-TG ghcid_numeric: 7306488298306063931 valid_from: '2025-12-06T23:38:32.958062+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TENRI GALLERY @@ -151,3 +152,28 @@ location: geonames_id: 11749713 geonames_name: Chiyoda feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:47:50.202906+00:00' + source_url: http://tokyotenrikyokan.co.jp/gallery + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tokyotenrikyokan.co.jp/wp-content/uploads/2025/03/icon-250x250.png + source_url: http://tokyotenrikyokan.co.jp/gallery + css_selector: '[document] > html.pc > head > link:nth-of-type(18)' + retrieved_on: '2025-12-24T23:47:50.202906+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://tokyotenrikyokan.co.jp/wp-content/uploads/2025/03/top_bg01.jpg + source_url: http://tokyotenrikyokan.co.jp/gallery + css_selector: '[document] > html.pc > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:47:50.202906+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHI-M-YYM.yaml b/data/custodian/JP-13-CHI-M-YYM.yaml index 6b7bad8c18..6dce39a159 100644 --- a/data/custodian/JP-13-CHI-M-YYM.yaml +++ b/data/custodian/JP-13-CHI-M-YYM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHI-M-YYM - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHI-M-YYM valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHI-M-YYM ghcid_numeric: 9020294876737363351 valid_from: '2025-12-06T23:38:32.975670+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YASUKUNIJINJA YUSHUKAN MUSEUM @@ -200,7 +201,8 @@ wikidata_enrichment: wikidata_label_ja: 遊就館 wikidata_label_fr: Yūshūkan wikidata_descriptions: - fr: musée de propagande militariste dédié à la période du Japon Impérial situé près du temple Yasukuni à Tokyo, Japon + fr: musée de propagande militariste dédié à la période du Japon Impérial situé + près du temple Yasukuni à Tokyo, Japon en: military museum in Tokyo, Japan nl: militair museum in Chiyoda, Japan ja: 靖国神社境内に併設された宝物館 @@ -291,3 +293,23 @@ location: postal_code: 102-8246 street_address: KUDANKITA, Chiyoda Ku, Tokyo To, 102-8246 normalization_timestamp: '2025-12-09T12:21:28.164264+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:48:06.566967+00:00' + source_url: http://www.yasukuni.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.yasukuni.or.jp/img/header/header_logo.png + source_url: http://www.yasukuni.or.jp + css_selector: '#container > header > div.nav_sp:nth-of-type(3) > div.nav_sp_box + > div.inner:nth-of-type(2) > div.nav_sp_top > a > img' + retrieved_on: '2025-12-24T23:48:06.566967+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: header logo + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CL.yaml b/data/custodian/JP-13-CHO-L-CL.yaml index b6de34ede5..41180dc075 100644 --- a/data/custodian/JP-13-CHO-L-CL.yaml +++ b/data/custodian/JP-13-CHO-L-CL.yaml @@ -206,3 +206,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?4&pid=29 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?4&pid=29 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:48:16.450036+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?4&pid=29 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?4&pid=29 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:48:16.450036+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLC.yaml b/data/custodian/JP-13-CHO-L-CLC.yaml index 59eb516f06..cf8e440811 100644 --- a/data/custodian/JP-13-CHO-L-CLC.yaml +++ b/data/custodian/JP-13-CHO-L-CLC.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?9&pid=31 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?9&pid=31 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:48:25.177454+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?9&pid=31 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?9&pid=31 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:48:25.177454+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLF.yaml b/data/custodian/JP-13-CHO-L-CLF.yaml index 144fb54c4c..6ff98f3de9 100644 --- a/data/custodian/JP-13-CHO-L-CLF.yaml +++ b/data/custodian/JP-13-CHO-L-CLF.yaml @@ -205,3 +205,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?10&pid=36 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?10&pid=36 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:48:34.512513+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?10&pid=36 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?10&pid=36 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:48:34.512513+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLJ-chofushiritsu_library_jindaijibunkan.yaml b/data/custodian/JP-13-CHO-L-CLJ-chofushiritsu_library_jindaijibunkan.yaml index 0c6f53dd00..35fc30048f 100644 --- a/data/custodian/JP-13-CHO-L-CLJ-chofushiritsu_library_jindaijibunkan.yaml +++ b/data/custodian/JP-13-CHO-L-CLJ-chofushiritsu_library_jindaijibunkan.yaml @@ -205,3 +205,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?7&pid=32 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?7&pid=32 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:48:43.158948+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?7&pid=32 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?7&pid=32 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:48:43.158948+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLJ.yaml b/data/custodian/JP-13-CHO-L-CLJ.yaml index 2e512f2a47..1cbe5931aa 100644 --- a/data/custodian/JP-13-CHO-L-CLJ.yaml +++ b/data/custodian/JP-13-CHO-L-CLJ.yaml @@ -205,3 +205,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?6&pid=33 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?6&pid=33 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:48:52.375486+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?6&pid=33 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?6&pid=33 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:48:52.375486+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLK.yaml b/data/custodian/JP-13-CHO-L-CLK.yaml index 6ed738cc28..445ebf5634 100644 --- a/data/custodian/JP-13-CHO-L-CLK.yaml +++ b/data/custodian/JP-13-CHO-L-CLK.yaml @@ -205,3 +205,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?5&pid=30 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?5&pid=30 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:49:01.755563+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?5&pid=30 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?5&pid=30 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:49:01.755563+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLM-chofushiritsu_library_miyanoshitabunkan.yaml b/data/custodian/JP-13-CHO-L-CLM-chofushiritsu_library_miyanoshitabunkan.yaml index 9bc2b53efd..66ef030a03 100644 --- a/data/custodian/JP-13-CHO-L-CLM-chofushiritsu_library_miyanoshitabunkan.yaml +++ b/data/custodian/JP-13-CHO-L-CLM-chofushiritsu_library_miyanoshitabunkan.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?12&pid=34 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?12&pid=34 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:49:10.925905+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?12&pid=34 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?12&pid=34 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:49:10.925905+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLM.yaml b/data/custodian/JP-13-CHO-L-CLM.yaml index a81e5b19b4..58d99f87fa 100644 --- a/data/custodian/JP-13-CHO-L-CLM.yaml +++ b/data/custodian/JP-13-CHO-L-CLM.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?11&pid=35 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?11&pid=35 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:49:19.857685+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?11&pid=35 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?11&pid=35 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:49:19.857685+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLS-chofushiritsu_library_sazubunkan.yaml b/data/custodian/JP-13-CHO-L-CLS-chofushiritsu_library_sazubunkan.yaml index 0c4a39c365..49fc5a8346 100644 --- a/data/custodian/JP-13-CHO-L-CLS-chofushiritsu_library_sazubunkan.yaml +++ b/data/custodian/JP-13-CHO-L-CLS-chofushiritsu_library_sazubunkan.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?14&pid=39 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?14&pid=39 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:49:29.646102+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?14&pid=39 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?14&pid=39 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:49:29.646102+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLS.yaml b/data/custodian/JP-13-CHO-L-CLS.yaml index 49c1d05099..c4890cad08 100644 --- a/data/custodian/JP-13-CHO-L-CLS.yaml +++ b/data/custodian/JP-13-CHO-L-CLS.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?8&pid=38 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?8&pid=38 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:49:38.969805+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?8&pid=38 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?8&pid=38 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:49:38.969805+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-CLW.yaml b/data/custodian/JP-13-CHO-L-CLW.yaml index 9482654926..1d25c03bac 100644 --- a/data/custodian/JP-13-CHO-L-CLW.yaml +++ b/data/custodian/JP-13-CHO-L-CLW.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.lib.city.chofu.tokyo.jp/contents?13&pid=37 wikidata_official_website: https://www.lib.city.chofu.tokyo.jp/contents?13&pid=37 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:49:48.085955+00:00' + source_url: https://www.lib.city.chofu.tokyo.jp/contents?13&pid=37 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.chofu.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.chofu.tokyo.jp/contents?13&pid=37 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:49:48.085955+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHO-L-HCSC.yaml b/data/custodian/JP-13-CHO-L-HCSC.yaml index 1ad8a92929..b3ba069119 100644 --- a/data/custodian/JP-13-CHO-L-HCSC.yaml +++ b/data/custodian/JP-13-CHO-L-HCSC.yaml @@ -1117,3 +1117,30 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/KgtTPj92AhI/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:49:59.539493+00:00' + source_url: http://kodomonoyakata.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://kodomonoyakata.jp/wp-content/uploads/2022/09/top_logo-removebg-preview.png + source_url: http://kodomonoyakata.jp + css_selector: '#site-header-container > div.site-header-logo > a > span > img' + retrieved_on: '2025-12-24T23:49:59.539493+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 兵庫県立こどもの館 + - claim_type: favicon_url + claim_value: https://kodomonoyakata.jp/wp-content/uploads/2022/09/こどもの館ロゴ.png + source_url: http://kodomonoyakata.jp + css_selector: '[document] > html > head > link:nth-of-type(25)' + retrieved_on: '2025-12-24T23:49:59.539493+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-CHO-L-SUL.yaml b/data/custodian/JP-13-CHO-L-SUL.yaml index 0ce10cd64e..7115e2a2f5 100644 --- a/data/custodian/JP-13-CHO-L-SUL.yaml +++ b/data/custodian/JP-13-CHO-L-SUL.yaml @@ -211,3 +211,28 @@ location: geonames_id: 1864518 geonames_name: Chōfu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:50:17.679751+00:00' + source_url: https://www.shirayuri.ac.jp/lib/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.shirayuri.ac.jp/favicon.ico + source_url: https://www.shirayuri.ac.jp/lib/index.html + css_selector: '[document] > html.scroll.hideheader > head > link' + retrieved_on: '2025-12-24T23:50:17.679751+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.shirayuri.ac.jp/common/images/ogp_logo.gif + source_url: https://www.shirayuri.ac.jp/lib/index.html + css_selector: '[document] > html.scroll.hideheader > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-24T23:50:17.679751+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHO-L-TGSMCL.yaml b/data/custodian/JP-13-CHO-L-TGSMCL.yaml index 5052fb7053..b60255228b 100644 --- a/data/custodian/JP-13-CHO-L-TGSMCL.yaml +++ b/data/custodian/JP-13-CHO-L-TGSMCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHO-L-TGSMCL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHO-L-TGSMCL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHO-L-TGSMCL ghcid_numeric: 1944084365589440371 valid_from: '2025-12-06T23:38:59.785869+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOHO GAKUEN SCHOOL OF MUSIC CHOFU LIBRARY @@ -204,3 +205,28 @@ location: geonames_id: 1864518 geonames_name: Chōfu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:50:22.642736+00:00' + source_url: https://www.toho-lib.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://webopac.tohomusic.ac.jp/wp-content/themes/opac_basic/assets/images/apple-touch-icon.png + source_url: https://www.toho-lib.com + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T23:50:22.642736+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://webopac.tohomusic.ac.jp/wp-content/themes/opac_basic/images/ogp_img.jpg + source_url: https://www.toho-lib.com + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T23:50:22.642736+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHO-L-TGSMSL.yaml b/data/custodian/JP-13-CHO-L-TGSMSL.yaml index efc83b0a14..318f535790 100644 --- a/data/custodian/JP-13-CHO-L-TGSMSL.yaml +++ b/data/custodian/JP-13-CHO-L-TGSMSL.yaml @@ -205,3 +205,28 @@ location: geonames_id: 1864518 geonames_name: Chōfu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:50:26.736109+00:00' + source_url: https://www.toho-lib.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://webopac.tohomusic.ac.jp/wp-content/themes/opac_basic/assets/images/apple-touch-icon.png + source_url: https://www.toho-lib.com + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T23:50:26.736109+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://webopac.tohomusic.ac.jp/wp-content/themes/opac_basic/images/ogp_img.jpg + source_url: https://www.toho-lib.com + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-24T23:50:26.736109+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHO-L-TL.yaml b/data/custodian/JP-13-CHO-L-TL.yaml index d838b08618..0d90324891 100644 --- a/data/custodian/JP-13-CHO-L-TL.yaml +++ b/data/custodian/JP-13-CHO-L-TL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHO-L-TL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHO-L-TL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHO-L-TL ghcid_numeric: 13158139431771078070 valid_from: '2025-12-06T23:38:56.927069+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOHOGAKUENGEIJUTSUTANKIDAIGAKU Library @@ -204,3 +205,28 @@ location: geonames_id: 1864518 geonames_name: Chōfu feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:50:36.850620+00:00' + source_url: http://www.toho.ac.jp/college/campus_life/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://college.toho.ac.jp/common/image/app-icon.png + source_url: http://www.toho.ac.jp/college/campus_life/library + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-24T23:50:36.850620+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://college.toho.ac.jp/common/image/sns-icon.jpg + source_url: http://www.toho.ac.jp/college/campus_life/library + css_selector: '[document] > html.js > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-24T23:50:36.850620+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-CHU-L-CL-chuokuritsunihombashi_library.yaml b/data/custodian/JP-13-CHU-L-CL-chuokuritsunihombashi_library.yaml index 44c82933a4..380e4d611a 100644 --- a/data/custodian/JP-13-CHU-L-CL-chuokuritsunihombashi_library.yaml +++ b/data/custodian/JP-13-CHU-L-CL-chuokuritsunihombashi_library.yaml @@ -199,3 +199,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.chuo.tokyo.jp/libguide?13&pid=12 wikidata_official_website: https://www.library.city.chuo.tokyo.jp/libguide?13&pid=12 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:54:02.881108+00:00' + source_url: https://www.library.city.chuo.tokyo.jp/contents?11&pid=12 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.chuo.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.chuo.tokyo.jp/contents?11&pid=12 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:54:02.881108+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHU-L-CL-chuokuritsutsukishima_library.yaml b/data/custodian/JP-13-CHU-L-CL-chuokuritsutsukishima_library.yaml index 07ddbe9e45..9c2c754e61 100644 --- a/data/custodian/JP-13-CHU-L-CL-chuokuritsutsukishima_library.yaml +++ b/data/custodian/JP-13-CHU-L-CL-chuokuritsutsukishima_library.yaml @@ -199,3 +199,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.chuo.tokyo.jp/libguide?11&pid=13 wikidata_official_website: https://www.library.city.chuo.tokyo.jp/libguide?11&pid=13 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:54:11.401304+00:00' + source_url: https://www.library.city.chuo.tokyo.jp/contents?9&pid=13 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.chuo.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.chuo.tokyo.jp/contents?9&pid=13 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:54:11.401304+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHU-L-CL.yaml b/data/custodian/JP-13-CHU-L-CL.yaml index 4f49f31eaa..eded5f5125 100644 --- a/data/custodian/JP-13-CHU-L-CL.yaml +++ b/data/custodian/JP-13-CHU-L-CL.yaml @@ -199,3 +199,20 @@ wikidata_enrichment: wikidata_web: official_website: https://www.library.city.chuo.tokyo.jp/libguide?9&pid=11 wikidata_official_website: https://www.library.city.chuo.tokyo.jp/libguide?9&pid=11 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:54:21.188335+00:00' + source_url: https://www.library.city.chuo.tokyo.jp/contents?1&pid=11 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.city.chuo.tokyo.jp/images/ogimage.png + source_url: https://www.library.city.chuo.tokyo.jp/contents?1&pid=11 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:54:21.188335+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHU-L-EPDCLL.yaml b/data/custodian/JP-13-CHU-L-EPDCLL.yaml index deecc090fe..834d2da336 100644 --- a/data/custodian/JP-13-CHU-L-EPDCLL.yaml +++ b/data/custodian/JP-13-CHU-L-EPDCLL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHU-L-EPDCLL - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHU-L-EPDCLL valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHU-L-EPDCLL ghcid_numeric: 2893332929778622738 valid_from: '2025-12-06T23:38:57.834789+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Electric Power Development Co., Ltd. Library @@ -151,3 +152,36 @@ location: geonames_id: 13353695 geonames_name: Chūō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:54:38.546905+00:00' + source_url: http://www.jpower.co.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.jpower.co.jp/_assets/images/logo.svg + source_url: http://www.jpower.co.jp + css_selector: '#siteID > a > img' + retrieved_on: '2025-12-24T23:54:38.546905+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: J-POWER 電源開発 + - claim_type: favicon_url + claim_value: http://www.jpower.co.jp/apple-touch-icon.png + source_url: http://www.jpower.co.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T23:54:38.546905+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.jpower.co.jp/_assets/images/ogp.png + source_url: http://www.jpower.co.jp + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T23:54:38.546905+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHU-L-I.yaml b/data/custodian/JP-13-CHU-L-I.yaml index 58dd8e839e..de313bf0e1 100644 --- a/data/custodian/JP-13-CHU-L-I.yaml +++ b/data/custodian/JP-13-CHU-L-I.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHU-L-I - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHU-L-I valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHU-L-I ghcid_numeric: 17478200871498803303 valid_from: '2025-12-06T23:38:57.899876+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: IPPANZAIDANHOJINNIHONENERUGIKEIZAIKENKYUJOSHIRYOSHITSU @@ -151,3 +152,37 @@ location: geonames_id: 13353695 geonames_name: Chūō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:54:54.370631+00:00' + source_url: http://eneken.ieej.or.jp/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://eneken.ieej.or.jp/img/logo.svg + source_url: http://eneken.ieej.or.jp/library/index.html + css_selector: '#ij-2024renew-home > header > div.ij-header > div.container > div.row.ij-header-wrapper + > div.ij-header-logo > a > img' + retrieved_on: '2025-12-24T23:54:54.370631+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: IEEJ 一般財団法人 日本エネルギー経済研究所 + - claim_type: favicon_url + claim_value: http://eneken.ieej.or.jp/img/favicon.ico + source_url: http://eneken.ieej.or.jp/library/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-24T23:54:54.370631+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://eneken.ieej.or.jp/img/ogp-img.png + source_url: http://eneken.ieej.or.jp/library/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-24T23:54:54.370631+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-CHU-L-ICR.yaml b/data/custodian/JP-13-CHU-L-ICR.yaml index 8bdea734bb..048cb5b312 100644 --- a/data/custodian/JP-13-CHU-L-ICR.yaml +++ b/data/custodian/JP-13-CHU-L-ICR.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHU-L-ICR - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHU-L-ICR valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHU-L-ICR ghcid_numeric: 8124569218506764773 valid_from: '2025-12-06T23:38:58.920219+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Institute of Cetacean Research @@ -151,3 +152,29 @@ location: geonames_id: 13353695 geonames_name: Chūō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:55:01.983351+00:00' + source_url: http://www.icrwhale.org + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.icrwhale.org/img/logo.png + source_url: http://www.icrwhale.org + css_selector: '[document] > html > body > header > div.top_header.lang_box > div.logo_left + > div.logo_text_flex > div > img.logo_box' + retrieved_on: '2025-12-24T23:55:01.983351+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 一般財団法人 日本鯨類研究所 ロゴマーク + - claim_type: og_image_url + claim_value: https://icrwhale.org/img/ogp.jpg + source_url: http://www.icrwhale.org + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-24T23:55:01.983351+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-CHU-L-JLAJ.yaml b/data/custodian/JP-13-CHU-L-JLAJ.yaml index 9ef7c12e7f..8c9db7dc5e 100644 --- a/data/custodian/JP-13-CHU-L-JLAJ.yaml +++ b/data/custodian/JP-13-CHU-L-JLAJ.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHU-L-JLAJ - valid_from: "2025-12-10T09:44:01Z" + valid_from: '2025-12-10T09:44:01Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHU-L-JLAJ valid_from: null - valid_to: "2025-12-10T09:44:01Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:01Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHU-L-JLAJ ghcid_numeric: 11871393703828176730 valid_from: '2025-12-06T23:38:58.338599+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Japan Library Association(JLA) @@ -151,3 +152,37 @@ location: geonames_id: 13353695 geonames_name: Chūō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:55:26.620748+00:00' + source_url: http://www.jla.or.jp/activities/shiryou/tabid/302/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.jla.or.jp/wp/wp-content/uploads/2025/03/site_logo.png + source_url: http://www.jla.or.jp/activities/shiryou/tabid/302/Default.aspx + css_selector: '#header-in > div.wrapper > div.item1 > div.logo.logo-header > a.site-name.site-name-text-link + > span.site-name-text > img.site-logo-image.header-site-logo-image' + retrieved_on: '2025-12-24T23:55:26.620748+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日本図書館協会オフィシャルサイト + - claim_type: favicon_url + claim_value: https://www.jla.or.jp/wp/wp-content/uploads/2025/01/cropped-JLAアイコン_New-180x180.png + source_url: http://www.jla.or.jp/activities/shiryou/tabid/302/Default.aspx + css_selector: '[document] > html > head > link:nth-of-type(49)' + retrieved_on: '2025-12-24T23:55:26.620748+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://jla-orjp.check-xserver.jp/wp/wp-content/themes/cocoon-master/screenshot.jpg + source_url: http://www.jla.or.jp/activities/shiryou/tabid/302/Default.aspx + css_selector: '[document] > html > head > meta:nth-of-type(24)' + retrieved_on: '2025-12-24T23:55:26.620748+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-CHU-L-NFCNMMAT.yaml b/data/custodian/JP-13-CHU-L-NFCNMMAT.yaml index 87da489771..bfac28ea7c 100644 --- a/data/custodian/JP-13-CHU-L-NFCNMMAT.yaml +++ b/data/custodian/JP-13-CHU-L-NFCNMMAT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-CHU-L-NFCNMMAT - valid_from: "2025-12-10T09:44:02Z" + valid_from: '2025-12-10T09:44:02Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-CHU-L-NFCNMMAT valid_from: null - valid_to: "2025-12-10T09:44:02Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:02Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-CHU-L-NFCNMMAT ghcid_numeric: 224426593231375376 valid_from: '2025-12-06T23:38:58.858194+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: National Film Center, The National Museum of Modern Art, Tokyo @@ -151,3 +152,22 @@ location: geonames_id: 13353695 geonames_name: Chūō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:56:30.444650+00:00' + source_url: http://www.momat.go.jp/fc/research/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.momat.go.jp/wp-content/themes/momat/images/favicon/favicon.svg + source_url: http://www.momat.go.jp/fc/research/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-24T23:56:30.444650+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-CHU-L-RLT.yaml b/data/custodian/JP-13-CHU-L-RLT.yaml index d2ad2117d5..f1c4df282d 100644 --- a/data/custodian/JP-13-CHU-L-RLT.yaml +++ b/data/custodian/JP-13-CHU-L-RLT.yaml @@ -152,3 +152,20 @@ location: geonames_id: 13353695 geonames_name: Chūō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-24T23:56:37.981562+00:00' + source_url: http://jruskin.la.coocan.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://jruskin.jp/wp-content/uploads/2023/08/takamura_ruskin_zou.png + source_url: http://jruskin.la.coocan.jp + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-24T23:56:37.981562+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0