diff --git a/backend/rag/dspy_heritage_rag.py b/backend/rag/dspy_heritage_rag.py index 54e4f8f2fb..7c67f52b6e 100644 --- a/backend/rag/dspy_heritage_rag.py +++ b/backend/rag/dspy_heritage_rag.py @@ -1312,6 +1312,129 @@ def normalize_custodian_type(type_value: str) -> str | None: return None +def extract_institution_slug_from_query(query: str) -> str | None: + """Extract institution name from query and convert to slug format for filtering. + + This function identifies when a user is asking about staff at a SPECIFIC institution + and extracts the institution name, converting it to a slug format that matches + the custodian_slug field in Qdrant's heritage_persons collection. + + Args: + query: User's natural language question + + Returns: + Institution slug (e.g., 'het-utrechts-archief', 'nationaal-archief') or None + + Examples: + >>> extract_institution_slug_from_query("welke data expert werken voor Het Utrechts Archief?") + 'het-utrechts-archief' + >>> extract_institution_slug_from_query("who works at Nationaal Archief?") + 'nationaal-archief' + >>> extract_institution_slug_from_query("medewerkers van het Rijksmuseum") + 'rijksmuseum' + >>> extract_institution_slug_from_query("wie zijn de curatoren?") # No specific institution + None + """ + # Known Dutch heritage institutions with their slug mappings + # This helps with exact matching for common institutions + KNOWN_INSTITUTIONS = { + # Archives + 'het utrechts archief': 'het-utrechts-archief', + 'utrechts archief': 'het-utrechts-archief', + 'nationaal archief': 'nationaal-archief', + 'stadsarchief amsterdam': 'stadsarchief-amsterdam', + 'stadsarchief rotterdam': 'stadsarchief-rotterdam', + 'noord-hollands archief': 'noord-hollands-archief', + 'gelders archief': 'gelders-archief', + 'brabants historisch informatie centrum': 'brabants-historisch-informatie-centrum', + 'bhic': 'brabants-historisch-informatie-centrum', + 'regionaal archief tilburg': 'regionaal-archief-tilburg', + 'zeeuws archief': 'zeeuws-archief', + 'tresoar': 'tresoar', + 'drents archief': 'drents-archief', + 'historisch centrum overijssel': 'historisch-centrum-overijssel', + 'erfgoed leiden': 'erfgoed-leiden-en-omstreken', + # Museums + 'rijksmuseum': 'rijksmuseum', + 'van gogh museum': 'van-gogh-museum', + 'stedelijk museum': 'stedelijk-museum-amsterdam', + 'mauritshuis': 'mauritshuis', + 'kröller-müller': 'kroller-muller-museum', + 'kroller-muller': 'kroller-muller-museum', + 'boijmans van beuningen': 'museum-boijmans-van-beuningen', + 'eye filmmuseum': 'eye-filmmuseum', + 'eye': 'eye-filmmuseum', + 'tropenmuseum': 'tropenmuseum', + 'nederlands openluchtmuseum': 'nederlands-openluchtmuseum', + 'openluchtmuseum': 'nederlands-openluchtmuseum', + # Libraries + 'koninklijke bibliotheek': 'koninklijke-bibliotheek', + 'kb': 'koninklijke-bibliotheek', + 'universiteitsbibliotheek amsterdam': 'universiteitsbibliotheek-amsterdam', + 'uba': 'universiteitsbibliotheek-amsterdam', + 'universiteitsbibliotheek leiden': 'universiteitsbibliotheek-leiden', + # Other heritage organizations + 'beeld en geluid': 'beeld-en-geluid', + 'niod': 'niod', + 'rkd': 'rkd', + 'atria': 'atria', + 'meertens instituut': 'meertens-instituut', + } + + query_lower = query.lower() + + # First check for known institutions (exact substring match) + for name, slug in KNOWN_INSTITUTIONS.items(): + if name in query_lower: + logger.debug(f"Matched known institution: '{name}' -> '{slug}'") + return slug + + # Patterns to extract institution names from queries + # These patterns capture institution names mentioned with prepositions + patterns = [ + # Dutch patterns + r'(?:bij|voor|van|werken\s+(?:bij|voor)|medewerkers\s+(?:van|bij))\s+(?:het\s+)?([A-Z][a-zA-Z\s\-\']+(?:Archief|Museum|Bibliotheek|Instituut|Centrum))', + r'(?:bij|voor|van)\s+((?:Het\s+)?[A-Z][a-zA-Z\s\-\']+)', + # English patterns + r'(?:at|for|from|of|works?\s+(?:at|for))\s+(?:the\s+)?([A-Z][a-zA-Z\s\-\']+(?:Archive|Museum|Library|Institute|Center|Centre))', + r'(?:at|for|from)\s+((?:The\s+)?[A-Z][a-zA-Z\s\-\']+)', + ] + + for pattern in patterns: + match = re.search(pattern, query, re.IGNORECASE) + if match: + institution_name = match.group(1).strip() + + # Skip if it's just a generic term + generic_terms = {'het', 'de', 'een', 'the', 'a', 'an', 'museum', 'archief', 'bibliotheek'} + if institution_name.lower() in generic_terms: + continue + + # Convert to slug format + # 1. Normalize unicode and remove diacritics + import unicodedata + normalized = unicodedata.normalize('NFD', institution_name) + ascii_name = ''.join(c for c in normalized if unicodedata.category(c) != 'Mn') + + # 2. Convert to lowercase + slug = ascii_name.lower() + + # 3. Remove punctuation except hyphens + slug = re.sub(r"[''`\",.:;!?()[\]{}]", '', slug) + + # 4. Replace spaces with hyphens + slug = re.sub(r'[\s_]+', '-', slug) + + # 5. Remove multiple consecutive hyphens + slug = re.sub(r'-+', '-', slug).strip('-') + + if len(slug) >= 3: # Minimum reasonable slug length + logger.debug(f"Extracted institution from query: '{institution_name}' -> '{slug}'") + return slug + + return None + + # ============================================================================= # 2. DSPy MODULES # ============================================================================= @@ -1444,6 +1567,14 @@ class HeritageQueryRouter(dspy.Module): f"Fallback: extracted custodian type from query: '{target_custodian_type}'" ) + # Extract target institution slug for person queries (enables filtering by institution) + # This is critical for queries like "welke experts werken voor Het Utrechts Archief?" + target_custodian_slug = None + if entity_type == 'person': + target_custodian_slug = extract_institution_slug_from_query(question) + if target_custodian_slug: + logger.info(f"Extracted target institution for person query: '{target_custodian_slug}'") + # Build prediction with all fields (including validated schema-aware fields) prediction = Prediction( intent=result.intent, @@ -1456,6 +1587,8 @@ class HeritageQueryRouter(dspy.Module): target_role_category=target_role_category, target_staff_role=target_staff_role, target_custodian_type=target_custodian_type, + # Institution filter for person queries + target_custodian_slug=target_custodian_slug, ) return prediction @@ -3365,12 +3498,14 @@ class HeritageRAGPipeline(dspy.Module): # Use schema-aware filters from DSPy router when available target_role_category = getattr(routing, 'target_role_category', None) target_custodian_type = getattr(routing, 'target_custodian_type', None) + target_custodian_slug = getattr(routing, 'target_custodian_slug', None) # Only pass non-empty, non-unknown values effective_role_category = target_role_category if target_role_category not in (None, "", "UNKNOWN", "UNSPECIFIED") else None effective_custodian_type = target_custodian_type if target_custodian_type not in (None, "", "UNKNOWN", "UNSPECIFIED") else None + effective_custodian_slug = target_custodian_slug if target_custodian_slug not in (None, "") else None - logger.info(f"Performing PERSON retrieval for: {resolved_question[:50]}... (role_category={effective_role_category}, custodian_type={effective_custodian_type})") + logger.info(f"Performing PERSON retrieval for: {resolved_question[:50]}... (role_category={effective_role_category}, custodian_type={effective_custodian_type}, custodian_slug={effective_custodian_slug})") # Wrap retrieval with cost tracking if tracker: @@ -3381,6 +3516,7 @@ class HeritageRAGPipeline(dspy.Module): using=embedding_model, target_role_category=effective_role_category, target_custodian_type=effective_custodian_type, + filter_custodian=effective_custodian_slug, ) retrieval_timing.result_count = len(person_results) if person_results else 0 timing_breakdown["person_retrieval_ms"] = retrieval_timing.duration_ms @@ -3391,6 +3527,7 @@ class HeritageRAGPipeline(dspy.Module): using=embedding_model, target_role_category=effective_role_category, target_custodian_type=effective_custodian_type, + filter_custodian=effective_custodian_slug, ) if person_results: @@ -3815,9 +3952,20 @@ class HeritageRAGPipeline(dspy.Module): detected_query_type = "person" logger.info(f"Detected PERSON query for streaming: {resolved_question[:50]}...") + # Extract target institution slug for filtering (if query mentions a specific institution) + target_custodian_slug = getattr(routing, 'target_custodian_slug', None) + effective_custodian_slug = target_custodian_slug if target_custodian_slug not in (None, "") else None + if effective_custodian_slug: + logger.info(f"Filtering person search by custodian: {effective_custodian_slug}") + # Search for persons if hasattr(self.retriever, 'search_persons'): - person_results = self.retriever.search_persons(query=resolved_question, k=10, using=embedding_model) + person_results = self.retriever.search_persons( + query=resolved_question, + k=10, + using=embedding_model, + filter_custodian=effective_custodian_slug, + ) if person_results: context_parts.append("\n[RETRIEVED STAFF/PEOPLE - Real data from heritage database]:") diff --git a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json index 660a858f97..99372bae3a 100644 --- a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json +++ b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json @@ -12832,7 +12832,1007 @@ "JP-13-YAZ-L-YL.yaml", "JP-13-YAZ-M-HNMH.yaml", "JP-13-YAZ-M-WK.yaml", - "JP-13-YON-L-N.yaml" + "JP-13-YON-L-N.yaml", + "CZ-51-NOV-L-MKS.yaml", + "CZ-51-NOV-L-MKVNVNP.yaml", + "CZ-51-NOV-L-OKNVNN.yaml", + "CZ-51-NOV-L-OLKVO.yaml", + "CZ-51-OKN-L-MKVO.yaml", + "CZ-51-OSE-L-MKO.yaml", + "CZ-51-PEN-L-MKVP.yaml", + "CZ-51-PEN-L-MLKVL.yaml", + "CZ-51-PEN-L-OKVSU.yaml", + "CZ-51-PLA-L-OKP.yaml", + "CZ-51-PNJ-M-PZV.yaml", + "CZ-51-PON-L-MKP.yaml", + "CZ-51-PRE-L-MSRK.yaml", + "CZ-51-PRI-L-OKVP.yaml", + "CZ-51-PRY-L-MKVP.yaml", + "CZ-51-RAD-L-OKR.yaml", + "CZ-51-RAK-L-OKR.yaml", + "CZ-51-RAS-L-MKIC.yaml", + "CZ-51-ROK-L-MKRNJ.yaml", + "CZ-51-ROV-L-MKRPT.yaml", + "CZ-51-ROZ-L-OKRUJ.yaml", + "CZ-51-RYC-L-MKVRUJNN.yaml", + "CZ-51-SEM-A-AUMAVESS-archivalie_ulozene_mimo_archivy_v_evidenci_soka_se.yaml", + "CZ-51-SEM-A-SOAS-statni_okresni_archiv_semily.yaml", + "CZ-51-SEM-L-HSR.yaml", + "CZ-51-SEM-L-MKL.yaml", + "CZ-51-SEM-L-MKSPO.yaml", + "CZ-51-SEM-L-MKSRO.yaml", + "CZ-51-SEM-L-MKVP.yaml", + "CZ-51-SEM-L-MKVRUS.yaml", + "CZ-51-SEM-L-MKVS.yaml", + "CZ-51-SEM-L-MSNVSLK.yaml", + "CZ-51-SEM-L-OKVC.yaml", + "CZ-51-SEM-L-TZTK.yaml", + "CZ-51-SEM-M-MPG.yaml", + "CZ-51-SEM-O-SOAVLSOAS.yaml", + "CZ-51-SEN-M-SMKS.yaml", + "CZ-51-SIM-L-MKVS.yaml", + "CZ-51-SKA-L-MKVSUCL.yaml", + "CZ-51-SLA-L-MKVS.yaml", + "CZ-51-SMR-L-MKIS.yaml", + "CZ-51-SMR-M-MMHS.yaml", + "CZ-51-SOS-L-MKVS.yaml", + "CZ-51-SPR-A-AD.yaml", + "CZ-51-STA-L-OKVS.yaml", + "CZ-51-STR-L-MKVSNN.yaml", + "CZ-51-STR-L-MS.yaml", + "CZ-51-STR-O-JACK.yaml", + "CZ-51-STU-L-OKS.yaml", + "CZ-51-STV-L-MKVS.yaml", + "CZ-51-SVO-L-MKS-mistni_knihovna_svojkov.yaml", + "CZ-51-SVO-L-MKS.yaml", + "CZ-51-SVO-L-SS.yaml", + "CZ-51-SYC-L-MKVR.yaml", + "CZ-51-SYC-L-MKVV.yaml", + "CZ-51-SYC-L-MKVZ.yaml", + "CZ-51-SYC-L-OKP.yaml", + "CZ-51-SYC-M-PAD.yaml", + "CZ-51-TAN-L-MKT.yaml", + "CZ-51-TAN-L-STSK.yaml", + "CZ-51-TAT-L-OKVT.yaml", + "CZ-51-TRU-L-TT.yaml", + "CZ-51-TUR-E-SUSVOSK.yaml", + "CZ-51-TUR-L-DS.yaml", + "CZ-51-TUR-L-DTSR.yaml", + "CZ-51-TUR-L-GDUV.yaml", + "CZ-51-TUR-L-MKAMTPO.yaml", + "CZ-51-TUR-L-MKL.yaml", + "CZ-51-TUR-L-MKVK.yaml", + "CZ-51-TUR-L-OKHS.yaml", + "CZ-51-TUR-L-OKM.yaml", + "CZ-51-TUR-L-OKVK-obecni_knihovna_v_klokoci.yaml", + "CZ-51-TUR-L-OKVK.yaml", + "CZ-51-TUR-L-OKVL.yaml", + "CZ-51-TUR-L-OKVO-obecni_knihovna_v_ohrazenicich.yaml", + "CZ-51-TUR-L-S.yaml", + "CZ-51-TUR-M-MCRVTK.yaml", + "CZ-51-VEL-L-MKAJVVH.yaml", + "CZ-51-VES-L-MKVV.yaml", + "CZ-51-VEV-L-MZKB.yaml", + "CZ-51-VIC-L-MKVNJ.yaml", + "CZ-51-VNJ-M-VMPVNJO.yaml", + "CZ-51-VOL-L-OMKV.yaml", + "CZ-51-VRA-L-KIV.yaml", + "CZ-51-VSE-L-MKVP.yaml", + "CZ-51-VSE-L-OKFJTVV.yaml", + "CZ-51-VYS-L-MKVNJ.yaml", + "CZ-51-ZAH-L-MKVZ.yaml", + "CZ-51-ZAN-L-MKZ.yaml", + "CZ-51-ZAN-L-SZSK.yaml", + "CZ-51-ZBR-M-MMVZB.yaml", + "CZ-51-ZEL-L-JGSTK.yaml", + "CZ-51-ZEL-L-MLKV.yaml", + "CZ-51-ZEL-L-OKK.yaml", + "CZ-51-ZEL-L-OKL.yaml", + "CZ-51-ZEL-L-OKR.yaml", + "CZ-51-ZLA-L-OKZO.yaml", + "CZ-52-BAT-L-OKB.yaml", + "CZ-52-BEL-L-OKBNO.yaml", + "CZ-52-BEL-M-MKSLBPKVR.yaml", + "CZ-52-BER-L-MKB.yaml", + "CZ-52-BER-L-OKL.yaml", + "CZ-52-BIL-E-ZSMSBTSKVL.yaml", + "CZ-52-BIL-L-OKVBT.yaml", + "CZ-52-BOH-L-MKB.yaml", + "CZ-52-BOL-L-MKB.yaml", + "CZ-52-BOR-L-MKB.yaml", + "CZ-52-BOR-L-OKVB.yaml", + "CZ-52-BRE-H-KPK.yaml", + "CZ-52-BRE-H-SKAJK.yaml", + "CZ-52-BRE-L-KMCPB.yaml", + "CZ-52-BRE-L-UKVPLFVFNI-univerzita_karlova_v_praze_1lekarska_fakulta_a_vse.yaml", + "CZ-52-BRE-L-UVNVFNP.yaml", + "CZ-52-BRE-O-MZVCOAZIUV.yaml", + "CZ-52-BRO-L-MKK.yaml", + "CZ-52-BRO-L-VTZSK.yaml", + "CZ-52-BUT-L-KB.yaml", + "CZ-52-BYL-M-MMNB.yaml", + "CZ-52-CAK-L-VTUSPOZVTK.yaml", + "CZ-52-CER-L-MKC.yaml", + "CZ-52-CER-L-MKCCD.yaml", + "CZ-52-CER-L-OKVCD.yaml", + "CZ-52-CER-L-OKVCH.yaml", + "CZ-52-CER-L-T.yaml", + "CZ-52-CER-L-TP.yaml", + "CZ-52-CES-L-KUMMZK.yaml", + "CZ-52-CES-L-MKC.yaml", + "CZ-52-CES-L-MKCM.yaml", + "CZ-52-CES-L-MKL.yaml", + "CZ-52-CES-L-O.yaml", + "CZ-52-CES-L-OKCC.yaml", + "CZ-52-CES-L-OKKL.yaml", + "CZ-52-CES-L-OKVCM.yaml", + "CZ-52-CES-L-OKVZ.yaml", + "CZ-52-CES-M-TMT.yaml", + "CZ-52-CHL-L-MKL.yaml", + "CZ-52-CHL-L-OKK.yaml", + "CZ-52-CHL-L-OKNM.yaml", + "CZ-52-CHL-L-OKP.yaml", + "CZ-52-CHL-L-OKVK.yaml", + "CZ-52-CHO-L-OKC.yaml", + "CZ-52-CHV-L-MKVC.yaml", + "CZ-52-CHV-L-MLKC.yaml", + "CZ-52-CIM-L-PNBLK.yaml", + "CZ-52-CIM-L-UCPVSMVVSH.yaml", + "CZ-52-DEO-M-MTZSR.yaml", + "CZ-52-DES-L-IKVDVOH.yaml", + "CZ-52-DET-L-MKVD.yaml", + "CZ-52-DKR-M-MMDKNL.yaml", + "CZ-52-DLI-A-VHA.yaml", + "CZ-52-DOB-L-BZKB.yaml", + "CZ-52-DOB-L-MKD-mistni_knihovna_dobrany.yaml", + "CZ-52-DOB-L-MKD-mistni_knihovna_dobre.yaml", + "CZ-52-DOB-L-MKD.yaml", + "CZ-52-DOB-L-MKDVUH.yaml", + "CZ-52-DOB-L-MKH.yaml", + "CZ-52-DOB-L-MKJ.yaml", + "CZ-52-DOB-L-MKK.yaml", + "CZ-52-DOB-L-MKR.yaml", + "CZ-52-DOB-L-MKVB-mistni_knihovna_v_bohdasine.yaml", + "CZ-52-DOB-L-MKVB.yaml", + "CZ-52-DOB-L-OKD.yaml", + "CZ-52-DOB-M-MMD-mestske_muzeum_dobruska.yaml", + "CZ-52-DOH-L-OKVD.yaml", + "CZ-52-DOL-L-MLKDR.yaml", + "CZ-52-DOL-L-NCZPVVVK.yaml", + "CZ-52-DOL-L-NPICRK.yaml", + "CZ-52-DOL-L-OKDL.yaml", + "CZ-52-DOL-L-OKDP.yaml", + "CZ-52-DOL-L-OKP.yaml", + "CZ-52-DOL-L-VUZTVVRPP.yaml", + "CZ-52-DOL-L-ZKSK.yaml", + "CZ-52-DOU-L-MKDNO.yaml", + "CZ-52-DUB-L-KD.yaml", + "CZ-52-DUB-L-MVKVPD.yaml", + "CZ-52-DVU-E-GDKNLK.yaml", + "CZ-52-DVU-L-ISR.yaml", + "CZ-52-DVU-L-MKSVDKNL.yaml", + "CZ-52-DVU-L-O.yaml", + "CZ-52-DVU-L-OKVL.yaml", + "CZ-52-DVU-L-SZ.yaml", + "CZ-52-DVU-L-T.yaml", + "CZ-52-DVU-L-TS.yaml", + "CZ-52-DVU-L-VZS.yaml", + "CZ-52-DVU-M-MMVDKNLK.yaml", + "CZ-52-DZA-L-PUK.yaml", + "CZ-52-DZA-L-UTAMACVVOK.yaml", + "CZ-52-HAJ-L-MKH.yaml", + "CZ-52-HAV-L-OKH.yaml", + "CZ-52-HER-L-OKH.yaml", + "CZ-52-HKR-M-VM.yaml", + "CZ-52-HLU-L-OKVH.yaml", + "CZ-52-HLU-L-OKVJ.yaml", + "CZ-52-HOL-M-NTM.yaml", + "CZ-52-HOR-L-M.yaml", + "CZ-52-HOR-L-MKH.yaml", + "CZ-52-HOR-L-MKHR.yaml", + "CZ-52-HOR-L-MKPUV.yaml", + "CZ-52-HOR-L-MKS-mistni_knihovna_sobcice.yaml", + "CZ-52-HOR-L-MKVJ.yaml", + "CZ-52-HOR-L-MKVL.yaml", + "CZ-52-HOR-L-OKB.yaml", + "CZ-52-HOR-L-OKH-obecni_knihovna_horineves.yaml", + "CZ-52-HOR-L-OKH.yaml", + "CZ-52-HOR-L-OKVHB.yaml", + "CZ-52-HOR-L-OKVHM.yaml", + "CZ-52-HOR-L-OKVHR.yaml", + "CZ-52-HOR-L-OKVT.yaml", + "CZ-52-HOR-L-OKZ.yaml", + "CZ-52-HOR-L-UKLFFNVMOK.yaml", + "CZ-52-HOR-L-UKUK.yaml", + "CZ-52-HOR-L-UMCACVVK.yaml", + "CZ-52-HOS-G-GAU.yaml", + "CZ-52-HOS-L-KPS.yaml", + "CZ-52-HOS-L-MKH.yaml", + "CZ-52-HRA-A-AUHK.yaml", + "CZ-52-HRA-A-AUMAVESHK-archivalie_ulozene_mimo_archivy_v_evidenci_soka_hr.yaml", + "CZ-52-HRA-A-AUMAVESHK.yaml", + "CZ-52-HRA-A-AUMAVESHKR-archivalie_ulozene_mimo_archivy_v_evidenci_soa_hra.yaml", + "CZ-52-HRA-A-AUMAVESHKR.yaml", + "CZ-52-HRA-A-ISAKHK.yaml", + "CZ-52-HRA-A-SOAHK.yaml", + "CZ-52-HRA-E-VOSZSZSHKS.yaml", + "CZ-52-HRA-G-GMUHK.yaml", + "CZ-52-HRA-H-BKBK.yaml", + "CZ-52-HRA-L-BP.yaml", + "CZ-52-HRA-L-CHN.yaml", + "CZ-52-HRA-L-CPZHK.yaml", + "CZ-52-HRA-L-ESSR.yaml", + "CZ-52-HRA-L-FBSR.yaml", + "CZ-52-HRA-L-FNHKLK.yaml", + "CZ-52-HRA-L-GS.yaml", + "CZ-52-HRA-L-HPVHK.yaml", + "CZ-52-HRA-L-I.yaml", + "CZ-52-HRA-L-IS.yaml", + "CZ-52-HRA-L-KHSKK.yaml", + "CZ-52-HRA-L-KMHK.yaml", + "CZ-52-HRA-L-KORTMHVK.yaml", + "CZ-52-HRA-L-KVRIS.yaml", + "CZ-52-HRA-L-OS.yaml", + "CZ-52-HRA-L-PPPSPCKKK.yaml", + "CZ-52-HRA-L-SK.yaml", + "CZ-52-HRA-L-SUHKSRSV.yaml", + "CZ-52-HRA-L-T.yaml", + "CZ-52-HRA-L-TBSTK.yaml", + "CZ-52-HRA-L-THK-tesla_hradec_kralove.yaml", + "CZ-52-HRA-L-THK.yaml", + "CZ-52-HRA-L-TPS.yaml", + "CZ-52-HRA-L-UKFFVHKSVK.yaml", + "CZ-52-HRA-L-UKLFVHKLK.yaml", + "CZ-52-HRA-L-UKVPLFVHKU.yaml", + "CZ-52-HRA-L-VEZSP.yaml", + "CZ-52-HRA-L-ZES.yaml", + "CZ-52-HRA-M-KMVCVHK.yaml", + "CZ-52-HRA-M-MVCVHK.yaml", + "CZ-52-HRA-M-MVCVHKPOPK.yaml", + "CZ-52-HRA-O-KSVHKK.yaml", + "CZ-52-HRA-O-SOAVHKSOAH.yaml", + "CZ-52-HRO-L-CPZH.yaml", + "CZ-52-HRO-L-MKEH.yaml", + "CZ-52-JAN-L-MKJL.yaml", + "CZ-52-JAN-L-SLLJLSPDLV.yaml", + "CZ-52-JAR-L-OKVR.yaml", + "CZ-52-JAR-L-OKVS.yaml", + "CZ-52-JAR-L-OKVV.yaml", + "CZ-52-JAR-M-MMVJK.yaml", + "CZ-52-JAS-L-OKJ.yaml", + "CZ-52-JAV-L-MKJ.yaml", + "CZ-52-JES-A-AUMAVESJ.yaml", + "CZ-52-JES-A-SOAJ-statni_okresni_archiv_jesenik.yaml", + "CZ-52-JET-L-OKVJ.yaml", + "CZ-52-JIC-A-SOAJ-statni_okresni_archiv_jicin.yaml", + "CZ-52-JIC-L-AS.yaml", + "CZ-52-JIC-L-KVCVJ.yaml", + "CZ-52-JIC-L-MKB.yaml", + "CZ-52-JIC-L-MKBR.yaml", + "CZ-52-JIC-L-MKM.yaml", + "CZ-52-JIC-L-MKP-mistni_knihovna_prachov.yaml", + "CZ-52-JIC-L-MKS.yaml", + "CZ-52-JIC-L-MKV.yaml", + "CZ-52-JIC-L-MKVO.yaml", + "CZ-52-JIC-L-OKVJ.yaml", + "CZ-52-JIC-L-ONJSLK.yaml", + "CZ-52-JIC-M-RMGJ.yaml", + "CZ-52-JIC-M-RMGVJK.yaml", + "CZ-52-JIC-O-SOAVHKSOAJ.yaml", + "CZ-52-JIL-L-MKVJ.yaml", + "CZ-52-JIN-L-COBSK.yaml", + "CZ-52-JIN-L-GSSR.yaml", + "CZ-52-JIN-L-UCPKS.yaml", + "CZ-52-KAC-L-MKKL.yaml", + "CZ-52-KLA-L-MKVK.yaml", + "CZ-52-KOC-L-OKK.yaml", + "CZ-52-KOH-L-MKK.yaml", + "CZ-52-KOL-L-KSIPK.yaml", + "CZ-52-KOP-L-KK.yaml", + "CZ-52-KOP-L-MKZ.yaml", + "CZ-52-KOP-L-MLKVB.yaml", + "CZ-52-KOS-L-MKB.yaml", + "CZ-52-KOS-L-MKKH.yaml", + "CZ-52-KOS-L-MKS.yaml", + "CZ-52-KOS-L-OK.yaml", + "CZ-52-KOS-L-OKK.yaml", + "CZ-52-KOS-L-OKLUP.yaml", + "CZ-52-KOS-L-OVKVP.yaml", + "CZ-52-KOU-L-OKVK.yaml", + "CZ-52-KRA-L-MKVPK.yaml", + "CZ-52-KUK-L-OKK.yaml", + "CZ-52-KUK-M-CFMVK.yaml", + "CZ-52-KUN-L-MKK.yaml", + "CZ-52-KVA-L-MKVK.yaml", + "CZ-52-LAH-E-KMC.yaml", + "CZ-52-LAH-L-LKM.yaml", + "CZ-52-LAZ-L-MKC.yaml", + "CZ-52-LHO-L-MKVU.yaml", + "CZ-52-LHO-L-OKLPL.yaml", + "CZ-52-LHO-L-OKO.yaml", + "CZ-52-LHO-L-OKR.yaml", + "CZ-52-LHO-L-OKS.yaml", + "CZ-52-LHO-L-OKT.yaml", + "CZ-52-LIB-L-KABL.yaml", + "CZ-52-LIB-L-MKL-mistni_knihovna_librice.yaml", + "CZ-52-LIB-L-MKL-mistni_knihovna_libunec.yaml", + "CZ-52-LIB-L-MKLPB.yaml", + "CZ-52-LIB-L-MKLPH.yaml", + "CZ-52-LIB-L-OKVL.yaml", + "CZ-52-LIC-L-MKL.yaml", + "CZ-52-LIP-L-MKLNO.yaml", + "CZ-52-LIT-A-AS.yaml", + "CZ-52-LIT-L-AOPKCK.yaml", + "CZ-52-LIT-L-CMIUFMK.yaml", + "CZ-52-LIT-L-CRSZSSRCK.yaml", + "CZ-52-LIT-L-MUPPSOKJH.yaml", + "CZ-52-LIT-L-PDBSRDKN.yaml", + "CZ-52-LIT-O-AHMPK.yaml", + "CZ-52-LUP-L-MKL.yaml", + "CZ-52-LUZ-L-OKL.yaml", + "CZ-52-LYS-L-CVPFSUKFSF.yaml", + "CZ-52-LYS-L-CVPVICOK.yaml", + "CZ-52-LYS-L-NTK.yaml", + "CZ-52-LYS-L-RPK.yaml", + "CZ-52-LYS-L-UEBACVVK.yaml", + "CZ-52-LYS-L-UPHACVVK.yaml", + "CZ-52-LYS-L-VSCTVPCIS.yaml", + "CZ-52-LYS-L-VSCTVPFCTU.yaml", + "CZ-52-MAL-L-VUD.yaml", + "CZ-52-MEZ-L-MKM.yaml", + "CZ-52-MEZ-L-OKVM.yaml", + "CZ-52-MIL-L-KKJE.yaml", + "CZ-52-MIL-L-LKT.yaml", + "CZ-52-MIL-L-LKU.yaml", + "CZ-52-MIL-L-VKSVM.yaml", + "CZ-52-MLA-L-LKM.yaml", + "CZ-52-MLA-L-MKM.yaml", + "CZ-52-NAC-A-SOAN.yaml", + "CZ-52-NAC-L-AENSK.yaml", + "CZ-52-NAC-L-MKNPS.yaml", + "CZ-52-NAC-L-OKVT.yaml", + "CZ-52-NAC-L-ONNSOK.yaml", + "CZ-52-NAC-L-RSZN.yaml", + "CZ-52-NAC-L-TS.yaml", + "CZ-52-NAC-M-KMN.yaml", + "CZ-52-NAC-O-SOAVHKSOAN.yaml", + "CZ-52-NAH-L-OKD.yaml", + "CZ-52-NAH-L-OKN.yaml", + "CZ-52-NEC-L-MKL.yaml", + "CZ-52-NEC-L-MKNPSSVS.yaml", + "CZ-52-NEC-L-OKH.yaml", + "CZ-52-NEC-L-OKP.yaml", + "CZ-52-NEC-L-OKVM.yaml", + "CZ-52-NEC-L-SMKN.yaml", + "CZ-52-NEM-L-OKN.yaml", + "CZ-52-NEP-L-OKN.yaml", + "CZ-52-NMN-M-MMNMNM.yaml", + "CZ-52-NOP-M-MMNP.yaml", + "CZ-52-NOV-E-GSOSVOSNBI.yaml", + "CZ-52-NOV-E-SPSSOSSOUN.yaml", + "CZ-52-NOV-L-ACRSTK.yaml", + "CZ-52-NOV-L-MKNMNM.yaml", + "CZ-52-NOV-L-MUACVVLGK.yaml", + "CZ-52-NOV-L-NES.yaml", + "CZ-52-NOV-L-OKC.yaml", + "CZ-52-NOV-L-OKH.yaml", + "CZ-52-NOV-L-OKJ.yaml", + "CZ-52-NOV-L-OKK.yaml", + "CZ-52-NOV-L-OKM.yaml", + "CZ-52-NOV-L-OKNP.yaml", + "CZ-52-NOV-L-OKSNM.yaml", + "CZ-52-NOV-L-OKSS.yaml", + "CZ-52-NOV-L-OKVB.yaml", + "CZ-52-NOV-L-OKVNH.yaml", + "CZ-52-NOV-L-OKVV.yaml", + "CZ-52-NOV-L-SSZ.yaml", + "CZ-52-NOV-L-ZNPS.yaml", + "CZ-52-NOV-M-MMNPK.yaml", + "CZ-52-OLO-A-AUMAVESO-archivalie_ulozene_mimo_archivy_v_evidenci_soka_ol.yaml", + "CZ-52-OPO-L-MKO.yaml", + "CZ-52-OPO-L-N.yaml", + "CZ-52-OSI-L-OKO.yaml", + "CZ-52-OST-L-OKES.yaml", + "CZ-52-OTO-L-OKO.yaml", + "CZ-52-PAB-E-ZSPSK.yaml", + "CZ-52-PAB-L-IPVVZOVI.yaml", + "CZ-52-PAB-L-MSRSIS.yaml", + "CZ-52-PAB-L-PMCPSDAK.yaml", + "CZ-52-PAB-L-PSK-pragoprojekt_as_knihovna.yaml", + "CZ-52-PAB-L-UKVPHTFUZS.yaml", + "CZ-52-PAB-L-UZFGACVVSP.yaml", + "CZ-52-PEC-L-KKH.yaml", + "CZ-52-PEC-L-MLKVBUP.yaml", + "CZ-52-PEC-L-OKP.yaml", + "CZ-52-PEL-L-CCIAZPK.yaml", + "CZ-52-PEL-L-KMUAACVVKV-knihovna_masarykova_ustavu_a_archivu_av_cr_v_v_i_k.yaml", + "CZ-52-PEL-L-KMUAACVVKV.yaml", + "CZ-52-PEL-L-KUJAKP.yaml", + "CZ-52-PEL-L-RFERL.yaml", + "CZ-52-PEL-L-SZUSVIK.yaml", + "CZ-52-PEL-L-UJFACVVDPO.yaml", + "CZ-52-PEL-O-NKUK.yaml", + "CZ-52-PIL-L-OKP.yaml", + "CZ-52-POD-L-MKP.yaml", + "CZ-52-POL-L-OLKVP.yaml", + "CZ-52-POL-O-AOPKCRRPVC.yaml", + "CZ-52-POR-M-MB-muzeum_broumovska.yaml", + "CZ-52-POT-L-MKZ.yaml", + "CZ-52-PRA-A-ABS.yaml", + "CZ-52-PRA-E-SPSEPJK.yaml", + "CZ-52-PRA-E-UK.yaml", + "CZ-52-PRA-H-CMTSSR.yaml", + "CZ-52-PRA-H-KBOE.yaml", + "CZ-52-PRA-H-SPCPZSK.yaml", + "CZ-52-PRA-L-ADISRK.yaml", + "CZ-52-PRA-L-ASRCPER.yaml", + "CZ-52-PRA-L-CAK.yaml", + "CZ-52-PRA-L-CAPSSPOZCK.yaml", + "CZ-52-PRA-L-CNBOK.yaml", + "CZ-52-PRA-L-CPSUPPSK.yaml", + "CZ-52-PRA-L-CRROK.yaml", + "CZ-52-PRA-L-CSEK.yaml", + "CZ-52-PRA-L-CSPC.yaml", + "CZ-52-PRA-L-CSSPKCRK.yaml", + "CZ-52-PRA-L-CTSKAAPF.yaml", + "CZ-52-PRA-L-CVPUKCKAC.yaml", + "CZ-52-PRA-L-CVPUKCLKFJ.yaml", + "CZ-52-PRA-L-CVTPSK.yaml", + "CZ-52-PRA-L-FIM-francouzsky_institut_mediateka.yaml", + "CZ-52-PRA-L-FIM.yaml", + "CZ-52-PRA-L-FUACVVK.yaml", + "CZ-52-PRA-L-HLK.yaml", + "CZ-52-PRA-L-HPHMPPP.yaml", + "CZ-52-PRA-L-ICVPKCF.yaml", + "CZ-52-PRA-L-IKREK.yaml", + "CZ-52-PRA-L-ITIK.yaml", + "CZ-52-PRA-L-KACVV.yaml", + "CZ-52-PRA-L-KAIC.yaml", + "CZ-52-PRA-L-KAS.yaml", + "CZ-52-PRA-L-KLP.yaml", + "CZ-52-PRA-L-KVHNF.yaml", + "CZ-52-PRA-L-KVSPOSPS.yaml", + "CZ-52-PRA-L-LSK.yaml", + "CZ-52-PRA-L-MDA.yaml", + "CZ-52-PRA-L-MSCCCKNPKU.yaml", + "CZ-52-PRA-L-MVCVSOLKPM.yaml", + "CZ-52-PRA-L-NFAK.yaml", + "CZ-52-PRA-L-NKCR.yaml", + "CZ-52-PRA-L-NKCRKFSOS.yaml", + "CZ-52-PRA-L-NKCRSKOS-narodni_knihovna_ceske_republiky_slovanska_knihovn.yaml", + "CZ-52-PRA-L-NKCRSKOS.yaml", + "CZ-52-PRA-L-NLK.yaml", + "CZ-52-PRA-L-NMKNMORST.yaml", + "CZ-52-PRA-L-NPUHKF.yaml", + "CZ-52-PRA-L-NPUK.yaml", + "CZ-52-PRA-L-OKVP.yaml", + "CZ-52-PRA-L-PUACVVPPK.yaml", + "CZ-52-PRA-L-RSVKVPK.yaml", + "CZ-52-PRA-L-SS-sweco_as.yaml", + "CZ-52-PRA-L-SUACVVK.yaml", + "CZ-52-PRA-L-SUROVVK.yaml", + "CZ-52-PRA-L-TPSK.yaml", + "CZ-52-PRA-L-UDUACVVK.yaml", + "CZ-52-PRA-L-UKFFFUK.yaml", + "CZ-52-PRA-L-UKFFHKK.yaml", + "CZ-52-PRA-L-UKFFKE.yaml", + "CZ-52-PRA-L-UKFFKUE.yaml", + "CZ-52-PRA-L-UKFFUHSD.yaml", + "CZ-52-PRA-L-UKLFAU.yaml", + "CZ-52-PRA-L-UKLFFUK.yaml", + "CZ-52-PRA-L-UKLFSVI.yaml", + "CZ-52-PRA-L-UKLFUVI.yaml", + "CZ-52-PRA-L-UKLFVFNICK.yaml", + "CZ-52-PRA-L-UKLFVFNIIK-univerzita_karlova_1_lekarska_fakulta_a_vseobecna_.yaml", + "CZ-52-PRA-L-UKMFFKMOI.yaml", + "CZ-52-PRA-L-UKPFBK.yaml", + "CZ-52-PRA-L-UKPFK-univerzita_karlova_pedagogicka_fakulta_knihovna.yaml", + "CZ-52-PRA-L-UKPFKC.yaml", + "CZ-52-PRA-L-UKPFKKFDPV.yaml", + "CZ-52-PRA-L-UKUKLUVSU.yaml", + "CZ-52-PRA-L-UKVPFFKAK.yaml", + "CZ-52-PRA-L-UKVPFFKDVK.yaml", + "CZ-52-PRA-L-UKVPLFFKK.yaml", + "CZ-52-PRA-L-UKVPLFVFNK.yaml", + "CZ-52-PRA-L-UPCLACVVK.yaml", + "CZ-52-PRA-L-UPPMDLK.yaml", + "CZ-52-PRA-L-UPSDACVVK.yaml", + "CZ-52-PRA-L-UPSTRKJL.yaml", + "CZ-52-PRA-M-NM.yaml", + "CZ-52-PRA-M-NMHMODTVSK.yaml", + "CZ-52-PRA-M-NMKNMOZK.yaml", + "CZ-52-PRA-M-NPMKJKPKJK-narodni_pedagogicke_muzeum_a_knihovna_j_a_komenske.yaml", + "CZ-52-PRA-M-NPMKJKPKJK.yaml", + "CZ-52-PRA-M-VHUPOHDOVK.yaml", + "CZ-52-PRA-O-KPCROSASAP.yaml", + "CZ-52-PRA-O-KSVPK.yaml", + "CZ-52-PRA-O-MFCOKM.yaml", + "CZ-52-PRA-O-MKCOUKKKO.yaml", + "CZ-52-PRA-O-UVCRK.yaml", + "CZ-52-PRE-A-AUMAVESP-archivalie_ulozene_mimo_archivy_v_evidenci_soka_pr.yaml", + "CZ-52-PRE-L-MKP-mistni_knihovna_prestavlky.yaml", + "CZ-52-PRE-L-MKP.yaml", + "CZ-52-PRE-L-MLKPK.yaml", + "CZ-52-PRE-L-OKPNL.yaml", + "CZ-52-PRO-A-SOAP.yaml", + "CZ-52-PRO-L-OKP-obecni_knihovna_prosecne.yaml", + "CZ-52-PRO-L-OKP.yaml", + "CZ-52-RAD-L-MKVR.yaml", + "CZ-52-RNK-A-AUMAVESRNK.yaml", + "CZ-52-ROK-L-MIKSZK.yaml", + "CZ-52-ROK-L-OKVBVOH.yaml", + "CZ-52-ROV-L-MKSL.yaml", + "CZ-52-RTY-L-MKRVP.yaml", + "CZ-52-RUD-L-MKR.yaml", + "CZ-52-RUD-L-RZR.yaml", + "CZ-52-RVP-M-MMRVP.yaml", + "CZ-52-RYC-A-SOARNK.yaml", + "CZ-52-RYC-E-VOSSPSZIS.yaml", + "CZ-52-RYC-L-KRNKSRMKKP.yaml", + "CZ-52-RYC-L-MKRNKPDV.yaml", + "CZ-52-RYC-L-MKRNKPL.yaml", + "CZ-52-RYC-L-MKRNKPR.yaml", + "CZ-52-RYC-L-MKT.yaml", + "CZ-52-RYC-L-OKR.yaml", + "CZ-52-RYC-L-ONRNKSLK.yaml", + "CZ-52-RYC-L-OS.yaml", + "CZ-52-RYC-M-MGOHK.yaml", + "CZ-52-RYC-M-OKOMOHK.yaml", + "CZ-52-SAM-L-MLKS.yaml", + "CZ-52-SED-L-MKS.yaml", + "CZ-52-SED-L-MKVS.yaml", + "CZ-52-SKR-L-OKS.yaml", + "CZ-52-SKU-L-MKSNB.yaml", + "CZ-52-SLA-L-MKS.yaml", + "CZ-52-SLA-L-OKS.yaml", + "CZ-52-SLA-L-OKVSNZ.yaml", + "CZ-52-SLI-L-VKS.yaml", + "CZ-52-SMI-L-MKL.yaml", + "CZ-52-SMI-L-OKB.yaml", + "CZ-52-SMI-L-OKH.yaml", + "CZ-52-SMI-L-OKV.yaml", + "CZ-52-SMI-L-OKVS.yaml", + "CZ-52-SMI-L-SKS.yaml", + "CZ-52-SOB-L-MKFS.yaml", + "CZ-52-SOL-L-A.yaml", + "CZ-52-SON-L-OKVS.yaml", + "CZ-52-SPI-L-MKSM.yaml", + "CZ-52-STA-L-MKSP.yaml", + "CZ-52-STA-L-OKS.yaml", + "CZ-52-STA-L-OKSB.yaml", + "CZ-52-STE-L-OKS-obecni_knihovna_stezirky.yaml", + "CZ-52-STE-L-OKS.yaml", + "CZ-52-STO-M-MHMPK.yaml", + "CZ-52-STR-L-MLKS.yaml", + "CZ-52-STR-L-OKS.yaml", + "CZ-52-STU-L-OKVS-obecni_knihovna_ve_starkoci.yaml", + "CZ-52-STU-L-OKVS.yaml", + "CZ-52-SUM-A-AUMAVESS.yaml", + "CZ-52-SVE-L-MVKPHP.yaml", + "CZ-52-SVO-L-MKSNU.yaml", + "CZ-52-TEP-L-MKVTNM.yaml", + "CZ-52-TPO-M-TMB.yaml", + "CZ-52-TRE-L-HMKTPO.yaml", + "CZ-52-TRE-L-OKJ.yaml", + "CZ-52-TRE-L-OKL-obecni_knihovna_libnikovice.yaml", + "CZ-52-TRE-L-OKL.yaml", + "CZ-52-TRE-L-TKSS.yaml", + "CZ-52-TRU-A-SOAT.yaml", + "CZ-52-TRU-E-CLATSSVOSZ.yaml", + "CZ-52-TRU-E-VOSZSZSSIC.yaml", + "CZ-52-TRU-L-CSEPK.yaml", + "CZ-52-TRU-L-I.yaml", + "CZ-52-TRU-L-KTS.yaml", + "CZ-52-TRU-L-LP.yaml", + "CZ-52-TRU-L-MKSRFT.yaml", + "CZ-52-TRU-L-ONTSLK.yaml", + "CZ-52-TRU-L-ZCSRO.yaml", + "CZ-52-TRU-M-MP-muzeum_podkrkonosi.yaml", + "CZ-52-TRU-M-MPVTK.yaml", + "CZ-52-TRU-M-SKKMAK.yaml", + "CZ-52-TRU-O-SOAVHKSOAT.yaml", + "CZ-52-TUR-L-MKT.yaml", + "CZ-52-TYN-L-MKTNO.yaml", + "CZ-52-UHR-L-VUZVVVDK.yaml", + "CZ-52-ULI-L-LKU.yaml", + "CZ-52-UPI-L-HVUK.yaml", + "CZ-52-UPI-L-MKS.yaml", + "CZ-52-UPI-L-MKVU.yaml", + "CZ-52-UPI-L-TS.yaml", + "CZ-52-UPI-M-MMGJWM.yaml", + "CZ-52-VAL-L-MKV.yaml", + "CZ-52-VAM-L-EV.yaml", + "CZ-52-VAM-L-MKV.yaml", + "CZ-52-VAM-L-MKVPM.yaml", + "CZ-52-VAM-L-MKVPPNZ.yaml", + "CZ-52-VEL-L-KMVP.yaml", + "CZ-52-VEL-L-MKV.yaml", + "CZ-52-VEL-L-MLKV.yaml", + "CZ-52-VEL-L-OKVJ.yaml", + "CZ-52-VEL-L-OKVS.yaml", + "CZ-52-VEL-L-OKVV-obecni_knihovna_velky_vrestov.yaml", + "CZ-52-VEL-L-OKVV.yaml", + "CZ-52-VIL-L-OKV.yaml", + "CZ-52-VIN-L-MKPS.yaml", + "CZ-52-VIT-L-OKK.yaml", + "CZ-52-VOD-L-MKV.yaml", + "CZ-52-VOL-L-MKV.yaml", + "CZ-52-VRB-L-MKV.yaml", + "CZ-52-VRC-L-TVS.yaml", + "CZ-52-VRC-M-SKNPKMK.yaml", + "CZ-52-VRS-L-MLKV.yaml", + "CZ-52-VSE-L-KV.yaml", + "CZ-52-VSE-L-MKDD.yaml", + "CZ-52-VSE-L-MKS.yaml", + "CZ-52-VSE-L-OKR.yaml", + "CZ-52-VYS-L-MKVV.yaml", + "CZ-52-VYS-L-MLKS.yaml", + "CZ-52-ZAB-L-MVKVPZ.yaml", + "CZ-52-ZAC-L-MKVZ.yaml", + "CZ-52-ZAM-A-SOAVHK.yaml", + "CZ-52-ZDA-L-MKZNO.yaml", + "CZ-52-ZDA-L-OKVZ.yaml", + "CZ-52-ZDA-L-OKVZNM.yaml", + "CZ-52-ZDE-L-MKZ.yaml", + "CZ-52-ZLU-L-MLKZ.yaml", + "CZ-53-BAN-L-KB.yaml", + "CZ-53-BEL-L-OKVBNS.yaml", + "CZ-53-BEZ-L-OKBUT.yaml", + "CZ-53-BNO-A-PSJAK.yaml", + "CZ-53-BOH-L-MKVB.yaml", + "CZ-53-BOH-L-OKB.yaml", + "CZ-53-BOJ-L-OKVB.yaml", + "CZ-53-BOR-L-MKVB.yaml", + "CZ-53-BRA-L-MKBNO.yaml", + "CZ-53-BRN-H-PBFKKFVD.yaml", + "CZ-53-BRN-H-PBFKKFVMT.yaml", + "CZ-53-BRN-H-RFMTK.yaml", + "CZ-53-BRN-L-KB.yaml", + "CZ-53-BRN-L-OKVC.yaml", + "CZ-53-BRN-L-OKVS.yaml", + "CZ-53-BRU-A-AUMAVESB.yaml", + "CZ-53-BRU-A-SOABSSVK.yaml", + "CZ-53-BUD-L-OKB.yaml", + "CZ-53-BYL-L-MKB.yaml", + "CZ-53-BYS-L-MKVB.yaml", + "CZ-53-BYS-L-OKB.yaml", + "CZ-53-BYS-L-OKVB-obecni_knihovna_v_belecku.yaml", + "CZ-53-BYS-L-OKVB.yaml", + "CZ-53-BYS-L-OKVH-obecni_knihovna_v_hrachovisti.yaml", + "CZ-53-BYS-L-OKVH.yaml", + "CZ-53-CEP-L-OKC.yaml", + "CZ-53-CER-L-OKVCNL.yaml", + "CZ-53-CES-E-SSTDGHCTK.yaml", + "CZ-53-CES-L-MKCTPP.yaml", + "CZ-53-CES-L-OKCL.yaml", + "CZ-53-CES-L-OKCR.yaml", + "CZ-53-CES-L-OKK.yaml", + "CZ-53-CES-L-OKP.yaml", + "CZ-53-CES-L-OKS-obecni_knihovna_svinna.yaml", + "CZ-53-CES-L-OKV.yaml", + "CZ-53-CES-L-SSTK.yaml", + "CZ-53-CES-M-MMCTK.yaml", + "CZ-53-CET-M-MMCT.yaml", + "CZ-53-CHO-L-CCS.yaml", + "CZ-53-CHO-L-MKC.yaml", + "CZ-53-CHO-L-MKCPD.yaml", + "CZ-53-CHO-L-MKCPH.yaml", + "CZ-53-CHO-L-OKC-obecni_knihovna_chornice.yaml", + "CZ-53-CHO-L-OKK.yaml", + "CZ-53-CHO-L-OKN.yaml", + "CZ-53-CHO-L-OKS.yaml", + "CZ-53-CHO-L-OKUUC.yaml", + "CZ-53-CHO-L-OKVZL.yaml", + "CZ-53-CHO-L-OS.yaml", + "CZ-53-CHO-M-VMC.yaml", + "CZ-53-CHR-A-SOAC-statni_okresni_archiv_chrudim.yaml", + "CZ-53-CHR-E-SPSCTK.yaml", + "CZ-53-CHR-L-MKC.yaml", + "CZ-53-CHR-L-MKVH.yaml", + "CZ-53-CHR-L-OKR.yaml", + "CZ-53-CHR-L-OKVB.yaml", + "CZ-53-CHR-L-OKVRL.yaml", + "CZ-53-CHR-L-OKVS.yaml", + "CZ-53-CHR-L-OKVT-obecni_knihovna_v_topoli.yaml", + "CZ-53-CHR-L-OKVT-obecni_knihovna_v_tribrichach.yaml", + "CZ-53-CHR-L-TS.yaml", + "CZ-53-CHR-L-VUTZ.yaml", + "CZ-53-CHR-M-MLKVC.yaml", + "CZ-53-CHR-M-MMCUC.yaml", + "CZ-53-CHR-M-RMVC.yaml", + "CZ-53-CHR-O-SOAVHKSOAC.yaml", + "CZ-53-CHV-L-ES.yaml", + "CZ-53-CHV-L-OKK.yaml", + "CZ-53-COT-L-MKC.yaml", + "CZ-53-CTE-L-OKVC.yaml", + "CZ-53-DAM-L-OKL.yaml", + "CZ-53-DAS-L-MKD.yaml", + "CZ-53-DLO-L-OKDT.yaml", + "CZ-53-DOL-L-CSK.yaml", + "CZ-53-DOL-L-KDU.yaml", + "CZ-53-DOL-L-MKHR.yaml", + "CZ-53-DOL-L-OKDD.yaml", + "CZ-53-DOL-L-OKDR.yaml", + "CZ-53-DOL-L-OKHD.yaml", + "CZ-53-DOL-L-OKL.yaml", + "CZ-53-DOL-L-OKVHR.yaml", + "CZ-53-DRE-L-MKVD.yaml", + "CZ-53-DRI-L-OKVD.yaml", + "CZ-53-DZB-L-OKVD.yaml", + "CZ-53-FRY-A-AUMAVESFM.yaml", + "CZ-53-HER-L-MKVHM.yaml", + "CZ-53-HER-L-OKKUHM.yaml", + "CZ-53-HER-L-OKR.yaml", + "CZ-53-HER-L-OKS.yaml", + "CZ-53-HER-L-OKVL.yaml", + "CZ-53-HER-L-OKVM.yaml", + "CZ-53-HER-L-OKVU.yaml", + "CZ-53-HER-L-OKVVP.yaml", + "CZ-53-HLI-L-ES.yaml", + "CZ-53-HLI-L-MKH.yaml", + "CZ-53-HLI-L-MKV.yaml", + "CZ-53-HLI-L-OKJ.yaml", + "CZ-53-HLI-L-OKM.yaml", + "CZ-53-HLI-L-OKS.yaml", + "CZ-53-HLI-L-OKVP.yaml", + "CZ-53-HLI-M-MGH.yaml", + "CZ-53-HOL-L-OKJ.yaml", + "CZ-53-HOL-L-OKT.yaml", + "CZ-53-HOL-L-OKVPUH.yaml", + "CZ-53-HOL-L-OKVUH.yaml", + "CZ-53-HOL-M-PDEHAM.yaml", + "CZ-53-HOR-L-MKHJ.yaml", + "CZ-53-HOR-L-OKHC.yaml", + "CZ-53-HOR-L-OKVHUL.yaml", + "CZ-53-HOS-L-MLKHUP.yaml", + "CZ-53-HRO-L-MKHT.yaml", + "CZ-53-HRO-L-OKVC.yaml", + "CZ-53-HRU-L-OKVHZK.yaml", + "CZ-53-JAB-L-MKJNO.yaml", + "CZ-53-JAB-L-OKS.yaml", + "CZ-53-JAB-L-OKVS.yaml", + "CZ-53-JAB-L-TLSZ.yaml", + "CZ-53-JAM-L-MLKJNO.yaml", + "CZ-53-JAR-L-OKJ.yaml", + "CZ-53-JAR-L-OKVJ.yaml", + "CZ-53-JEN-L-MLKVJ.yaml", + "CZ-53-JEV-L-MKJ.yaml", + "CZ-53-JEV-L-MLKVBUJ.yaml", + "CZ-53-JEV-L-OKVB.yaml", + "CZ-53-JEV-L-OKVV.yaml", + "CZ-53-KAM-L-OKVK-obecni_knihovna_v_kamenicne.yaml", + "CZ-53-KAR-A-AUMAVESK-archivalie_ulozene_mimo_archivy_v_evidenci_soka_ka.yaml", + "CZ-53-KAR-A-SOAK-statni_okresni_archiv_karvina.yaml", + "CZ-53-KLA-L-OKVKNL.yaml", + "CZ-53-KLE-L-OKVK.yaml", + "CZ-53-KOC-L-MKVK.yaml", + "CZ-53-KOR-L-MKVK.yaml", + "CZ-53-KRA-L-MKK.yaml", + "CZ-53-KRA-L-MKKPDL.yaml", + "CZ-53-KRA-L-MKVDM.yaml", + "CZ-53-KRE-L-OKVK.yaml", + "CZ-53-KRO-L-OKK.yaml", + "CZ-53-KUN-L-MKVKNV.yaml", + "CZ-53-KUN-L-MLKK.yaml", + "CZ-53-LAN-L-MKAS.yaml", + "CZ-53-LAN-L-MKL.yaml", + "CZ-53-LAN-L-MKS.yaml", + "CZ-53-LAN-L-OKK.yaml", + "CZ-53-LAN-L-OKL.yaml", + "CZ-53-LAN-L-OKZ.yaml", + "CZ-53-LAN-L-OPSV.yaml", + "CZ-53-LAN-L-TLS.yaml", + "CZ-53-LAZ-L-KIOO.yaml", + "CZ-53-LAZ-L-MKLB.yaml", + "CZ-53-LAZ-L-OKK.yaml", + "CZ-53-LAZ-L-OKP.yaml", + "CZ-53-LAZ-L-OKR.yaml", + "CZ-53-LAZ-L-OKVB.yaml", + "CZ-53-LAZ-L-OKVN.yaml", + "CZ-53-LAZ-L-OKVV.yaml", + "CZ-53-LET-E-PSSVLK.yaml", + "CZ-53-LET-L-MKLPC.yaml", + "CZ-53-LET-L-MKLPO.yaml", + "CZ-53-LET-L-OSRTK.yaml", + "CZ-53-LIB-L-OKL.yaml", + "CZ-53-LIB-L-OKVL.yaml", + "CZ-53-LIT-L-MKL.yaml", + "CZ-53-LIT-L-NPKSLNLK.yaml", + "CZ-53-LIT-L-OKHU.yaml", + "CZ-53-LIT-L-OKVC-obecni_knihovna_v_chotenove.yaml", + "CZ-53-LIT-L-OKVP.yaml", + "CZ-53-LIT-L-OKVS.yaml", + "CZ-53-LIT-L-OKVVS.yaml", + "CZ-53-LIT-L-SGVS.yaml", + "CZ-53-LIT-M-RMVL.yaml", + "CZ-53-LIT-O-SOAVHKSOAS.yaml", + "CZ-53-LUB-L-MLKL.yaml", + "CZ-53-LUZ-L-HOLPDDLK.yaml", + "CZ-53-LUZ-L-KFL.yaml", + "CZ-53-LUZ-L-MKVL.yaml", + "CZ-53-LUZ-L-OKS.yaml", + "CZ-53-MED-L-OKVM.yaml", + "CZ-53-MES-L-MKL.yaml", + "CZ-53-MES-L-MKP-mistni_knihovna_pecikov.yaml", + "CZ-53-MES-L-OKMT.yaml", + "CZ-53-MLA-L-MKVMM.yaml", + "CZ-53-MOR-E-MOCVSSVOSM.yaml", + "CZ-53-MOR-L-HS.yaml", + "CZ-53-MOR-L-MKLZBVMT.yaml", + "CZ-53-MOR-L-MKVB.yaml", + "CZ-53-MOR-L-MKVDUMT.yaml", + "CZ-53-MOR-L-OKU.yaml", + "CZ-53-MOR-L-OKVB.yaml", + "CZ-53-MOR-L-OKVM.yaml", + "CZ-53-MTR-M-KSMMTMM.yaml", + "CZ-53-NAS-L-MKN.yaml", + "CZ-53-NAS-L-MKS.yaml", + "CZ-53-NAS-L-MKVK.yaml", + "CZ-53-NAS-L-OKVL.yaml", + "CZ-53-NEK-L-MKVN.yaml", + "CZ-53-NOV-L-OKVNS.yaml", + "CZ-53-OLD-L-MKVO.yaml", + "CZ-53-OPA-A-AUMAVESO.yaml", + "CZ-53-OPA-A-AUMAVEZO.yaml", + "CZ-53-OPA-A-SOAO-statni_okresni_archiv_opava.yaml", + "CZ-53-OPA-E-SUO.yaml", + "CZ-53-OPA-L-IPOS.yaml", + "CZ-53-OPA-L-OKC.yaml", + "CZ-53-OPA-L-OKONL.yaml", + "CZ-53-OPA-L-OKVO.yaml", + "CZ-53-ORL-L-OKO.yaml", + "CZ-53-OSI-L-OKO.yaml", + "CZ-53-OST-E-OUO.yaml", + "CZ-53-OST-E-VSBTUO.yaml", + "CZ-53-OST-L-SVKO.yaml", + "CZ-53-OTR-L-OKVO.yaml", + "CZ-53-PAR-A-SOAP-statni_okresni_archiv_pardubice.yaml", + "CZ-53-PAR-E-OAJSSPSJZK.yaml", + "CZ-53-PAR-E-SPSEVOSPK.yaml", + "CZ-53-PAR-E-SZSPK.yaml", + "CZ-53-PAR-G-VGVP.yaml", + "CZ-53-PAR-L-ASOZSTK.yaml", + "CZ-53-PAR-L-CSR.yaml", + "CZ-53-PAR-L-ESRK.yaml", + "CZ-53-PAR-L-ESTKV.yaml", + "CZ-53-PAR-L-GZPK.yaml", + "CZ-53-PAR-L-HTPSR.yaml", + "CZ-53-PAR-L-KMOPI.yaml", + "CZ-53-PAR-L-KMOPIMK.yaml", + "CZ-53-PAR-L-MKD.yaml", + "CZ-53-PAR-L-MKG.yaml", + "CZ-53-PAR-L-MKN.yaml", + "CZ-53-PAR-L-MKO.yaml", + "CZ-53-PAR-L-MKP-mestska_knihovna_preloucska_23.yaml", + "CZ-53-PAR-L-MKP.yaml", + "CZ-53-PAR-L-MKRNL.yaml", + "CZ-53-PAR-L-NPKSPNSVIL.yaml", + "CZ-53-PAR-L-NPUUOPVPOK.yaml", + "CZ-53-PAR-L-OKK.yaml", + "CZ-53-PAR-L-OKO.yaml", + "CZ-53-PAR-L-OKS.yaml", + "CZ-53-PAR-L-OKVB.yaml", + "CZ-53-PAR-L-OKVM.yaml", + "CZ-53-PAR-L-PPSTK.yaml", + "CZ-53-PAR-L-PSR.yaml", + "CZ-53-PAR-L-PSTK.yaml", + "CZ-53-PAR-L-SAS.yaml", + "CZ-53-PAR-L-TMSS.yaml", + "CZ-53-PAR-L-TP.yaml", + "CZ-53-PAR-L-U.yaml", + "CZ-53-PAR-L-UPICUKPLMM.yaml", + "CZ-53-PAR-L-VPC.yaml", + "CZ-53-PIS-L-MKP.yaml", + "CZ-53-POL-L-MKP.yaml", + "CZ-53-POL-L-MKPPL.yaml", + "CZ-53-POL-L-MKVBUP.yaml", + "CZ-53-POL-L-MKVKUP.yaml", + "CZ-53-POL-L-MKVPR.yaml", + "CZ-53-POL-L-MKVS.yaml", + "CZ-53-POL-L-MKVSD.yaml", + "CZ-53-POL-L-PNSR.yaml", + "CZ-53-POL-M-MMGPK.yaml", + "CZ-53-PRA-L-HCSCK.yaml", + "CZ-53-PRA-L-OKVP.yaml", + "CZ-53-PRE-L-A.yaml", + "CZ-53-PRE-L-MKVS.yaml", + "CZ-53-PRE-L-MLKVP.yaml", + "CZ-53-PRE-L-OKS.yaml", + "CZ-53-PRE-L-OKT.yaml", + "CZ-53-PRE-L-OKV.yaml", + "CZ-53-PRE-L-OVKB.yaml", + "CZ-53-PRE-L-TP.yaml", + "CZ-53-PRE-M-MMP-mestske_muzeum_prelouc.yaml", + "CZ-53-PRI-L-MKP.yaml", + "CZ-53-PRO-L-MKP.yaml", + "CZ-53-PRO-L-OKVBUS.yaml", + "CZ-53-PRO-L-OKVP.yaml", + "CZ-53-PRO-L-ZOKVP.yaml", + "CZ-53-PUS-L-MKVPK.yaml", + "CZ-53-RAD-L-MKVR.yaml", + "CZ-53-RAN-L-OKR.yaml", + "CZ-53-RET-L-OKR.yaml", + "CZ-53-ROH-L-OKRB.yaml", + "CZ-53-ROH-L-SSRK.yaml", + "CZ-53-RON-L-MKRND.yaml", + "CZ-53-ROS-L-OKR.yaml", + "CZ-53-RUD-L-OKR.yaml", + "CZ-53-RYB-L-OKOR.yaml", + "CZ-53-RYC-L-MKVRM.yaml", + "CZ-53-SEC-L-OKH.yaml", + "CZ-53-SED-L-MKVS.yaml", + "CZ-53-SEZ-L-OKUUS.yaml", + "CZ-53-SKU-L-MKS.yaml", + "CZ-53-SKU-L-MKVS.yaml", + "CZ-53-SKU-L-MKVZ.yaml", + "CZ-53-SKU-L-OKVL.yaml", + "CZ-53-SKU-L-OPSB.yaml", + "CZ-53-SKU-M-MMVS-mestske_muzeum_ve_skutci.yaml", + "CZ-53-SLA-L-NHKNLHSVC.yaml", + "CZ-53-SLA-L-NHKNLSPSSK.yaml", + "CZ-53-SLO-L-OKS.yaml", + "CZ-53-SRN-L-OKS.yaml", + "CZ-53-SRU-L-OKS.yaml", + "CZ-53-STA-L-OKR.yaml", + "CZ-53-STA-L-OKS.yaml", + "CZ-53-STA-L-OKVB.yaml", + "CZ-53-SUC-L-OKVSL.yaml", + "CZ-53-SUD-L-OKS.yaml", + "CZ-53-SVA-L-OKSJ.yaml", + "CZ-53-SVI-E-GJSSPSJZSS.yaml", + "CZ-53-SVI-L-FSK.yaml", + "CZ-53-SVI-L-MKVS.yaml", + "CZ-53-SVI-L-OKVD.yaml", + "CZ-53-SVI-L-OKVL.yaml", + "CZ-53-SVI-L-OKVO.yaml", + "CZ-53-SVI-L-TSS.yaml", + "CZ-53-SVI-M-MMGVS.yaml", + "CZ-53-SVI-M-MMGVSOK.yaml", + "CZ-53-SVI-M-MMGVSSK.yaml", + "CZ-53-SVO-L-OKS.yaml", + "CZ-53-SVO-L-OKSDL.yaml", + "CZ-53-SVO-L-OKVS.yaml", + "CZ-53-SVO-L-OKVSS.yaml", + "CZ-53-SVR-L-OKVS.yaml", + "CZ-53-TEC-L-MLKT.yaml", + "CZ-53-TEL-L-MKVT.yaml", + "CZ-53-TET-L-MLKT.yaml", + "CZ-53-TRE-L-MKT.yaml", + "CZ-53-TRE-L-MKVT.yaml", + "CZ-53-TRE-L-OKB.yaml", + "CZ-53-TRE-L-OKT.yaml", + "CZ-53-TRH-L-OKVTK.yaml", + "CZ-53-TRO-L-OKVT.yaml", + "CZ-53-TRP-L-OKVT.yaml", + "CZ-53-TRS-L-OKVT.yaml", + "CZ-53-TRZ-L-MKVT.yaml", + "CZ-53-TUR-L-MLKVT.yaml", + "CZ-53-UHE-L-OKU.yaml", + "CZ-53-UHR-L-OKVU.yaml", + "CZ-53-UNO-A-AUMAVESUNO.yaml", + "CZ-53-UNO-M-MMUNO.yaml", + "CZ-53-UST-L-MKUNOPK.yaml", + "CZ-53-UST-L-NPKSONOK.yaml", + "CZ-53-UST-L-OKJ.yaml", + "CZ-53-UST-L-OKOPR.yaml", + "CZ-53-UST-L-OKVS.yaml", + "CZ-53-UST-L-PBZS.yaml", + "CZ-53-UST-L-RES.yaml", + "CZ-53-UST-L-VSOST.yaml", + "CZ-53-UST-O-SOAVHKSOAU.yaml", + "CZ-53-VAL-L-OKVNL.yaml", + "CZ-53-VAP-L-OKC.yaml", + "CZ-53-VAP-L-OKP.yaml", + "CZ-53-VAP-L-OKUUP.yaml", + "CZ-53-VAP-L-OVKS.yaml", + "CZ-53-VCE-L-OKV.yaml", + "CZ-53-VER-L-OKV.yaml", + "CZ-53-VIT-L-OKVV.yaml", + "CZ-53-VMV-M-RMVVM.yaml", + "CZ-53-VOR-L-OKVV.yaml", + "CZ-53-VRA-L-MKVV.yaml", + "CZ-53-VRA-L-OKVV.yaml", + "CZ-53-VRA-L-OKVVL.yaml" ], "last_index": 499 } \ No newline at end of file diff --git a/data/custodian/CZ-52-PRA-L-UPCLACVVK.yaml b/data/custodian/CZ-52-PRA-L-UPCLACVVK.yaml index e2d37dc7eb..195fe97d0d 100644 --- a/data/custodian/CZ-52-PRA-L-UPCLACVVK.yaml +++ b/data/custodian/CZ-52-PRA-L-UPCLACVVK.yaml @@ -274,3 +274,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Ústav pro českou literaturu AV ČR, v. v. i. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:43.172368+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:57:56.030319+00:00' + source_url: https://ucl.cas.cz/katalogy-knihoven + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ucl.cas.cz/wp-content/uploads/2019/10/cropped-UCL-logo_00_Piktogram_RGB_Cerna-180x180.png + source_url: https://ucl.cas.cz/katalogy-knihoven + css_selector: '[document] > html.objectfit.object-fit > body > link:nth-of-type(20)' + retrieved_on: '2025-12-26T15:57:56.030319+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://ucl.cas.cz/wp-content/uploads/2021/11/ucl_hp-22.jpg + source_url: https://ucl.cas.cz/katalogy-knihoven + css_selector: '[document] > html.objectfit.object-fit > body > meta:nth-of-type(12)' + retrieved_on: '2025-12-26T15:57:56.030319+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-PRA-L-UPSDACVVK.yaml b/data/custodian/CZ-52-PRA-L-UPSDACVVK.yaml index 791d5d7c61..b41c35c355 100644 --- a/data/custodian/CZ-52-PRA-L-UPSDACVVK.yaml +++ b/data/custodian/CZ-52-PRA-L-UPSDACVVK.yaml @@ -237,3 +237,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Ústav pro soudobé dějiny AV ČR, v. v. i. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:44.514831+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:58:35.581116+00:00' + source_url: https://katalog.lib.cas.cz/USD + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/USD/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/USD + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-26T15:58:35.581116+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-PRA-L-UPSTRKJL.yaml b/data/custodian/CZ-52-PRA-L-UPSTRKJL.yaml index 58ed19ccb5..b1c2d97765 100644 --- a/data/custodian/CZ-52-PRA-L-UPSTRKJL.yaml +++ b/data/custodian/CZ-52-PRA-L-UPSTRKJL.yaml @@ -243,3 +243,22 @@ youtube_status: NOT_FOUND youtube_search_query: Ústav pro studium totalitních režimů - Knihovna Jána Langoše official youtube_search_timestamp: '2025-12-09T09:33:45.173455+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:58:43.584709+00:00' + source_url: https://koha-intra.ustrcr.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://koha-intra.ustrcr.cz/intranet-tmpl/prog/img/favicon.ico + source_url: https://koha-intra.ustrcr.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T15:58:43.584709+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-PRA-M-NM.yaml b/data/custodian/CZ-52-PRA-M-NM.yaml index 11496066eb..d175675be6 100644 --- a/data/custodian/CZ-52-PRA-M-NM.yaml +++ b/data/custodian/CZ-52-PRA-M-NM.yaml @@ -1288,3 +1288,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/1Q7gtENw6ag/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:58:49.730260+00:00' + source_url: https://www.nm.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nm.cz/file/ad1e3d8b659d4c5536c61a5d693fed81/4/favicon/nmicon.png + source_url: https://www.nm.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T15:58:49.730260+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.nm.cz/file/eaf1feaf5af2a554f1fc5e4b07f5cfda/3497/HB%20NM_web.jpg + source_url: https://www.nm.cz + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-26T15:58:49.730260+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-52-PRA-M-NMHMODTVSK.yaml b/data/custodian/CZ-52-PRA-M-NMHMODTVSK.yaml index 9e076cc151..49dd6d7890 100644 --- a/data/custodian/CZ-52-PRA-M-NMHMODTVSK.yaml +++ b/data/custodian/CZ-52-PRA-M-NMHMODTVSK.yaml @@ -234,3 +234,28 @@ youtube_status: NOT_FOUND youtube_search_query: Národní muzeum - Historické muzeum - Oddělení dějin tělesné výchovy a sportu - knihovna official youtube_search_timestamp: '2025-12-09T09:33:46.515054+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:58:55.774922+00:00' + source_url: https://www.nm.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nm.cz/file/ad1e3d8b659d4c5536c61a5d693fed81/4/favicon/nmicon.png + source_url: https://www.nm.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T15:58:55.774922+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.nm.cz/file/eaf1feaf5af2a554f1fc5e4b07f5cfda/3497/HB%20NM_web.jpg + source_url: https://www.nm.cz + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-26T15:58:55.774922+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-52-PRA-M-NMKNMOZK.yaml b/data/custodian/CZ-52-PRA-M-NMKNMOZK.yaml index a591aaf9a2..bde0ec259e 100644 --- a/data/custodian/CZ-52-PRA-M-NMKNMOZK.yaml +++ b/data/custodian/CZ-52-PRA-M-NMKNMOZK.yaml @@ -260,3 +260,36 @@ youtube_status: NOT_FOUND youtube_search_query: Národní muzeum - Knihovna Národního muzea - oddělení zámeckých knihoven official youtube_search_timestamp: '2025-12-09T09:33:47.182845+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:59:01.728186+00:00' + source_url: https://www.nm.cz/knihovna-narodniho-muzea/oddeleni-zameckych-knihoven#o-nas + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.nm.cz/img/logo.png + source_url: https://www.nm.cz/knihovna-narodniho-muzea/oddeleni-zameckych-knihoven#o-nas + css_selector: '#page > header > div.section > div.header > div.logo > a > img' + retrieved_on: '2025-12-26T15:59:01.728186+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Národní muzeum + - claim_type: favicon_url + claim_value: https://www.nm.cz/file/ad1e3d8b659d4c5536c61a5d693fed81/4/favicon/nmicon.png + source_url: https://www.nm.cz/knihovna-narodniho-muzea/oddeleni-zameckych-knihoven#o-nas + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T15:59:01.728186+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.nm.cz/file/8e97c63072517a2391247e0f2350df5a/9231/DSC_0005_narovnani_orez_HB_studovna_zahlavi_web.jpg + source_url: https://www.nm.cz/knihovna-narodniho-muzea/oddeleni-zameckych-knihoven#o-nas + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-26T15:59:01.728186+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-PRA-M-NPMKJKPKJK.yaml b/data/custodian/CZ-52-PRA-M-NPMKJKPKJK.yaml index 023f25697b..e31839f0f9 100644 --- a/data/custodian/CZ-52-PRA-M-NPMKJKPKJK.yaml +++ b/data/custodian/CZ-52-PRA-M-NPMKJKPKJK.yaml @@ -241,3 +241,22 @@ youtube_status: NOT_FOUND youtube_search_query: Národní pedagogické muzeum a knihovna J. A. Komenského - Pedagogická knihovna J. A. Komenského official youtube_search_timestamp: '2025-12-09T09:33:48.512429+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:59:12.543753+00:00' + source_url: https://katalog.npmk.gov.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.npmk.gov.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.npmk.gov.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T15:59:12.543753+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-PRA-M-VHUPOHDOVK.yaml b/data/custodian/CZ-52-PRA-M-VHUPOHDOVK.yaml index 049e4ec331..9ef3434146 100644 --- a/data/custodian/CZ-52-PRA-M-VHUPOHDOVK.yaml +++ b/data/custodian/CZ-52-PRA-M-VHUPOHDOVK.yaml @@ -252,3 +252,32 @@ youtube_status: NOT_FOUND youtube_search_query: Vojenský historický ústav Praha - Odbor historicko dokumentační - Oddělení vojenských knihoven official youtube_search_timestamp: '2025-12-09T09:33:49.189442+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:59:27.885123+00:00' + source_url: https://vhupraha.kpsys.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://vhupraha.kpsys.cz/custom/design/logo3i.png + source_url: https://vhupraha.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 > div > a > img' + retrieved_on: '2025-12-26T15:59:27.885123+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://vhupraha.kpsys.cz/favicon.png?v=2.3.0-32050 + source_url: https://vhupraha.kpsys.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T15:59:27.885123+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-PRA-O-KPCROSASAP.yaml b/data/custodian/CZ-52-PRA-O-KPCROSASAP.yaml index a86ea6670e..0f07b5244e 100644 --- a/data/custodian/CZ-52-PRA-O-KPCROSASAP.yaml +++ b/data/custodian/CZ-52-PRA-O-KPCROSASAP.yaml @@ -237,3 +237,28 @@ youtube_status: NOT_FOUND youtube_search_query: Kancelář prezidenta České republiky - Odbor spisové a archivní služby - Archivy PH a KPR - Odborná knihovna APH a AKPR official youtube_search_timestamp: '2025-12-09T09:33:49.848641+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:59:50.552957+00:00' + source_url: https://www.prazskyhradarchiv.cz/cs/archivph + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.prazskyhradarchiv.cz/img/safari-pinned-tab.svg + source_url: https://www.prazskyhradarchiv.cz/cs/archivph + css_selector: '[document] > html.js > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T15:59:50.552957+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.prazskyhradarchiv.cz/img/social-media-logo-aph.png + source_url: https://www.prazskyhradarchiv.cz/cs/archivph + css_selector: '[document] > html.js > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-26T15:59:50.552957+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-PRA-O-KSVPK.yaml b/data/custodian/CZ-52-PRA-O-KSVPK.yaml index 0e2332f07e..d52bc3f3a8 100644 --- a/data/custodian/CZ-52-PRA-O-KSVPK.yaml +++ b/data/custodian/CZ-52-PRA-O-KSVPK.yaml @@ -222,3 +222,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Krajský soud v Praze - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:50.516476+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T15:59:59.331761+00:00' + source_url: https://msp.gov.cz/web/krajsky-soud-v-praze + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://msp.gov.cz/o/justicecz-js-theme/images/favicon.ico + source_url: https://msp.gov.cz/web/krajsky-soud-v-praze + css_selector: '[document] > html.ltr.yui3-js-enabled > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T15:59:59.331761+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-PRA-O-MFCOKM.yaml b/data/custodian/CZ-52-PRA-O-MFCOKM.yaml index c8105edfe0..839810c194 100644 --- a/data/custodian/CZ-52-PRA-O-MFCOKM.yaml +++ b/data/custodian/CZ-52-PRA-O-MFCOKM.yaml @@ -244,3 +244,32 @@ location: youtube_status: NOT_FOUND youtube_search_query: Ministerstvo financí ČR - Odborná knihovna MF official youtube_search_timestamp: '2025-12-09T09:33:51.176879+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:00:07.584521+00:00' + source_url: https://portaro.mfcr.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://portaro.mfcr.cz/custom/design/logo_mf_portaro.png + source_url: https://portaro.mfcr.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 > div > a > img' + retrieved_on: '2025-12-26T16:00:07.584521+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: O knihovně + - claim_type: favicon_url + claim_value: https://portaro.mfcr.cz/favicon.png?v=2.3.0-32050 + source_url: https://portaro.mfcr.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:00:07.584521+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-PRA-O-MKCOUKKKO.yaml b/data/custodian/CZ-52-PRA-O-MKCOUKKKO.yaml index 2e5f89294c..db1e81328c 100644 --- a/data/custodian/CZ-52-PRA-O-MKCOUKKKO.yaml +++ b/data/custodian/CZ-52-PRA-O-MKCOUKKKO.yaml @@ -239,3 +239,22 @@ youtube_status: NOT_FOUND youtube_search_query: Ministerstvo kultury ČR - Odbor umění, knihoven, kulturních a kreativních odvětví official youtube_search_timestamp: '2025-12-09T09:33:51.831473+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:00:14.565788+00:00' + source_url: https://mk.gov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mk.gov.cz/custom/img/favicon.ico + source_url: https://mk.gov.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:00:14.565788+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-PRA-O-UVCRK.yaml b/data/custodian/CZ-52-PRA-O-UVCRK.yaml index b3668181a3..a6f72c0326 100644 --- a/data/custodian/CZ-52-PRA-O-UVCRK.yaml +++ b/data/custodian/CZ-52-PRA-O-UVCRK.yaml @@ -235,3 +235,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Úřad vlády České republiky - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:52.495167+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:00:19.128112+00:00' + source_url: https://vlada.gov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vlada.gov.cz/images/favicon-512.png + source_url: https://vlada.gov.cz + css_selector: '[document] > html.header-fixed > head > link:nth-of-type(12)' + retrieved_on: '2025-12-26T16:00:19.128112+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 512x512 + - claim_type: og_image_url + claim_value: https://vlada.gov.cz/images/og-home-20251217.jpg?v=6 + source_url: https://vlada.gov.cz + css_selector: '[document] > html.header-fixed > head > meta:nth-of-type(20)' + retrieved_on: '2025-12-26T16:00:19.128112+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-PRE-L-MKP.yaml b/data/custodian/CZ-52-PRE-L-MKP.yaml index 4b8cbf4bbf..a88013abcf 100644 --- a/data/custodian/CZ-52-PRE-L-MKP.yaml +++ b/data/custodian/CZ-52-PRE-L-MKP.yaml @@ -211,3 +211,22 @@ location: postal_code: 517 32 street_address: Přepychy 125 normalization_timestamp: '2025-12-09T10:53:04.699131+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:00:29.931784+00:00' + source_url: https://prepychy.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prepychy.cz/favicon/apple-icon-180x180.png + source_url: https://prepychy.cz/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:00:29.931784+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-52-PRE-L-OKPNL.yaml b/data/custodian/CZ-52-PRE-L-OKPNL.yaml index 6deda80a94..547eac3ced 100644 --- a/data/custodian/CZ-52-PRE-L-OKPNL.yaml +++ b/data/custodian/CZ-52-PRE-L-OKPNL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-PRE-L-OKPNL - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-PRE-L-OKPNL 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-KR-PRE-L-OKPNL ghcid_numeric: 14770606362091221765 valid_from: '2025-12-06T23:37:24.489078+00:00' @@ -214,3 +215,22 @@ location: postal_code: 503 02 street_address: Školská 279 normalization_timestamp: '2025-12-09T10:53:04.728640+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:00:42.305043+00:00' + source_url: https://kmhk.tritius.cz/library/predmerice + 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/predmerice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:00:42.305043+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-PRO-A-SOAP.yaml b/data/custodian/CZ-52-PRO-A-SOAP.yaml index fe2b94c785..22772f1944 100644 --- a/data/custodian/CZ-52-PRO-A-SOAP.yaml +++ b/data/custodian/CZ-52-PRO-A-SOAP.yaml @@ -229,3 +229,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Prostějov official youtube_search_timestamp: '2025-12-09T09:33:54.514696+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:00:53.960152+00:00' + source_url: http://www.archives.cz/web/soka/prostejov/o_archivu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.archives.cz/web/favicon/safari-pinned-tab.svg + source_url: http://www.archives.cz/web/soka/prostejov/o_archivu + css_selector: '[document] > html.js.no-touchevents > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:00:53.960152+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: 12 diff --git a/data/custodian/CZ-52-PRO-L-OKP-obecni_knihovna_prosecne.yaml b/data/custodian/CZ-52-PRO-L-OKP-obecni_knihovna_prosecne.yaml index d4cfff7e8e..f330c88e1c 100644 --- a/data/custodian/CZ-52-PRO-L-OKP-obecni_knihovna_prosecne.yaml +++ b/data/custodian/CZ-52-PRO-L-OKP-obecni_knihovna_prosecne.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-PRO-L-OKP-obecni_knihovna_prosecne - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-PRO-L-OKP-obecni_knihovna_prosecne 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-KR-PRO-L-OKP-obecni_knihovna_prosecne ghcid_numeric: 13788965130159281522 valid_from: '2025-12-06T23:37:35.679586+00:00' @@ -210,3 +211,22 @@ location: postal_code: 543 73 street_address: Prosečné 24 normalization_timestamp: '2025-12-09T10:53:04.786760+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:01:02.182208+00:00' + source_url: https://trutnov.tritius.cz/library/prosecne + 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/prosecne + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:01:02.182208+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-PRO-L-OKP.yaml b/data/custodian/CZ-52-PRO-L-OKP.yaml index 5ace4ac538..03b0cee1df 100644 --- a/data/custodian/CZ-52-PRO-L-OKP.yaml +++ b/data/custodian/CZ-52-PRO-L-OKP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-PRO-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-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-PRO-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-KR-PRO-L-OKP ghcid_numeric: 8952662731625077050 valid_from: '2025-12-06T23:37:35.358127+00:00' @@ -207,3 +208,22 @@ location: postal_code: 549 08 street_address: Provodov 74 normalization_timestamp: '2025-12-09T10:53:04.871432+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:01:13.489461+00:00' + source_url: https://www.provodovsonov.cz/zivot-v-obci/knihovny + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.provodovsonov.cz/skins/provodovsonov.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.provodovsonov.cz/zivot-v-obci/knihovny + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:01:13.489461+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-RAD-L-MKVR.yaml b/data/custodian/CZ-52-RAD-L-MKVR.yaml index b81375e4d6..ae29fa047c 100644 --- a/data/custodian/CZ-52-RAD-L-MKVR.yaml +++ b/data/custodian/CZ-52-RAD-L-MKVR.yaml @@ -215,3 +215,22 @@ location: postal_code: 507 12 street_address: Radim 41 normalization_timestamp: '2025-12-09T10:53:04.898804+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:01:24.396596+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=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:01:24.396596+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-ROK-L-MIKSZK.yaml b/data/custodian/CZ-52-ROK-L-MIKSZK.yaml index db09a7af67..a8f137101b 100644 --- a/data/custodian/CZ-52-ROK-L-MIKSZK.yaml +++ b/data/custodian/CZ-52-ROK-L-MIKSZK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-ROK-L-MIKSZK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-ROK-L-MIKSZK 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-KR-ROK-L-MIKSZK ghcid_numeric: 7177529473421463726 valid_from: '2025-12-06T23:37:26.725933+00:00' @@ -217,3 +218,22 @@ location: postal_code: 517 61 street_address: nám. T.G.Masaryka 68 normalization_timestamp: '2025-12-09T10:53:04.918951+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:01:34.188240+00:00' + source_url: https://info.rokytnicevoh.cz/kultura-a-volny-cas/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://info.rokytnicevoh.cz/skins/infokulturarokytnice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://info.rokytnicevoh.cz/kultura-a-volny-cas/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:01:34.188240+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-ROK-L-OKVBVOH.yaml b/data/custodian/CZ-52-ROK-L-OKVBVOH.yaml index e1c825af69..0195781ed5 100644 --- a/data/custodian/CZ-52-ROK-L-OKVBVOH.yaml +++ b/data/custodian/CZ-52-ROK-L-OKVBVOH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-ROK-L-OKVBVOH - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-ROK-L-OKVBVOH 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-KR-ROK-L-OKVBVOH ghcid_numeric: 12568820049282228068 valid_from: '2025-12-06T23:37:35.562366+00:00' @@ -210,3 +211,28 @@ location: postal_code: 517 61 street_address: Bartošovice v O. h. 35 normalization_timestamp: '2025-12-09T10:53:04.947154+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:01:42.685309+00:00' + source_url: https://www.bartosovice.eu/sluzby + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bartosovice.eu/safari-pinned-tab.svg + source_url: https://www.bartosovice.eu/sluzby + css_selector: '[document] > html.sizes.customelements > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:01:42.685309+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.bartosovice.eu/www.bartosovice.eu/images/logo_znak.png + source_url: https://www.bartosovice.eu/sluzby + css_selector: '[document] > html.sizes.customelements > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-26T16:01:42.685309+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-RTY-L-MKRVP.yaml b/data/custodian/CZ-52-RTY-L-MKRVP.yaml index 070c045a89..7f0b8cbdbb 100644 --- a/data/custodian/CZ-52-RTY-L-MKRVP.yaml +++ b/data/custodian/CZ-52-RTY-L-MKRVP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-RTY-L-MKRVP - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-RTY-L-MKRVP 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-KR-RTY-L-MKRVP ghcid_numeric: 2802367803403928390 valid_from: '2025-12-06T23:37:20.381536+00:00' @@ -219,3 +220,22 @@ location: postal_code: 542 33 street_address: nám. Horníků 440 normalization_timestamp: '2025-12-09T10:53:05.017771+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:01:51.540273+00:00' + source_url: https://vck.tritius.cz/library/rtyne + 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/rtyne + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:01:51.540273+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-RUD-L-MKR.yaml b/data/custodian/CZ-52-RUD-L-MKR.yaml index 6590735c40..b5d8602698 100644 --- a/data/custodian/CZ-52-RUD-L-MKR.yaml +++ b/data/custodian/CZ-52-RUD-L-MKR.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-RUD-L-MKR - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-RUD-L-MKR 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-KR-RUD-L-MKR ghcid_numeric: 18400465961853835707 valid_from: '2025-12-06T23:37:35.685003+00:00' @@ -236,3 +237,22 @@ location: postal_code: 543 72 street_address: Rudník 51 normalization_timestamp: '2025-12-09T10:53:05.068238+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:01:58.749045+00:00' + source_url: https://trutnov.tritius.cz/library/rudnik + 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/rudnik + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:01:58.749045+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-RYC-E-VOSSPSZIS.yaml b/data/custodian/CZ-52-RYC-E-VOSSPSZIS.yaml index e343e26bb2..a3a2a6aefb 100644 --- a/data/custodian/CZ-52-RYC-E-VOSSPSZIS.yaml +++ b/data/custodian/CZ-52-RYC-E-VOSSPSZIS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-RYC-E-VOSSPSZIS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-RYC-E-VOSSPSZIS 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-KR-RYC-E-VOSSPSZIS ghcid_numeric: 15071505157304399009 valid_from: '2025-12-08T11:21:26.749295+00:00' @@ -223,3 +224,30 @@ location: postal_code: 516 01 street_address: U stadionu 1166 normalization_timestamp: '2025-12-09T10:53:05.119108+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:02:17.894598+00:00' + source_url: https://www.vosrk.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vosrk.cz/wp-content/uploads/2025/02/cropped-vosrk-180x180.png + source_url: https://www.vosrk.cz + css_selector: '[document] > html.wf-roboto-n1-active.wf-roboto-i1-active > head + > link:nth-of-type(83)' + retrieved_on: '2025-12-26T16:02:17.894598+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://vosrk.cz/wp-content/uploads/2023/04/vos-sps-OG.jpg + source_url: https://www.vosrk.cz + css_selector: '[document] > html.wf-roboto-n1-active.wf-roboto-i1-active > head + > meta:nth-of-type(12)' + retrieved_on: '2025-12-26T16:02:17.894598+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-RYC-L-KRNKSRMKKP.yaml b/data/custodian/CZ-52-RYC-L-KRNKSRMKKP.yaml index 725aebae0f..7b2aab9d93 100644 --- a/data/custodian/CZ-52-RYC-L-KRNKSRMKKP.yaml +++ b/data/custodian/CZ-52-RYC-L-KRNKSRMKKP.yaml @@ -181,3 +181,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q114617264 +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:02:23.300700+00:00' + source_url: https://rychnov.tritius.cz + 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 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:02:23.300700+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-RYC-L-MKRNKPDV.yaml b/data/custodian/CZ-52-RYC-L-MKRNKPDV.yaml index ef05b5cb86..78c66df748 100644 --- a/data/custodian/CZ-52-RYC-L-MKRNKPDV.yaml +++ b/data/custodian/CZ-52-RYC-L-MKRNKPDV.yaml @@ -36,13 +36,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-RYC-L-MKRNKPDV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-RYC-L-MKRNKPDV 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-KR-RYC-L-MKRNKPDV ghcid_numeric: 9348641783794840588 valid_from: '2025-12-06T23:37:42.524855+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 Rychnov nad Kněžnou - pobočka Dlouhá Ves @@ -212,3 +213,22 @@ location: geonames_id: 3066503 geonames_name: Rychnov nad Kněžnou feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:02:34.777551+00:00' + source_url: https://www.kulturark.cz/knihovna/knihovny-v-regionu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kulturark.cz/images/layout/favicon.svg + source_url: https://www.kulturark.cz/knihovna/knihovny-v-regionu + css_selector: '[document] > html.show--consent.n3tcc--loaded > head > link:nth-of-type(18)' + retrieved_on: '2025-12-26T16:02:34.777551+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/CZ-52-RYC-L-MKRNKPR.yaml b/data/custodian/CZ-52-RYC-L-MKRNKPR.yaml index 4f1235ad00..6815169ed0 100644 --- a/data/custodian/CZ-52-RYC-L-MKRNKPR.yaml +++ b/data/custodian/CZ-52-RYC-L-MKRNKPR.yaml @@ -216,3 +216,22 @@ location: postal_code: 516 01 street_address: Roveň 71 normalization_timestamp: '2025-12-09T10:53:05.221003+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:02:46.151088+00:00' + source_url: https://www.kulturark.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kulturark.cz/images/layout/favicon.svg + source_url: https://www.kulturark.cz/knihovna + css_selector: '[document] > html.show--consent.n3tcc--loaded > head > link:nth-of-type(22)' + retrieved_on: '2025-12-26T16:02:46.151088+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/CZ-52-RYC-L-MKT.yaml b/data/custodian/CZ-52-RYC-L-MKT.yaml index 31c2bc8793..dfce708308 100644 --- a/data/custodian/CZ-52-RYC-L-MKT.yaml +++ b/data/custodian/CZ-52-RYC-L-MKT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-RYC-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-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-RYC-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-KR-RYC-L-MKT ghcid_numeric: 18096606550178656123 valid_from: '2025-12-06T23:37:35.596396+00:00' @@ -210,3 +211,22 @@ location: postal_code: 516 01 street_address: Třebešov 47 normalization_timestamp: '2025-12-09T10:53:05.249096+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:03:02.528688+00:00' + source_url: https://trebesov.cz/?id=10052&lang=cze + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trebesov.cz/wp-content/uploads/2017/05/favicon180.png + source_url: https://trebesov.cz/?id=10052&lang=cze + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T16:03:02.528688+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/CZ-52-RYC-L-OKR.yaml b/data/custodian/CZ-52-RYC-L-OKR.yaml index ea64e1575e..2e8a23574b 100644 --- a/data/custodian/CZ-52-RYC-L-OKR.yaml +++ b/data/custodian/CZ-52-RYC-L-OKR.yaml @@ -211,3 +211,22 @@ location: postal_code: 552 25 street_address: Rychnovek 50 normalization_timestamp: '2025-12-09T10:53:05.276231+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:03:13.356108+00:00' + source_url: https://jaromer.tritius.cz/library/rychnovek + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jaromer.tritius.cz/apple-touch-icon-180x180.png + source_url: https://jaromer.tritius.cz/library/rychnovek + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:03:13.356108+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-RYC-M-MGOHK.yaml b/data/custodian/CZ-52-RYC-M-MGOHK.yaml index 8e9690e59c..a1c10f94d6 100644 --- a/data/custodian/CZ-52-RYC-M-MGOHK.yaml +++ b/data/custodian/CZ-52-RYC-M-MGOHK.yaml @@ -211,3 +211,28 @@ location: postal_code: 516 01 street_address: Jiráskova 2 normalization_timestamp: '2025-12-09T10:53:05.354698+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:03:33.600823+00:00' + source_url: https://www.moh.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.moh.cz/src/Frontend/Themes/moh/Core/Layout/img/favicon/safari-pinned-tab.svg + source_url: https://www.moh.cz/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:03:33.600823+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.moh.cz/src/Frontend/Themes/moh/Core/Layout/img/og-image.jpg + source_url: https://www.moh.cz/knihovna + css_selector: '[document] > html.js > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-26T16:03:33.600823+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-SAM-L-MLKS.yaml b/data/custodian/CZ-52-SAM-L-MLKS.yaml index 16e14b4856..4d4e920aed 100644 --- a/data/custodian/CZ-52-SAM-L-MLKS.yaml +++ b/data/custodian/CZ-52-SAM-L-MLKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SAM-L-MLKS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SAM-L-MLKS 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-KR-SAM-L-MLKS ghcid_numeric: 16633193400531270890 valid_from: '2025-12-06T23:37:35.191467+00:00' @@ -210,3 +211,30 @@ location: postal_code: 506 01 street_address: Samšina 54 normalization_timestamp: '2025-12-09T10:53:05.403977+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:03:47.000983+00:00' + source_url: https://knihovnasamsina.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnasamsina.webk.cz/themes/new/orange/logo1.png + source_url: https://knihovnasamsina.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-26T16:03:47.000983+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnasamsina.webk.cz/themes/new/favicon.ico + source_url: https://knihovnasamsina.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T16:03:47.000983+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-SED-L-MKVS.yaml b/data/custodian/CZ-52-SED-L-MKVS.yaml index 2e3eefa49e..9c1fc5729a 100644 --- a/data/custodian/CZ-52-SED-L-MKVS.yaml +++ b/data/custodian/CZ-52-SED-L-MKVS.yaml @@ -210,3 +210,32 @@ location: geocoding_timestamp: '2025-12-09T21:45:48.770026+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Praskačka +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:04:05.961483+00:00' + source_url: https://www.praskacka.cz/informace/knihovny + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.praskacka.cz/content/images/znak.svg + source_url: https://www.praskacka.cz/informace/knihovny + css_selector: '#header > div.container.position-relative > nav.navbar.navbar-expand-md + > div.d-flex.flex-grow-1 > a.navbar-brand > span.navbar-brandwrapper.d-flex + > img' + retrieved_on: '2025-12-26T16:04:05.961483+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo obce Praskačka + - claim_type: favicon_url + claim_value: https://www.praskacka.cz/apple-touch-icon.png + source_url: https://www.praskacka.cz/informace/knihovny + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T16:04:05.961483+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-52-SKR-L-OKS.yaml b/data/custodian/CZ-52-SKR-L-OKS.yaml index ad43c5d098..9bfb915992 100644 --- a/data/custodian/CZ-52-SKR-L-OKS.yaml +++ b/data/custodian/CZ-52-SKR-L-OKS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SKR-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-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-SKR-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-KR-SKR-L-OKS ghcid_numeric: 6132472354592741805 valid_from: '2025-12-06T23:37:35.059258+00:00' @@ -214,3 +215,22 @@ location: postal_code: 503 52 street_address: Skřivany 39 normalization_timestamp: '2025-12-09T10:53:05.478123+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:04:20.199015+00:00' + source_url: https://www.skrivany.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.skrivany.cz/skins/skrivany.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.skrivany.cz/obec/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:04:20.199015+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-SKU-L-MKSNB.yaml b/data/custodian/CZ-52-SKU-L-MKSNB.yaml index 67dfb9f1a9..e79fbc931b 100644 --- a/data/custodian/CZ-52-SKU-L-MKSNB.yaml +++ b/data/custodian/CZ-52-SKU-L-MKSNB.yaml @@ -215,3 +215,22 @@ location: postal_code: 517 03 street_address: Skuhrov nad Bělou 84 normalization_timestamp: '2025-12-09T10:53:05.502360+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:04:31.403156+00:00' + source_url: https://rychnov.tritius.cz/library/skuhrov + 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/skuhrov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:04:31.403156+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-SLA-L-MKS.yaml b/data/custodian/CZ-52-SLA-L-MKS.yaml index a92f17c6b2..7ce9c13e3c 100644 --- a/data/custodian/CZ-52-SLA-L-MKS.yaml +++ b/data/custodian/CZ-52-SLA-L-MKS.yaml @@ -211,3 +211,22 @@ location: postal_code: 506 01 street_address: Slatiny 64 normalization_timestamp: '2025-12-09T10:53:05.529759+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:04:44.618324+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=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:04:44.618324+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-SLA-L-OKS.yaml b/data/custodian/CZ-52-SLA-L-OKS.yaml index 51e7b6c607..48256ce706 100644 --- a/data/custodian/CZ-52-SLA-L-OKS.yaml +++ b/data/custodian/CZ-52-SLA-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SLA-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-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-SLA-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-KR-SLA-L-OKS ghcid_numeric: 5310272173880929570 valid_from: '2025-12-06T23:37:35.377672+00:00' @@ -210,3 +211,28 @@ location: postal_code: 549 01 street_address: Slavoňov normalization_timestamp: '2025-12-09T10:53:05.556227+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:04:58.487546+00:00' + source_url: https://www.slavonov.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.slavonov.cz/images/local/icons/favicon.svg + source_url: https://www.slavonov.cz/knihovna + css_selector: '[document] > html.no-js > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:04:58.487546+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.slavonov.cz/images/local/v-202405150920/logo-social-networks.jpg + source_url: https://www.slavonov.cz/knihovna + css_selector: '[document] > html.no-js > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-26T16:04:58.487546+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-SLA-L-OKVSNZ.yaml b/data/custodian/CZ-52-SLA-L-OKVSNZ.yaml index c003a977b2..03a3f4d82f 100644 --- a/data/custodian/CZ-52-SLA-L-OKVSNZ.yaml +++ b/data/custodian/CZ-52-SLA-L-OKVSNZ.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SLA-L-OKVSNZ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SLA-L-OKVSNZ 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-KR-SLA-L-OKVSNZ ghcid_numeric: 5520778493570311243 valid_from: '2025-12-06T23:37:35.576138+00:00' @@ -214,3 +215,22 @@ location: postal_code: 517 56 street_address: Slatina nad Zdobnicí 38 normalization_timestamp: '2025-12-09T10:53:05.584151+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:05:06.765555+00:00' + source_url: https://rychnov.tritius.cz/library/slatinanz + 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/slatinanz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:05:06.765555+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-SMI-L-MKL.yaml b/data/custodian/CZ-52-SMI-L-MKL.yaml index 7056bc6947..83bb79b77d 100644 --- a/data/custodian/CZ-52-SMI-L-MKL.yaml +++ b/data/custodian/CZ-52-SMI-L-MKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SMI-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-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-SMI-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-KR-SMI-L-MKL ghcid_numeric: 12119049361221263148 valid_from: '2025-12-06T23:37:24.479057+00:00' @@ -210,3 +211,28 @@ location: postal_code: 503 03 street_address: Lejšovka 52 normalization_timestamp: '2025-12-09T10:53:05.609523+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:05:20.839566+00:00' + source_url: https://www.lejsovka.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lejsovka.cz/www//cache/images-favicon-180-180.png + source_url: https://www.lejsovka.cz/obec/obecni-knihovna + css_selector: '[document] > html.wide.wow-animation > head > link' + retrieved_on: '2025-12-26T16:05:20.839566+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.lejsovka.cz/www//cache/images-logo-256-256.png + source_url: https://www.lejsovka.cz/obec/obecni-knihovna + css_selector: '[document] > html.wide.wow-animation > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-26T16:05:20.839566+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-SMI-L-OKB.yaml b/data/custodian/CZ-52-SMI-L-OKB.yaml index daa8c27266..396693f6df 100644 --- a/data/custodian/CZ-52-SMI-L-OKB.yaml +++ b/data/custodian/CZ-52-SMI-L-OKB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SMI-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-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-SMI-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-KR-SMI-L-OKB ghcid_numeric: 17810940777457472457 valid_from: '2025-12-06T23:37:35.076026+00:00' @@ -210,3 +211,28 @@ location: postal_code: 503 06 street_address: Benátky normalization_timestamp: '2025-12-09T10:53:05.637675+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:05:45.212014+00:00' + source_url: https://oubenatky.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://oubenatky.cz/wp-content/uploads/2024/03/cropped-Benatky_HK_vlajka-180x180.jpg + source_url: https://oubenatky.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:05:45.212014+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://oubenatky.cz/wp-content/uploads/2024/03/pile-of-books-e1710705294285.jpg + source_url: https://oubenatky.cz/knihovna + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-26T16:05:45.212014+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-SMI-L-OKH.yaml b/data/custodian/CZ-52-SMI-L-OKH.yaml index a0dbb9fa31..3847291de6 100644 --- a/data/custodian/CZ-52-SMI-L-OKH.yaml +++ b/data/custodian/CZ-52-SMI-L-OKH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SMI-L-OKH - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SMI-L-OKH 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-KR-SMI-L-OKH ghcid_numeric: 17644853589982377465 valid_from: '2025-12-06T23:37:35.073012+00:00' @@ -210,3 +211,22 @@ location: postal_code: 503 03 street_address: Habřina 28 normalization_timestamp: '2025-12-09T10:53:05.680632+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:05:33.967745+00:00' + source_url: https://www.habrina.cz/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.habrina.cz/image.php?nid=1074&oid=11815252 + source_url: https://www.habrina.cz/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-26T16:05:33.967745+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-SMI-L-OKVS.yaml b/data/custodian/CZ-52-SMI-L-OKVS.yaml index 0d5e4b9433..a7beb4c697 100644 --- a/data/custodian/CZ-52-SMI-L-OKVS.yaml +++ b/data/custodian/CZ-52-SMI-L-OKVS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SMI-L-OKVS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SMI-L-OKVS 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-KR-SMI-L-OKVS ghcid_numeric: 12020753144120539021 valid_from: '2025-12-06T23:37:35.064883+00:00' @@ -214,3 +215,22 @@ location: postal_code: 503 03 street_address: Skalice 32 normalization_timestamp: '2025-12-09T10:53:05.751884+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:05:40.868543+00:00' + source_url: https://www.skalice.info/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.skalice.info/image.php?nid=17657&oid=7080449 + source_url: https://www.skalice.info/knihovna + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-26T16:05:40.868543+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-SMI-L-SKS.yaml b/data/custodian/CZ-52-SMI-L-SKS.yaml index f89481cd35..a1850952e3 100644 --- a/data/custodian/CZ-52-SMI-L-SKS.yaml +++ b/data/custodian/CZ-52-SMI-L-SKS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SMI-L-SKS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SMI-L-SKS 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-KR-SMI-L-SKS ghcid_numeric: 12686316141801066929 valid_from: '2025-12-06T23:37:23.337630+00:00' @@ -220,3 +221,22 @@ location: postal_code: 503 53 street_address: Náměstí Prof. Babáka 106 normalization_timestamp: '2025-12-09T10:53:05.779401+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:05:46.875040+00:00' + source_url: https://vck.tritius.cz/library/smidary + 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/smidary + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:05:46.875040+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-SOB-L-MKFS.yaml b/data/custodian/CZ-52-SOB-L-MKFS.yaml index 3de29a786a..d3df399273 100644 --- a/data/custodian/CZ-52-SOB-L-MKFS.yaml +++ b/data/custodian/CZ-52-SOB-L-MKFS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SOB-L-MKFS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SOB-L-MKFS 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-KR-SOB-L-MKFS ghcid_numeric: 14775745294421521939 valid_from: '2025-12-08T11:21:39.620695+00:00' @@ -221,3 +222,22 @@ location: postal_code: 507 43 street_address: nám. Míru 4 normalization_timestamp: '2025-12-09T10:53:05.804830+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:06:15.113877+00:00' + source_url: https://katalog.knihovnasobotka.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnasobotka.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovnasobotka.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:06:15.113877+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-SON-L-OKVS.yaml b/data/custodian/CZ-52-SON-L-OKVS.yaml index bd73630c7c..23f250b78a 100644 --- a/data/custodian/CZ-52-SON-L-OKVS.yaml +++ b/data/custodian/CZ-52-SON-L-OKVS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SON-L-OKVS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SON-L-OKVS 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-KR-SON-L-OKVS ghcid_numeric: 1676848780163030101 valid_from: '2025-12-08T11:21:25.937854+00:00' @@ -215,3 +216,32 @@ location: postal_code: 549 71 street_address: Šonov 318 normalization_timestamp: '2025-12-09T10:53:05.850460+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:06:17.246530+00:00' + source_url: https://sonov.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sonov.mknachod.cz/custom/design/logo.png + source_url: https://sonov.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: '2025-12-26T16:06:17.246530+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://sonov.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://sonov.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:06:17.246530+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-STA-L-MKSP.yaml b/data/custodian/CZ-52-STA-L-MKSP.yaml index dc9e9de1dd..8677da9c05 100644 --- a/data/custodian/CZ-52-STA-L-MKSP.yaml +++ b/data/custodian/CZ-52-STA-L-MKSP.yaml @@ -217,3 +217,30 @@ location: postal_code: 507 91 street_address: Revoluční 22 normalization_timestamp: '2025-12-09T10:53:05.907263+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:06:33.857329+00:00' + source_url: https://knihovnastarapaka.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnastarapaka.webk.cz/themes/new/orange/logo1.png + source_url: https://knihovnastarapaka.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-26T16:06:33.857329+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnastarapaka.webk.cz/themes/new/favicon.ico + source_url: https://knihovnastarapaka.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T16:06:33.857329+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-STA-L-OKS.yaml b/data/custodian/CZ-52-STA-L-OKS.yaml index 0285660884..1adc809a50 100644 --- a/data/custodian/CZ-52-STA-L-OKS.yaml +++ b/data/custodian/CZ-52-STA-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-STA-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-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-STA-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-KR-STA-L-OKS ghcid_numeric: 12334434239917567617 valid_from: '2025-12-06T23:37:35.380390+00:00' @@ -210,3 +211,32 @@ location: postal_code: 549 36 street_address: Stárkov 87 normalization_timestamp: '2025-12-09T10:53:05.943745+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:06:40.900929+00:00' + source_url: https://starkov.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://starkov.mknachod.cz/custom/design/logo.png + source_url: https://starkov.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: '2025-12-26T16:06:40.900929+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://starkov.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://starkov.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:06:40.900929+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-STA-L-OKSB.yaml b/data/custodian/CZ-52-STA-L-OKSB.yaml index 512012c216..69fdc1869e 100644 --- a/data/custodian/CZ-52-STA-L-OKSB.yaml +++ b/data/custodian/CZ-52-STA-L-OKSB.yaml @@ -211,3 +211,22 @@ location: postal_code: 503 57 street_address: Starý Bydžov 13 normalization_timestamp: '2025-12-09T10:53:05.989258+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:06:47.134259+00:00' + source_url: https://www.starybydzov.cz/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.starybydzov.cz/image.php?nid=939&oid=8347757&width=29 + source_url: https://www.starybydzov.cz/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-26T16:06:47.134259+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-STE-L-OKS-obecni_knihovna_stezirky.yaml b/data/custodian/CZ-52-STE-L-OKS-obecni_knihovna_stezirky.yaml index 924a096fa0..763e27b68d 100644 --- a/data/custodian/CZ-52-STE-L-OKS-obecni_knihovna_stezirky.yaml +++ b/data/custodian/CZ-52-STE-L-OKS-obecni_knihovna_stezirky.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-STE-L-OKS-obecni_knihovna_stezirky - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-STE-L-OKS-obecni_knihovna_stezirky 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-KR-STE-L-OKS-obecni_knihovna_stezirky ghcid_numeric: 9011157507171231934 valid_from: '2025-12-06T23:37:42.536335+00:00' @@ -212,3 +213,30 @@ location: postal_code: 503 12 street_address: Stěžírky 85 normalization_timestamp: '2025-12-09T10:53:06.019672+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:06:52.456760+00:00' + source_url: https://knihovnastezirky.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnastezirky.webk.cz/themes/new/green/logo1.png + source_url: https://knihovnastezirky.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-26T16:06:52.456760+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnastezirky.webk.cz/themes/new/favicon.ico + source_url: https://knihovnastezirky.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T16:06:52.456760+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-STE-L-OKS.yaml b/data/custodian/CZ-52-STE-L-OKS.yaml index 530450bb69..a1c53f84da 100644 --- a/data/custodian/CZ-52-STE-L-OKS.yaml +++ b/data/custodian/CZ-52-STE-L-OKS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-STE-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-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-STE-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-KR-STE-L-OKS ghcid_numeric: 3661751248275194899 valid_from: '2025-12-06T23:37:24.501688+00:00' @@ -220,3 +221,22 @@ location: postal_code: 503 21 street_address: Lipová 380 normalization_timestamp: '2025-12-09T10:53:06.043691+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:07:01.451413+00:00' + source_url: https://vck.tritius.cz/library/stezery + 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/stezery + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:07:01.451413+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-STO-M-MHMPK.yaml b/data/custodian/CZ-52-STO-M-MHMPK.yaml index 966bc6668e..6b1ff110e4 100644 --- a/data/custodian/CZ-52-STO-M-MHMPK.yaml +++ b/data/custodian/CZ-52-STO-M-MHMPK.yaml @@ -234,3 +234,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Muzeum hlavního města Prahy - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:57.843905+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:07:12.149061+00:00' + source_url: https://muzeumprahy.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeumprahy.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeumprahy.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:07:12.149061+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-STR-L-MLKS.yaml b/data/custodian/CZ-52-STR-L-MLKS.yaml index 9163c8fbb8..7bd77942d0 100644 --- a/data/custodian/CZ-52-STR-L-MLKS.yaml +++ b/data/custodian/CZ-52-STR-L-MLKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-STR-L-MLKS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-STR-L-MLKS 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-KR-STR-L-MLKS ghcid_numeric: 414772981295881964 valid_from: '2025-12-06T23:37:35.203326+00:00' @@ -210,3 +211,22 @@ location: postal_code: 507 22 street_address: Střevač 49 normalization_timestamp: '2025-12-09T10:53:06.069942+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:07:21.784229+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=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:07:21.784229+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-STR-L-OKS.yaml b/data/custodian/CZ-52-STR-L-OKS.yaml index 547e925572..02a2f64900 100644 --- a/data/custodian/CZ-52-STR-L-OKS.yaml +++ b/data/custodian/CZ-52-STR-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-STR-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-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-STR-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-KR-STR-L-OKS ghcid_numeric: 15334558282251380869 valid_from: '2025-12-06T23:37:35.081450+00:00' @@ -216,3 +217,22 @@ location: postal_code: 503 14 street_address: Stračov 133 normalization_timestamp: '2025-12-09T10:53:06.097149+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:07:26.820386+00:00' + source_url: https://www.stracov.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.stracov.cz/images/favicon-114px.png + source_url: https://www.stracov.cz/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T16:07:26.820386+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 114x114 + 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-STU-L-OKVS-obecni_knihovna_ve_starkoci.yaml b/data/custodian/CZ-52-STU-L-OKVS-obecni_knihovna_ve_starkoci.yaml index c7ddf16ef2..d35cf9158b 100644 --- a/data/custodian/CZ-52-STU-L-OKVS-obecni_knihovna_ve_starkoci.yaml +++ b/data/custodian/CZ-52-STU-L-OKVS-obecni_knihovna_ve_starkoci.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-STU-L-OKVS-obecni_knihovna_ve_starkoci - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-STU-L-OKVS-obecni_knihovna_ve_starkoci 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-KR-STU-L-OKVS-obecni_knihovna_ve_starkoci ghcid_numeric: 3643639751306834936 valid_from: '2025-12-06T23:37:35.385890+00:00' @@ -205,3 +206,22 @@ location: postal_code: 549 48 street_address: Starkoč normalization_timestamp: '2025-12-09T10:53:06.119962+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:07:35.429495+00:00' + source_url: https://www.starkoc.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.starkoc.cz/skins/starkoc.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.starkoc.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:07:35.429495+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-STU-L-OKVS.yaml b/data/custodian/CZ-52-STU-L-OKVS.yaml index 7ec7afbfa3..64f62732f0 100644 --- a/data/custodian/CZ-52-STU-L-OKVS.yaml +++ b/data/custodian/CZ-52-STU-L-OKVS.yaml @@ -217,3 +217,32 @@ location: postal_code: 549 48 street_address: Studnice 1 normalization_timestamp: '2025-12-09T10:53:06.150295+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:07:43.701540+00:00' + source_url: https://studnice.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://studnice.mknachod.cz/custom/design/logo_studnice.png + source_url: https://studnice.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: '2025-12-26T16:07:43.701540+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://studnice.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://studnice.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:07:43.701540+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-SVO-L-MKSNU.yaml b/data/custodian/CZ-52-SVO-L-MKSNU.yaml index 8af66453a5..bac9b6a4bd 100644 --- a/data/custodian/CZ-52-SVO-L-MKSNU.yaml +++ b/data/custodian/CZ-52-SVO-L-MKSNU.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-SVO-L-MKSNU - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-SVO-L-MKSNU 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-KR-SVO-L-MKSNU ghcid_numeric: 1517136628594194905 valid_from: '2025-12-08T11:21:41.666214+00:00' @@ -228,3 +229,22 @@ location: postal_code: 542 24 street_address: nám. Svornosti 474 normalization_timestamp: '2025-12-09T10:53:06.182992+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:07:59.146303+00:00' + source_url: https://svobodanup.tritius.cz/library/svoboda + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://svobodanup.tritius.cz/apple-touch-icon-180x180.png + source_url: https://svobodanup.tritius.cz/library/svoboda + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:07:59.146303+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-TEP-L-MKVTNM.yaml b/data/custodian/CZ-52-TEP-L-MKVTNM.yaml index 783ad9782a..4c4f817c5e 100644 --- a/data/custodian/CZ-52-TEP-L-MKVTNM.yaml +++ b/data/custodian/CZ-52-TEP-L-MKVTNM.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TEP-L-MKVTNM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-TEP-L-MKVTNM 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-KR-TEP-L-MKVTNM ghcid_numeric: 2071389135853017481 valid_from: '2025-12-06T23:37:21.404149+00:00' @@ -220,3 +221,22 @@ location: postal_code: 549 57 street_address: Rooseveltova 106 normalization_timestamp: '2025-12-09T10:53:06.211590+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:08:06.281362+00:00' + source_url: https://vck.tritius.cz/library/teplicenmet + 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/teplicenmet + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:08:06.281362+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-TRE-L-HMKTPO.yaml b/data/custodian/CZ-52-TRE-L-HMKTPO.yaml index f94807a5f7..c8a19403b5 100644 --- a/data/custodian/CZ-52-TRE-L-HMKTPO.yaml +++ b/data/custodian/CZ-52-TRE-L-HMKTPO.yaml @@ -221,3 +221,22 @@ location: postal_code: 503 46 street_address: Komenského 437 normalization_timestamp: '2025-12-09T10:53:06.238833+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:08:17.226365+00:00' + source_url: https://trebechovice.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trebechovice.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trebechovice.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:08:17.226365+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-TRE-L-OKJ.yaml b/data/custodian/CZ-52-TRE-L-OKJ.yaml index 5c315b34a8..a9d36da0dc 100644 --- a/data/custodian/CZ-52-TRE-L-OKJ.yaml +++ b/data/custodian/CZ-52-TRE-L-OKJ.yaml @@ -215,3 +215,30 @@ location: postal_code: 503 46 street_address: Jeníkovice 25 normalization_timestamp: '2025-12-09T10:53:06.267178+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:08:22.412104+00:00' + source_url: https://knihovnajenikovice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnajenikovice.webk.cz/themes/new/lila/logo2.png + source_url: https://knihovnajenikovice.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-26T16:08:22.412104+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnajenikovice.webk.cz/themes/new/favicon.ico + source_url: https://knihovnajenikovice.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T16:08:22.412104+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-TRE-L-OKL-obecni_knihovna_libnikovice.yaml b/data/custodian/CZ-52-TRE-L-OKL-obecni_knihovna_libnikovice.yaml index 34d783410e..b4d72b307d 100644 --- a/data/custodian/CZ-52-TRE-L-OKL-obecni_knihovna_libnikovice.yaml +++ b/data/custodian/CZ-52-TRE-L-OKL-obecni_knihovna_libnikovice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TRE-L-OKL-obecni_knihovna_libnikovice - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-TRE-L-OKL-obecni_knihovna_libnikovice 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-KR-TRE-L-OKL-obecni_knihovna_libnikovice ghcid_numeric: 13394915577216579750 valid_from: '2025-12-06T23:37:35.092591+00:00' @@ -210,3 +211,28 @@ location: postal_code: 503 46 street_address: Libníkovice 40 normalization_timestamp: '2025-12-09T10:53:06.303917+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:08:29.023489+00:00' + source_url: https://www.libnikovice.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.libnikovice.cz/www//cache/images-favicon-180-180.png + source_url: https://www.libnikovice.cz/obec/knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:08:29.023489+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.libnikovice.cz/www//cache/images-logo-256-256.png + source_url: https://www.libnikovice.cz/obec/knihovna + css_selector: '[document] > html > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-26T16:08:29.023489+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-TRE-L-OKL.yaml b/data/custodian/CZ-52-TRE-L-OKL.yaml index b4e5ecf069..ac8d761664 100644 --- a/data/custodian/CZ-52-TRE-L-OKL.yaml +++ b/data/custodian/CZ-52-TRE-L-OKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TRE-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-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-TRE-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-KR-TRE-L-OKL ghcid_numeric: 8600715432952312296 valid_from: '2025-12-06T23:37:35.089827+00:00' @@ -211,3 +212,22 @@ location: postal_code: 503 46 street_address: Librantice 119 normalization_timestamp: '2025-12-09T10:53:06.327697+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:08:36.703381+00:00' + source_url: https://kmhk.tritius.cz/library/librantice/detail/2425445 + 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/librantice/detail/2425445 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:08:36.703381+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-TRU-E-CLATSSVOSZ.yaml b/data/custodian/CZ-52-TRU-E-CLATSSVOSZ.yaml index 1c19c3de03..804119870c 100644 --- a/data/custodian/CZ-52-TRU-E-CLATSSVOSZ.yaml +++ b/data/custodian/CZ-52-TRU-E-CLATSSVOSZ.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TRU-E-CLATSSVOSZ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-TRU-E-CLATSSVOSZ 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-KR-TRU-E-CLATSSVOSZ ghcid_numeric: 6454742255730077578 valid_from: '2025-12-08T11:21:32.808813+00:00' @@ -228,3 +229,30 @@ location: postal_code: 541 11 street_address: Lesnická 9 normalization_timestamp: '2025-12-09T10:53:06.380298+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:08:50.001576+00:00' + source_url: https://www.clatrutnov.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.clatrutnov.cz/images/lesarna/lesarna-logo.png + source_url: https://www.clatrutnov.cz + css_selector: '#logo > div.logo.logo-image > a > img.logo-image.primary-logo-image' + retrieved_on: '2025-12-26T16:08:50.001576+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo + - claim_type: favicon_url + claim_value: https://www.clatrutnov.cz/templates/j51_robyn/favicon.ico + source_url: https://www.clatrutnov.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T16:08:50.001576+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-52-TRU-E-VOSZSZSSIC.yaml b/data/custodian/CZ-52-TRU-E-VOSZSZSSIC.yaml index 74e53b1959..809029a79b 100644 --- a/data/custodian/CZ-52-TRU-E-VOSZSZSSIC.yaml +++ b/data/custodian/CZ-52-TRU-E-VOSZSZSSIC.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TRU-E-VOSZSZSSIC - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-TRU-E-VOSZSZSSIC 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-KR-TRU-E-VOSZSZSSIC ghcid_numeric: 9428000902050574430 valid_from: '2025-12-08T11:21:30.541014+00:00' @@ -214,3 +215,22 @@ location: postal_code: 541 01 street_address: Procházkova 303 normalization_timestamp: '2025-12-09T10:53:06.410576+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:08:55.475437+00:00' + source_url: https://www.szstrutnov.cz/stranka/skolni-informacni-centrum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.szstrutnov.cz/img/favicon.png + source_url: https://www.szstrutnov.cz/stranka/skolni-informacni-centrum + css_selector: '[document] > html.csstransforms.csstransforms3d > head > link' + retrieved_on: '2025-12-26T16:08:55.475437+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-TRU-L-MKSRFT.yaml b/data/custodian/CZ-52-TRU-L-MKSRFT.yaml index be58e94202..28d1a7c7d2 100644 --- a/data/custodian/CZ-52-TRU-L-MKSRFT.yaml +++ b/data/custodian/CZ-52-TRU-L-MKSRFT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TRU-L-MKSRFT - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-TRU-L-MKSRFT 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-KR-TRU-L-MKSRFT ghcid_numeric: 6888361403429324593 valid_from: '2025-12-06T23:37:20.375530+00:00' @@ -243,3 +244,22 @@ location: postal_code: 541 01 street_address: Krakonošovo nám. 128 normalization_timestamp: '2025-12-09T10:53:06.518678+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:09:12.419002+00:00' + source_url: https://trutnov.tritius.cz + 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 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:09:12.419002+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-TRU-M-MP-muzeum_podkrkonosi.yaml b/data/custodian/CZ-52-TRU-M-MP-muzeum_podkrkonosi.yaml index 0a46ee1e1d..30301aa99e 100644 --- a/data/custodian/CZ-52-TRU-M-MP-muzeum_podkrkonosi.yaml +++ b/data/custodian/CZ-52-TRU-M-MP-muzeum_podkrkonosi.yaml @@ -224,3 +224,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Muzeum Podkrkonoší official youtube_search_timestamp: '2025-12-09T09:34:01.148484+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:09:22.483796+00:00' + source_url: http://www.muzeumtrutnov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.muzeumtrutnov.cz/favicon.ico + source_url: http://www.muzeumtrutnov.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T16:09:22.483796+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.muzeumtrutnov.cz/images/logo.png + source_url: http://www.muzeumtrutnov.cz + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-26T16:09:22.483796+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-52-TRU-M-MPVTK.yaml b/data/custodian/CZ-52-TRU-M-MPVTK.yaml index 3d7755ad58..c0aa4c9e1d 100644 --- a/data/custodian/CZ-52-TRU-M-MPVTK.yaml +++ b/data/custodian/CZ-52-TRU-M-MPVTK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TRU-M-MPVTK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-TRU-M-MPVTK 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-KR-TRU-M-MPVTK ghcid_numeric: 15731288153147155550 valid_from: '2025-12-06T23:37:20.319593+00:00' @@ -210,3 +211,28 @@ location: postal_code: 541 01 street_address: Školní 150 normalization_timestamp: '2025-12-09T10:53:06.586484+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:09:29.645801+00:00' + source_url: http://www.muzeumtrutnov.cz/online-katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.muzeumtrutnov.cz/favicon.ico + source_url: http://www.muzeumtrutnov.cz/online-katalog + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T16:09:29.645801+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.muzeumtrutnov.cz/images/logo.png + source_url: http://www.muzeumtrutnov.cz/online-katalog + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-26T16:09:29.645801+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-52-TRU-O-SOAVHKSOAT.yaml b/data/custodian/CZ-52-TRU-O-SOAVHKSOAT.yaml index 8b5a350038..d8c7a1306a 100644 --- a/data/custodian/CZ-52-TRU-O-SOAVHKSOAT.yaml +++ b/data/custodian/CZ-52-TRU-O-SOAVHKSOAT.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TRU-O-SOAVHKSOAT - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-TRU-O-SOAVHKSOAT 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-KR-TRU-O-SOAVHKSOAT ghcid_numeric: 8359230411226433992 valid_from: '2025-12-06T23:37:24.317177+00:00' @@ -218,3 +219,33 @@ location: postal_code: 541 01 street_address: Komenského 128 normalization_timestamp: '2025-12-09T10:53:06.608840+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:09:38.926325+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: '2025-12-26T16:09:38.926325+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: '2025-12-26T16:09:38.926325+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-TUR-L-MKT.yaml b/data/custodian/CZ-52-TUR-L-MKT.yaml index 49d67369a9..f8508c4b43 100644 --- a/data/custodian/CZ-52-TUR-L-MKT.yaml +++ b/data/custodian/CZ-52-TUR-L-MKT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-TUR-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-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-TUR-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-KR-TUR-L-MKT ghcid_numeric: 10953938343125184539 valid_from: '2025-12-06T23:37:35.211678+00:00' @@ -210,3 +211,22 @@ location: postal_code: 506 01 street_address: Tuř 13 normalization_timestamp: '2025-12-09T10:53:06.637939+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:22:58.948872+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=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:22:58.948872+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-TYN-L-MKTNO.yaml b/data/custodian/CZ-52-TYN-L-MKTNO.yaml index b38bc41a6f..cfd6a77518 100644 --- a/data/custodian/CZ-52-TYN-L-MKTNO.yaml +++ b/data/custodian/CZ-52-TYN-L-MKTNO.yaml @@ -224,3 +224,32 @@ location: postal_code: 517 21 street_address: Čs.armády 937 normalization_timestamp: '2025-12-09T10:53:06.677319+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:23:05.847849+00:00' + source_url: https://tyniste.kpsys.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tyniste.kpsys.cz/custom/design/logo.png + source_url: https://tyniste.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 > div > img' + retrieved_on: '2025-12-26T16:23:05.847849+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://tyniste.kpsys.cz/favicon.png?v=2.3.0-32050 + source_url: https://tyniste.kpsys.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:23:05.847849+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-UHR-L-VUZVVVDK.yaml b/data/custodian/CZ-52-UHR-L-VUZVVVDK.yaml index 2e1a957f95..c1ba2fa4e8 100644 --- a/data/custodian/CZ-52-UHR-L-VUZVVVDK.yaml +++ b/data/custodian/CZ-52-UHR-L-VUZVVVDK.yaml @@ -232,3 +232,22 @@ youtube_status: NOT_FOUND youtube_search_query: Výzkumný ústav živočišné výroby, v. v. i. - Dokumentace a knihovna official youtube_search_timestamp: '2025-12-09T09:34:02.468553+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:23:23.011539+00:00' + source_url: https://vuzv.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://vuzv.cz/wp-content/themes/vantage/images/logo_ofi.komplet_kopie_290px.jpg + source_url: https://vuzv.cz + css_selector: '#masthead > div.container-menu:nth-of-type(2) > a.logo > img' + retrieved_on: '2025-12-26T16:23:23.011539+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/CZ-52-ULI-L-LKU.yaml b/data/custodian/CZ-52-ULI-L-LKU.yaml index 87dffae7c3..888a449f58 100644 --- a/data/custodian/CZ-52-ULI-L-LKU.yaml +++ b/data/custodian/CZ-52-ULI-L-LKU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-ULI-L-LKU - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-ULI-L-LKU 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-KR-ULI-L-LKU ghcid_numeric: 7979941876089502284 valid_from: '2025-12-08T11:21:40.993750+00:00' @@ -221,3 +222,22 @@ location: postal_code: 507 07 street_address: Úlibice 53 normalization_timestamp: '2025-12-09T10:53:06.715823+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:23:20.644482+00:00' + source_url: https://knihovnaulibice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaulibice.files.webk.cz/logov.png + source_url: https://knihovnaulibice.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T16:23:20.644482+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-UPI-L-MKS.yaml b/data/custodian/CZ-52-UPI-L-MKS.yaml index fbd97a68d6..765d4cbead 100644 --- a/data/custodian/CZ-52-UPI-L-MKS.yaml +++ b/data/custodian/CZ-52-UPI-L-MKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-UPI-L-MKS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-UPI-L-MKS 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-KR-UPI-L-MKS ghcid_numeric: 10651109856694649050 valid_from: '2025-12-06T23:37:35.690696+00:00' @@ -210,3 +211,22 @@ location: postal_code: 542 32 street_address: Suchovršice 122 normalization_timestamp: '2025-12-09T10:53:06.765870+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:24:30.178762+00:00' + source_url: https://trutnov.tritius.cz/library/suchovrsice + 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/suchovrsice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:24:30.178762+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-UPI-L-MKVU.yaml b/data/custodian/CZ-52-UPI-L-MKVU.yaml index 765e8c0756..99fdc479fe 100644 --- a/data/custodian/CZ-52-UPI-L-MKVU.yaml +++ b/data/custodian/CZ-52-UPI-L-MKVU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-UPI-L-MKVU - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-UPI-L-MKVU 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-KR-UPI-L-MKVU ghcid_numeric: 9493349148947058595 valid_from: '2025-12-08T11:21:31.162393+00:00' @@ -224,3 +225,22 @@ location: postal_code: 542 32 street_address: Bratří Čapků 1075 normalization_timestamp: '2025-12-09T10:53:06.789559+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:24:32.149858+00:00' + source_url: https://katalog.knihovnaupice.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnaupice.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovnaupice.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:24:32.149858+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-VAM-L-MKV.yaml b/data/custodian/CZ-52-VAM-L-MKV.yaml index c5bb16ec7d..98fa3f19db 100644 --- a/data/custodian/CZ-52-VAM-L-MKV.yaml +++ b/data/custodian/CZ-52-VAM-L-MKV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VAM-L-MKV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VAM-L-MKV 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-KR-VAM-L-MKV ghcid_numeric: 6160392538062726452 valid_from: '2025-12-06T23:37:21.444978+00:00' @@ -223,3 +224,22 @@ location: postal_code: 517 54 street_address: Voříškova 84 normalization_timestamp: '2025-12-09T10:53:06.882521+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:26:50.572382+00:00' + source_url: https://katalog.knihovna-vamberk.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-vamberk.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-vamberk.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:26:50.572382+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-VEL-L-MLKV.yaml b/data/custodian/CZ-52-VEL-L-MLKV.yaml index dca9f75c39..360cbdef9f 100644 --- a/data/custodian/CZ-52-VEL-L-MLKV.yaml +++ b/data/custodian/CZ-52-VEL-L-MLKV.yaml @@ -211,3 +211,30 @@ location: postal_code: 507 21 street_address: Veliš 4 normalization_timestamp: '2025-12-09T10:53:07.018568+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:27:19.256999+00:00' + source_url: https://knihovnavelis.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnavelis.webk.cz/themes/new/orange/logo1.png + source_url: https://knihovnavelis.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-26T16:27:19.256999+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnavelis.webk.cz/themes/new/favicon.ico + source_url: https://knihovnavelis.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T16:27:19.256999+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-VEL-L-OKVJ.yaml b/data/custodian/CZ-52-VEL-L-OKVJ.yaml index 55987d2154..54051668eb 100644 --- a/data/custodian/CZ-52-VEL-L-OKVJ.yaml +++ b/data/custodian/CZ-52-VEL-L-OKVJ.yaml @@ -40,13 +40,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VEL-L-OKVJ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VEL-L-OKVJ 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-KR-VEL-L-OKVJ ghcid_numeric: 5834859117959544595 valid_from: '2025-12-06T23:37:25.449804+00:00' @@ -208,3 +209,22 @@ location: country: *id006 postal_code: 552 24 normalization_timestamp: '2025-12-09T10:53:07.045336+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:27:27.925657+00:00' + source_url: https://jaromer.tritius.cz/library/velkajesenice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jaromer.tritius.cz/apple-touch-icon-180x180.png + source_url: https://jaromer.tritius.cz/library/velkajesenice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:27:27.925657+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-VEL-L-OKVS.yaml b/data/custodian/CZ-52-VEL-L-OKVS.yaml index f39923c668..9b64d17e0d 100644 --- a/data/custodian/CZ-52-VEL-L-OKVS.yaml +++ b/data/custodian/CZ-52-VEL-L-OKVS.yaml @@ -211,3 +211,22 @@ location: postal_code: 542 35 street_address: Velké Svatoňovice 286 normalization_timestamp: '2025-12-09T10:53:07.071223+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:27:36.092764+00:00' + source_url: https://trutnov.tritius.cz/library/vsvatonovice + 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/vsvatonovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:27:36.092764+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-VEL-L-OKVV-obecni_knihovna_velky_vrestov.yaml b/data/custodian/CZ-52-VEL-L-OKVV-obecni_knihovna_velky_vrestov.yaml index 79097ac833..eb6da9f312 100644 --- a/data/custodian/CZ-52-VEL-L-OKVV-obecni_knihovna_velky_vrestov.yaml +++ b/data/custodian/CZ-52-VEL-L-OKVV-obecni_knihovna_velky_vrestov.yaml @@ -211,3 +211,22 @@ location: postal_code: 544 54 street_address: Velký Vřešťov 34 normalization_timestamp: '2025-12-09T10:53:07.098523+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:27:43.506308+00:00' + source_url: https://trutnov.tritius.cz/library/velkyvrestov + 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/velkyvrestov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:27:43.506308+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-VEL-L-OKVV.yaml b/data/custodian/CZ-52-VEL-L-OKVV.yaml index 06ab178e74..5f8cd9a6f1 100644 --- a/data/custodian/CZ-52-VEL-L-OKVV.yaml +++ b/data/custodian/CZ-52-VEL-L-OKVV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VEL-L-OKVV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VEL-L-OKVV 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-KR-VEL-L-OKVV ghcid_numeric: 10639334761332797224 valid_from: '2025-12-06T23:37:35.396723+00:00' @@ -210,3 +211,22 @@ location: postal_code: 552 11 street_address: Na Zátiší 1 normalization_timestamp: '2025-12-09T10:53:07.122038+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:27:51.530250+00:00' + source_url: https://jaromer.tritius.cz/library/velichovky + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jaromer.tritius.cz/apple-touch-icon-180x180.png + source_url: https://jaromer.tritius.cz/library/velichovky + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:27:51.530250+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-VIL-L-OKV.yaml b/data/custodian/CZ-52-VIL-L-OKV.yaml index fc086e5861..a9f43d87dd 100644 --- a/data/custodian/CZ-52-VIL-L-OKV.yaml +++ b/data/custodian/CZ-52-VIL-L-OKV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VIL-L-OKV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VIL-L-OKV 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-KR-VIL-L-OKV ghcid_numeric: 1150297931881030826 valid_from: '2025-12-06T23:37:35.703171+00:00' @@ -210,3 +211,22 @@ location: postal_code: 544 01 street_address: Vilantice 101 normalization_timestamp: '2025-12-09T10:53:07.151159+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:27:58.327952+00:00' + source_url: https://trutnov.tritius.cz/library/vilantice + 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/vilantice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:27:58.327952+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-VIT-L-OKK.yaml b/data/custodian/CZ-52-VIT-L-OKK.yaml index 0bb0471637..bb5c783ae2 100644 --- a/data/custodian/CZ-52-VIT-L-OKK.yaml +++ b/data/custodian/CZ-52-VIT-L-OKK.yaml @@ -211,3 +211,22 @@ location: postal_code: 544 62 street_address: Kocléřov 123 normalization_timestamp: '2025-12-09T10:53:07.176637+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:28:13.926477+00:00' + source_url: https://trutnov.tritius.cz/library/koclerov + 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/koclerov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:28:13.926477+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-VOD-L-MKV.yaml b/data/custodian/CZ-52-VOD-L-MKV.yaml index df6fa74c0a..402dc62ee8 100644 --- a/data/custodian/CZ-52-VOD-L-MKV.yaml +++ b/data/custodian/CZ-52-VOD-L-MKV.yaml @@ -212,3 +212,22 @@ location: postal_code: 517 34 street_address: Voděrady 91 normalization_timestamp: '2025-12-09T10:53:07.203481+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:28:24.037405+00:00' + source_url: https://voderady-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://voderady-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://voderady-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:28:24.037405+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-VOL-L-MKV.yaml b/data/custodian/CZ-52-VOL-L-MKV.yaml index 3e69be13e2..cc4a02f200 100644 --- a/data/custodian/CZ-52-VOL-L-MKV.yaml +++ b/data/custodian/CZ-52-VOL-L-MKV.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VOL-L-MKV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VOL-L-MKV 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-KR-VOL-L-MKV ghcid_numeric: 2286943577177845628 valid_from: '2025-12-06T23:37:35.228392+00:00' @@ -214,3 +215,22 @@ location: postal_code: 507 03 street_address: Volanice 130 normalization_timestamp: '2025-12-09T10:53:07.230508+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:28:32.509604+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=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:28:32.509604+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-VRB-L-MKV.yaml b/data/custodian/CZ-52-VRB-L-MKV.yaml index 83b954ce14..1205146753 100644 --- a/data/custodian/CZ-52-VRB-L-MKV.yaml +++ b/data/custodian/CZ-52-VRB-L-MKV.yaml @@ -215,3 +215,22 @@ location: postal_code: 507 03 street_address: Vrbice 25 normalization_timestamp: '2025-12-09T10:53:07.256628+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:28:42.427609+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=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:28:42.427609+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-VRC-M-SKNPKMK.yaml b/data/custodian/CZ-52-VRC-M-SKNPKMK.yaml index 59ce213b55..6113c9edab 100644 --- a/data/custodian/CZ-52-VRC-M-SKNPKMK.yaml +++ b/data/custodian/CZ-52-VRC-M-SKNPKMK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VRC-M-SKNPKMK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VRC-M-SKNPKMK 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-KR-VRC-M-SKNPKMK ghcid_numeric: 14228715331342475269 valid_from: '2025-12-06T23:37:20.330082+00:00' @@ -217,3 +218,22 @@ location: postal_code: 543 01 street_address: Husova 213 normalization_timestamp: '2025-12-09T10:53:07.298784+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:28:50.066865+00:00' + source_url: https://tritius.krnap.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.krnap.cz/apple-touch-icon-180x180.png + source_url: https://tritius.krnap.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:28:50.066865+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-VRS-L-MLKV.yaml b/data/custodian/CZ-52-VRS-L-MLKV.yaml index c17a3bf7b1..6f0bc41769 100644 --- a/data/custodian/CZ-52-VRS-L-MLKV.yaml +++ b/data/custodian/CZ-52-VRS-L-MLKV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VRS-L-MLKV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VRS-L-MLKV 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-KR-VRS-L-MLKV ghcid_numeric: 1271407420322835844 valid_from: '2025-12-06T23:37:35.234014+00:00' @@ -210,3 +211,22 @@ location: postal_code: 507 33 street_address: Vršce 91 normalization_timestamp: '2025-12-09T10:53:07.335435+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:29:01.707295+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=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:29:01.707295+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-VSE-L-KV.yaml b/data/custodian/CZ-52-VSE-L-KV.yaml index 5b39d04ad7..3c7644178c 100644 --- a/data/custodian/CZ-52-VSE-L-KV.yaml +++ b/data/custodian/CZ-52-VSE-L-KV.yaml @@ -221,3 +221,22 @@ location: postal_code: 503 12 street_address: Všestary 57 normalization_timestamp: '2025-12-09T10:53:07.364423+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:29:08.775880+00:00' + source_url: https://kmhk.tritius.cz/library/vsestary + 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/vsestary + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:29:08.775880+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-VSE-L-OKR.yaml b/data/custodian/CZ-52-VSE-L-OKR.yaml index 2c146c12b1..f3fae5c2ea 100644 --- a/data/custodian/CZ-52-VSE-L-OKR.yaml +++ b/data/custodian/CZ-52-VSE-L-OKR.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VSE-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-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-VSE-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-KR-VSE-L-OKR ghcid_numeric: 13694520811341605484 valid_from: '2025-12-06T23:37:35.098405+00:00' @@ -202,3 +203,22 @@ location: postal_code: 503 12 street_address: Rozběřice normalization_timestamp: '2025-12-09T10:53:07.452466+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:29:22.235912+00:00' + source_url: https://www.vsestary-obec.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vsestary-obec.cz/skins/vsestary-obec.cz_lego3/favicons/safari-pinned-tab.svg + source_url: https://www.vsestary-obec.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:29:22.235912+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-VYS-L-MKVV.yaml b/data/custodian/CZ-52-VYS-L-MKVV.yaml index d1c5007fcc..67c50f83e6 100644 --- a/data/custodian/CZ-52-VYS-L-MKVV.yaml +++ b/data/custodian/CZ-52-VYS-L-MKVV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VYS-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-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-VYS-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-KR-VYS-L-MKVV ghcid_numeric: 7167273800857356016 valid_from: '2025-12-06T23:37:23.407695+00:00' @@ -216,3 +217,22 @@ location: postal_code: 507 03 street_address: Mírové nám. 23 normalization_timestamp: '2025-12-09T10:53:07.479884+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:29:29.143828+00:00' + source_url: https://knihovnavv.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnavv.webk.cz/themes/cbdb-klasicky/default/logo3.png + source_url: https://knihovnavv.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T16:29:29.143828+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-VYS-L-MLKS.yaml b/data/custodian/CZ-52-VYS-L-MLKS.yaml index f419f8d5b9..f7c5287f3b 100644 --- a/data/custodian/CZ-52-VYS-L-MLKS.yaml +++ b/data/custodian/CZ-52-VYS-L-MLKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-VYS-L-MLKS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-VYS-L-MLKS 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-KR-VYS-L-MLKS ghcid_numeric: 14299775540041090848 valid_from: '2025-12-06T23:37:35.194384+00:00' @@ -210,3 +211,30 @@ location: postal_code: 507 03 street_address: Sběř 94 normalization_timestamp: '2025-12-09T10:53:07.506660+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:29:34.892692+00:00' + source_url: https://knihovnasber.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnasber.webk.cz/themes/new/orange/logo3.png + source_url: https://knihovnasber.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-26T16:29:34.892692+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnasber.webk.cz/themes/new/favicon.ico + source_url: https://knihovnasber.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T16:29:34.892692+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-ZAB-L-MVKVPZ.yaml b/data/custodian/CZ-52-ZAB-L-MVKVPZ.yaml index 1b2a188501..607ce1b8d2 100644 --- a/data/custodian/CZ-52-ZAB-L-MVKVPZ.yaml +++ b/data/custodian/CZ-52-ZAB-L-MVKVPZ.yaml @@ -190,3 +190,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q2326815 +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:29:44.093326+00:00' + source_url: https://katalog.knihovna-zbraslav.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-zbraslav.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-zbraslav.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:29:44.093326+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-ZAC-L-MKVZ.yaml b/data/custodian/CZ-52-ZAC-L-MKVZ.yaml index 7d652b9f79..48272ddc20 100644 --- a/data/custodian/CZ-52-ZAC-L-MKVZ.yaml +++ b/data/custodian/CZ-52-ZAC-L-MKVZ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-ZAC-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-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-ZAC-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-KR-ZAC-L-MKVZ ghcid_numeric: 10112564257607228020 valid_from: '2025-12-08T11:21:29.076500+00:00' @@ -220,3 +221,22 @@ location: postal_code: 542 01 street_address: Na pilíři 204 normalization_timestamp: '2025-12-09T10:53:07.535028+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:29:51.449798+00:00' + source_url: https://vck.tritius.cz/library/zacler + 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/zacler + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:29:51.449798+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-ZAM-A-SOAVHK.yaml b/data/custodian/CZ-52-ZAM-A-SOAVHK.yaml index c4cb92a3f0..4fcdf8f2df 100644 --- a/data/custodian/CZ-52-ZAM-A-SOAVHK.yaml +++ b/data/custodian/CZ-52-ZAM-A-SOAVHK.yaml @@ -40,13 +40,14 @@ ghcid: iso_code_source: CZ-521 ghcid_history: - ghcid: CZ-52-ZAM-A-SOAVHK - 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-ZAM-A-SOAVHK 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-SOAVHK ghcid_numeric: 6234925827149830915 valid_from: '2025-12-06T23:37:43.767931+00:00' @@ -87,7 +88,8 @@ provenance: confidence_score: 0.85 notes: - 'Country resolved 2025-12-06T23:54:39Z: XX→CZ via Wikidata P17' - - 'City resolved 2025-12-07T00:34:52Z: XXX->ZAM via Wikidata Q17156873 coords (49.9862,16.1288) -> Zamrsk (GeoNames:3061872)' + - 'City resolved 2025-12-07T00:34:52Z: XXX->ZAM via Wikidata Q17156873 coords (49.9862,16.1288) + -> Zamrsk (GeoNames:3061872)' - 'Region resolved 2025-12-07T11:30:37Z: XX->521 via Wikidata P131 (CZ-521)' - 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 @@ -119,8 +121,8 @@ 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: Státní oblastní archiv v Hradci Králové @@ -283,3 +285,33 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní oblastní archiv v Hradci Králové official youtube_search_timestamp: '2025-12-09T09:34:09.142287+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:30:12.655589+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: '2025-12-26T16:30:12.655589+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: '2025-12-26T16:30:12.655589+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-ZDA-L-MKZNO.yaml b/data/custodian/CZ-52-ZDA-L-MKZNO.yaml index aeb690ad26..50dc6597f1 100644 --- a/data/custodian/CZ-52-ZDA-L-MKZNO.yaml +++ b/data/custodian/CZ-52-ZDA-L-MKZNO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-ZDA-L-MKZNO - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-ZDA-L-MKZNO 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-KR-ZDA-L-MKZNO ghcid_numeric: 7831516836994331621 valid_from: '2025-12-08T11:21:31.307331+00:00' @@ -215,3 +216,22 @@ location: postal_code: 517 23 street_address: Žďár nad Orlicí 133 normalization_timestamp: '2025-12-09T10:53:07.560908+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:30:11.155985+00:00' + source_url: https://zdar-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://zdar-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://zdar-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:30:11.155985+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-ZDA-L-OKVZ.yaml b/data/custodian/CZ-52-ZDA-L-OKVZ.yaml index 14329a597f..bbf504956d 100644 --- a/data/custodian/CZ-52-ZDA-L-OKVZ.yaml +++ b/data/custodian/CZ-52-ZDA-L-OKVZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-ZDA-L-OKVZ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-ZDA-L-OKVZ 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-KR-ZDA-L-OKVZ ghcid_numeric: 16600439932437167733 valid_from: '2025-12-08T11:21:37.694827+00:00' @@ -221,3 +222,32 @@ location: postal_code: 549 37 street_address: Žďárky 35 normalization_timestamp: '2025-12-09T10:53:07.589821+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:30:32.028886+00:00' + source_url: https://zdarky.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://zdarky.mknachod.cz/custom/design/logo.png + source_url: https://zdarky.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: '2025-12-26T16:30:32.028886+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://zdarky.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://zdarky.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:30:32.028886+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-ZDA-L-OKVZNM.yaml b/data/custodian/CZ-52-ZDA-L-OKVZNM.yaml index 46241df89a..07a56f25d3 100644 --- a/data/custodian/CZ-52-ZDA-L-OKVZNM.yaml +++ b/data/custodian/CZ-52-ZDA-L-OKVZNM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-ZDA-L-OKVZNM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' 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-ZDA-L-OKVZNM 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-KR-ZDA-L-OKVZNM ghcid_numeric: 14046730031053293892 valid_from: '2025-12-08T11:21:40.425702+00:00' @@ -215,3 +216,22 @@ location: postal_code: 549 55 street_address: Žďár nad Metují 60 normalization_timestamp: '2025-12-09T10:53:07.617432+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:30:41.355107+00:00' + source_url: https://knihovnazdarnadmetuji.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnazdarnadmetuji.files.webk.cz/logov.png + source_url: https://knihovnazdarnadmetuji.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T16:30:41.355107+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-53-BAN-L-KB.yaml b/data/custodian/CZ-53-BAN-L-KB.yaml index cf11e04e1e..a1a27335a2 100644 --- a/data/custodian/CZ-53-BAN-L-KB.yaml +++ b/data/custodian/CZ-53-BAN-L-KB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BAN-L-KB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BAN-L-KB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BAN-L-KB ghcid_numeric: 13558457992846917346 valid_from: '2025-12-06T23:37:40.519342+00:00' @@ -208,3 +209,22 @@ location: postal_code: 568 02 street_address: Banín 41 normalization_timestamp: '2025-12-09T10:53:32.271837+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:30:55.397701+00:00' + source_url: https://tritius.booksy.cz/library/banin + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/banin + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:30:55.397701+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-53-BEL-L-OKVBNS.yaml b/data/custodian/CZ-53-BEL-L-OKVBNS.yaml index 9bd75af70b..6ce3dec183 100644 --- a/data/custodian/CZ-53-BEL-L-OKVBNS.yaml +++ b/data/custodian/CZ-53-BEL-L-OKVBNS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BEL-L-OKVBNS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BEL-L-OKVBNS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BEL-L-OKVBNS ghcid_numeric: 5004375315735181230 valid_from: '2025-12-06T23:37:40.522190+00:00' @@ -212,3 +213,22 @@ location: postal_code: 569 05 street_address: Bělá nad Svitavou 89 normalization_timestamp: '2025-12-09T10:53:32.295226+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:31:02.015567+00:00' + source_url: https://tritius.booksy.cz/library/belansvitavou + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/belansvitavou + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:31:02.015567+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-53-BEZ-L-OKBUT.yaml b/data/custodian/CZ-53-BEZ-L-OKBUT.yaml index 50e15bb3d6..9f7047a138 100644 --- a/data/custodian/CZ-53-BEZ-L-OKBUT.yaml +++ b/data/custodian/CZ-53-BEZ-L-OKBUT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BEZ-L-OKBUT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BEZ-L-OKBUT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BEZ-L-OKBUT ghcid_numeric: 2288782143293573997 valid_from: '2025-12-06T23:37:40.526095+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 43 street_address: Bezděčí u Trnávky 19 normalization_timestamp: '2025-12-09T10:53:32.322297+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:31:14.740562+00:00' + source_url: https://bezdeci-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bezdeci-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://bezdeci-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:31:14.740562+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-53-BOH-L-MKVB.yaml b/data/custodian/CZ-53-BOH-L-MKVB.yaml index 4d55d23e98..b0e6cb6ae6 100644 --- a/data/custodian/CZ-53-BOH-L-MKVB.yaml +++ b/data/custodian/CZ-53-BOH-L-MKVB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BOH-L-MKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BOH-L-MKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BOH-L-MKVB ghcid_numeric: 6455979906167041122 valid_from: '2025-12-06T23:37:40.533620+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 06 street_address: Bohuňovice 13 normalization_timestamp: '2025-12-09T10:53:32.348052+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:31:25.293686+00:00' + source_url: https://www.bohunovice.net/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bohunovice.net/favicon.png + source_url: https://www.bohunovice.net/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T16:31:25.293686+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-53-BOH-L-OKB.yaml b/data/custodian/CZ-53-BOH-L-OKB.yaml index 4a283a78ec..0b7403c2c7 100644 --- a/data/custodian/CZ-53-BOH-L-OKB.yaml +++ b/data/custodian/CZ-53-BOH-L-OKB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BOH-L-OKB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BOH-L-OKB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BOH-L-OKB ghcid_numeric: 5215718868405364792 valid_from: '2025-12-06T23:37:40.529817+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 04 street_address: Bohuňov 49 normalization_timestamp: '2025-12-09T10:53:32.373768+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:31:45.173423+00:00' + source_url: https://tritius.booksy.cz/library/bohunov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/bohunov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:31:45.173423+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-53-BOJ-L-OKVB.yaml b/data/custodian/CZ-53-BOJ-L-OKVB.yaml index 53c1b6632a..2c7cc51243 100644 --- a/data/custodian/CZ-53-BOJ-L-OKVB.yaml +++ b/data/custodian/CZ-53-BOJ-L-OKVB.yaml @@ -206,3 +206,22 @@ location: postal_code: 538 26 street_address: Bojanov 18 normalization_timestamp: '2025-12-09T10:53:32.400680+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:31:56.827992+00:00' + source_url: https://www.bojanov.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bojanov.cz/image.php?nid=806&oid=7441088 + source_url: https://www.bojanov.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-26T16:31:56.827992+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-53-BOR-L-MKVB.yaml b/data/custodian/CZ-53-BOR-L-MKVB.yaml index af969d9c59..6ac275e055 100644 --- a/data/custodian/CZ-53-BOR-L-MKVB.yaml +++ b/data/custodian/CZ-53-BOR-L-MKVB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BOR-L-MKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BOR-L-MKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BOR-L-MKVB ghcid_numeric: 15330104924988660089 valid_from: '2025-12-06T23:37:40.539140+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 82 street_address: Borová 111 normalization_timestamp: '2025-12-09T10:53:32.427590+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:32:10.411736+00:00' + source_url: https://tritius.knihovna.policka.org/library/borova + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna.policka.org/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna.policka.org/library/borova + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:32:10.411736+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-53-BRA-L-MKBNO.yaml b/data/custodian/CZ-53-BRA-L-MKBNO.yaml index 81d51b52f7..e9ade85a5e 100644 --- a/data/custodian/CZ-53-BRA-L-MKBNO.yaml +++ b/data/custodian/CZ-53-BRA-L-MKBNO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BRA-L-MKBNO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BRA-L-MKBNO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BRA-L-MKBNO ghcid_numeric: 4420766657084404894 valid_from: '2025-12-06T23:37:20.573806+00:00' @@ -213,3 +214,22 @@ location: postal_code: 561 12 street_address: Českých bratří 133 normalization_timestamp: '2025-12-09T10:53:32.453375+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:32:24.925350+00:00' + source_url: https://katalog.mesto-brandys.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.mesto-brandys.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.mesto-brandys.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:32:24.925350+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-53-BRN-H-PBFKKFVD.yaml b/data/custodian/CZ-53-BRN-H-PBFKKFVD.yaml index 7b0ab6a0e1..b30a91677e 100644 --- a/data/custodian/CZ-53-BRN-H-PBFKKFVD.yaml +++ b/data/custodian/CZ-53-BRN-H-PBFKKFVD.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BRN-H-PBFKKFVD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BRN-H-PBFKKFVD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BRN-H-PBFKKFVD ghcid_numeric: 10185733964455771455 valid_from: '2025-12-06T23:37:27.412839+00:00' @@ -219,3 +220,37 @@ location: postal_code: 601 87 street_address: Kounicova 65a normalization_timestamp: '2025-12-09T10:53:32.476901+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:32:32.286006+00:00' + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.ofm.cz/wp-content/uploads/2020/03/Logo-mobil-s-tau.png + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + css_selector: '#mobhead > div.bg-area.stickyable > div.logo-main-wrap.logo-mob-wrap + > div.logo.logo-mobile > a > span.logo-img > img' + retrieved_on: '2025-12-26T16:32:32.286006+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.ofm.cz/wp-content/uploads/2020/03/cropped-tau-180x180.png + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + css_selector: '[document] > html > head > link:nth-of-type(22)' + retrieved_on: '2025-12-26T16:32:32.286006+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mlw0ch6jmb2y.i.optimole.com/GKBUCrI-YU42fkBF/w:1024/h:555/q:auto/https://www.ofm.cz/wp-content/uploads/2015/07/mt.jpg + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-26T16:32:32.286006+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/CZ-53-BRN-H-PBFKKFVMT.yaml b/data/custodian/CZ-53-BRN-H-PBFKKFVMT.yaml index b7b7b3594b..3a7acb8054 100644 --- a/data/custodian/CZ-53-BRN-H-PBFKKFVMT.yaml +++ b/data/custodian/CZ-53-BRN-H-PBFKKFVMT.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BRN-H-PBFKKFVMT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BRN-H-PBFKKFVMT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BRN-H-PBFKKFVMT ghcid_numeric: 7048541378980577702 valid_from: '2025-12-06T23:37:27.403992+00:00' @@ -224,3 +225,37 @@ location: postal_code: 601 87 street_address: Kounicova 65a normalization_timestamp: '2025-12-09T10:53:32.505425+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:32:40.918151+00:00' + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.ofm.cz/wp-content/uploads/2020/03/Logo-mobil-s-tau.png + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + css_selector: '#mobhead > div.bg-area.stickyable > div.logo-main-wrap.logo-mob-wrap + > div.logo.logo-mobile > a > span.logo-img > img' + retrieved_on: '2025-12-26T16:32:40.918151+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.ofm.cz/wp-content/uploads/2020/03/cropped-tau-180x180.png + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + css_selector: '[document] > html > head > link:nth-of-type(22)' + retrieved_on: '2025-12-26T16:32:40.918151+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mlw0ch6jmb2y.i.optimole.com/GKBUCrI-YU42fkBF/w:1024/h:555/q:auto/https://www.ofm.cz/wp-content/uploads/2015/07/mt.jpg + source_url: https://www.ofm.cz/kontakty-3/moravska-trebova + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-26T16:32:40.918151+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/CZ-53-BRN-H-RFMTK.yaml b/data/custodian/CZ-53-BRN-H-RFMTK.yaml index 7b3d07f521..7657f502a8 100644 --- a/data/custodian/CZ-53-BRN-H-RFMTK.yaml +++ b/data/custodian/CZ-53-BRN-H-RFMTK.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BRN-H-RFMTK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BRN-H-RFMTK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BRN-H-RFMTK ghcid_numeric: 7841514708853085232 valid_from: '2025-12-08T11:21:25.286453+00:00' @@ -221,3 +222,28 @@ location: postal_code: 601 87 street_address: Kounicova 65a normalization_timestamp: '2025-12-09T10:53:32.534080+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:32:57.753271+00:00' + source_url: http://www.farnostmoravskatrebova.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.farnostmoravskatrebova.cz/wp-content/uploads/2018/08/URC-LOGO-Device-greyscale.png + source_url: http://www.farnostmoravskatrebova.cz + css_selector: '[document] > html.has-offscreen.js > head > link:nth-of-type(22)' + retrieved_on: '2025-12-26T16:32:57.753271+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://www.farnostmoravskatrebova.cz/wp-content/uploads/2018/09/pokus2-2.png + source_url: http://www.farnostmoravskatrebova.cz + css_selector: '[document] > html.has-offscreen.js > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-26T16:32:57.753271+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-53-BRN-L-KB.yaml b/data/custodian/CZ-53-BRN-L-KB.yaml index 50b6627cc1..97da62770e 100644 --- a/data/custodian/CZ-53-BRN-L-KB.yaml +++ b/data/custodian/CZ-53-BRN-L-KB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BRN-L-KB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BRN-L-KB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BRN-L-KB ghcid_numeric: 5007639303860637456 valid_from: '2025-12-06T23:37:40.544901+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 04 street_address: Moravská Chrastová 77 normalization_timestamp: '2025-12-09T10:53:32.560225+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:33:07.029165+00:00' + source_url: https://tritius.booksy.cz/library/brnenec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/brnenec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:33:07.029165+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-53-BRN-L-OKVC.yaml b/data/custodian/CZ-53-BRN-L-OKVC.yaml index d2fd63fbb3..09432ebe53 100644 --- a/data/custodian/CZ-53-BRN-L-OKVC.yaml +++ b/data/custodian/CZ-53-BRN-L-OKVC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BRN-L-OKVC - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BRN-L-OKVC valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BRN-L-OKVC ghcid_numeric: 5562632222835279268 valid_from: '2025-12-06T23:37:40.542010+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 04 street_address: Chrastavec 55 normalization_timestamp: '2025-12-09T10:53:32.585193+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:33:17.453387+00:00' + source_url: https://tritius.booksy.cz/library/chrastavec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/chrastavec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:33:17.453387+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-53-BRN-L-OKVS.yaml b/data/custodian/CZ-53-BRN-L-OKVS.yaml index 329dcfc21f..fe3029bf73 100644 --- a/data/custodian/CZ-53-BRN-L-OKVS.yaml +++ b/data/custodian/CZ-53-BRN-L-OKVS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BRN-L-OKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BRN-L-OKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BRN-L-OKVS ghcid_numeric: 5646060575198425402 valid_from: '2025-12-08T11:21:35.557399+00:00' @@ -213,3 +214,22 @@ location: postal_code: 569 04 street_address: Študlov 26 normalization_timestamp: '2025-12-09T10:53:32.611865+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:33:25.603645+00:00' + source_url: https://tritius.booksy.cz/library/studlov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/studlov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:33:25.603645+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-53-BUD-L-OKB.yaml b/data/custodian/CZ-53-BUD-L-OKB.yaml index a08bb50863..db517f811a 100644 --- a/data/custodian/CZ-53-BUD-L-OKB.yaml +++ b/data/custodian/CZ-53-BUD-L-OKB.yaml @@ -40,13 +40,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BUD-L-OKB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BUD-L-OKB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BUD-L-OKB ghcid_numeric: 18411520121750529400 valid_from: '2025-12-06T23:37:26.595226+00:00' @@ -210,3 +211,22 @@ location: country: *id006 postal_code: 569 65 normalization_timestamp: '2025-12-09T10:53:32.638262+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:33:40.467703+00:00' + source_url: https://budislav-katalog.knihovna-litomysl.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://budislav-katalog.knihovna-litomysl.cz/themes/root/images/vufind-favicon.ico + source_url: https://budislav-katalog.knihovna-litomysl.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:33:40.467703+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-53-BYL-L-MKB.yaml b/data/custodian/CZ-53-BYL-L-MKB.yaml index ef00639055..0fe17598b0 100644 --- a/data/custodian/CZ-53-BYL-L-MKB.yaml +++ b/data/custodian/CZ-53-BYL-L-MKB.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BYL-L-MKB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BYL-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BYL-L-MKB ghcid_numeric: 13077841354277589705 valid_from: '2025-12-06T23:37:40.015039+00:00' @@ -200,3 +201,22 @@ location: postal_code: 538 01 street_address: Bylany 77 normalization_timestamp: '2025-12-09T10:53:32.664738+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:33:47.157758+00:00' + source_url: https://www.bylany.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bylany.cz/image.php?nid=17961&oid=7492401 + source_url: https://www.bylany.cz + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-26T16:33:47.157758+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-53-BYS-L-MKVB.yaml b/data/custodian/CZ-53-BYS-L-MKVB.yaml index 8cfbbe1cda..17c0052e1a 100644 --- a/data/custodian/CZ-53-BYS-L-MKVB.yaml +++ b/data/custodian/CZ-53-BYS-L-MKVB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BYS-L-MKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BYS-L-MKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BYS-L-MKVB ghcid_numeric: 14059748542288689898 valid_from: '2025-12-06T23:37:20.140247+00:00' @@ -219,3 +220,22 @@ location: postal_code: 569 92 street_address: nám. Na Podkově 68 normalization_timestamp: '2025-12-09T10:53:32.689959+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:33:54.476713+00:00' + source_url: https://jmk.tritius.cz/library/bystre + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jmk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://jmk.tritius.cz/library/bystre + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:33:54.476713+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-53-BYS-L-OKB.yaml b/data/custodian/CZ-53-BYS-L-OKB.yaml index 7e0221c105..2bdb12a55e 100644 --- a/data/custodian/CZ-53-BYS-L-OKB.yaml +++ b/data/custodian/CZ-53-BYS-L-OKB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BYS-L-OKB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BYS-L-OKB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BYS-L-OKB ghcid_numeric: 8968941112670111886 valid_from: '2025-12-06T23:37:40.851038+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 54 street_address: Bystřec 86 normalization_timestamp: '2025-12-09T10:53:32.716900+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:34:01.104456+00:00' + source_url: https://www.bystrec.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bystrec.cz/image.php?nid=18714&oid=8354514&width=29 + source_url: https://www.bystrec.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-26T16:34:01.104456+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-53-BYS-L-OKVB.yaml b/data/custodian/CZ-53-BYS-L-OKVB.yaml index f619cb6e27..b57d5f403e 100644 --- a/data/custodian/CZ-53-BYS-L-OKVB.yaml +++ b/data/custodian/CZ-53-BYS-L-OKVB.yaml @@ -35,13 +35,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-BYS-L-OKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-BYS-L-OKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-BYS-L-OKVB ghcid_numeric: 142657414698710896 valid_from: '2025-12-06T23:37:22.379774+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 v Býšti @@ -209,3 +210,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:09.617905+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Býšť +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:34:10.277954+00:00' + source_url: https://kkpce.tritius.cz/library/byst?device=503 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kkpce.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kkpce.tritius.cz/library/byst?device=503 + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:34:10.277954+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-53-CER-L-OKVCNL.yaml b/data/custodian/CZ-53-CER-L-OKVCNL.yaml index b573c4f87d..1f1d94faed 100644 --- a/data/custodian/CZ-53-CER-L-OKVCNL.yaml +++ b/data/custodian/CZ-53-CER-L-OKVCNL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CER-L-OKVCNL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CER-L-OKVCNL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CER-L-OKVCNL ghcid_numeric: 3797704256327877796 valid_from: '2025-12-06T23:37:40.561224+00:00' @@ -205,3 +206,28 @@ location: postal_code: 569 53 street_address: Cerekvice nad Loučnou 8 normalization_timestamp: '2025-12-09T10:53:32.877807+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:34:27.768067+00:00' + source_url: https://www.facebook.com/Knihovna-v-Cerekvici-nad-Lou%C4%8Dnou-181204118697422 + 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/Knihovna-v-Cerekvici-nad-Lou%C4%8Dnou-181204118697422 + css_selector: '#facebook > head > link' + retrieved_on: '2025-12-26T16:34:27.768067+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/t39.30808-1/587209400_866138062760993_7848421164893412891_n.jpg?stp=dst-jpg_tt6&cstp=mx1200x1200&ctp=s720x720&_nc_cat=105&ccb=1-7&_nc_sid=3ab345&_nc_ohc=ajvyccVpXoQQ7kNvwEwL_g2&_nc_oc=AdmzObQyaceaW9Gqrz9Ky7GMuPtc5K495ld23n9PQ9d6ng5Akf9MyF3g7EgkrcHRA1I&_nc_zt=24&_nc_ht=scontent.frtm1-3.fna&_nc_gid=k-soiUoca8zCXXI7stiNrw&oh=00_AfkMARVInBR7fOQRuPxdhrhNRndoI6NW-JwGjB1NEP3k-A&oe=69549F7B + source_url: https://www.facebook.com/Knihovna-v-Cerekvici-nad-Lou%C4%8Dnou-181204118697422 + css_selector: '#facebook > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-26T16:34:27.768067+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-53-CES-E-SSTDGHCTK.yaml b/data/custodian/CZ-53-CES-E-SSTDGHCTK.yaml index 1399f26404..3d64ec5575 100644 --- a/data/custodian/CZ-53-CES-E-SSTDGHCTK.yaml +++ b/data/custodian/CZ-53-CES-E-SSTDGHCTK.yaml @@ -225,3 +225,22 @@ location: postal_code: 560 02 street_address: Habrmanova 1540 normalization_timestamp: '2025-12-09T10:53:32.908832+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:34:35.186198+00:00' + source_url: https://skola.tritius.cz/library/vdact + 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/vdact + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:34:35.186198+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-53-CES-L-MKCTPP.yaml b/data/custodian/CZ-53-CES-L-MKCTPP.yaml index f60e122efc..c9c8ca362f 100644 --- a/data/custodian/CZ-53-CES-L-MKCTPP.yaml +++ b/data/custodian/CZ-53-CES-L-MKCTPP.yaml @@ -36,13 +36,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CES-L-MKCTPP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CES-L-MKCTPP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CES-L-MKCTPP ghcid_numeric: 2126818566582307640 valid_from: '2025-12-08T11:21:26.672968+00:00' @@ -105,8 +106,8 @@ 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 Česká Třebová - pobočka Parník @@ -217,3 +218,30 @@ location: geonames_id: 3077920 geonames_name: Česká Třebová feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:34:43.092783+00:00' + source_url: https://moderniknihovna.cz/cs/kontakty/adresy-telefony-a-e-maily + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://moderniknihovna.cz/images/flex/mkct_logo_white.png + source_url: https://moderniknihovna.cz/cs/kontakty/adresy-telefony-a-e-maily + css_selector: '#sp-logo > div.sp-column > a.logo > img.sp-default-logo.hidden-xs' + retrieved_on: '2025-12-26T16:34:43.092783+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Městská knihovna Česká Třebová + - claim_type: favicon_url + claim_value: https://moderniknihovna.cz/images/flex/mkct_favicon.png + source_url: https://moderniknihovna.cz/cs/kontakty/adresy-telefony-a-e-maily + css_selector: '[document] > html.webkit.chrome > head > link' + retrieved_on: '2025-12-26T16:34:43.092783+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: 2 diff --git a/data/custodian/CZ-53-CES-L-OKCL.yaml b/data/custodian/CZ-53-CES-L-OKCL.yaml index 1947d02f5c..ac5e1c8711 100644 --- a/data/custodian/CZ-53-CES-L-OKCL.yaml +++ b/data/custodian/CZ-53-CES-L-OKCL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CES-L-OKCL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CES-L-OKCL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CES-L-OKCL ghcid_numeric: 5950005723131232185 valid_from: '2025-12-08T11:21:38.750393+00:00' @@ -213,3 +214,22 @@ location: postal_code: 561 14 street_address: České Libchavy 160 normalization_timestamp: '2025-12-09T10:53:32.963062+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:34:50.242964+00:00' + source_url: https://vufind.knihovna-uo.cz/clibchavy + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/clibchavy/themes/bootprint3Rbit-clibchavy/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/clibchavy + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:34:50.242964+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-53-CES-L-OKK.yaml b/data/custodian/CZ-53-CES-L-OKK.yaml index 2d1566290d..ae9977b4ef 100644 --- a/data/custodian/CZ-53-CES-L-OKK.yaml +++ b/data/custodian/CZ-53-CES-L-OKK.yaml @@ -211,3 +211,22 @@ location: geonames_id: 3077920 geonames_name: Česká Třebová feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:00.529229+00:00' + source_url: https://kozlov.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kozlov.knihovna.cz/favicon.svg + source_url: https://kozlov.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:35:00.529229+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-53-CES-L-OKP.yaml b/data/custodian/CZ-53-CES-L-OKP.yaml index 8ecb75b0fb..058c487203 100644 --- a/data/custodian/CZ-53-CES-L-OKP.yaml +++ b/data/custodian/CZ-53-CES-L-OKP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CES-L-OKP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CES-L-OKP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CES-L-OKP ghcid_numeric: 3334501169056676795 valid_from: '2025-12-06T23:37:40.863933+00:00' @@ -205,3 +206,22 @@ location: postal_code: 560 02 street_address: Přívrat 11 normalization_timestamp: '2025-12-09T10:53:33.043384+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:05.463692+00:00' + source_url: https://www.privrat.knihovna.cz/on-line-katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.privrat.knihovna.cz/favicon.svg + source_url: https://www.privrat.knihovna.cz/on-line-katalog + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:35:05.463692+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-53-CES-L-OKS-obecni_knihovna_svinna.yaml b/data/custodian/CZ-53-CES-L-OKS-obecni_knihovna_svinna.yaml index 1446b3112e..ef14f4f11f 100644 --- a/data/custodian/CZ-53-CES-L-OKS-obecni_knihovna_svinna.yaml +++ b/data/custodian/CZ-53-CES-L-OKS-obecni_knihovna_svinna.yaml @@ -206,3 +206,22 @@ location: postal_code: 560 02 street_address: Svinná 3 normalization_timestamp: '2025-12-09T10:53:33.068865+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:10.344712+00:00' + source_url: https://svinna.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://svinna.knihovna.cz/favicon.svg + source_url: https://svinna.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:35:10.344712+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-53-CES-L-OKV.yaml b/data/custodian/CZ-53-CES-L-OKV.yaml index 490321a0df..cecb41b077 100644 --- a/data/custodian/CZ-53-CES-L-OKV.yaml +++ b/data/custodian/CZ-53-CES-L-OKV.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CES-L-OKV - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CES-L-OKV valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CES-L-OKV ghcid_numeric: 9146326820470611822 valid_from: '2025-12-06T23:37:40.870582+00:00' @@ -200,3 +201,22 @@ location: postal_code: 560 02 street_address: Vlčkov 11 normalization_timestamp: '2025-12-09T10:53:33.091151+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:15.235472+00:00' + source_url: http://www.vlckov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://parking.vedos.cz + source_url: http://www.vlckov.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:35:15.235472+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-53-CES-L-SSTK.yaml b/data/custodian/CZ-53-CES-L-SSTK.yaml index ea103e5cb8..5a64dbc8a9 100644 --- a/data/custodian/CZ-53-CES-L-SSTK.yaml +++ b/data/custodian/CZ-53-CES-L-SSTK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CES-L-SSTK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CES-L-SSTK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CES-L-SSTK ghcid_numeric: 1215623506649845924 valid_from: '2025-12-06T23:37:20.511517+00:00' @@ -217,3 +218,32 @@ location: postal_code: 560 02 street_address: Moravská 1078 normalization_timestamp: '2025-12-09T10:53:33.114561+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:23.806414+00:00' + source_url: https://www.sintex.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sintex.cz/wp-content/uploads/2024/11/sintex_logo.png + source_url: https://www.sintex.cz + css_selector: '#header > div.e-con-inner > div.elementor-element.elementor-element-9080e3d + > div.elementor-element.elementor-element-3107202 > div.elementor-widget-container + > a > img.attachment-1536x1536.size-1536x1536' + retrieved_on: '2025-12-26T16:35:23.806414+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://sintex.cz/wp-content/uploads/2025/02/cropped-favicon-180x180.png + source_url: https://www.sintex.cz + css_selector: '[document] > html > head > link:nth-of-type(42)' + retrieved_on: '2025-12-26T16:35:23.806414+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-53-CES-M-MMCTK.yaml b/data/custodian/CZ-53-CES-M-MMCTK.yaml index aed2462c08..21fe004394 100644 --- a/data/custodian/CZ-53-CES-M-MMCTK.yaml +++ b/data/custodian/CZ-53-CES-M-MMCTK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CES-M-MMCTK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CES-M-MMCTK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CES-M-MMCTK ghcid_numeric: 3265367616438059563 valid_from: '2025-12-08T11:21:40.411499+00:00' @@ -215,3 +216,22 @@ location: postal_code: 560 02 street_address: Klácelova 80 normalization_timestamp: '2025-12-09T10:53:33.142669+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:33.054656+00:00' + source_url: https://katalog.mmct.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.mmct.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.mmct.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:35:33.054656+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-53-CET-M-MMCT.yaml b/data/custodian/CZ-53-CET-M-MMCT.yaml index c6bd1d6d48..48929afaa6 100644 --- a/data/custodian/CZ-53-CET-M-MMCT.yaml +++ b/data/custodian/CZ-53-CET-M-MMCT.yaml @@ -39,10 +39,11 @@ ghcid: city_label: Ceska Trebova geonames_id: 3077920 ghcid_history: - - previous_ghcid_component: "CT" - new_ghcid_component: "CET" - change_date: "2025-12-20T19:55:24Z" - reason: "Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Ceska Trebova" + - previous_ghcid_component: CT + new_ghcid_component: CET + change_date: '2025-12-20T19:55:24Z' + reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: + Ceska Trebova' - ghcid: CZ-53-CT-M-MMCT ghcid_numeric: 12393921886611132648 valid_from: '2025-12-08T11:21:28.102646+00:00' @@ -89,7 +90,8 @@ provenance: notes: - 'Country resolved 2025-12-06T23:54:38Z: XX→CZ via Wikidata P17' - 'Region resolved 2025-12-07T00:00:34Z: XX->53 via Wikidata P131 (CZ-53)' - - 'City resolved 2025-12-07T00:25:33Z: XXX->CT via Wikidata Q85620599 coords (49.9019,16.4473) -> Ceska Trebova (GeoNames:3077920)' + - 'City resolved 2025-12-07T00:25:33Z: XXX->CT via Wikidata Q85620599 coords (49.9019,16.4473) + -> Ceska Trebova (GeoNames:3077920)' - Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:19Z - Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:45Z - 'YouTube/Google Maps enrichment 2025-12-09T09:34:14Z: YouTube: not found' @@ -120,8 +122,8 @@ 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: Městské muzeum Česká Třebová @@ -224,3 +226,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Městské muzeum Česká Třebová official youtube_search_timestamp: '2025-12-09T09:34:14.401884+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:41.502939+00:00' + source_url: http://www.mmct.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mmct.cz/wp-content/uploads/fbrfg/safari-pinned-tab.svg + source_url: http://www.mmct.cz + css_selector: '[document] > html > head > link:nth-of-type(25)' + retrieved_on: '2025-12-26T16:35:41.502939+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-53-CHO-L-MKC.yaml b/data/custodian/CZ-53-CHO-L-MKC.yaml index fafbae2383..a5d0071256 100644 --- a/data/custodian/CZ-53-CHO-L-MKC.yaml +++ b/data/custodian/CZ-53-CHO-L-MKC.yaml @@ -474,3 +474,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/K2KR63Yu2i8/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:47.133305+00:00' + source_url: https://chocen-katalog.koha.cloud + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://chocen-katalog.koha.cloud/themes/root/images/vufind-favicon.ico + source_url: https://chocen-katalog.koha.cloud + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:35:47.133305+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-53-CHO-L-MKCPD.yaml b/data/custodian/CZ-53-CHO-L-MKCPD.yaml index d4dedb11e3..d01ac7d1ef 100644 --- a/data/custodian/CZ-53-CHO-L-MKCPD.yaml +++ b/data/custodian/CZ-53-CHO-L-MKCPD.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHO-L-MKCPD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHO-L-MKCPD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHO-L-MKCPD ghcid_numeric: 2451909120627918385 valid_from: '2025-12-06T23:37:42.703284+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 Choceň - pobočka Dvořisko @@ -222,3 +223,22 @@ location: geonames_id: 3077725 geonames_name: Choceň feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:51.951273+00:00' + source_url: https://knihovnadvorisko.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnadvorisko.webk.cz/themes/cbdb-klasicky/letni/logo3.png + source_url: https://knihovnadvorisko.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T16:35:51.951273+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-53-CHO-L-MKCPH.yaml b/data/custodian/CZ-53-CHO-L-MKCPH.yaml index bcc01c2d6f..13ddc2cbd9 100644 --- a/data/custodian/CZ-53-CHO-L-MKCPH.yaml +++ b/data/custodian/CZ-53-CHO-L-MKCPH.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHO-L-MKCPH - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHO-L-MKCPH valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHO-L-MKCPH ghcid_numeric: 9346229686454183055 valid_from: '2025-12-06T23:37:42.700407+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 Choceň - pobočka Hemže @@ -222,3 +223,28 @@ location: geonames_id: 3077725 geonames_name: Choceň feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:35:58.204909+00:00' + source_url: https://www.chocen.cz/mestska%2Dknihovna/ms-24185/p1=24185 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.chocen.cz/favicon.svg + source_url: https://www.chocen.cz/mestska%2Dknihovna/ms-24185/p1=24185 + css_selector: '[document] > html.no-js.no-touchevents > head > link:nth-of-type(4)' + retrieved_on: '2025-12-26T16:35:58.204909+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.chocen.cz/imgs/logo.svg + source_url: https://www.chocen.cz/mestska%2Dknihovna/ms-24185/p1=24185 + css_selector: '[document] > html.no-js.no-touchevents > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-26T16:35:58.204909+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-53-CHO-L-OKC-obecni_knihovna_chornice.yaml b/data/custodian/CZ-53-CHO-L-OKC-obecni_knihovna_chornice.yaml index b32b87366e..08a69af0ea 100644 --- a/data/custodian/CZ-53-CHO-L-OKC-obecni_knihovna_chornice.yaml +++ b/data/custodian/CZ-53-CHO-L-OKC-obecni_knihovna_chornice.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHO-L-OKC-obecni_knihovna_chornice - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHO-L-OKC-obecni_knihovna_chornice valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHO-L-OKC-obecni_knihovna_chornice ghcid_numeric: 13605974699821535077 valid_from: '2025-12-06T23:37:40.577117+00:00' @@ -209,3 +210,22 @@ location: postal_code: 569 42 street_address: Jevíčská 41 normalization_timestamp: '2025-12-09T10:53:33.283667+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:36:04.859711+00:00' + source_url: https://knihovna.jevicko.cz/library/Chornice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.jevicko.cz/apple-touch-icon-180x180.png + source_url: https://knihovna.jevicko.cz/library/Chornice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:36:04.859711+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-53-CHO-L-OKK.yaml b/data/custodian/CZ-53-CHO-L-OKK.yaml index e5ff393bb5..3d0a112a87 100644 --- a/data/custodian/CZ-53-CHO-L-OKK.yaml +++ b/data/custodian/CZ-53-CHO-L-OKK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHO-L-OKK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHO-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHO-L-OKK ghcid_numeric: 13505312194354623593 valid_from: '2025-12-06T23:37:40.913043+00:00' @@ -205,3 +206,22 @@ location: postal_code: 565 01 street_address: Koldín 15 normalization_timestamp: '2025-12-09T10:53:33.309032+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:36:11.746379+00:00' + source_url: https://koldin.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://koldin.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://koldin.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:36:11.746379+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-53-CHO-L-OKN.yaml b/data/custodian/CZ-53-CHO-L-OKN.yaml index 924304a790..d65c560d2b 100644 --- a/data/custodian/CZ-53-CHO-L-OKN.yaml +++ b/data/custodian/CZ-53-CHO-L-OKN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHO-L-OKN - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHO-L-OKN valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHO-L-OKN ghcid_numeric: 10029929499305199978 valid_from: '2025-12-06T23:37:40.924259+00:00' @@ -208,3 +209,22 @@ location: postal_code: 565 01 street_address: Nasavrky 31 normalization_timestamp: '2025-12-09T10:53:33.334996+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:36:15.719048+00:00' + source_url: https://knihovnanasavrky.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnanasavrky.webk.cz/themes/cbdb-klasicky/default/logo1.png + source_url: https://knihovnanasavrky.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T16:36:15.719048+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-53-CHO-L-OKS.yaml b/data/custodian/CZ-53-CHO-L-OKS.yaml index 1f6680b99b..c0f478355b 100644 --- a/data/custodian/CZ-53-CHO-L-OKS.yaml +++ b/data/custodian/CZ-53-CHO-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHO-L-OKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHO-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHO-L-OKS ghcid_numeric: 9202210077393783138 valid_from: '2025-12-06T23:37:40.940231+00:00' @@ -205,3 +206,22 @@ location: postal_code: 565 01 street_address: Skořenice 23 normalization_timestamp: '2025-12-09T10:53:33.357639+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:36:20.697547+00:00' + source_url: https://skorenice.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://skorenice.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://skorenice.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:36:20.697547+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-53-CHO-L-OKUUC.yaml b/data/custodian/CZ-53-CHO-L-OKUUC.yaml index 00c28ec3c2..7935a5e325 100644 --- a/data/custodian/CZ-53-CHO-L-OKUUC.yaml +++ b/data/custodian/CZ-53-CHO-L-OKUUC.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHO-L-OKUUC - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHO-L-OKUUC valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHO-L-OKUUC ghcid_numeric: 11512944180843790075 valid_from: '2025-12-08T11:21:31.213930+00:00' @@ -210,3 +211,22 @@ location: postal_code: 565 01 street_address: Újezd u Chocně normalization_timestamp: '2025-12-09T10:53:33.381310+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:36:25.545894+00:00' + source_url: https://knihovnaujezduchocne.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaujezduchocne.webk.cz/themes/cbdb-klasicky/default/logo1.png + source_url: https://knihovnaujezduchocne.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T16:36:25.545894+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-53-CHR-L-MKC.yaml b/data/custodian/CZ-53-CHR-L-MKC.yaml index e38b1f2958..da55d262a1 100644 --- a/data/custodian/CZ-53-CHR-L-MKC.yaml +++ b/data/custodian/CZ-53-CHR-L-MKC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHR-L-MKC - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHR-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHR-L-MKC ghcid_numeric: 10393454585563758343 valid_from: '2025-12-06T23:37:17.418467+00:00' @@ -236,3 +237,22 @@ location: postal_code: 537 49 street_address: Filištínská 36 normalization_timestamp: '2025-12-09T10:53:33.466986+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:36:45.859338+00:00' + source_url: https://katalog.knihovna-cr.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-cr.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-cr.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:36:45.859338+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-53-CHR-L-OKR.yaml b/data/custodian/CZ-53-CHR-L-OKR.yaml index 3a3b96557d..01e30ef427 100644 --- a/data/custodian/CZ-53-CHR-L-OKR.yaml +++ b/data/custodian/CZ-53-CHR-L-OKR.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHR-L-OKR - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHR-L-OKR valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHR-L-OKR ghcid_numeric: 15974905546139332871 valid_from: '2025-12-08T11:21:39.411235+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 51 street_address: Řestoky č.p.18 normalization_timestamp: '2025-12-09T10:53:33.517188+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:36:55.590930+00:00' + source_url: https://www.restoky.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.restoky.cz/skins/restoky.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.restoky.cz + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:36:55.590930+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-53-CHR-L-OKVB.yaml b/data/custodian/CZ-53-CHR-L-OKVB.yaml index 40de2fdce7..2d0067901d 100644 --- a/data/custodian/CZ-53-CHR-L-OKVB.yaml +++ b/data/custodian/CZ-53-CHR-L-OKVB.yaml @@ -209,3 +209,22 @@ location: postal_code: 538 51 street_address: Bítovany 19 normalization_timestamp: '2025-12-09T10:53:33.543399+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:37:01.097986+00:00' + source_url: https://bitovany-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bitovany-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://bitovany-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:37:01.097986+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-53-CHR-L-OKVRL.yaml b/data/custodian/CZ-53-CHR-L-OKVRL.yaml index 4bcbf87190..5817807eb6 100644 --- a/data/custodian/CZ-53-CHR-L-OKVRL.yaml +++ b/data/custodian/CZ-53-CHR-L-OKVRL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHR-L-OKVRL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHR-L-OKVRL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHR-L-OKVRL ghcid_numeric: 14411891856885641528 valid_from: '2025-12-06T23:37:40.211341+00:00' @@ -205,3 +206,22 @@ location: postal_code: 537 01 street_address: Rabštejnská Lhota 130 normalization_timestamp: '2025-12-09T10:53:33.570257+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:37:05.763996+00:00' + source_url: https://rabstejnskalhota-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rabstejnskalhota-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://rabstejnskalhota-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:37:05.763996+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-53-CHR-L-OKVS.yaml b/data/custodian/CZ-53-CHR-L-OKVS.yaml index cedbae7700..8f4a7b2fde 100644 --- a/data/custodian/CZ-53-CHR-L-OKVS.yaml +++ b/data/custodian/CZ-53-CHR-L-OKVS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHR-L-OKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHR-L-OKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHR-L-OKVS ghcid_numeric: 7709147581229891472 valid_from: '2025-12-06T23:37:40.214089+00:00' @@ -205,3 +206,22 @@ location: postal_code: 537 01 street_address: Sobětuchy - Pouchobrady 4 normalization_timestamp: '2025-12-09T10:53:33.595374+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:37:10.868546+00:00' + source_url: https://sobetuchy-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sobetuchy-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://sobetuchy-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:37:10.868546+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-53-CHR-L-OKVT-obecni_knihovna_v_tribrichach.yaml b/data/custodian/CZ-53-CHR-L-OKVT-obecni_knihovna_v_tribrichach.yaml index 26bc47636e..f87a731805 100644 --- a/data/custodian/CZ-53-CHR-L-OKVT-obecni_knihovna_v_tribrichach.yaml +++ b/data/custodian/CZ-53-CHR-L-OKVT-obecni_knihovna_v_tribrichach.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHR-L-OKVT-obecni_knihovna_v_tribrichach - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHR-L-OKVT-obecni_knihovna_v_tribrichach valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHR-L-OKVT-obecni_knihovna_v_tribrichach ghcid_numeric: 7257808958644009777 valid_from: '2025-12-06T23:37:40.217170+00:00' @@ -205,3 +206,32 @@ location: postal_code: 537 01 street_address: Třibřichy 34 normalization_timestamp: '2025-12-09T10:53:33.648265+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:37:21.386784+00:00' + source_url: https://obectribrichy.cz/w/knihovna + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://obectribrichy.cz/w/wp-content/uploads/2020/02/ttt.gif + source_url: https://obectribrichy.cz/w/knihovna + css_selector: '#header > div.header__inner > div.header__content:nth-of-type(2) + > div.lsvr-container > div.header__content-inner > div.header-logo > a.header-logo__link + > img.header-logo__image' + retrieved_on: '2025-12-26T16:37:21.386784+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Obec Třibřichy + - claim_type: favicon_url + claim_value: https://obectribrichy.cz/w/wp-content/uploads/2020/02/ttt-1-150x150.gif + source_url: https://obectribrichy.cz/w/knihovna + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-26T16:37:21.386784+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/CZ-53-CHR-M-RMVC.yaml b/data/custodian/CZ-53-CHR-M-RMVC.yaml index b29de05cf6..4bb4dd451b 100644 --- a/data/custodian/CZ-53-CHR-M-RMVC.yaml +++ b/data/custodian/CZ-53-CHR-M-RMVC.yaml @@ -282,3 +282,32 @@ location: postal_code: 537 01 street_address: Široká 86 normalization_timestamp: '2025-12-09T10:53:33.717393+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:39:40.541610+00:00' + source_url: https://katalog.muzeumcr.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://katalog.muzeumcr.cz/custom/design/logo_cr.png + source_url: https://katalog.muzeumcr.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 > div > a > img' + retrieved_on: '2025-12-26T16:39:40.541610+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Stránky knihovny + - claim_type: favicon_url + claim_value: https://katalog.muzeumcr.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.muzeumcr.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T16:39:40.541610+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-53-CHR-O-SOAVHKSOAC.yaml b/data/custodian/CZ-53-CHR-O-SOAVHKSOAC.yaml index 1d9791282c..9c4c4400cc 100644 --- a/data/custodian/CZ-53-CHR-O-SOAVHKSOAC.yaml +++ b/data/custodian/CZ-53-CHR-O-SOAVHKSOAC.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CHR-O-SOAVHKSOAC - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CHR-O-SOAVHKSOAC valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CHR-O-SOAVHKSOAC ghcid_numeric: 3131068159857103851 valid_from: '2025-12-06T23:37:17.399598+00:00' @@ -220,3 +221,33 @@ location: postal_code: 537 01 street_address: Filištínská 37 normalization_timestamp: '2025-12-09T10:53:33.745662+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:39:52.810755+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: '2025-12-26T16:39:52.810755+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: '2025-12-26T16:39:52.810755+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-53-COT-L-MKC.yaml b/data/custodian/CZ-53-COT-L-MKC.yaml index 4338d28e60..bd74c341e1 100644 --- a/data/custodian/CZ-53-COT-L-MKC.yaml +++ b/data/custodian/CZ-53-COT-L-MKC.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-COT-L-MKC - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-COT-L-MKC valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-COT-L-MKC ghcid_numeric: 9895710380780670495 valid_from: '2025-12-06T23:37:40.854054+00:00' @@ -201,3 +202,22 @@ location: postal_code: 561 32 street_address: Cotkytle 3 normalization_timestamp: '2025-12-09T10:53:33.816359+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:40:48.781790+00:00' + source_url: https://knihovnacotkytle.webk.cz/pages/uvod.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnacotkytle.webk.cz/themes/cbdb-klasicky/default/logo1.png + source_url: https://knihovnacotkytle.webk.cz/pages/uvod.html + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T16:40:48.781790+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-53-CTE-L-OKVC.yaml b/data/custodian/CZ-53-CTE-L-OKVC.yaml index 0266334abd..ddc0dd6bc4 100644 --- a/data/custodian/CZ-53-CTE-L-OKVC.yaml +++ b/data/custodian/CZ-53-CTE-L-OKVC.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-CTE-L-OKVC - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-CTE-L-OKVC valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-CTE-L-OKVC ghcid_numeric: 10632537789280019419 valid_from: '2025-12-06T23:37:40.018509+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 25 street_address: Ctětín 23 normalization_timestamp: '2025-12-09T10:53:33.841030+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:41:21.122833+00:00' + source_url: https://ctetin.cz/p/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://admin-storage.munipolis.com/ctetin/logo.png?v=1713254402 + source_url: https://ctetin.cz/p/knihovna + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-26T16:41:21.122833+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-53-DAM-L-OKL.yaml b/data/custodian/CZ-53-DAM-L-OKL.yaml index a7c839cc58..2e14094697 100644 --- a/data/custodian/CZ-53-DAM-L-OKL.yaml +++ b/data/custodian/CZ-53-DAM-L-OKL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DAM-L-OKL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DAM-L-OKL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DAM-L-OKL ghcid_numeric: 14763259894634815976 valid_from: '2025-12-06T23:37:40.883363+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 23 street_address: Luková 97 normalization_timestamp: '2025-12-09T10:53:33.866559+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:41:46.336185+00:00' + source_url: https://www.lukova.cz/sluzby/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lukova.cz/skins/lukova.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.lukova.cz/sluzby/obecni-knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:41:46.336185+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-53-DAS-L-MKD.yaml b/data/custodian/CZ-53-DAS-L-MKD.yaml index d4bb591c18..d63e519226 100644 --- a/data/custodian/CZ-53-DAS-L-MKD.yaml +++ b/data/custodian/CZ-53-DAS-L-MKD.yaml @@ -36,13 +36,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DAS-L-MKD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DAS-L-MKD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DAS-L-MKD ghcid_numeric: 11758082967333810413 valid_from: '2025-12-06T23:37:22.408789+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 Dašice @@ -211,3 +212,22 @@ location: geocoding_timestamp: '2025-12-09T21:40:11.736949+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Dašice +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:42:06.709714+00:00' + source_url: https://kkpce.tritius.cz/library/dasice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kkpce.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kkpce.tritius.cz/library/dasice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:42:06.709714+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-53-DLO-L-OKDT.yaml b/data/custodian/CZ-53-DLO-L-OKDT.yaml index 1829370531..8faa741bc0 100644 --- a/data/custodian/CZ-53-DLO-L-OKDT.yaml +++ b/data/custodian/CZ-53-DLO-L-OKDT.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DLO-L-OKDT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DLO-L-OKDT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DLO-L-OKDT ghcid_numeric: 5635016418874975600 valid_from: '2025-12-06T23:37:40.886317+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 17 street_address: Dlouhá Třebová 235 normalization_timestamp: '2025-12-09T10:53:33.918391+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:42:28.164801+00:00' + source_url: https://vufind.knihovna-uo.cz/dtrebova + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/dtrebova/themes/bootprint3Rbit-dtrebova/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/dtrebova + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:42:28.164801+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-53-DOL-L-CSK.yaml b/data/custodian/CZ-53-DOL-L-CSK.yaml index 3c37103fe4..d2c41553d2 100644 --- a/data/custodian/CZ-53-DOL-L-CSK.yaml +++ b/data/custodian/CZ-53-DOL-L-CSK.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DOL-L-CSK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DOL-L-CSK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DOL-L-CSK ghcid_numeric: 16716089705717947850 valid_from: '2025-12-06T23:37:20.530581+00:00' @@ -213,3 +214,28 @@ location: country: *id007 postal_code: 561 02 normalization_timestamp: '2025-12-09T10:53:33.944148+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:42:50.982791+00:00' + source_url: https://www.contipro.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.contipro.cz/safari-pinned-tab.svg + source_url: https://www.contipro.cz + css_selector: '[document] > html > head > link:nth-of-type(30)' + retrieved_on: '2025-12-26T16:42:50.982791+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.contipro.cz/images/2017/05/31/1200x628_contipro_home.png + source_url: https://www.contipro.cz + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-26T16:42:50.982791+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/CZ-53-DOL-L-KDU.yaml b/data/custodian/CZ-53-DOL-L-KDU.yaml index 91b5cbab89..0cf62c1fce 100644 --- a/data/custodian/CZ-53-DOL-L-KDU.yaml +++ b/data/custodian/CZ-53-DOL-L-KDU.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DOL-L-KDU - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DOL-L-KDU valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DOL-L-KDU ghcid_numeric: 15913415106573772056 valid_from: '2025-12-08T11:21:24.594485+00:00' @@ -223,3 +224,22 @@ location: country: *id007 postal_code: 569 61 normalization_timestamp: '2025-12-09T10:53:33.971570+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:43:00.907708+00:00' + source_url: https://www.dolniujezd.cz/knihovna/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.dolniujezd.cz/favicon.ico + source_url: https://www.dolniujezd.cz/knihovna/knihovna + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:43:00.907708+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-53-DOL-L-OKDD.yaml b/data/custodian/CZ-53-DOL-L-OKDD.yaml index e1f5a5fd37..a784be48a5 100644 --- a/data/custodian/CZ-53-DOL-L-OKDD.yaml +++ b/data/custodian/CZ-53-DOL-L-OKDD.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DOL-L-OKDD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DOL-L-OKDD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DOL-L-OKDD ghcid_numeric: 3004024359035222107 valid_from: '2025-12-06T23:37:40.892159+00:00' @@ -208,3 +209,22 @@ location: postal_code: 561 02 street_address: Dolní Dobrouč 62 normalization_timestamp: '2025-12-09T10:53:34.024152+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:43:22.165762+00:00' + source_url: https://vufind.knihovna-uo.cz/ddobrouc + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/ddobrouc/themes/bootprint3Rbit-ddobrouc/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/ddobrouc + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:43:22.165762+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-53-DOL-L-OKHD.yaml b/data/custodian/CZ-53-DOL-L-OKHD.yaml index 85212310db..2b7ed4427e 100644 --- a/data/custodian/CZ-53-DOL-L-OKHD.yaml +++ b/data/custodian/CZ-53-DOL-L-OKHD.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DOL-L-OKHD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DOL-L-OKHD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DOL-L-OKHD ghcid_numeric: 744272118484068514 valid_from: '2025-12-06T23:37:40.895406+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 02 street_address: Horní Dobrouč 2 normalization_timestamp: '2025-12-09T10:53:34.080077+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:43:37.406988+00:00' + source_url: https://vufind.knihovna-uo.cz/hdobrouc + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/hdobrouc/themes/bootprint3Rbit-hdobrouc/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/hdobrouc + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:43:37.406988+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-53-DRE-L-MKVD.yaml b/data/custodian/CZ-53-DRE-L-MKVD.yaml index 6b9f3018b3..0e32858ae7 100644 --- a/data/custodian/CZ-53-DRE-L-MKVD.yaml +++ b/data/custodian/CZ-53-DRE-L-MKVD.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DRE-L-MKVD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DRE-L-MKVD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DRE-L-MKVD ghcid_numeric: 2876261736092042932 valid_from: '2025-12-06T23:37:40.024940+00:00' @@ -200,3 +201,22 @@ location: postal_code: 538 31 street_address: Dřenice 14 normalization_timestamp: '2025-12-09T10:53:34.152731+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:44:05.427852+00:00' + source_url: https://www.drenice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.drenice.cz/image.php?nid=20385&oid=9188341&width=32 + source_url: https://www.drenice.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T16:44:05.427852+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-53-DZB-L-OKVD.yaml b/data/custodian/CZ-53-DZB-L-OKVD.yaml index cecb4cd415..0cfcda299c 100644 --- a/data/custodian/CZ-53-DZB-L-OKVD.yaml +++ b/data/custodian/CZ-53-DZB-L-OKVD.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-DZB-L-OKVD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-DZB-L-OKVD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-DZB-L-OKVD ghcid_numeric: 12149591178488935429 valid_from: '2025-12-06T23:37:40.901683+00:00' @@ -202,3 +203,22 @@ location: postal_code: 566 01 street_address: Džbánov 15 normalization_timestamp: '2025-12-09T10:53:34.211713+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:44:08.907293+00:00' + source_url: https://vufind.knihovna-uo.cz/dzbanov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/dzbanov/themes/bootprint3Rbit-dzbanov/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/dzbanov + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T16:44:08.907293+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-53-HER-L-MKVHM.yaml b/data/custodian/CZ-53-HER-L-MKVHM.yaml index bf1099efa2..a8ac0cd024 100644 --- a/data/custodian/CZ-53-HER-L-MKVHM.yaml +++ b/data/custodian/CZ-53-HER-L-MKVHM.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HER-L-MKVHM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HER-L-MKVHM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HER-L-MKVHM ghcid_numeric: 6909255962548578507 valid_from: '2025-12-06T23:37:17.425659+00:00' @@ -223,3 +224,22 @@ location: postal_code: 538 03 street_address: nám. Míru 288 normalization_timestamp: '2025-12-09T10:53:34.246840+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:44:21.492721+00:00' + source_url: https://katalog.knihovna-hm.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-hm.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-hm.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:44:21.492721+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-53-HER-L-OKKUHM.yaml b/data/custodian/CZ-53-HER-L-OKKUHM.yaml index 64f40cbe98..3063185973 100644 --- a/data/custodian/CZ-53-HER-L-OKKUHM.yaml +++ b/data/custodian/CZ-53-HER-L-OKKUHM.yaml @@ -206,3 +206,22 @@ location: postal_code: 538 03 street_address: Kostelec u Heřmanova Městce 64 normalization_timestamp: '2025-12-09T10:53:34.275579+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:44:26.738401+00:00' + source_url: https://kostelechm-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kostelechm-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://kostelechm-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:44:26.738401+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-53-HER-L-OKVL.yaml b/data/custodian/CZ-53-HER-L-OKVL.yaml index 8271458248..1467d7161d 100644 --- a/data/custodian/CZ-53-HER-L-OKVL.yaml +++ b/data/custodian/CZ-53-HER-L-OKVL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HER-L-OKVL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HER-L-OKVL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HER-L-OKVL ghcid_numeric: 6778987360976720417 valid_from: '2025-12-06T23:37:40.047561+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 03 street_address: Licomělice 13 normalization_timestamp: '2025-12-09T10:53:34.356660+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:44:47.186159+00:00' + source_url: https://www.nacesice.eu/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nacesice.eu/skins/nacesice.eu_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.nacesice.eu/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:44:47.186159+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-53-HER-L-OKVM.yaml b/data/custodian/CZ-53-HER-L-OKVM.yaml index 868251fd0d..dbfed6ecd6 100644 --- a/data/custodian/CZ-53-HER-L-OKVM.yaml +++ b/data/custodian/CZ-53-HER-L-OKVM.yaml @@ -206,3 +206,22 @@ location: postal_code: 538 03 street_address: Míčov 32 normalization_timestamp: '2025-12-09T10:53:34.382010+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:44:54.926967+00:00' + source_url: https://micov-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://micov-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://micov-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:44:54.926967+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-53-HER-L-OKVU.yaml b/data/custodian/CZ-53-HER-L-OKVU.yaml index 6145885150..14fd42018c 100644 --- a/data/custodian/CZ-53-HER-L-OKVU.yaml +++ b/data/custodian/CZ-53-HER-L-OKVU.yaml @@ -211,3 +211,22 @@ location: postal_code: 538 03 street_address: Úherčice 32 normalization_timestamp: '2025-12-09T10:53:34.406976+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:45:03.772143+00:00' + source_url: https://www.uhercice.com/o-nas/sluzby/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.uhercice.com/skins/uhercice.com_lego2/favicons/apple-touch-icon.png + source_url: https://www.uhercice.com/o-nas/sluzby/knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T16:45:03.772143+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-53-HER-L-OKVVP.yaml b/data/custodian/CZ-53-HER-L-OKVVP.yaml index b3a131a712..27e5427a3e 100644 --- a/data/custodian/CZ-53-HER-L-OKVVP.yaml +++ b/data/custodian/CZ-53-HER-L-OKVVP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HER-L-OKVVP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HER-L-OKVVP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HER-L-OKVVP ghcid_numeric: 17807257253766689054 valid_from: '2025-12-06T23:37:40.038321+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 03 street_address: Vápenný Podol 74 normalization_timestamp: '2025-12-09T10:53:34.440845+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:45:06.340532+00:00' + source_url: https://vapennypodol-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vapennypodol-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://vapennypodol-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:45:06.340532+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-53-HLI-L-MKH.yaml b/data/custodian/CZ-53-HLI-L-MKH.yaml index 9d7e5914bf..807883994f 100644 --- a/data/custodian/CZ-53-HLI-L-MKH.yaml +++ b/data/custodian/CZ-53-HLI-L-MKH.yaml @@ -254,3 +254,22 @@ location: postal_code: 539 01 street_address: Adámkova tř. 554 normalization_timestamp: '2025-12-09T10:53:34.498563+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:45:19.043470+00:00' + source_url: https://katalog.knihovna-hlinsko.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-hlinsko.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-hlinsko.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T16:45:19.043470+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-53-HLI-L-MKV.yaml b/data/custodian/CZ-53-HLI-L-MKV.yaml index 8725fe68b5..5349892c40 100644 --- a/data/custodian/CZ-53-HLI-L-MKV.yaml +++ b/data/custodian/CZ-53-HLI-L-MKV.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HLI-L-MKV - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HLI-L-MKV valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HLI-L-MKV ghcid_numeric: 15473199872677190465 valid_from: '2025-12-06T23:37:40.069839+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 01 street_address: Všeradov 39 normalization_timestamp: '2025-12-09T10:53:34.529623+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T16:45:32.860361+00:00' + source_url: https://vseradov.cz/spol/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vseradov-cz.hqv.cz/favicon/safari-pinned-tab.svg + source_url: https://vseradov.cz/spol/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T16:45:32.860361+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-53-HLI-L-OKJ.yaml b/data/custodian/CZ-53-HLI-L-OKJ.yaml index 3dac27a501..e8492594c9 100644 --- a/data/custodian/CZ-53-HLI-L-OKJ.yaml +++ b/data/custodian/CZ-53-HLI-L-OKJ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HLI-L-OKJ - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HLI-L-OKJ valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HLI-L-OKJ ghcid_numeric: 4331794302067966721 valid_from: '2025-12-06T23:37:40.072989+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 01 street_address: Jeníkov 7 normalization_timestamp: '2025-12-09T10:53:34.541445+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:33:22.081897+00:00' + source_url: https://www.obec-jenikov.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-jenikov.cz/skins/obec-jenikov.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.obec-jenikov.cz/obec/obecni-knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T17:33:22.081897+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-53-HLI-L-OKM.yaml b/data/custodian/CZ-53-HLI-L-OKM.yaml index e258cd0329..e943ccb42c 100644 --- a/data/custodian/CZ-53-HLI-L-OKM.yaml +++ b/data/custodian/CZ-53-HLI-L-OKM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HLI-L-OKM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HLI-L-OKM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HLI-L-OKM ghcid_numeric: 9626728852031365138 valid_from: '2025-12-06T23:37:40.164609+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 01 street_address: Mrákotín 52 normalization_timestamp: '2025-12-09T10:53:34.557424+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:33:39.082991+00:00' + source_url: https://mrakotin-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mrakotin-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://mrakotin-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:33:39.082991+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-53-HLI-L-OKS.yaml b/data/custodian/CZ-53-HLI-L-OKS.yaml index 56bcfa3364..73cc455615 100644 --- a/data/custodian/CZ-53-HLI-L-OKS.yaml +++ b/data/custodian/CZ-53-HLI-L-OKS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HLI-L-OKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HLI-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HLI-L-OKS ghcid_numeric: 15751885649957154568 valid_from: '2025-12-06T23:37:40.076341+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 01 street_address: Studnice 105 normalization_timestamp: '2025-12-09T10:53:34.577421+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:34:17.954555+00:00' + source_url: https://studnice-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://studnice-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://studnice-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:34:17.954555+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-53-HLI-L-OKVP.yaml b/data/custodian/CZ-53-HLI-L-OKVP.yaml index 15a4000124..15ec7cfab2 100644 --- a/data/custodian/CZ-53-HLI-L-OKVP.yaml +++ b/data/custodian/CZ-53-HLI-L-OKVP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HLI-L-OKVP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HLI-L-OKVP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HLI-L-OKVP ghcid_numeric: 18303434601055813518 valid_from: '2025-12-06T23:37:40.083689+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 01 street_address: Pokřikov 93 normalization_timestamp: '2025-12-09T10:53:34.589741+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:34:19.798410+00:00' + source_url: https://www.pokrikov.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pokrikov.cz/image.php?nid=20334&oid=8948177&width=32 + source_url: https://www.pokrikov.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-26T17:34:19.798410+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-53-HLI-M-MGH.yaml b/data/custodian/CZ-53-HLI-M-MGH.yaml index daa7d14df1..d7ced332cc 100644 --- a/data/custodian/CZ-53-HLI-M-MGH.yaml +++ b/data/custodian/CZ-53-HLI-M-MGH.yaml @@ -247,3 +247,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Muzeum a galerie Hlinsko official youtube_search_timestamp: '2025-12-09T09:34:15.742091+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:34:47.404206+00:00' + source_url: http://www.mmghlinsko.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mmghlinsko.cz/wp-content/uploads/2025/11/cropped-favicon-mmg-180x180.png + source_url: http://www.mmghlinsko.cz + css_selector: '[document] > html.html > head > link:nth-of-type(44)' + retrieved_on: '2025-12-26T17:34:47.404206+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mmghlinsko.cz/wp-content/uploads/2025/07/coverphoto-mmg.jpg + source_url: http://www.mmghlinsko.cz + css_selector: '[document] > html.html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-26T17:34:47.404206+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-53-HOR-L-MKHJ.yaml b/data/custodian/CZ-53-HOR-L-MKHJ.yaml index 9dd794a76f..00f67f345d 100644 --- a/data/custodian/CZ-53-HOR-L-MKHJ.yaml +++ b/data/custodian/CZ-53-HOR-L-MKHJ.yaml @@ -211,3 +211,22 @@ location: postal_code: 533 74 street_address: nám. Komenského 114 normalization_timestamp: '2025-12-09T10:53:34.726463+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:35:45.385929+00:00' + source_url: https://www.hornijeleni.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hornijeleni.cz/images/favicon/apple-icon-180x180.png + source_url: https://www.hornijeleni.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(21)' + retrieved_on: '2025-12-26T17:35:45.385929+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-53-HOR-L-OKHC.yaml b/data/custodian/CZ-53-HOR-L-OKHC.yaml index 0603698542..a0b110abf3 100644 --- a/data/custodian/CZ-53-HOR-L-OKHC.yaml +++ b/data/custodian/CZ-53-HOR-L-OKHC.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HOR-L-OKHC - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HOR-L-OKHC valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HOR-L-OKHC ghcid_numeric: 730310667516901430 valid_from: '2025-12-08T11:21:29.169910+00:00' @@ -210,3 +211,22 @@ location: postal_code: 561 56 street_address: Horní Čermná 94 normalization_timestamp: '2025-12-09T10:53:34.753211+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:36:06.937564+00:00' + source_url: https://hornicermna.cz/default/default/12055_knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hornicermna.cz/files/hornicermna/logo/apple-touch-icon.png + source_url: https://hornicermna.cz/default/default/12055_knihovna + css_selector: '[document] > html.show--consent > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T17:36:06.937564+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-53-HOR-L-OKVHUL.yaml b/data/custodian/CZ-53-HOR-L-OKVHUL.yaml index 2a63017477..bd86f63b62 100644 --- a/data/custodian/CZ-53-HOR-L-OKVHUL.yaml +++ b/data/custodian/CZ-53-HOR-L-OKVHUL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HOR-L-OKVHUL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HOR-L-OKVHUL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HOR-L-OKVHUL ghcid_numeric: 1356574949333617135 valid_from: '2025-12-06T23:37:40.571224+00:00' @@ -205,3 +206,22 @@ location: postal_code: 570 01 street_address: Horky 55 normalization_timestamp: '2025-12-09T10:53:34.779463+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:36:19.001663+00:00' + source_url: https://www.horkyulitomysle.cz/knihovna/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.horkyulitomysle.cz/favicon.ico + source_url: https://www.horkyulitomysle.cz/knihovna/knihovna + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T17:36:19.001663+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-53-HRU-L-OKVHZK.yaml b/data/custodian/CZ-53-HRU-L-OKVHZK.yaml index 2ad1725742..6c0cf9c4f4 100644 --- a/data/custodian/CZ-53-HRU-L-OKVHZK.yaml +++ b/data/custodian/CZ-53-HRU-L-OKVHZK.yaml @@ -36,13 +36,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-HRU-L-OKVHZK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-HRU-L-OKVHZK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-HRU-L-OKVHZK ghcid_numeric: 16138821261233057672 valid_from: '2025-12-06T23:37:43.354858+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: Obecní knihovna v Hrušové - základní knihovna @@ -213,3 +214,22 @@ location: geonames_id: 3074768 geonames_name: Hrušová feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:36:56.430075+00:00' + source_url: http://hrusova.cz/index.php/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://hrusova.cz/templates/hrusova-template/favicon.ico + source_url: http://hrusova.cz/index.php/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T17:36:56.430075+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-53-JAB-L-MKJNO.yaml b/data/custodian/CZ-53-JAB-L-MKJNO.yaml index 0798406901..6782ef5f65 100644 --- a/data/custodian/CZ-53-JAB-L-MKJNO.yaml +++ b/data/custodian/CZ-53-JAB-L-MKJNO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JAB-L-MKJNO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JAB-L-MKJNO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JAB-L-MKJNO ghcid_numeric: 6344401270578395388 valid_from: '2025-12-06T23:37:20.580552+00:00' @@ -226,3 +227,22 @@ location: postal_code: 561 64 street_address: Aloise Hanuše 85 normalization_timestamp: '2025-12-09T10:53:34.931751+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:37:16.405755+00:00' + source_url: https://katalog.knihovnajablonne.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnajablonne.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovnajablonne.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:37:16.405755+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-53-JAB-L-OKVS.yaml b/data/custodian/CZ-53-JAB-L-OKVS.yaml index 7882c0c129..0d6347a73b 100644 --- a/data/custodian/CZ-53-JAB-L-OKVS.yaml +++ b/data/custodian/CZ-53-JAB-L-OKVS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JAB-L-OKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JAB-L-OKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JAB-L-OKVS ghcid_numeric: 12089993280230287885 valid_from: '2025-12-06T23:37:40.946403+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 64 street_address: Studené 15 normalization_timestamp: '2025-12-09T10:53:35.026448+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:37:34.915425+00:00' + source_url: https://studene.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://studene.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://studene.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:37:34.915425+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-53-JAM-L-MLKJNO.yaml b/data/custodian/CZ-53-JAM-L-MLKJNO.yaml index 48fc4d7cb4..b11ca4d587 100644 --- a/data/custodian/CZ-53-JAM-L-MLKJNO.yaml +++ b/data/custodian/CZ-53-JAM-L-MLKJNO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JAM-L-MLKJNO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JAM-L-MLKJNO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JAM-L-MLKJNO ghcid_numeric: 5863751379950441146 valid_from: '2025-12-06T23:37:40.955559+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 65 street_address: Jamné nad Orlicí 280 normalization_timestamp: '2025-12-09T10:53:35.096936+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:37:45.638883+00:00' + source_url: https://jamne.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jamne.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://jamne.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:37:45.638883+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-53-JAR-L-OKJ.yaml b/data/custodian/CZ-53-JAR-L-OKJ.yaml index df6d96eb0f..c154562963 100644 --- a/data/custodian/CZ-53-JAR-L-OKJ.yaml +++ b/data/custodian/CZ-53-JAR-L-OKJ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JAR-L-OKJ - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JAR-L-OKJ valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JAR-L-OKJ ghcid_numeric: 10530619438099866273 valid_from: '2025-12-06T23:37:40.581365+00:00' @@ -213,3 +214,22 @@ location: postal_code: 569 44 street_address: Jaroměřice 200 normalization_timestamp: '2025-12-09T10:53:35.235792+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:37:59.689584+00:00' + source_url: https://knihovna.jevicko.cz/library/Jaromerice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.jevicko.cz/apple-touch-icon-180x180.png + source_url: https://knihovna.jevicko.cz/library/Jaromerice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T17:37:59.689584+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-53-JAR-L-OKVJ.yaml b/data/custodian/CZ-53-JAR-L-OKVJ.yaml index d1b584af02..b245afea9d 100644 --- a/data/custodian/CZ-53-JAR-L-OKVJ.yaml +++ b/data/custodian/CZ-53-JAR-L-OKVJ.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JAR-L-OKVJ - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JAR-L-OKVJ valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JAR-L-OKVJ ghcid_numeric: 10265563383519615045 valid_from: '2025-12-06T23:37:40.584252+00:00' @@ -212,3 +213,22 @@ location: postal_code: 569 66 street_address: Jarošov 96 normalization_timestamp: '2025-12-09T10:53:35.286267+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:38:24.954056+00:00' + source_url: http://www.obecjarosov.cz/obec-jarosov/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.obecjarosov.cz/favicon.ico + source_url: http://www.obecjarosov.cz/obec-jarosov/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T17:38:24.954056+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-53-JEN-L-MLKVJ.yaml b/data/custodian/CZ-53-JEN-L-MLKVJ.yaml index 70ad929623..07aeb0dce5 100644 --- a/data/custodian/CZ-53-JEN-L-MLKVJ.yaml +++ b/data/custodian/CZ-53-JEN-L-MLKVJ.yaml @@ -206,3 +206,22 @@ location: postal_code: 538 64 street_address: Jenišovice 42 normalization_timestamp: '2025-12-09T10:53:35.315764+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:39:04.469247+00:00' + source_url: https://obecjenisovice.cz/mistni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://obecjenisovice.cz/template/jenisovicenew/favicon.png + source_url: https://obecjenisovice.cz/mistni-knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T17:39:04.469247+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-53-JEV-L-MKJ.yaml b/data/custodian/CZ-53-JEV-L-MKJ.yaml index e92d3b55ee..57d29153ed 100644 --- a/data/custodian/CZ-53-JEV-L-MKJ.yaml +++ b/data/custodian/CZ-53-JEV-L-MKJ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JEV-L-MKJ - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JEV-L-MKJ valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JEV-L-MKJ ghcid_numeric: 10230805493191806051 valid_from: '2025-12-06T23:37:21.092107+00:00' @@ -219,3 +220,22 @@ location: postal_code: 569 43 street_address: U Zámečku 451 normalization_timestamp: '2025-12-09T10:53:35.346093+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:39:20.889834+00:00' + source_url: https://knihovna.jevicko.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.jevicko.cz/apple-touch-icon-180x180.png + source_url: https://knihovna.jevicko.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T17:39:20.889834+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-53-JEV-L-MLKVBUJ.yaml b/data/custodian/CZ-53-JEV-L-MLKVBUJ.yaml index e800e5d50f..b5b08fadf5 100644 --- a/data/custodian/CZ-53-JEV-L-MLKVBUJ.yaml +++ b/data/custodian/CZ-53-JEV-L-MLKVBUJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JEV-L-MLKVBUJ - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JEV-L-MLKVBUJ valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JEV-L-MLKVBUJ ghcid_numeric: 2784342487180611284 valid_from: '2025-12-06T23:37:40.599713+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 43 street_address: Bělá u Jevíčka 7 normalization_timestamp: '2025-12-09T10:53:35.371877+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:39:52.308464+00:00' + source_url: https://knihovna.jevicko.cz/library/BelaUJevicka + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna.jevicko.cz/apple-touch-icon-180x180.png + source_url: https://knihovna.jevicko.cz/library/BelaUJevicka + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T17:39:52.308464+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-53-JEV-L-OKVB.yaml b/data/custodian/CZ-53-JEV-L-OKVB.yaml index a95a0de46b..73f8d05829 100644 --- a/data/custodian/CZ-53-JEV-L-OKVB.yaml +++ b/data/custodian/CZ-53-JEV-L-OKVB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JEV-L-OKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JEV-L-OKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JEV-L-OKVB ghcid_numeric: 17348703284427372564 valid_from: '2025-12-06T23:37:40.596631+00:00' @@ -205,3 +206,23 @@ location: postal_code: 569 43 street_address: Březinky 42 normalization_timestamp: '2025-12-09T10:53:35.421680+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:40:31.228827+00:00' + source_url: https://www.knihovna-jevicko.cz/obecni-knihovna-brezinky + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovna-jevicko.cz/apple-touch-icon.png?v=pgqpaaynm5 + source_url: https://www.knihovna-jevicko.cz/obecni-knihovna-brezinky + css_selector: '[document] > html.fontawesome-i2svg-active.fontawesome-i2svg-complete + > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T17:40:31.228827+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: 5 diff --git a/data/custodian/CZ-53-JEV-L-OKVV.yaml b/data/custodian/CZ-53-JEV-L-OKVV.yaml index 1943896fb7..3cc4d0d310 100644 --- a/data/custodian/CZ-53-JEV-L-OKVV.yaml +++ b/data/custodian/CZ-53-JEV-L-OKVV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-JEV-L-OKVV - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-JEV-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-JEV-L-OKVV ghcid_numeric: 9839053106972806518 valid_from: '2025-12-06T23:37:40.590501+00:00' @@ -206,3 +207,23 @@ location: postal_code: 569 43 street_address: Vysoká 33 normalization_timestamp: '2025-12-09T10:53:35.510915+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:40:52.993544+00:00' + source_url: https://www.knihovna-jevicko.cz/obecni-knihovna-vysoka + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovna-jevicko.cz/apple-touch-icon.png?v=pgqpaaynm5 + source_url: https://www.knihovna-jevicko.cz/obecni-knihovna-vysoka + css_selector: '[document] > html.fontawesome-i2svg-active.fontawesome-i2svg-complete + > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T17:40:52.993544+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: 5 diff --git a/data/custodian/CZ-53-KAM-L-OKVK-obecni_knihovna_v_kamenicne.yaml b/data/custodian/CZ-53-KAM-L-OKVK-obecni_knihovna_v_kamenicne.yaml index 982e0ec4a7..bfac02d1d5 100644 --- a/data/custodian/CZ-53-KAM-L-OKVK-obecni_knihovna_v_kamenicne.yaml +++ b/data/custodian/CZ-53-KAM-L-OKVK-obecni_knihovna_v_kamenicne.yaml @@ -206,3 +206,22 @@ location: postal_code: 564 01 street_address: Kameničná 33 normalization_timestamp: '2025-12-09T10:53:35.542638+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:41:17.357590+00:00' + source_url: https://www.kamenicna.cz/volny-cas/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kamenicna.cz/skins/kamenicna_lego/favicons/safari-pinned-tab.svg + source_url: https://www.kamenicna.cz/volny-cas/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T17:41:17.357590+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-53-KAR-A-SOAK-statni_okresni_archiv_karvina.yaml b/data/custodian/CZ-53-KAR-A-SOAK-statni_okresni_archiv_karvina.yaml index eb2b5e342b..0aaa1bfb62 100644 --- a/data/custodian/CZ-53-KAR-A-SOAK-statni_okresni_archiv_karvina.yaml +++ b/data/custodian/CZ-53-KAR-A-SOAK-statni_okresni_archiv_karvina.yaml @@ -240,3 +240,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Karviná official youtube_search_timestamp: '2025-12-09T09:34:17.783105+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:42:05.936185+00:00' + source_url: http://www.archives.cz/web/soka/karvina/o_archivu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.archives.cz/web/favicon/safari-pinned-tab.svg + source_url: http://www.archives.cz/web/soka/karvina/o_archivu + css_selector: '[document] > html.js.no-touchevents > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T17:42:05.936185+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: 12 diff --git a/data/custodian/CZ-53-KLA-L-OKVKNL.yaml b/data/custodian/CZ-53-KLA-L-OKVKNL.yaml index f2c169ff49..4b34dbb840 100644 --- a/data/custodian/CZ-53-KLA-L-OKVKNL.yaml +++ b/data/custodian/CZ-53-KLA-L-OKVKNL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KLA-L-OKVKNL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KLA-L-OKVKNL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KLA-L-OKVKNL ghcid_numeric: 3921291387545913994 valid_from: '2025-12-06T23:37:43.357586+00:00' @@ -208,3 +209,22 @@ location: postal_code: 533 14 street_address: Kladruby nad Labem 11 normalization_timestamp: '2025-12-09T10:53:35.575259+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:47:36.844222+00:00' + source_url: https://www.kladrubynadlabem.cz/nase-obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kladrubynadlabem.cz/skins/kladrubynadlabem_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.kladrubynadlabem.cz/nase-obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T17:47:36.844222+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-53-KLE-L-OKVK.yaml b/data/custodian/CZ-53-KLE-L-OKVK.yaml index 5aad268c90..c849de1bd9 100644 --- a/data/custodian/CZ-53-KLE-L-OKVK.yaml +++ b/data/custodian/CZ-53-KLE-L-OKVK.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KLE-L-OKVK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KLE-L-OKVK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KLE-L-OKVK ghcid_numeric: 10931121283918164147 valid_from: '2025-12-06T23:37:24.950439+00:00' @@ -206,3 +207,22 @@ location: country: *id005 postal_code: 538 03 normalization_timestamp: '2025-12-09T10:53:35.608414+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:48:42.060963+00:00' + source_url: http://www.klesice.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.klesice.knihovna.cz/favicon.svg + source_url: http://www.klesice.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T17:48:42.060963+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-53-KOC-L-MKVK.yaml b/data/custodian/CZ-53-KOC-L-MKVK.yaml index c0126b8dac..612ca9a673 100644 --- a/data/custodian/CZ-53-KOC-L-MKVK.yaml +++ b/data/custodian/CZ-53-KOC-L-MKVK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KOC-L-MKVK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KOC-L-MKVK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KOC-L-MKVK ghcid_numeric: 15453640845070242017 valid_from: '2025-12-06T23:37:40.121629+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 61 street_address: Kočí 98 normalization_timestamp: '2025-12-09T10:53:35.635561+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:49:24.959913+00:00' + source_url: https://www.obec-koci.cz/volny-cas/knihovna-a-kavarna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-koci.cz/skins/koci/favicons/safari-pinned-tab.svg + source_url: https://www.obec-koci.cz/volny-cas/knihovna-a-kavarna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T17:49:24.959913+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-53-KOR-L-MKVK.yaml b/data/custodian/CZ-53-KOR-L-MKVK.yaml index febbd5249e..0db1e82d61 100644 --- a/data/custodian/CZ-53-KOR-L-MKVK.yaml +++ b/data/custodian/CZ-53-KOR-L-MKVK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KOR-L-MKVK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KOR-L-MKVK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KOR-L-MKVK ghcid_numeric: 288155251415668690 valid_from: '2025-12-06T23:37:40.618027+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 93 street_address: Korouhev 234 normalization_timestamp: '2025-12-09T10:53:35.668984+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:49:56.143905+00:00' + source_url: http://korouhev.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://korouhev.knihovna.cz/favicon.svg + source_url: http://korouhev.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T17:49:56.143905+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-53-KRA-L-MKK.yaml b/data/custodian/CZ-53-KRA-L-MKK.yaml index d47dd80944..26ab81cfae 100644 --- a/data/custodian/CZ-53-KRA-L-MKK.yaml +++ b/data/custodian/CZ-53-KRA-L-MKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KRA-L-MKK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KRA-L-MKK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KRA-L-MKK ghcid_numeric: 1504623725981707365 valid_from: '2025-12-06T23:37:20.559269+00:00' @@ -225,3 +226,22 @@ location: postal_code: 561 69 street_address: Velké náměstí 273 normalization_timestamp: '2025-12-09T10:53:35.707642+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:50:29.029135+00:00' + source_url: https://katalog.knihovnakraliky.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnakraliky.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovnakraliky.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:50:29.029135+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-53-KRA-L-MKVDM.yaml b/data/custodian/CZ-53-KRA-L-MKVDM.yaml index c7020b690a..f62949734f 100644 --- a/data/custodian/CZ-53-KRA-L-MKVDM.yaml +++ b/data/custodian/CZ-53-KRA-L-MKVDM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KRA-L-MKVDM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KRA-L-MKVDM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KRA-L-MKVDM ghcid_numeric: 9014658707707334407 valid_from: '2025-12-06T23:37:40.965383+00:00' @@ -201,3 +202,22 @@ location: postal_code: 561 69 street_address: Dolní Morava 35 normalization_timestamp: '2025-12-09T10:53:35.768456+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:51:26.529227+00:00' + source_url: https://www.obecdolnimorava.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obecdolnimorava.cz/image.php?nid=510&oid=10216477&width=32 + source_url: https://www.obecdolnimorava.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-26T17:51:26.529227+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-53-KRE-L-OKVK.yaml b/data/custodian/CZ-53-KRE-L-OKVK.yaml index 4504e01c1d..ce3f5bfa33 100644 --- a/data/custodian/CZ-53-KRE-L-OKVK.yaml +++ b/data/custodian/CZ-53-KRE-L-OKVK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KRE-L-OKVK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KRE-L-OKVK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KRE-L-OKVK ghcid_numeric: 6285550369185065478 valid_from: '2025-12-06T23:37:40.624185+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 22 street_address: Křenov 26 normalization_timestamp: '2025-12-09T10:53:35.804262+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:51:55.348018+00:00' + source_url: https://krenov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://krenov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://krenov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:51:55.348018+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-53-KRO-L-OKK.yaml b/data/custodian/CZ-53-KRO-L-OKK.yaml index a61c581c47..79b54723e6 100644 --- a/data/custodian/CZ-53-KRO-L-OKK.yaml +++ b/data/custodian/CZ-53-KRO-L-OKK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KRO-L-OKK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KRO-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KRO-L-OKK ghcid_numeric: 4799704520453049634 valid_from: '2025-12-06T23:37:40.124724+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 43 street_address: Krouna 218 normalization_timestamp: '2025-12-09T10:53:35.848772+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:52:23.602119+00:00' + source_url: https://www.krouna.cz/kontakty/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.krouna.cz/skins/krouna_lego/favicons/safari-pinned-tab.svg + source_url: https://www.krouna.cz/kontakty/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T17:52:23.602119+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-53-KUN-L-MKVKNV.yaml b/data/custodian/CZ-53-KUN-L-MKVKNV.yaml index 5e5fc1afe7..cf809f2787 100644 --- a/data/custodian/CZ-53-KUN-L-MKVKNV.yaml +++ b/data/custodian/CZ-53-KUN-L-MKVKNV.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-KUN-L-MKVKNV - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-KUN-L-MKVKNV valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-KUN-L-MKVKNV ghcid_numeric: 10686225992837240929 valid_from: '2025-12-06T23:37:40.630818+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 24 street_address: Nová Ves 93 normalization_timestamp: '2025-12-09T10:53:35.889036+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:52:55.282368+00:00' + source_url: https://novaves-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://novaves-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://novaves-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:52:55.282368+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-53-KUN-L-MLKK.yaml b/data/custodian/CZ-53-KUN-L-MLKK.yaml index 032919b8fb..d3cdbc0d72 100644 --- a/data/custodian/CZ-53-KUN-L-MLKK.yaml +++ b/data/custodian/CZ-53-KUN-L-MLKK.yaml @@ -209,3 +209,22 @@ location: postal_code: 561 81 street_address: Kunvald 40 normalization_timestamp: '2025-12-09T10:53:35.919995+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:53:22.983969+00:00' + source_url: https://www.kunvald.info/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kunvald.info/image.php?nid=18042&oid=7707561 + source_url: https://www.kunvald.info/knihovna + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-26T17:53:22.983969+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-53-LAN-L-MKAS.yaml b/data/custodian/CZ-53-LAN-L-MKAS.yaml index 260b0e5dec..2c21a3c66b 100644 --- a/data/custodian/CZ-53-LAN-L-MKAS.yaml +++ b/data/custodian/CZ-53-LAN-L-MKAS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAN-L-MKAS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAN-L-MKAS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAN-L-MKAS ghcid_numeric: 5705212533309625133 valid_from: '2025-12-06T23:37:40.974171+00:00' @@ -202,3 +203,22 @@ location: postal_code: 563 01 street_address: Anenská Studánka 16 normalization_timestamp: '2025-12-09T10:53:35.949818+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:53:35.696533+00:00' + source_url: https://anenskastudanka.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://anenskastudanka.knihovna.cz/favicon.svg + source_url: https://anenskastudanka.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T17:53:35.696533+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-53-LAN-L-MKL.yaml b/data/custodian/CZ-53-LAN-L-MKL.yaml index 65f63f1a77..98e12fdf3a 100644 --- a/data/custodian/CZ-53-LAN-L-MKL.yaml +++ b/data/custodian/CZ-53-LAN-L-MKL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAN-L-MKL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAN-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAN-L-MKL ghcid_numeric: 2311990769251844603 valid_from: '2025-12-06T23:37:20.565388+00:00' @@ -219,3 +220,22 @@ location: postal_code: 563 01 street_address: nám. A. Jiráska 142 normalization_timestamp: '2025-12-09T10:53:35.980222+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:53:52.224046+00:00' + source_url: https://katalog.knihovna-lanskroun.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-lanskroun.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-lanskroun.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:53:52.224046+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-53-LAN-L-MKS.yaml b/data/custodian/CZ-53-LAN-L-MKS.yaml index aebd45827b..46ca24a402 100644 --- a/data/custodian/CZ-53-LAN-L-MKS.yaml +++ b/data/custodian/CZ-53-LAN-L-MKS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAN-L-MKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAN-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAN-L-MKS ghcid_numeric: 8810096144662487392 valid_from: '2025-12-06T23:37:40.979880+00:00' @@ -201,3 +202,22 @@ location: postal_code: 563 01 street_address: Strážná 21 normalization_timestamp: '2025-12-09T10:53:36.015593+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:54:27.359177+00:00' + source_url: https://www.strazna.cz/organizace/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.strazna.cz/skins/strazna.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.strazna.cz/organizace/knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T17:54:27.359177+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-53-LAN-L-OKK.yaml b/data/custodian/CZ-53-LAN-L-OKK.yaml index 3c0235e3fb..7d4c355eaa 100644 --- a/data/custodian/CZ-53-LAN-L-OKK.yaml +++ b/data/custodian/CZ-53-LAN-L-OKK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAN-L-OKK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAN-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAN-L-OKK ghcid_numeric: 11776197464020137624 valid_from: '2025-12-06T23:37:40.977023+00:00' @@ -201,3 +202,22 @@ location: postal_code: 563 01 street_address: Krasíkov 64 normalization_timestamp: '2025-12-09T10:53:36.046184+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:54:54.270726+00:00' + source_url: https://www.obec-krasikov.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-krasikov.cz/skins/krasikov_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.obec-krasikov.cz/obec/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T17:54:54.270726+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-53-LAN-L-OKL.yaml b/data/custodian/CZ-53-LAN-L-OKL.yaml index e59183fe73..52d17ae6f3 100644 --- a/data/custodian/CZ-53-LAN-L-OKL.yaml +++ b/data/custodian/CZ-53-LAN-L-OKL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAN-L-OKL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAN-L-OKL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAN-L-OKL ghcid_numeric: 4137102185939255064 valid_from: '2025-12-06T23:37:43.560148+00:00' @@ -208,3 +209,22 @@ location: postal_code: 537 01 street_address: Lány 14 normalization_timestamp: '2025-12-09T10:53:36.080546+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:55:07.971011+00:00' + source_url: https://www.obeclany.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obeclany.cz/file.php?nid=683&oid=6804269 + source_url: https://www.obeclany.cz + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-26T17:55:07.971011+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-53-LAN-L-OKZ.yaml b/data/custodian/CZ-53-LAN-L-OKZ.yaml index 6c24c628cb..9844aed302 100644 --- a/data/custodian/CZ-53-LAN-L-OKZ.yaml +++ b/data/custodian/CZ-53-LAN-L-OKZ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAN-L-OKZ - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAN-L-OKZ valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAN-L-OKZ ghcid_numeric: 13239421984127866466 valid_from: '2025-12-08T11:21:28.984424+00:00' @@ -206,3 +207,22 @@ location: postal_code: 563 01 street_address: Žichlínek 208 normalization_timestamp: '2025-12-09T10:53:36.111258+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:55:13.454784+00:00' + source_url: https://knihovnazichlinek.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnazichlinek.webk.cz/themes/cbdb-klasicky/default/logo1.png + source_url: https://knihovnazichlinek.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T17:55:13.454784+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-53-LAZ-L-KIOO.yaml b/data/custodian/CZ-53-LAZ-L-KIOO.yaml index fe099233f5..b397122376 100644 --- a/data/custodian/CZ-53-LAZ-L-KIOO.yaml +++ b/data/custodian/CZ-53-LAZ-L-KIOO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAZ-L-KIOO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAZ-L-KIOO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAZ-L-KIOO ghcid_numeric: 4334232908381482901 valid_from: '2025-12-06T23:37:43.145078+00:00' @@ -209,3 +210,28 @@ location: postal_code: 533 41 street_address: Na Lužci 204 normalization_timestamp: '2025-12-09T10:53:36.195750+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:55:31.439270+00:00' + source_url: https://www.hzscr.cz/institut-ochrany-obyvatelstva.aspx + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hzscr.cz/favicon.ico + source_url: https://www.hzscr.cz/institut-ochrany-obyvatelstva.aspx + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T17:55:31.439270+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/ico + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://hzscr.gov.cz/design/img/logo-sn.jpg + source_url: https://www.hzscr.cz/institut-ochrany-obyvatelstva.aspx + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-26T17:55:31.439270+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-53-LAZ-L-MKLB.yaml b/data/custodian/CZ-53-LAZ-L-MKLB.yaml index 495d6a1b4e..81d806b7c4 100644 --- a/data/custodian/CZ-53-LAZ-L-MKLB.yaml +++ b/data/custodian/CZ-53-LAZ-L-MKLB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAZ-L-MKLB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAZ-L-MKLB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAZ-L-MKLB ghcid_numeric: 2621927140315215253 valid_from: '2025-12-06T23:37:23.059072+00:00' @@ -210,3 +211,22 @@ location: postal_code: 533 41 street_address: Masarykovo nám. 110 normalization_timestamp: '2025-12-09T10:53:36.226709+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:55:47.874217+00:00' + source_url: https://kkpce.tritius.cz/library/bohdanec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kkpce.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kkpce.tritius.cz/library/bohdanec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T17:55:47.874217+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-53-LAZ-L-OKP.yaml b/data/custodian/CZ-53-LAZ-L-OKP.yaml index 770bf0cd2d..2a9d185b81 100644 --- a/data/custodian/CZ-53-LAZ-L-OKP.yaml +++ b/data/custodian/CZ-53-LAZ-L-OKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAZ-L-OKP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAZ-L-OKP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAZ-L-OKP ghcid_numeric: 3665941126712034395 valid_from: '2025-12-06T23:37:40.294443+00:00' @@ -205,3 +206,22 @@ location: postal_code: 533 41 street_address: Přelovice 87 normalization_timestamp: '2025-12-09T10:53:36.289522+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:56:31.022530+00:00' + source_url: https://www.obecprelovice.cz/obecni-knihovna/d-3367/p1=4023 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obecprelovice.cz/html/images/favicon.ico + source_url: https://www.obecprelovice.cz/obecni-knihovna/d-3367/p1=4023 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T17:56:31.022530+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-53-LAZ-L-OKVB.yaml b/data/custodian/CZ-53-LAZ-L-OKVB.yaml index 52c91b76ff..746cba2d14 100644 --- a/data/custodian/CZ-53-LAZ-L-OKVB.yaml +++ b/data/custodian/CZ-53-LAZ-L-OKVB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAZ-L-OKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAZ-L-OKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAZ-L-OKVB ghcid_numeric: 1795480864245772422 valid_from: '2025-12-06T23:37:40.310273+00:00' @@ -205,3 +206,22 @@ location: postal_code: 533 41 street_address: Bukovka 28 normalization_timestamp: '2025-12-09T10:53:36.350160+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:57:15.074038+00:00' + source_url: https://www.bukovka.cz/nase-obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bukovka.cz/skins/bukovka.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.bukovka.cz/nase-obec/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T17:57:15.074038+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-53-LAZ-L-OKVN.yaml b/data/custodian/CZ-53-LAZ-L-OKVN.yaml index 05b3569be0..517262616c 100644 --- a/data/custodian/CZ-53-LAZ-L-OKVN.yaml +++ b/data/custodian/CZ-53-LAZ-L-OKVN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LAZ-L-OKVN - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LAZ-L-OKVN valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LAZ-L-OKVN ghcid_numeric: 5693802423464098856 valid_from: '2025-12-06T23:37:40.313568+00:00' @@ -205,3 +206,28 @@ location: postal_code: 533 41 street_address: Neratov čp. 12 normalization_timestamp: '2025-12-09T10:53:36.382045+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:57:31.022505+00:00' + source_url: https://www.neratov-novinsko.cz/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.neratov-novinsko.cz/file.php?nid=16272&oid=5805264 + source_url: https://www.neratov-novinsko.cz/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-26T17:57:31.022505+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.neratov-novinsko.cz/image.php?oid=5802293 + source_url: https://www.neratov-novinsko.cz/obecni-knihovna + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-26T17:57:31.022505+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-53-LET-E-PSSVLK.yaml b/data/custodian/CZ-53-LET-E-PSSVLK.yaml index 45d8efe3c5..77959cea57 100644 --- a/data/custodian/CZ-53-LET-E-PSSVLK.yaml +++ b/data/custodian/CZ-53-LET-E-PSSVLK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LET-E-PSSVLK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LET-E-PSSVLK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LET-E-PSSVLK ghcid_numeric: 3110376080863625919 valid_from: '2025-12-08T11:21:29.191663+00:00' @@ -222,3 +223,22 @@ location: postal_code: 561 51 street_address: Komenského 472 normalization_timestamp: '2025-12-09T10:53:36.433407+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:57:56.094433+00:00' + source_url: https://skola.tritius.cz/library/letohrad + 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/letohrad + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T17:57:56.094433+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-53-LET-L-MKLPO.yaml b/data/custodian/CZ-53-LET-L-MKLPO.yaml index 7bd3b9627a..711bd50d02 100644 --- a/data/custodian/CZ-53-LET-L-MKLPO.yaml +++ b/data/custodian/CZ-53-LET-L-MKLPO.yaml @@ -210,3 +210,22 @@ location: postal_code: 561 51 street_address: Orlice 181 normalization_timestamp: '2025-12-09T10:53:36.501233+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:58:31.109034+00:00' + source_url: https://orlice.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://orlice.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://orlice.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:58:31.109034+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-53-LET-L-OSRTK.yaml b/data/custodian/CZ-53-LET-L-OSRTK.yaml index 0fb730024d..f120acf97e 100644 --- a/data/custodian/CZ-53-LET-L-OSRTK.yaml +++ b/data/custodian/CZ-53-LET-L-OSRTK.yaml @@ -40,13 +40,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LET-L-OSRTK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LET-L-OSRTK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LET-L-OSRTK ghcid_numeric: 14079836632140967846 valid_from: '2025-12-06T23:37:20.551018+00:00' @@ -166,3 +167,22 @@ location: postal_code: 561 51 street_address: Šedivská 339 normalization_timestamp: '2025-12-09T06:52:18.709212+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T17:59:12.892864+00:00' + source_url: https://www.oez.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.oez.cz/usr/grafika/favicon.ico + source_url: https://www.oez.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T17:59:12.892864+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/CZ-53-LIT-L-MKL.yaml b/data/custodian/CZ-53-LIT-L-MKL.yaml index 5a7d36f881..906baa780f 100644 --- a/data/custodian/CZ-53-LIT-L-MKL.yaml +++ b/data/custodian/CZ-53-LIT-L-MKL.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LIT-L-MKL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LIT-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LIT-L-MKL ghcid_numeric: 9375730637053856688 valid_from: '2025-12-06T23:37:20.134525+00:00' @@ -258,3 +259,22 @@ location: postal_code: 570 01 street_address: Smetanovo nám. 50 normalization_timestamp: '2025-12-09T10:53:36.788143+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:00:00.894386+00:00' + source_url: https://katalog.knihovna-litomysl.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-litomysl.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-litomysl.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:00:00.894386+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-53-LIT-L-NPKSLNLK.yaml b/data/custodian/CZ-53-LIT-L-NPKSLNLK.yaml index caa2ee83dd..3898a54e44 100644 --- a/data/custodian/CZ-53-LIT-L-NPKSLNLK.yaml +++ b/data/custodian/CZ-53-LIT-L-NPKSLNLK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LIT-L-NPKSLNLK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LIT-L-NPKSLNLK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LIT-L-NPKSLNLK ghcid_numeric: 478117370142489606 valid_from: '2025-12-06T23:37:20.102390+00:00' @@ -216,3 +217,38 @@ location: postal_code: 570 14 street_address: J.E. Purkyně 652, 570 14 Litomyšl normalization_timestamp: '2025-12-09T10:53:36.819652+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:00:22.648306+00:00' + source_url: https://www.nempk.cz/informace/lekarska-knihovna-v-litomysli + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: '[inline-svg]' + source_url: https://www.nempk.cz/informace/lekarska-knihovna-v-litomysli + css_selector: '[document] > html.show--consent > body > header.header > div.header__main:nth-of-type(2) + > div.container-fluid > div.d-flex.justify-content-between > a.logo > svg.icon-logo' + retrieved_on: '2025-12-26T18:00:22.648306+00:00' + extraction_method: crawl4ai_svg_detection + detection_confidence: high + is_inline_svg: true + aria_label: '' + - claim_type: favicon_url + claim_value: https://www.nempk.cz/images/favicon/safari-pinned-tab.svg + source_url: https://www.nempk.cz/informace/lekarska-knihovna-v-litomysli + css_selector: '[document] > html.show--consent > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:00:22.648306+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.nempk.cz/images/og-image.png + source_url: https://www.nempk.cz/informace/lekarska-knihovna-v-litomysli + css_selector: '[document] > html.show--consent > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-26T18:00:22.648306+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-53-LIT-L-OKVC-obecni_knihovna_v_chotenove.yaml b/data/custodian/CZ-53-LIT-L-OKVC-obecni_knihovna_v_chotenove.yaml index 60a3144e1f..452567af2a 100644 --- a/data/custodian/CZ-53-LIT-L-OKVC-obecni_knihovna_v_chotenove.yaml +++ b/data/custodian/CZ-53-LIT-L-OKVC-obecni_knihovna_v_chotenove.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LIT-L-OKVC-obecni_knihovna_v_chotenove - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LIT-L-OKVC-obecni_knihovna_v_chotenove valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LIT-L-OKVC-obecni_knihovna_v_chotenove ghcid_numeric: 4824379540565687563 valid_from: '2025-12-06T23:37:40.662119+00:00' @@ -205,3 +206,22 @@ location: postal_code: 570 01 street_address: Chotěnov normalization_timestamp: '2025-12-09T10:53:36.886066+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:01:07.191066+00:00' + source_url: http://www.chotenov.cz/obecni-urad/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chotenov.cz/favicon.ico + source_url: http://www.chotenov.cz/obecni-urad/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:01:07.191066+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-53-LIT-L-OKVP.yaml b/data/custodian/CZ-53-LIT-L-OKVP.yaml index 0b9a7b8656..7be61907ca 100644 --- a/data/custodian/CZ-53-LIT-L-OKVP.yaml +++ b/data/custodian/CZ-53-LIT-L-OKVP.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LIT-L-OKVP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LIT-L-OKVP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LIT-L-OKVP ghcid_numeric: 8178535203006568786 valid_from: '2025-12-06T23:37:42.726971+00:00' @@ -200,3 +201,22 @@ location: postal_code: 570 01 street_address: Pohodlí 11 normalization_timestamp: '2025-12-09T10:53:36.913590+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:01:43.488791+00:00' + source_url: https://www.litomysl.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.litomysl.cz/program_files/favicon/apple-touch-icon-152x152.png + source_url: https://www.litomysl.cz + css_selector: '[document] > html.w-mod-js > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:01:43.488791+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 152x152 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 13 diff --git a/data/custodian/CZ-53-LIT-L-OKVS.yaml b/data/custodian/CZ-53-LIT-L-OKVS.yaml index e195edf557..565f5cf905 100644 --- a/data/custodian/CZ-53-LIT-L-OKVS.yaml +++ b/data/custodian/CZ-53-LIT-L-OKVS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LIT-L-OKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LIT-L-OKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LIT-L-OKVS ghcid_numeric: 1110426327322393679 valid_from: '2025-12-06T23:37:40.673958+00:00' @@ -205,3 +206,22 @@ location: postal_code: 570 01 street_address: Strakov 3 normalization_timestamp: '2025-12-09T10:53:36.945670+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:01:57.758599+00:00' + source_url: https://www.strakov.cz/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.strakov.cz/favicon.ico + source_url: https://www.strakov.cz/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:01:57.758599+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-53-LIT-M-RMVL.yaml b/data/custodian/CZ-53-LIT-M-RMVL.yaml index 794680eadd..db69dad49e 100644 --- a/data/custodian/CZ-53-LIT-M-RMVL.yaml +++ b/data/custodian/CZ-53-LIT-M-RMVL.yaml @@ -243,3 +243,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Regionální muzeum v Litomyšli official youtube_search_timestamp: '2025-12-09T09:34:18.442519+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:02:19.384046+00:00' + source_url: http://www.rml.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.rml.cz/favicon.ico + source_url: http://www.rml.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T18:02:19.384046+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-53-LIT-O-SOAVHKSOAS.yaml b/data/custodian/CZ-53-LIT-O-SOAVHKSOAS.yaml index 92db288331..b405a409d2 100644 --- a/data/custodian/CZ-53-LIT-O-SOAVHKSOAS.yaml +++ b/data/custodian/CZ-53-LIT-O-SOAVHKSOAS.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LIT-O-SOAVHKSOAS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LIT-O-SOAVHKSOAS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LIT-O-SOAVHKSOAS ghcid_numeric: 10232625954607107832 valid_from: '2025-12-06T23:37:20.114430+00:00' @@ -219,3 +220,33 @@ location: postal_code: 570 01 street_address: Jiráskovo nám. 270 normalization_timestamp: '2025-12-09T10:53:37.049941+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:02:56.942914+00:00' + source_url: https://vychodoceskearchivy.cz/home/prezentace-archivu/archivni-knihovny + 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/home/prezentace-archivu/archivni-knihovny + 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: '2025-12-26T18:02:56.942914+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/home/prezentace-archivu/archivni-knihovny + css_selector: '[document] > html > head > link:nth-of-type(31)' + retrieved_on: '2025-12-26T18:02:56.942914+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-53-LUZ-L-HOLPDDLK.yaml b/data/custodian/CZ-53-LUZ-L-HOLPDDLK.yaml index 2ac8a49a22..73918a3115 100644 --- a/data/custodian/CZ-53-LUZ-L-HOLPDDLK.yaml +++ b/data/custodian/CZ-53-LUZ-L-HOLPDDLK.yaml @@ -209,3 +209,28 @@ location: country: *id006 postal_code: 538 54 normalization_timestamp: '2025-12-09T10:53:37.099367+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:19:08.316875+00:00' + source_url: https://www.hamzova-lecebna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hamzova-lecebna.cz/skins/hamzova-lecebna.cz_lego2/favicons/apple-touch-icon.png + source_url: https://www.hamzova-lecebna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T18:19:08.316875+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.facebook.com/photo/?fbid=2736144476557522&set=a.145698815602114 + source_url: https://www.hamzova-lecebna.cz + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-26T18:19:08.316875+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-53-LUZ-L-KFL.yaml b/data/custodian/CZ-53-LUZ-L-KFL.yaml index 69478d8703..6b56c33a77 100644 --- a/data/custodian/CZ-53-LUZ-L-KFL.yaml +++ b/data/custodian/CZ-53-LUZ-L-KFL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LUZ-L-KFL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LUZ-L-KFL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LUZ-L-KFL ghcid_numeric: 9473726642742525255 valid_from: '2025-12-06T23:37:40.130460+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 54 street_address: Hroubovice 51 normalization_timestamp: '2025-12-09T10:53:37.121546+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:19:30.442800+00:00' + source_url: https://hroubovice-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hroubovice-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://hroubovice-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:19:30.442800+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-53-LUZ-L-OKS.yaml b/data/custodian/CZ-53-LUZ-L-OKS.yaml index 83db10baf0..fc9d84867b 100644 --- a/data/custodian/CZ-53-LUZ-L-OKS.yaml +++ b/data/custodian/CZ-53-LUZ-L-OKS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-LUZ-L-OKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-LUZ-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-LUZ-L-OKS ghcid_numeric: 14593698550752760364 valid_from: '2025-12-06T23:37:40.127572+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 54 street_address: Střemošice 62 normalization_timestamp: '2025-12-09T10:53:37.168417+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:20:10.877242+00:00' + source_url: https://www.stremosice.cz/obecni-knihovna-stremosice/ds-1002/p1=1010 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.stremosice.cz/html/images/favicon.ico + source_url: https://www.stremosice.cz/obecni-knihovna-stremosice/ds-1002/p1=1010 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T18:20:10.877242+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-53-MED-L-OKVM.yaml b/data/custodian/CZ-53-MED-L-OKVM.yaml index e9f2d18132..0d6f26a7cb 100644 --- a/data/custodian/CZ-53-MED-L-OKVM.yaml +++ b/data/custodian/CZ-53-MED-L-OKVM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-MED-L-OKVM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-MED-L-OKVM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-MED-L-OKVM ghcid_numeric: 8232025678283692508 valid_from: '2025-12-06T23:37:42.744047+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 v Medlešicích @@ -210,3 +211,22 @@ location: geonames_id: 3070892 geonames_name: Medlešice feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:20:30.432367+00:00' + source_url: https://medlesice-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://medlesice-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://medlesice-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:20:30.432367+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-53-MES-L-MKL.yaml b/data/custodian/CZ-53-MES-L-MKL.yaml index 628eef8d61..be1a4956d7 100644 --- a/data/custodian/CZ-53-MES-L-MKL.yaml +++ b/data/custodian/CZ-53-MES-L-MKL.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-MES-L-MKL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-MES-L-MKL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-MES-L-MKL ghcid_numeric: 7520942797709349780 valid_from: '2025-12-06T23:37:42.714592+00:00' @@ -200,3 +201,22 @@ location: postal_code: 569 41 street_address: Lázy 52 normalization_timestamp: '2025-12-09T10:53:37.217979+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:21:02.513568+00:00' + source_url: https://www.mesteckotrnavka.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mesteckotrnavka.cz/content/theme/css/images/favicons/apple-touch-icon.png + source_url: https://www.mesteckotrnavka.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T18:21:02.513568+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-53-MES-L-MKP-mistni_knihovna_pecikov.yaml b/data/custodian/CZ-53-MES-L-MKP-mistni_knihovna_pecikov.yaml index f72c0b5570..d6042ee678 100644 --- a/data/custodian/CZ-53-MES-L-MKP-mistni_knihovna_pecikov.yaml +++ b/data/custodian/CZ-53-MES-L-MKP-mistni_knihovna_pecikov.yaml @@ -206,3 +206,22 @@ location: postal_code: 571 01 street_address: Pěčíkov 53 normalization_timestamp: '2025-12-09T10:53:37.256082+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:21:19.535453+00:00' + source_url: https://pecikov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://pecikov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://pecikov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:21:19.535453+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-53-MES-L-OKMT.yaml b/data/custodian/CZ-53-MES-L-OKMT.yaml index 9aef61e647..d4729cc895 100644 --- a/data/custodian/CZ-53-MES-L-OKMT.yaml +++ b/data/custodian/CZ-53-MES-L-OKMT.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-MES-L-OKMT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-MES-L-OKMT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-MES-L-OKMT ghcid_numeric: 10621172109165891755 valid_from: '2025-12-06T23:37:23.236456+00:00' @@ -214,3 +215,22 @@ location: country: *id005 postal_code: 569 41 normalization_timestamp: '2025-12-09T10:53:37.325759+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:21:39.741566+00:00' + source_url: https://trnavka-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trnavka-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://trnavka-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:21:39.741566+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-53-MLA-L-MKVMM.yaml b/data/custodian/CZ-53-MLA-L-MKVMM.yaml index ea9221cd41..1283c501c8 100644 --- a/data/custodian/CZ-53-MLA-L-MKVMM.yaml +++ b/data/custodian/CZ-53-MLA-L-MKVMM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-MLA-L-MKVMM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-MLA-L-MKVMM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-MLA-L-MKVMM ghcid_numeric: 16371011187650713018 valid_from: '2025-12-06T23:37:40.683587+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 35 street_address: Mladějov na Moravě 122 normalization_timestamp: '2025-12-09T10:53:37.362191+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:22:02.694305+00:00' + source_url: https://mladejov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mladejov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://mladejov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:22:02.694305+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-53-MOR-L-MKLZBVMT.yaml b/data/custodian/CZ-53-MOR-L-MKLZBVMT.yaml index 23ba13c1df..1177969153 100644 --- a/data/custodian/CZ-53-MOR-L-MKLZBVMT.yaml +++ b/data/custodian/CZ-53-MOR-L-MKLZBVMT.yaml @@ -248,3 +248,22 @@ location: postal_code: 571 01 street_address: Zámecké náměstí 185/1 normalization_timestamp: '2025-12-09T10:53:37.447288+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:22:46.510998+00:00' + source_url: https://katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:22:46.510998+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-53-MOR-L-MKVB.yaml b/data/custodian/CZ-53-MOR-L-MKVB.yaml index b9560ed288..a2bf74e437 100644 --- a/data/custodian/CZ-53-MOR-L-MKVB.yaml +++ b/data/custodian/CZ-53-MOR-L-MKVB.yaml @@ -206,3 +206,22 @@ location: postal_code: 571 01 street_address: Boršov 102 normalization_timestamp: '2025-12-09T10:53:37.472952+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:23:17.465752+00:00' + source_url: https://borsov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://borsov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://borsov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:23:17.465752+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-53-MOR-L-MKVDUMT.yaml b/data/custodian/CZ-53-MOR-L-MKVDUMT.yaml index 54b593e3d2..7d2ecdecbf 100644 --- a/data/custodian/CZ-53-MOR-L-MKVDUMT.yaml +++ b/data/custodian/CZ-53-MOR-L-MKVDUMT.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-MOR-L-MKVDUMT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-MOR-L-MKVDUMT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-MOR-L-MKVDUMT ghcid_numeric: 9043783242979633563 valid_from: '2025-12-06T23:37:40.696273+00:00' @@ -205,3 +206,22 @@ location: postal_code: 571 01 street_address: Dětřichov u Moravské Třebové 25 normalization_timestamp: '2025-12-09T10:53:37.497728+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:23:33.229770+00:00' + source_url: https://detrichov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://detrichov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://detrichov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:23:33.229770+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-53-MOR-L-OKU.yaml b/data/custodian/CZ-53-MOR-L-OKU.yaml index e6ebc09a05..1effea2857 100644 --- a/data/custodian/CZ-53-MOR-L-OKU.yaml +++ b/data/custodian/CZ-53-MOR-L-OKU.yaml @@ -211,3 +211,22 @@ location: postal_code: 571 01 street_address: Útěchov 65 normalization_timestamp: '2025-12-09T10:53:37.526229+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:23:51.435516+00:00' + source_url: https://utechov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://utechov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://utechov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:23:51.435516+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-53-MOR-L-OKVB.yaml b/data/custodian/CZ-53-MOR-L-OKVB.yaml index 3a2e881bf5..4ddf07f48e 100644 --- a/data/custodian/CZ-53-MOR-L-OKVB.yaml +++ b/data/custodian/CZ-53-MOR-L-OKVB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-MOR-L-OKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-MOR-L-OKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-MOR-L-OKVB ghcid_numeric: 7201700222289685322 valid_from: '2025-12-06T23:37:40.689659+00:00' @@ -205,3 +206,22 @@ location: postal_code: 571 01 street_address: Borušov 60 normalization_timestamp: '2025-12-09T10:53:37.553968+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:24:09.997132+00:00' + source_url: https://borusov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://borusov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://borusov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:24:09.997132+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-53-MOR-L-OKVM.yaml b/data/custodian/CZ-53-MOR-L-OKVM.yaml index ab09d63107..77704a5510 100644 --- a/data/custodian/CZ-53-MOR-L-OKVM.yaml +++ b/data/custodian/CZ-53-MOR-L-OKVM.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-MOR-L-OKVM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-MOR-L-OKVM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-MOR-L-OKVM ghcid_numeric: 877864343705497209 valid_from: '2025-12-06T23:37:40.686765+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 51 street_address: Morašice 96 normalization_timestamp: '2025-12-09T10:53:37.578260+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:24:23.900787+00:00' + source_url: http://www.morasice.cz/knihovna/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.morasice.cz/favicon.ico + source_url: http://www.morasice.cz/knihovna/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:24:23.900787+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-53-NAS-L-MKN.yaml b/data/custodian/CZ-53-NAS-L-MKN.yaml index c1c7d86ba2..b23293d8d0 100644 --- a/data/custodian/CZ-53-NAS-L-MKN.yaml +++ b/data/custodian/CZ-53-NAS-L-MKN.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-NAS-L-MKN - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-NAS-L-MKN valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-NAS-L-MKN ghcid_numeric: 15223340484519675120 valid_from: '2025-12-06T23:37:25.264575+00:00' @@ -214,3 +215,22 @@ location: postal_code: 538 25 street_address: Náměstí 37 normalization_timestamp: '2025-12-09T10:53:37.603304+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:24:46.928811+00:00' + source_url: https://nasavrky-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nasavrky-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://nasavrky-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:24:46.928811+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-53-NAS-L-MKS.yaml b/data/custodian/CZ-53-NAS-L-MKS.yaml index 59566f268b..44fd2a7409 100644 --- a/data/custodian/CZ-53-NAS-L-MKS.yaml +++ b/data/custodian/CZ-53-NAS-L-MKS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-NAS-L-MKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-NAS-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-NAS-L-MKS ghcid_numeric: 13991132732937167683 valid_from: '2025-12-08T11:21:32.388821+00:00' @@ -210,3 +211,22 @@ location: postal_code: 538 25 street_address: Švihov 31 normalization_timestamp: '2025-12-09T10:53:37.624842+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:25:04.530763+00:00' + source_url: https://svihov-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://svihov-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://svihov-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:25:04.530763+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-53-NAS-L-MKVK.yaml b/data/custodian/CZ-53-NAS-L-MKVK.yaml index 557027afda..406a364ec7 100644 --- a/data/custodian/CZ-53-NAS-L-MKVK.yaml +++ b/data/custodian/CZ-53-NAS-L-MKVK.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-NAS-L-MKVK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-NAS-L-MKVK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-NAS-L-MKVK ghcid_numeric: 4697026352958848272 valid_from: '2025-12-06T23:37:40.138984+00:00' @@ -200,3 +201,23 @@ location: postal_code: 538 25 street_address: Krásné 15 normalization_timestamp: '2025-12-09T10:53:37.655240+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:25:20.961527+00:00' + source_url: http://obeckrasne.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://obeckrasne.cz/wp-content/uploads/2018/06/logo2.png + source_url: http://obeckrasne.cz + css_selector: '#header > div.header-inner > div.header-content > div.c-container + > div.header-content-inner > div.header-branding.m-small-logo > a > span > img' + retrieved_on: '2025-12-26T18:25:20.961527+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Obec Krásné + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-53-NAS-L-OKVL.yaml b/data/custodian/CZ-53-NAS-L-OKVL.yaml index e8b9b0615f..6caba54608 100644 --- a/data/custodian/CZ-53-NAS-L-OKVL.yaml +++ b/data/custodian/CZ-53-NAS-L-OKVL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-NAS-L-OKVL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-NAS-L-OKVL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-NAS-L-OKVL ghcid_numeric: 16847027557838911710 valid_from: '2025-12-06T23:37:40.141976+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 25 street_address: Libkov 31 normalization_timestamp: '2025-12-09T10:53:37.679127+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:25:39.665580+00:00' + source_url: https://libkov-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://libkov-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://libkov-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:25:39.665580+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-53-NEK-L-MKVN.yaml b/data/custodian/CZ-53-NEK-L-MKVN.yaml index c1d3ee7ffa..8a53ce3f0a 100644 --- a/data/custodian/CZ-53-NEK-L-MKVN.yaml +++ b/data/custodian/CZ-53-NEK-L-MKVN.yaml @@ -206,3 +206,22 @@ location: postal_code: 561 63 street_address: náměstíčko č.p. 32 normalization_timestamp: '2025-12-09T10:53:37.705380+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:26:01.449619+00:00' + source_url: https://nekor.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nekor.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://nekor.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:26:01.449619+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-53-NOV-L-OKVNS.yaml b/data/custodian/CZ-53-NOV-L-OKVNS.yaml index b01228f21f..aa4bc2e273 100644 --- a/data/custodian/CZ-53-NOV-L-OKVNS.yaml +++ b/data/custodian/CZ-53-NOV-L-OKVNS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-NOV-L-OKVNS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-NOV-L-OKVNS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-NOV-L-OKVNS ghcid_numeric: 8660613784109732778 valid_from: '2025-12-06T23:37:40.702444+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 51 street_address: Nová Sídla normalization_timestamp: '2025-12-09T10:53:37.732875+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:26:19.049636+00:00' + source_url: http://www.novasidla.cz/knihovna/zakladni-informace-a-kontakty + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.novasidla.cz/favicon.ico + source_url: http://www.novasidla.cz/knihovna/zakladni-informace-a-kontakty + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:26:19.049636+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-53-OLD-L-MKVO.yaml b/data/custodian/CZ-53-OLD-L-MKVO.yaml index 6436a3e8ee..8c1dca5108 100644 --- a/data/custodian/CZ-53-OLD-L-MKVO.yaml +++ b/data/custodian/CZ-53-OLD-L-MKVO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-OLD-L-MKVO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-OLD-L-MKVO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-OLD-L-MKVO ghcid_numeric: 5630033014754375908 valid_from: '2025-12-06T23:37:40.705722+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 82 street_address: Oldřiš 132 normalization_timestamp: '2025-12-09T10:53:37.757350+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:26:41.443260+00:00' + source_url: https://tritius.knihovna.policka.org/library/oldris + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna.policka.org/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna.policka.org/library/oldris + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:26:41.443260+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-53-OPA-A-SOAO-statni_okresni_archiv_opava.yaml b/data/custodian/CZ-53-OPA-A-SOAO-statni_okresni_archiv_opava.yaml index 964e6ff52a..a75f537417 100644 --- a/data/custodian/CZ-53-OPA-A-SOAO-statni_okresni_archiv_opava.yaml +++ b/data/custodian/CZ-53-OPA-A-SOAO-statni_okresni_archiv_opava.yaml @@ -241,3 +241,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Opava official youtube_search_timestamp: '2025-12-09T09:34:21.065421+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:27:30.047432+00:00' + source_url: http://www.archives.cz/web/soka/opava/o_archivu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.archives.cz/web/favicon/safari-pinned-tab.svg + source_url: http://www.archives.cz/web/soka/opava/o_archivu + css_selector: '[document] > html.js.no-touchevents > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:27:30.047432+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: 12 diff --git a/data/custodian/CZ-53-OPA-L-OKC.yaml b/data/custodian/CZ-53-OPA-L-OKC.yaml index 86a620e00b..c21d29c1df 100644 --- a/data/custodian/CZ-53-OPA-L-OKC.yaml +++ b/data/custodian/CZ-53-OPA-L-OKC.yaml @@ -224,3 +224,22 @@ location: postal_code: '53345' street_address: Boženy Němcové 1 normalization_timestamp: '2025-12-09T10:53:37.811775+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:27:34.712472+00:00' + source_url: https://www.ceperka.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ceperka.cz/image.php?nid=19847&oid=8543749&width=36 + source_url: https://www.ceperka.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-26T18:27:34.712472+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-53-OPA-L-OKONL.yaml b/data/custodian/CZ-53-OPA-L-OKONL.yaml index 7eadc6f540..fff681638f 100644 --- a/data/custodian/CZ-53-OPA-L-OKONL.yaml +++ b/data/custodian/CZ-53-OPA-L-OKONL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-OPA-L-OKONL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-OPA-L-OKONL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-OPA-L-OKONL ghcid_numeric: 15156239367355277660 valid_from: '2025-12-06T23:37:22.530867+00:00' @@ -226,3 +227,22 @@ location: postal_code: 533 45 street_address: Neplachova 206 normalization_timestamp: '2025-12-09T10:53:37.837320+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:28:00.084412+00:00' + source_url: https://kkpce.tritius.cz/library/opatovicenl + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kkpce.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kkpce.tritius.cz/library/opatovicenl + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:28:00.084412+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-53-OPA-L-OKVO.yaml b/data/custodian/CZ-53-OPA-L-OKVO.yaml index 2b29ad399c..772e35efcf 100644 --- a/data/custodian/CZ-53-OPA-L-OKVO.yaml +++ b/data/custodian/CZ-53-OPA-L-OKVO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-OPA-L-OKVO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-OPA-L-OKVO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-OPA-L-OKVO ghcid_numeric: 13944768740044734122 valid_from: '2025-12-06T23:37:40.708800+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 12 street_address: Opatov 159 normalization_timestamp: '2025-12-09T10:53:37.859627+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:28:34.384057+00:00' + source_url: https://tritius.booksy.cz/library/opatov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/opatov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:28:34.384057+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-53-ORL-L-OKO.yaml b/data/custodian/CZ-53-ORL-L-OKO.yaml index 3e214369aa..ea1864d9d1 100644 --- a/data/custodian/CZ-53-ORL-L-OKO.yaml +++ b/data/custodian/CZ-53-ORL-L-OKO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-ORL-L-OKO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-ORL-L-OKO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-ORL-L-OKO ghcid_numeric: 15610164437879580165 valid_from: '2025-12-06T23:37:40.999723+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 55 street_address: Orličky 176 normalization_timestamp: '2025-12-09T10:53:37.888640+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:28:56.643111+00:00' + source_url: https://orlicky.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://orlicky.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://orlicky.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:28:56.643111+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-53-OSI-L-OKO.yaml b/data/custodian/CZ-53-OSI-L-OKO.yaml index c22c80eb54..6048abb520 100644 --- a/data/custodian/CZ-53-OSI-L-OKO.yaml +++ b/data/custodian/CZ-53-OSI-L-OKO.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-OSI-L-OKO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-OSI-L-OKO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-OSI-L-OKO ghcid_numeric: 12837941341376688318 valid_from: '2025-12-06T23:37:40.711880+00:00' @@ -209,3 +210,22 @@ location: postal_code: 569 67 street_address: Osík 240 normalization_timestamp: '2025-12-09T10:53:37.916429+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:29:46.487034+00:00' + source_url: https://www.osik.cz/knihovna/d-1040/p1=1067 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.osik.cz/html/images/favicon.ico + source_url: https://www.osik.cz/knihovna/d-1040/p1=1067 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T18:29:46.487034+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-53-OTR-L-OKVO.yaml b/data/custodian/CZ-53-OTR-L-OKVO.yaml index 47080f1a4a..716e61c5c5 100644 --- a/data/custodian/CZ-53-OTR-L-OKVO.yaml +++ b/data/custodian/CZ-53-OTR-L-OKVO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-OTR-L-OKVO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-OTR-L-OKVO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-OTR-L-OKVO ghcid_numeric: 3819201148461286418 valid_from: '2025-12-06T23:37:43.462507+00:00' @@ -208,3 +209,22 @@ location: postal_code: 539 43 street_address: Otradov 112 normalization_timestamp: '2025-12-09T10:53:37.942476+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:30:20.086718+00:00' + source_url: https://otradov-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://otradov-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://otradov-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:30:20.086718+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-53-PAR-E-OAJSSPSJZK.yaml b/data/custodian/CZ-53-PAR-E-OAJSSPSJZK.yaml index b9112f86a9..67390dafff 100644 --- a/data/custodian/CZ-53-PAR-E-OAJSSPSJZK.yaml +++ b/data/custodian/CZ-53-PAR-E-OAJSSPSJZK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-E-OAJSSPSJZK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-E-OAJSSPSJZK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-E-OAJSSPSJZK ghcid_numeric: 2840868914770651770 valid_from: '2025-12-08T11:21:32.682441+00:00' @@ -217,3 +218,22 @@ location: postal_code: 530 43 street_address: Štefánikova 325 normalization_timestamp: '2025-12-09T10:53:37.970189+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:30:41.579932+00:00' + source_url: https://oapce.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://oapce.cz/design/favicons/safari-pinned-tab.svg + source_url: https://oapce.cz + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-26T18:30:41.579932+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-53-PAR-E-SPSEVOSPK.yaml b/data/custodian/CZ-53-PAR-E-SPSEVOSPK.yaml index a09e3f8783..22bb910197 100644 --- a/data/custodian/CZ-53-PAR-E-SPSEVOSPK.yaml +++ b/data/custodian/CZ-53-PAR-E-SPSEVOSPK.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-E-SPSEVOSPK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-E-SPSEVOSPK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-E-SPSEVOSPK ghcid_numeric: 10547530283598496105 valid_from: '2025-12-08T11:21:35.126127+00:00' @@ -224,3 +225,31 @@ location: postal_code: 530 02 street_address: Karla IV. č.13 normalization_timestamp: '2025-12-09T10:53:37.993981+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:31:02.415973+00:00' + source_url: http://www.spse.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.spse.cz/css/spse-logo.png + source_url: http://www.spse.cz + css_selector: '[document] > html > body.view > header > div.nav:nth-of-type(2) + > div.logo > a > img' + retrieved_on: '2025-12-26T18:31:02.415973+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo SPŠE + - claim_type: favicon_url + claim_value: http://www.spse.cz/favicon.svg + source_url: http://www.spse.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:31:02.415973+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + 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/CZ-53-PAR-E-SZSPK.yaml b/data/custodian/CZ-53-PAR-E-SZSPK.yaml index 9c7f309c60..e7f34e0d26 100644 --- a/data/custodian/CZ-53-PAR-E-SZSPK.yaml +++ b/data/custodian/CZ-53-PAR-E-SZSPK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-E-SZSPK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-E-SZSPK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-E-SZSPK ghcid_numeric: 10220355677543724384 valid_from: '2025-12-08T11:21:37.259709+00:00' @@ -218,3 +219,32 @@ location: postal_code: 530 03 street_address: Průmyslová 395 normalization_timestamp: '2025-12-09T10:53:38.019801+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:31:40.946167+00:00' + source_url: https://szspce.kpsys.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://szspce.kpsys.cz/custom/design/szslogo.png + source_url: https://szspce.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 > div > a > img' + retrieved_on: '2025-12-26T18:31:40.946167+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Střední zdravotnická škola Pardubice + - claim_type: favicon_url + claim_value: https://szspce.kpsys.cz/favicon.png?v=2.3.0-32050 + source_url: https://szspce.kpsys.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T18:31:40.946167+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-53-PAR-L-ESRK.yaml b/data/custodian/CZ-53-PAR-L-ESRK.yaml index 905ff73e46..46e38d24b2 100644 --- a/data/custodian/CZ-53-PAR-L-ESRK.yaml +++ b/data/custodian/CZ-53-PAR-L-ESRK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-ESRK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-ESRK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-ESRK ghcid_numeric: 6425869574591650552 valid_from: '2025-12-06T23:37:19.339941+00:00' @@ -215,3 +216,22 @@ location: postal_code: 533 53 street_address: Ohrazenice 211 normalization_timestamp: '2025-12-09T10:53:38.094801+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:32:25.881474+00:00' + source_url: https://www.elgas.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.elgas.cz/sites/default/files/favicon_1-1.png + source_url: https://www.elgas.cz + css_selector: '[document] > html.js.no-touchevents > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T18:32:25.881474+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-53-PAR-L-ESTKV.yaml b/data/custodian/CZ-53-PAR-L-ESTKV.yaml index f95136873b..4b309e3ac1 100644 --- a/data/custodian/CZ-53-PAR-L-ESTKV.yaml +++ b/data/custodian/CZ-53-PAR-L-ESTKV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-ESTKV - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-ESTKV valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-ESTKV ghcid_numeric: 11739693641548029065 valid_from: '2025-12-06T23:37:19.271569+00:00' @@ -211,3 +212,22 @@ location: postal_code: 530 02 street_address: Semtín 107, budova M7 normalization_timestamp: '2025-12-09T10:53:38.124910+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:32:46.519270+00:00' + source_url: https://explosia.cz/vyzkum/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://explosia.cz/wp-content/themes/main/img/favicon.svg + source_url: https://explosia.cz/vyzkum/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T18:32:46.519270+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: 7 diff --git a/data/custodian/CZ-53-PAR-L-GZPK.yaml b/data/custodian/CZ-53-PAR-L-GZPK.yaml index e2bb3008aa..6b859babf0 100644 --- a/data/custodian/CZ-53-PAR-L-GZPK.yaml +++ b/data/custodian/CZ-53-PAR-L-GZPK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-GZPK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-GZPK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-GZPK ghcid_numeric: 14734135247819564706 valid_from: '2025-12-06T23:37:43.124695+00:00' @@ -211,3 +212,28 @@ location: postal_code: 530 02 street_address: Klášterní 54 normalization_timestamp: '2025-12-09T10:53:38.148565+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:33:06.531156+00:00' + source_url: https://www.goethepardubice.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.goethepardubice.org/cokg5f8rsvf6e/themes/gzp/favicons/safari-pinned-tab.svg + source_url: https://www.goethepardubice.org + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-26T18:33:06.531156+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.goethepardubice.org/cokg5f8rsvf6e/uploads/2021/09/7.10.jpg + source_url: https://www.goethepardubice.org + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-26T18:33:06.531156+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-53-PAR-L-KMOPI.yaml b/data/custodian/CZ-53-PAR-L-KMOPI.yaml index d457f6baf4..4e94277735 100644 --- a/data/custodian/CZ-53-PAR-L-KMOPI.yaml +++ b/data/custodian/CZ-53-PAR-L-KMOPI.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-KMOPI - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-KMOPI valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-KMOPI ghcid_numeric: 5437175820623545495 valid_from: '2025-12-06T23:37:40.490437+00:00' @@ -214,3 +215,22 @@ location: postal_code: 530 09 street_address: Družby 334 normalization_timestamp: '2025-12-09T10:53:38.167242+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:33:41.100462+00:00' + source_url: http://knihovna-polabiny.mmp.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://knihovna-polabiny.mmp.cz/favicon.png?v=2.3.0-32050 + source_url: http://knihovna-polabiny.mmp.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T18:33:41.100462+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-53-PAR-L-KMOPIMK.yaml b/data/custodian/CZ-53-PAR-L-KMOPIMK.yaml index 9ca6e8dc17..f438bd16ee 100644 --- a/data/custodian/CZ-53-PAR-L-KMOPIMK.yaml +++ b/data/custodian/CZ-53-PAR-L-KMOPIMK.yaml @@ -182,3 +182,21 @@ wikidata_enrichment: image: https://commons.wikimedia.org/wiki/Special:FilePath/Interiér_knihovna_(5).jpg instance_of: - Q7075 +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:37:34.985101+00:00' + source_url: https://ekatalog.knihovna-dubina.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://knihovna-dubina.cz/wp-content/uploads/2025/05/fake-novinka2.webp + source_url: https://ekatalog.knihovna-dubina.cz/#! + css_selector: '[document] > html.avada-html-layout-wide.avada-html-header-position-top + > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T18:37:34.985101+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-53-PAR-L-MKD.yaml b/data/custodian/CZ-53-PAR-L-MKD.yaml index a031226f0c..dbf4366390 100644 --- a/data/custodian/CZ-53-PAR-L-MKD.yaml +++ b/data/custodian/CZ-53-PAR-L-MKD.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-MKD - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-MKD valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-MKD ghcid_numeric: 452620386313724783 valid_from: '2025-12-06T23:37:40.507152+00:00' @@ -212,3 +213,28 @@ location: postal_code: 533 51 street_address: Doubravice 8 normalization_timestamp: '2025-12-09T10:53:38.207302+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:39:38.090391+00:00' + source_url: http://www.pardubice7.cz/mistni-knihovny-v-mo-pardubice-vii + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.pardubice7.cz/assets/frontend/img/favicons/safari-pinned-tab.1765527499.svg + source_url: http://www.pardubice7.cz/mistni-knihovny-v-mo-pardubice-vii + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:39:38.090391+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://pardubice.eu/assets/frontend/img/og.png + source_url: http://www.pardubice7.cz/mistni-knihovny-v-mo-pardubice-vii + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T18:39:38.090391+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-53-PAR-L-MKG.yaml b/data/custodian/CZ-53-PAR-L-MKG.yaml index 76eee20083..cce5f5cc68 100644 --- a/data/custodian/CZ-53-PAR-L-MKG.yaml +++ b/data/custodian/CZ-53-PAR-L-MKG.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-MKG - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-MKG valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-MKG ghcid_numeric: 13458986865153976707 valid_from: '2025-12-06T23:37:40.460250+00:00' @@ -221,3 +222,28 @@ location: postal_code: 530 02 street_address: Josefa Ressla 2278 normalization_timestamp: '2025-12-09T10:53:38.238107+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:40:43.283731+00:00' + source_url: https://pardubice.eu/organizacni-struktura-mo5?page_articles=2 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://pardubice.eu/assets/frontend/img/favicons/safari-pinned-tab.1765527499.svg + source_url: https://pardubice.eu/organizacni-struktura-mo5?page_articles=2 + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:40:43.283731+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://pardubice.eu/assets/frontend/img/og.png + source_url: https://pardubice.eu/organizacni-struktura-mo5?page_articles=2 + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T18:40:43.283731+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-53-PAR-L-MKO.yaml b/data/custodian/CZ-53-PAR-L-MKO.yaml index e09afdac13..07b268a3e9 100644 --- a/data/custodian/CZ-53-PAR-L-MKO.yaml +++ b/data/custodian/CZ-53-PAR-L-MKO.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-MKO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-MKO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-MKO ghcid_numeric: 15507766532972140164 valid_from: '2025-12-06T23:37:40.516434+00:00' @@ -212,3 +213,28 @@ location: postal_code: 533 53 street_address: Trnovská 42 normalization_timestamp: '2025-12-09T10:53:38.299737+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:44:16.043446+00:00' + source_url: https://pardubice.eu/mistni-knihovny-mo7 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://pardubice.eu/assets/frontend/img/favicons/safari-pinned-tab.1765527499.svg + source_url: https://pardubice.eu/mistni-knihovny-mo7 + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:44:16.043446+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://pardubice.eu/assets/frontend/img/og.png + source_url: https://pardubice.eu/mistni-knihovny-mo7 + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T18:44:16.043446+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-53-PAR-L-MKRNL.yaml b/data/custodian/CZ-53-PAR-L-MKRNL.yaml index 11706eb960..deb866703f 100644 --- a/data/custodian/CZ-53-PAR-L-MKRNL.yaml +++ b/data/custodian/CZ-53-PAR-L-MKRNL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-MKRNL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-MKRNL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-MKRNL ghcid_numeric: 10843464909463222359 valid_from: '2025-12-06T23:37:40.502244+00:00' @@ -212,3 +213,28 @@ location: postal_code: 533 51 street_address: Gen. Svobody 198 normalization_timestamp: '2025-12-09T10:53:38.405911+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:44:33.869885+00:00' + source_url: http://pardubice7.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://pardubice7.cz/assets/frontend/img/favicons/safari-pinned-tab.1765527499.svg + source_url: http://pardubice7.cz + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:44:33.869885+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://pardubice.eu/assets/frontend/img/og.png + source_url: http://pardubice7.cz + css_selector: '[document] > html.swup-enabled.is-mouse-pointer > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T18:44:33.869885+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-53-PAR-L-NPKSPNSVIL.yaml b/data/custodian/CZ-53-PAR-L-NPKSPNSVIL.yaml index 12f771aa59..ce4e565cc8 100644 --- a/data/custodian/CZ-53-PAR-L-NPKSPNSVIL.yaml +++ b/data/custodian/CZ-53-PAR-L-NPKSPNSVIL.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-NPKSPNSVIL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-NPKSPNSVIL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-NPKSPNSVIL ghcid_numeric: 6212673141073285240 valid_from: '2025-12-06T23:37:19.294388+00:00' @@ -226,3 +227,38 @@ location: postal_code: 532 03 street_address: Kyjevská 44 normalization_timestamp: '2025-12-09T10:53:38.430761+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:44:42.196672+00:00' + source_url: https://pardubice.nempk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: '[inline-svg]' + source_url: https://pardubice.nempk.cz + css_selector: '[document] > html.show--consent > body > header.header > div.header__top + > div.container-fluid > nav.d-flex.justify-content-between > a > svg.icon-logo' + retrieved_on: '2025-12-26T18:44:42.196672+00:00' + extraction_method: crawl4ai_svg_detection + detection_confidence: high + is_inline_svg: true + aria_label: '' + - claim_type: favicon_url + claim_value: https://pardubice.nempk.cz/images/favicon/safari-pinned-tab.svg + source_url: https://pardubice.nempk.cz + css_selector: '[document] > html.show--consent > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:44:42.196672+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://pardubice.nempk.cz/images/og-image.png + source_url: https://pardubice.nempk.cz + css_selector: '[document] > html.show--consent > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-26T18:44:42.196672+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-53-PAR-L-NPUUOPVPOK.yaml b/data/custodian/CZ-53-PAR-L-NPUUOPVPOK.yaml index 7c62c65328..c8eaeadc29 100644 --- a/data/custodian/CZ-53-PAR-L-NPUUOPVPOK.yaml +++ b/data/custodian/CZ-53-PAR-L-NPUUOPVPOK.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-NPUUOPVPOK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-NPUUOPVPOK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-NPUUOPVPOK ghcid_numeric: 2727743687282109454 valid_from: '2025-12-08T11:21:40.955822+00:00' @@ -229,3 +230,28 @@ location: postal_code: 531 16 street_address: Přihrádek 5 normalization_timestamp: '2025-12-09T10:53:38.465967+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:44:54.248283+00:00' + source_url: https://www.npu.cz/cs + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.npu.cz/safari-pinned-tab.svg + source_url: https://www.npu.cz/cs + css_selector: '[document] > html.show--consent > head > link:nth-of-type(10)' + retrieved_on: '2025-12-26T18:44:54.248283+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.npu.cz/portal/001-hp/ilustracni-fotky/zastupny-obrazek_web.jpg + source_url: https://www.npu.cz/cs + css_selector: '[document] > html.show--consent > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-26T18:44:54.248283+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-53-PAR-L-OKVB.yaml b/data/custodian/CZ-53-PAR-L-OKVB.yaml index 94e4b84212..9d9d020633 100644 --- a/data/custodian/CZ-53-PAR-L-OKVB.yaml +++ b/data/custodian/CZ-53-PAR-L-OKVB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-OKVB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-OKVB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-OKVB ghcid_numeric: 11725675223437627408 valid_from: '2025-12-06T23:37:40.466997+00:00' @@ -208,3 +209,22 @@ location: postal_code: 530 02 street_address: Blato normalization_timestamp: '2025-12-09T10:53:38.635286+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:45:22.614335+00:00' + source_url: https://www.obecmikulovice.cz/zivot-v-obci/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obecmikulovice.cz/skins/obecmikulovice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.obecmikulovice.cz/zivot-v-obci/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:45:22.614335+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-53-PAR-L-OKVM.yaml b/data/custodian/CZ-53-PAR-L-OKVM.yaml index 71c11bc34b..3c54e7fbfd 100644 --- a/data/custodian/CZ-53-PAR-L-OKVM.yaml +++ b/data/custodian/CZ-53-PAR-L-OKVM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PAR-L-OKVM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PAR-L-OKVM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PAR-L-OKVM ghcid_numeric: 13305947466553380028 valid_from: '2025-12-06T23:37:40.463766+00:00' @@ -208,3 +209,22 @@ location: postal_code: 530 02 street_address: Valčíkova 52 normalization_timestamp: '2025-12-09T10:53:38.662578+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:45:30.742106+00:00' + source_url: https://www.obecmikulovice.cz/zivot-v-obci/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obecmikulovice.cz/skins/obecmikulovice.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.obecmikulovice.cz/zivot-v-obci/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:45:30.742106+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-53-PAR-L-SAS.yaml b/data/custodian/CZ-53-PAR-L-SAS.yaml index 7081c3cd1b..b8635f3b54 100644 --- a/data/custodian/CZ-53-PAR-L-SAS.yaml +++ b/data/custodian/CZ-53-PAR-L-SAS.yaml @@ -181,3 +181,28 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1438040 +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:45:43.438136+00:00' + source_url: https://www.synpo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.synpo.cz/files/resize/76/76/kopie-navrhu-synpo-rebranding-1.png + source_url: https://www.synpo.cz + css_selector: '[document] > html.html.js > head > link:nth-of-type(11)' + retrieved_on: '2025-12-26T18:45:43.438136+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 76x76 + - claim_type: og_image_url + claim_value: https://www.synpo.cz/files/fotky-synpo-2.png + source_url: https://www.synpo.cz + css_selector: '[document] > html.html.js > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T18:45:43.438136+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 8 diff --git a/data/custodian/CZ-53-PIS-L-MKP.yaml b/data/custodian/CZ-53-PIS-L-MKP.yaml index 2d9ca063f0..0c2c9034af 100644 --- a/data/custodian/CZ-53-PIS-L-MKP.yaml +++ b/data/custodian/CZ-53-PIS-L-MKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PIS-L-MKP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PIS-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PIS-L-MKP ghcid_numeric: 957549690319523638 valid_from: '2025-12-06T23:37:41.003016+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 70 street_address: Písečná 115 normalization_timestamp: '2025-12-09T10:53:38.904615+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:45:59.891120+00:00' + source_url: https://pisecna.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://pisecna.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://pisecna.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:45:59.891120+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-53-POL-L-MKP.yaml b/data/custodian/CZ-53-POL-L-MKP.yaml index f4b840391d..ca77f7ef11 100644 --- a/data/custodian/CZ-53-POL-L-MKP.yaml +++ b/data/custodian/CZ-53-POL-L-MKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-POL-L-MKP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-POL-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-POL-L-MKP ghcid_numeric: 5646912052146120066 valid_from: '2025-12-06T23:37:20.143964+00:00' @@ -224,3 +225,22 @@ location: postal_code: 572 01 street_address: Palackého nám. 64 normalization_timestamp: '2025-12-09T10:53:38.932236+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:46:04.903494+00:00' + source_url: https://katalog.vecizpolicky.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.vecizpolicky.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.vecizpolicky.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:46:04.903494+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-53-POL-L-MKPPL.yaml b/data/custodian/CZ-53-POL-L-MKPPL.yaml index 8ff0b8062a..aca55c8d3d 100644 --- a/data/custodian/CZ-53-POL-L-MKPPL.yaml +++ b/data/custodian/CZ-53-POL-L-MKPPL.yaml @@ -207,3 +207,23 @@ location: postal_code: 572 01 street_address: Lezník 68 normalization_timestamp: '2025-12-09T10:53:38.961747+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:46:11.728207+00:00' + source_url: https://www.policka.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.policka.org/images/favicon/apple-icon-180x180.png + source_url: https://www.policka.org + css_selector: '[document] > html.fontawesome-i2svg-active.fontawesome-i2svg-complete + > head > link:nth-of-type(16)' + retrieved_on: '2025-12-26T18:46:11.728207+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-53-POL-L-MKVBUP.yaml b/data/custodian/CZ-53-POL-L-MKVBUP.yaml index 93d8558f91..bcff5e2be0 100644 --- a/data/custodian/CZ-53-POL-L-MKVBUP.yaml +++ b/data/custodian/CZ-53-POL-L-MKVBUP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-POL-L-MKVBUP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-POL-L-MKVBUP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-POL-L-MKVBUP ghcid_numeric: 15348249181124197745 valid_from: '2025-12-06T23:37:40.621208+00:00' @@ -208,3 +209,30 @@ location: postal_code: 569 95 street_address: Březiny u Poličky 32 normalization_timestamp: '2025-12-09T10:53:38.987351+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:46:19.320504+00:00' + source_url: https://www.breziny.net/index.php/sluzby/knihovna + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.breziny.net/images/web/logobre.png + source_url: https://www.breziny.net/index.php/sluzby/knihovna + css_selector: '#logo > p > img' + retrieved_on: '2025-12-26T18:46:19.320504+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.breziny.net/templates/yoo_cloud/apple_touch_icon.png + source_url: https://www.breziny.net/index.php/sluzby/knihovna + css_selector: '[document] > html.uk-notouch > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:46:19.320504+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-53-POL-L-MKVKUP.yaml b/data/custodian/CZ-53-POL-L-MKVKUP.yaml index 7afb9fbd89..a7dbd52363 100644 --- a/data/custodian/CZ-53-POL-L-MKVKUP.yaml +++ b/data/custodian/CZ-53-POL-L-MKVKUP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-POL-L-MKVKUP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-POL-L-MKVKUP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-POL-L-MKVKUP ghcid_numeric: 16665298841981273465 valid_from: '2025-12-06T23:37:40.611894+00:00' @@ -208,3 +209,22 @@ location: postal_code: 572 01 street_address: Kamenec u Poličky 90 normalization_timestamp: '2025-12-09T10:53:39.012333+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:46:24.625825+00:00' + source_url: http://www.obec-kamenec.cz/index.php?hmn=1&vmn=8 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.obec-kamenec.cz/png/osh-ico.png + source_url: http://www.obec-kamenec.cz/index.php?hmn=1&vmn=8 + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T18:46:24.625825+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-53-POL-L-MKVS.yaml b/data/custodian/CZ-53-POL-L-MKVS.yaml index 756378c6d6..42d917cb9c 100644 --- a/data/custodian/CZ-53-POL-L-MKVS.yaml +++ b/data/custodian/CZ-53-POL-L-MKVS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-POL-L-MKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-POL-L-MKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-POL-L-MKVS ghcid_numeric: 11492796829955876413 valid_from: '2025-12-06T23:37:40.714858+00:00' @@ -208,3 +209,22 @@ location: postal_code: 572 01 street_address: Sádek 150 normalization_timestamp: '2025-12-09T10:53:39.064814+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:46:38.822642+00:00' + source_url: https://tritius.knihovna.policka.org/library/Sadek + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna.policka.org/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna.policka.org/library/Sadek + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:46:38.822642+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-53-POL-M-MMGPK.yaml b/data/custodian/CZ-53-POL-M-MMGPK.yaml index 9469c51740..5aee2eb8ab 100644 --- a/data/custodian/CZ-53-POL-M-MMGPK.yaml +++ b/data/custodian/CZ-53-POL-M-MMGPK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-POL-M-MMGPK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-POL-M-MMGPK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-POL-M-MMGPK ghcid_numeric: 12163036953645492239 valid_from: '2025-12-06T23:37:20.111447+00:00' @@ -207,3 +208,22 @@ location: postal_code: 572 01 street_address: Tylova 114 normalization_timestamp: '2025-12-09T10:53:39.142508+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:46:49.537432+00:00' + source_url: https://www.muzeum-policka.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.muzeum-policka.cz/templates/CBM-25/favicon.ico + source_url: https://www.muzeum-policka.cz + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T18:46:49.537432+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-53-PRA-L-OKVP.yaml b/data/custodian/CZ-53-PRA-L-OKVP.yaml index 3e7dc6c9df..15a9446217 100644 --- a/data/custodian/CZ-53-PRA-L-OKVP.yaml +++ b/data/custodian/CZ-53-PRA-L-OKVP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRA-L-OKVP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRA-L-OKVP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRA-L-OKVP ghcid_numeric: 1583967970570806418 valid_from: '2025-12-06T23:37:43.329259+00:00' @@ -208,3 +209,22 @@ location: postal_code: 538 04 street_address: Školní 116 normalization_timestamp: '2025-12-09T10:53:39.192251+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:46:57.990048+00:00' + source_url: https://prachovice-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prachovice-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://prachovice-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:46:57.990048+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-53-PRE-L-OKS.yaml b/data/custodian/CZ-53-PRE-L-OKS.yaml index 2cf80aa446..e9c6d177bc 100644 --- a/data/custodian/CZ-53-PRE-L-OKS.yaml +++ b/data/custodian/CZ-53-PRE-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRE-L-OKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRE-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRE-L-OKS ghcid_numeric: 13560872725739111361 valid_from: '2025-12-06T23:37:40.338457+00:00' @@ -208,3 +209,22 @@ location: postal_code: 535 01 street_address: Semín 102 normalization_timestamp: '2025-12-09T10:53:39.292793+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:47:18.334117+00:00' + source_url: http://seminuprelouce.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://seminuprelouce.cz/html/images/favicon.ico + source_url: http://seminuprelouce.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T18:47:18.334117+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-53-PRE-L-OKT.yaml b/data/custodian/CZ-53-PRE-L-OKT.yaml index b9dbc56810..47f4587521 100644 --- a/data/custodian/CZ-53-PRE-L-OKT.yaml +++ b/data/custodian/CZ-53-PRE-L-OKT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRE-L-OKT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRE-L-OKT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRE-L-OKT ghcid_numeric: 3044207816539121872 valid_from: '2025-12-06T23:37:40.335332+00:00' @@ -208,3 +209,28 @@ location: postal_code: 535 01 street_address: Lipová 93 normalization_timestamp: '2025-12-09T10:53:39.320837+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:47:26.173929+00:00' + source_url: https://www.trnavka-obec.cz/kontakt-1/kontakt + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.trnavka-obec.cz/skins/trnavka-obec.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.trnavka-obec.cz/kontakt-1/kontakt + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:47:26.173929+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.trnavka-obec.cz/data/headerfooter/header_images/vlajkatrnavka.jpg + source_url: https://www.trnavka-obec.cz/kontakt-1/kontakt + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-26T18:47:26.173929+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-53-PRE-L-OVKB.yaml b/data/custodian/CZ-53-PRE-L-OVKB.yaml index a7c9a374dd..ca86d93509 100644 --- a/data/custodian/CZ-53-PRE-L-OVKB.yaml +++ b/data/custodian/CZ-53-PRE-L-OVKB.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRE-L-OVKB - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRE-L-OVKB valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRE-L-OVKB ghcid_numeric: 17156673900594761144 valid_from: '2025-12-06T23:37:40.327802+00:00' @@ -214,3 +215,22 @@ location: postal_code: 535 01 street_address: Bahníkova 192 normalization_timestamp: '2025-12-09T10:53:39.382709+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:47:39.711044+00:00' + source_url: https://kkpce.tritius.cz/library/brehy + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kkpce.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kkpce.tritius.cz/library/brehy + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:47:39.711044+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-53-PRI-L-MKP.yaml b/data/custodian/CZ-53-PRI-L-MKP.yaml index 86baf5b459..25429128fa 100644 --- a/data/custodian/CZ-53-PRI-L-MKP.yaml +++ b/data/custodian/CZ-53-PRI-L-MKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRI-L-MKP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRI-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRI-L-MKP ghcid_numeric: 1130299554055811320 valid_from: '2025-12-06T23:37:40.737720+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 44 street_address: Příluka 61 normalization_timestamp: '2025-12-09T10:53:39.427135+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:47:50.599099+00:00' + source_url: https://www.priluka.cz/mistni-knihovna/oteviraci-doba-1 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.priluka.cz/favicon.ico + source_url: https://www.priluka.cz/mistni-knihovna/oteviraci-doba-1 + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:47:50.599099+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-53-PRO-L-MKP.yaml b/data/custodian/CZ-53-PRO-L-MKP.yaml index 3c98694a85..ce9d0a1afc 100644 --- a/data/custodian/CZ-53-PRO-L-MKP.yaml +++ b/data/custodian/CZ-53-PRO-L-MKP.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRO-L-MKP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRO-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRO-L-MKP ghcid_numeric: 4627904737267411680 valid_from: '2025-12-06T23:37:21.275167+00:00' @@ -216,3 +217,31 @@ location: country: *id005 postal_code: 539 44 normalization_timestamp: '2025-12-09T10:53:39.451516+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:47:56.195489+00:00' + source_url: https://www.knihovnaprosec.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.knihovnaprosec.cz/wp-content/uploads/2021/06/cropped-burza_knih2019podzim.png + source_url: https://www.knihovnaprosec.cz + css_selector: '#masthead > div.custom-header > div.site-branding > div.wrap > + a.custom-logo-link > img.custom-logo' + retrieved_on: '2025-12-26T18:47:56.195489+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Městská knihovna Proseč + - claim_type: favicon_url + claim_value: https://www.knihovnaprosec.cz/wp-content/uploads/2021/06/ikona.png + source_url: https://www.knihovnaprosec.cz + css_selector: '[document] > html.js.svg > head > link:nth-of-type(10)' + retrieved_on: '2025-12-26T18:47:56.195489+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-53-PRO-L-OKVBUS.yaml b/data/custodian/CZ-53-PRO-L-OKVBUS.yaml index be40c33c59..99d9dc7f85 100644 --- a/data/custodian/CZ-53-PRO-L-OKVBUS.yaml +++ b/data/custodian/CZ-53-PRO-L-OKVBUS.yaml @@ -201,3 +201,22 @@ location: postal_code: 539 44 street_address: Bor u Skutče normalization_timestamp: '2025-12-09T10:53:39.476509+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:01.769794+00:00' + source_url: https://www.mastale.cz/cs/obecni-urad-bor-u-skutce + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mastale.cz/sites/default/files/logo.png + source_url: https://www.mastale.cz/cs/obecni-urad-bor-u-skutce + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-26T18:48:01.769794+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-53-PRO-L-OKVP.yaml b/data/custodian/CZ-53-PRO-L-OKVP.yaml index 2b55a6e929..d35cefcca6 100644 --- a/data/custodian/CZ-53-PRO-L-OKVP.yaml +++ b/data/custodian/CZ-53-PRO-L-OKVP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRO-L-OKVP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRO-L-OKVP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRO-L-OKVP ghcid_numeric: 7595137850817274235 valid_from: '2025-12-06T23:37:40.156125+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 76 street_address: Prosetín 22 normalization_timestamp: '2025-12-09T10:53:39.498618+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:06.684209+00:00' + source_url: https://prosetin-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prosetin-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://prosetin-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:48:06.684209+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-53-PRO-L-ZOKVP.yaml b/data/custodian/CZ-53-PRO-L-ZOKVP.yaml index 4fe26dc11c..5514925a2f 100644 --- a/data/custodian/CZ-53-PRO-L-ZOKVP.yaml +++ b/data/custodian/CZ-53-PRO-L-ZOKVP.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PRO-L-ZOKVP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PRO-L-ZOKVP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PRO-L-ZOKVP ghcid_numeric: 8138357610277641763 valid_from: '2025-12-06T23:37:40.147628+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 44 street_address: Perálec 24 normalization_timestamp: '2025-12-09T10:53:39.523323+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:12.883792+00:00' + source_url: http://www.peralec.cz/obec-peralec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.peralec.cz/favicon.ico + source_url: http://www.peralec.cz/obec-peralec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:48:12.883792+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-53-PUS-L-MKVPK.yaml b/data/custodian/CZ-53-PUS-L-MKVPK.yaml index f30e4a6d53..787995a60c 100644 --- a/data/custodian/CZ-53-PUS-L-MKVPK.yaml +++ b/data/custodian/CZ-53-PUS-L-MKVPK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-PUS-L-MKVPK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-PUS-L-MKVPK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-PUS-L-MKVPK ghcid_numeric: 2083938856859934696 valid_from: '2025-12-06T23:37:40.740819+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 82 street_address: Pustá Kamenice 64 normalization_timestamp: '2025-12-09T10:53:39.554203+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:18.129244+00:00' + source_url: https://tritius.knihovna.policka.org/library/pustakamenice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovna.policka.org/apple-touch-icon-180x180.png + source_url: https://tritius.knihovna.policka.org/library/pustakamenice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:48:18.129244+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-53-RAD-L-MKVR.yaml b/data/custodian/CZ-53-RAD-L-MKVR.yaml index e87a5e05d8..0740ec4b33 100644 --- a/data/custodian/CZ-53-RAD-L-MKVR.yaml +++ b/data/custodian/CZ-53-RAD-L-MKVR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-RAD-L-MKVR - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-RAD-L-MKVR valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-RAD-L-MKVR ghcid_numeric: 17101457561107653804 valid_from: '2025-12-06T23:37:40.743956+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 07 street_address: Radiměř 515 normalization_timestamp: '2025-12-09T10:53:39.579359+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:23.726314+00:00' + source_url: https://tritius.booksy.cz/library/radimer + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/radimer + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:48:23.726314+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-53-RET-L-OKR.yaml b/data/custodian/CZ-53-RET-L-OKR.yaml index 0e1ce64207..7cc11c171f 100644 --- a/data/custodian/CZ-53-RET-L-OKR.yaml +++ b/data/custodian/CZ-53-RET-L-OKR.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-RET-L-OKR - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-RET-L-OKR valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-RET-L-OKR ghcid_numeric: 2978465874192786505 valid_from: '2025-12-08T11:21:36.662491+00:00' @@ -212,3 +213,22 @@ location: postal_code: 561 41 street_address: Řetová 190 normalization_timestamp: '2025-12-09T10:53:39.629736+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:35.478456+00:00' + source_url: https://vufind.knihovna-uo.cz/retova + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/retova/themes/bootprint3Rbit-retova/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/retova + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:48:35.478456+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-53-ROH-L-OKRB.yaml b/data/custodian/CZ-53-ROH-L-OKRB.yaml index 1ccafad2e5..c70e8218b9 100644 --- a/data/custodian/CZ-53-ROH-L-OKRB.yaml +++ b/data/custodian/CZ-53-ROH-L-OKRB.yaml @@ -219,3 +219,22 @@ location: postal_code: 533 42 street_address: Rohovládova Bělá 32 normalization_timestamp: '2025-12-09T10:53:39.657741+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:43.001253+00:00' + source_url: https://www.rohovladovabela.cz/obec-1/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rohovladovabela.cz/skins/rohovladovabela.cz_lego3/favicons/safari-pinned-tab.svg + source_url: https://www.rohovladovabela.cz/obec-1/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:48:43.001253+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-53-ROS-L-OKR.yaml b/data/custodian/CZ-53-ROS-L-OKR.yaml index aae8c18697..9ee72ceafb 100644 --- a/data/custodian/CZ-53-ROS-L-OKR.yaml +++ b/data/custodian/CZ-53-ROS-L-OKR.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-ROS-L-OKR - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-ROS-L-OKR valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-ROS-L-OKR ghcid_numeric: 5086306424311024137 valid_from: '2025-12-06T23:37:42.746757+00:00' @@ -205,3 +206,22 @@ location: postal_code: 538 34 street_address: Rosice 96 normalization_timestamp: '2025-12-09T10:53:39.739038+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:48:58.008588+00:00' + source_url: https://rosice-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rosice-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://rosice-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:48:58.008588+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-53-RYC-L-MKVRM.yaml b/data/custodian/CZ-53-RYC-L-MKVRM.yaml index 31d183b886..379a550975 100644 --- a/data/custodian/CZ-53-RYC-L-MKVRM.yaml +++ b/data/custodian/CZ-53-RYC-L-MKVRM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-RYC-L-MKVRM - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-RYC-L-MKVRM valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-RYC-L-MKVRM ghcid_numeric: 2065649543546747504 valid_from: '2025-12-06T23:37:40.750553+00:00' @@ -205,3 +206,22 @@ location: postal_code: 569 34 street_address: Rychnov na Moravě 63 normalization_timestamp: '2025-12-09T10:53:39.808449+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:49:13.913824+00:00' + source_url: https://rychnovnm-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rychnovnm-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://rychnovnm-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:49:13.913824+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-53-SEC-L-OKH.yaml b/data/custodian/CZ-53-SEC-L-OKH.yaml index 56793420b2..4de5a8fa8c 100644 --- a/data/custodian/CZ-53-SEC-L-OKH.yaml +++ b/data/custodian/CZ-53-SEC-L-OKH.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SEC-L-OKH - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SEC-L-OKH valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SEC-L-OKH ghcid_numeric: 17733073244248552051 valid_from: '2025-12-06T23:37:40.170310+00:00' @@ -200,3 +201,22 @@ location: postal_code: 538 07 street_address: Hoješín normalization_timestamp: '2025-12-09T10:53:39.834401+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:49:20.307368+00:00' + source_url: https://www.mestosec.cz/index.asp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mestosec.cz/html/images/favicon.ico + source_url: https://www.mestosec.cz/index.asp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T18:49:20.307368+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-53-SED-L-MKVS.yaml b/data/custodian/CZ-53-SED-L-MKVS.yaml index ff4e9a5c0f..d220c28ea3 100644 --- a/data/custodian/CZ-53-SED-L-MKVS.yaml +++ b/data/custodian/CZ-53-SED-L-MKVS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SED-L-MKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SED-L-MKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SED-L-MKVS ghcid_numeric: 15509659383687859078 valid_from: '2025-12-06T23:37:40.757394+00:00' @@ -205,3 +206,32 @@ location: postal_code: 570 01 street_address: Sedliště 46 normalization_timestamp: '2025-12-09T10:53:39.862264+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:49:25.371721+00:00' + source_url: https://www.sedliste.net/knihovna + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://406897a1fd.clvaw-cdnwnd.com/9fd6e1641bde216d766ab5e43a47da2d/200000939-ce189ce18b/znak%20jpeg.jpeg?ph=406897a1fd + source_url: https://www.sedliste.net/knihovna + css_selector: '#wnd_LogoBlock_9114 > div.b-l-c.logo-content > a.b-l-link.logo-link + > div.b-l-image.logo-image > div.b-l-image-w.logo-image-cell > picture > source + > img.wnd-logo-img' + retrieved_on: '2025-12-26T18:49:25.371721+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://duyn491kcolsw.cloudfront.net/files/2d/2di/2div3h.svg?ph=406897a1fd + source_url: https://www.sedliste.net/knihovna + css_selector: '[document] > html.js.sizes > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T18:49:25.371721+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-53-SEZ-L-OKUUS.yaml b/data/custodian/CZ-53-SEZ-L-OKUUS.yaml index 723770606b..00fad68edb 100644 --- a/data/custodian/CZ-53-SEZ-L-OKUUS.yaml +++ b/data/custodian/CZ-53-SEZ-L-OKUUS.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SEZ-L-OKUUS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SEZ-L-OKUUS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SEZ-L-OKUUS ghcid_numeric: 14796937043728464811 valid_from: '2025-12-08T11:21:34.814870+00:00' @@ -205,3 +206,22 @@ location: postal_code: 533 04 street_address: Újezd u Sezemic 30 normalization_timestamp: '2025-12-09T10:53:39.887199+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:49:32.308229+00:00' + source_url: https://www.ujezdusezemic.cz/kontakt + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ujezdusezemic.cz/skins/ujezdusezemic.cz_lego2/favicons/safari-pinned-tab.svg + source_url: https://www.ujezdusezemic.cz/kontakt + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:49:32.308229+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-53-SKU-L-MKS.yaml b/data/custodian/CZ-53-SKU-L-MKS.yaml index 96685a367a..9ec6bd4117 100644 --- a/data/custodian/CZ-53-SKU-L-MKS.yaml +++ b/data/custodian/CZ-53-SKU-L-MKS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SKU-L-MKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SKU-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SKU-L-MKS ghcid_numeric: 2366968506395297134 valid_from: '2025-12-06T23:37:21.341050+00:00' @@ -223,3 +224,22 @@ location: postal_code: 539 73 street_address: Smetanova 254 normalization_timestamp: '2025-12-09T10:53:39.913300+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:49:37.157299+00:00' + source_url: https://katalog.knihovna-skutec.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-skutec.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-skutec.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:49:37.157299+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-53-SLA-L-NHKNLSPSSK.yaml b/data/custodian/CZ-53-SLA-L-NHKNLSPSSK.yaml index 6de0fce7d9..f334df7572 100644 --- a/data/custodian/CZ-53-SLA-L-NHKNLSPSSK.yaml +++ b/data/custodian/CZ-53-SLA-L-NHKNLSPSSK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SLA-L-NHKNLSPSSK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SLA-L-NHKNLSPSSK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SLA-L-NHKNLSPSSK ghcid_numeric: 12993733291616609272 valid_from: '2025-12-06T23:37:17.402376+00:00' @@ -217,3 +218,22 @@ location: postal_code: 538 21 street_address: Zámecký park 169 normalization_timestamp: '2025-12-09T10:53:40.045844+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:50:05.527613+00:00' + source_url: https://www.nhkladruby.cz/slatinany-hrebcin + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nhkladruby.cz/data/Favicons/nhkladrubycz/apple-touch-icon-180x180.png + source_url: https://www.nhkladruby.cz/slatinany-hrebcin + css_selector: '[document] > html.js.homepage > head > link:nth-of-type(10)' + retrieved_on: '2025-12-26T18:50:05.527613+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-53-SLO-L-OKS.yaml b/data/custodian/CZ-53-SLO-L-OKS.yaml index cbc87dd1c1..af65fc0050 100644 --- a/data/custodian/CZ-53-SLO-L-OKS.yaml +++ b/data/custodian/CZ-53-SLO-L-OKS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SLO-L-OKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SLO-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SLO-L-OKS ghcid_numeric: 5084348864713073610 valid_from: '2025-12-06T23:37:41.015275+00:00' @@ -205,3 +206,22 @@ location: postal_code: 565 53 street_address: Horní Sloupnice 399 normalization_timestamp: '2025-12-09T10:53:40.073860+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:50:10.441680+00:00' + source_url: https://vufind.knihovna-uo.cz/sloupnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/sloupnice/themes/bootprint3Rbit-sloupnice/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/sloupnice + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:50:10.441680+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-53-SRU-L-OKS.yaml b/data/custodian/CZ-53-SRU-L-OKS.yaml index e399e55e97..70d8efc629 100644 --- a/data/custodian/CZ-53-SRU-L-OKS.yaml +++ b/data/custodian/CZ-53-SRU-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SRU-L-OKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SRU-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SRU-L-OKS ghcid_numeric: 11725914629150632004 valid_from: '2025-12-06T23:37:41.021395+00:00' @@ -205,3 +206,22 @@ location: postal_code: 565 44 street_address: Sruby 28 normalization_timestamp: '2025-12-09T10:53:40.127192+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:50:20.780615+00:00' + source_url: https://knihovnasruby.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnasruby.webk.cz/themes/cbdb-klasicky/letni/logo1.png + source_url: https://knihovnasruby.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T18:50:20.780615+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-53-SUC-L-OKVSL.yaml b/data/custodian/CZ-53-SUC-L-OKVSL.yaml index 2e99ad399a..149abc531e 100644 --- a/data/custodian/CZ-53-SUC-L-OKVSL.yaml +++ b/data/custodian/CZ-53-SUC-L-OKVSL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SUC-L-OKVSL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SUC-L-OKVSL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SUC-L-OKVSL ghcid_numeric: 10506420120372127853 valid_from: '2025-12-06T23:37:40.763610+00:00' @@ -208,3 +209,30 @@ location: postal_code: 569 53 street_address: Suchá Lhota normalization_timestamp: '2025-12-09T10:53:40.262059+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:50:39.978616+00:00' + source_url: http://www.suchalhota.cz/obecni-knihovna/zakladni-informace-1 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.suchalhota.cz/soubory-zahlavi/logo-vr-.jpg + source_url: http://www.suchalhota.cz/obecni-knihovna/zakladni-informace-1 + css_selector: '#fotozahlavi_41 > img.slickimg' + retrieved_on: '2025-12-26T18:50:39.978616+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo-vr-.jpg + - claim_type: favicon_url + claim_value: http://www.suchalhota.cz/favicon.ico + source_url: http://www.suchalhota.cz/obecni-knihovna/zakladni-informace-1 + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:50:39.978616+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-53-SUD-L-OKS.yaml b/data/custodian/CZ-53-SUD-L-OKS.yaml index 8d1c9a62b9..ffd403b8e5 100644 --- a/data/custodian/CZ-53-SUD-L-OKS.yaml +++ b/data/custodian/CZ-53-SUD-L-OKS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SUD-L-OKS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SUD-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SUD-L-OKS ghcid_numeric: 3768418057754091812 valid_from: '2025-12-06T23:37:41.025359+00:00' @@ -205,3 +206,22 @@ location: postal_code: 561 13 street_address: Sudslava 64 normalization_timestamp: '2025-12-09T10:53:40.288704+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:50:44.749139+00:00' + source_url: https://vufind.knihovna-uo.cz/sudslava + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/sudslava/themes/bootprint3Rbit-sudslava/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/sudslava + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:50:44.749139+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-53-SVA-L-OKSJ.yaml b/data/custodian/CZ-53-SVA-L-OKSJ.yaml index d227722405..f997051d83 100644 --- a/data/custodian/CZ-53-SVA-L-OKSJ.yaml +++ b/data/custodian/CZ-53-SVA-L-OKSJ.yaml @@ -210,3 +210,22 @@ location: geocoding_timestamp: '2025-12-09T21:45:47.644116+00:00' geocoding_method: CITY_NAME_LOOKUP geonames_matched_name: Choceň +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:50:49.735555+00:00' + source_url: https://knihovnasvatyjiri.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnasvatyjiri.webk.cz/themes/cbdb-klasicky/default/logo1.png + source_url: https://knihovnasvatyjiri.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-26T18:50:49.735555+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-53-SVI-E-GJSSPSJZSS.yaml b/data/custodian/CZ-53-SVI-E-GJSSPSJZSS.yaml index ab341fc589..03c3e8306c 100644 --- a/data/custodian/CZ-53-SVI-E-GJSSPSJZSS.yaml +++ b/data/custodian/CZ-53-SVI-E-GJSSPSJZSS.yaml @@ -45,13 +45,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SVI-E-GJSSPSJZSS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SVI-E-GJSSPSJZSS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SVI-E-GJSSPSJZSS ghcid_numeric: 18266371239995501615 valid_from: '2025-12-08T11:21:38.836269+00:00' @@ -221,3 +222,31 @@ location: postal_code: 568 02 street_address: Sokolovská 1638 normalization_timestamp: '2025-12-09T10:53:40.352038+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:50:57.233757+00:00' + source_url: http://www.gy.svitavy.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.gyoa.svitavy.cz/wp-content/uploads/2024/08/gyoa_fb2mensi.png + source_url: http://www.gy.svitavy.cz + css_selector: '#masthead > div.container > div.site-branding > a.custom-logo-link + > img.custom-logo' + retrieved_on: '2025-12-26T18:50:57.233757+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Gymnázium, obchodní akademie a jazyková škola Svitavy + - claim_type: favicon_url + claim_value: http://www.gyoa.svitavy.cz/wp-content/uploads/2024/08/gyoa_fb2mensi.png + source_url: http://www.gy.svitavy.cz + css_selector: '[document] > html.js_active.vc_desktop > head > link:nth-of-type(48)' + retrieved_on: '2025-12-26T18:50:57.233757+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-53-SVI-L-MKVS.yaml b/data/custodian/CZ-53-SVI-L-MKVS.yaml index 32b6d304db..7b34a2af92 100644 --- a/data/custodian/CZ-53-SVI-L-MKVS.yaml +++ b/data/custodian/CZ-53-SVI-L-MKVS.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SVI-L-MKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SVI-L-MKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SVI-L-MKVS ghcid_numeric: 10751528666982197599 valid_from: '2025-12-06T23:37:20.130976+00:00' @@ -231,3 +232,31 @@ location: postal_code: 568 02 street_address: Wolkerova alej 92/18 normalization_timestamp: '2025-12-09T10:53:40.395958+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:51:04.644560+00:00' + source_url: https://tritius.booksy.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tritius.booksy.cz/images/comgate_logo.png + source_url: https://tritius.booksy.cz + css_selector: '#footer > div.container > nav.row.hidden-print > div.col-sm-12.col-md-6 + > div.comgate-logo > span > img' + retrieved_on: '2025-12-26T18:51:04.644560+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Comgate + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:51:04.644560+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-53-SVI-L-OKVD.yaml b/data/custodian/CZ-53-SVI-L-OKVD.yaml index d935bae6de..e3a4800cf6 100644 --- a/data/custodian/CZ-53-SVI-L-OKVD.yaml +++ b/data/custodian/CZ-53-SVI-L-OKVD.yaml @@ -209,3 +209,22 @@ location: postal_code: 568 02 street_address: Dětřichov 42 normalization_timestamp: '2025-12-09T10:53:40.425892+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:51:10.236380+00:00' + source_url: https://tritius.booksy.cz/library/detrichov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/detrichov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:51:10.236380+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-53-SVI-L-OKVL.yaml b/data/custodian/CZ-53-SVI-L-OKVL.yaml index 472a738480..1f89844221 100644 --- a/data/custodian/CZ-53-SVI-L-OKVL.yaml +++ b/data/custodian/CZ-53-SVI-L-OKVL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SVI-L-OKVL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SVI-L-OKVL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SVI-L-OKVL ghcid_numeric: 11373499549668121157 valid_from: '2025-12-06T23:37:40.845354+00:00' @@ -205,3 +206,22 @@ location: postal_code: 571 01 street_address: Linhartice 16 normalization_timestamp: '2025-12-09T10:53:40.455065+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:51:15.375145+00:00' + source_url: https://linhartice-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://linhartice-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://linhartice-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:51:15.375145+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-53-SVI-L-OKVO.yaml b/data/custodian/CZ-53-SVI-L-OKVO.yaml index adc757fd75..042190aad1 100644 --- a/data/custodian/CZ-53-SVI-L-OKVO.yaml +++ b/data/custodian/CZ-53-SVI-L-OKVO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SVI-L-OKVO - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SVI-L-OKVO valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SVI-L-OKVO ghcid_numeric: 2607606152812769566 valid_from: '2025-12-06T23:37:40.835280+00:00' @@ -205,3 +206,22 @@ location: postal_code: 568 02 street_address: Opatovec 40 normalization_timestamp: '2025-12-09T10:53:40.481067+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:51:21.020065+00:00' + source_url: https://tritius.booksy.cz/library/opatovec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/opatovec + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:51:21.020065+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-53-SVO-L-OKSDL.yaml b/data/custodian/CZ-53-SVO-L-OKSDL.yaml index 4b836a8c8d..44333b7584 100644 --- a/data/custodian/CZ-53-SVO-L-OKSDL.yaml +++ b/data/custodian/CZ-53-SVO-L-OKSDL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SVO-L-OKSDL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SVO-L-OKSDL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SVO-L-OKSDL ghcid_numeric: 11565024726149421213 valid_from: '2025-12-06T23:37:40.773351+00:00' @@ -205,3 +206,32 @@ location: postal_code: 569 73 street_address: Dolní Lhota 31 normalization_timestamp: '2025-12-09T10:53:40.602959+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:51:49.086971+00:00' + source_url: https://mestyssvojanov.cz/w/knihovny + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://mestyssvojanov.cz/w/wp-content/uploads/2020/08/svojanov.gif + source_url: https://mestyssvojanov.cz/w/knihovny + css_selector: '#header > div.header__inner > div.header__content:nth-of-type(2) + > div.lsvr-container > div.header__content-inner > div.header-logo.header-logo--front + > a.header-logo__link > img.header-logo__image' + retrieved_on: '2025-12-26T18:51:49.086971+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Městys Svojanov + - claim_type: favicon_url + claim_value: https://mestyssvojanov.cz/w/wp-content/uploads/2020/08/vel02-150x150.jpg + source_url: https://mestyssvojanov.cz/w/knihovny + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-26T18:51:49.086971+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/CZ-53-SVO-L-OKVS.yaml b/data/custodian/CZ-53-SVO-L-OKVS.yaml index 5127f3782e..34b4a300e4 100644 --- a/data/custodian/CZ-53-SVO-L-OKVS.yaml +++ b/data/custodian/CZ-53-SVO-L-OKVS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SVO-L-OKVS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SVO-L-OKVS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SVO-L-OKVS ghcid_numeric: 2957219203520316124 valid_from: '2025-12-06T23:37:40.766700+00:00' @@ -205,3 +206,32 @@ location: postal_code: 569 73 street_address: Svojanov 19 normalization_timestamp: '2025-12-09T10:53:40.630077+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:51:54.133925+00:00' + source_url: https://mestyssvojanov.cz/w/knihovny + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://mestyssvojanov.cz/w/wp-content/uploads/2020/08/svojanov.gif + source_url: https://mestyssvojanov.cz/w/knihovny + css_selector: '#header > div.header__inner > div.header__content:nth-of-type(2) + > div.lsvr-container > div.header__content-inner > div.header-logo > a.header-logo__link + > img.header-logo__image' + retrieved_on: '2025-12-26T18:51:54.133925+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Městys Svojanov + - claim_type: favicon_url + claim_value: https://mestyssvojanov.cz/w/wp-content/uploads/2020/08/vel02-150x150.jpg + source_url: https://mestyssvojanov.cz/w/knihovny + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-26T18:51:54.133925+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/CZ-53-SVO-L-OKVSS.yaml b/data/custodian/CZ-53-SVO-L-OKVSS.yaml index ee9e3870e5..2c9ca66d88 100644 --- a/data/custodian/CZ-53-SVO-L-OKVSS.yaml +++ b/data/custodian/CZ-53-SVO-L-OKVSS.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-SVO-L-OKVSS - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-SVO-L-OKVSS valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-SVO-L-OKVSS ghcid_numeric: 5811252721132629305 valid_from: '2025-12-06T23:37:40.769806+00:00' @@ -205,3 +206,32 @@ location: postal_code: 569 73 street_address: Starý Svojanov 81 normalization_timestamp: '2025-12-09T10:53:40.655222+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:51:59.388594+00:00' + source_url: https://mestyssvojanov.cz/w/knihovny + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://mestyssvojanov.cz/w/wp-content/uploads/2020/08/svojanov.gif + source_url: https://mestyssvojanov.cz/w/knihovny + css_selector: '#header > div.header__inner > div.header__content:nth-of-type(2) + > div.lsvr-container > div.header__content-inner > div.header-logo.header-logo--front + > a.header-logo__link > img.header-logo__image' + retrieved_on: '2025-12-26T18:51:59.388594+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Městys Svojanov + - claim_type: favicon_url + claim_value: https://mestyssvojanov.cz/w/wp-content/uploads/2020/08/vel02-150x150.jpg + source_url: https://mestyssvojanov.cz/w/knihovny + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-26T18:51:59.388594+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/CZ-53-TEC-L-MLKT.yaml b/data/custodian/CZ-53-TEC-L-MLKT.yaml index e355bc5a51..988fc5602d 100644 --- a/data/custodian/CZ-53-TEC-L-MLKT.yaml +++ b/data/custodian/CZ-53-TEC-L-MLKT.yaml @@ -206,3 +206,22 @@ location: postal_code: 561 66 street_address: Těchonín 80 normalization_timestamp: '2025-12-09T10:53:40.701526+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:06.583711+00:00' + source_url: https://techonin.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://techonin.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://techonin.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:52:06.583711+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-53-TEL-L-MKVT.yaml b/data/custodian/CZ-53-TEL-L-MKVT.yaml index 3e8f9e1fbf..526d120546 100644 --- a/data/custodian/CZ-53-TEL-L-MKVT.yaml +++ b/data/custodian/CZ-53-TEL-L-MKVT.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-TEL-L-MKVT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-TEL-L-MKVT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-TEL-L-MKVT ghcid_numeric: 6784355552985682958 valid_from: '2025-12-06T23:37:40.776514+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 94 street_address: Telecí 156 normalization_timestamp: '2025-12-09T10:53:40.727244+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:11.376298+00:00' + source_url: http://teleci.cz/infoknihovna.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://teleci.cz/favicon.ico + source_url: http://teleci.cz/infoknihovna.php + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T18:52:11.376298+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-53-TET-L-MLKT.yaml b/data/custodian/CZ-53-TET-L-MLKT.yaml index cb78b0bf73..3824b95a65 100644 --- a/data/custodian/CZ-53-TET-L-MLKT.yaml +++ b/data/custodian/CZ-53-TET-L-MLKT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-TET-L-MLKT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-TET-L-MLKT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-TET-L-MLKT ghcid_numeric: 5724590413292649828 valid_from: '2025-12-06T23:37:40.405588+00:00' @@ -208,3 +209,22 @@ location: postal_code: 533 16 street_address: Tetov normalization_timestamp: '2025-12-09T10:53:40.754192+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:16.228068+00:00' + source_url: https://www.tetov.cz/dulezite-kontakty + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tetov.cz/image.php?nid=975&oid=10779773&width=32 + source_url: https://www.tetov.cz/dulezite-kontakty + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-26T18:52:16.228068+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-53-TRE-L-MKT.yaml b/data/custodian/CZ-53-TRE-L-MKT.yaml index e582b39e22..d86ca42e35 100644 --- a/data/custodian/CZ-53-TRE-L-MKT.yaml +++ b/data/custodian/CZ-53-TRE-L-MKT.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-TRE-L-MKT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-TRE-L-MKT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-TRE-L-MKT ghcid_numeric: 16108626599586959067 valid_from: '2025-12-06T23:37:24.956851+00:00' @@ -216,3 +217,22 @@ location: postal_code: 538 43 street_address: ul. 1.máje 56 normalization_timestamp: '2025-12-09T10:53:40.787296+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:21.013692+00:00' + source_url: https://katalog.knihovna-tremosnice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-tremosnice.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-tremosnice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:52:21.013692+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-53-TRE-L-MKVT.yaml b/data/custodian/CZ-53-TRE-L-MKVT.yaml index c1e0941afc..add3384bda 100644 --- a/data/custodian/CZ-53-TRE-L-MKVT.yaml +++ b/data/custodian/CZ-53-TRE-L-MKVT.yaml @@ -206,3 +206,22 @@ location: postal_code: 569 33 street_address: Třebařov 82 normalization_timestamp: '2025-12-09T10:53:40.824531+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:25.776635+00:00' + source_url: https://trebarov-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trebarov-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://trebarov-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:52:25.776635+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-53-TRE-L-OKT.yaml b/data/custodian/CZ-53-TRE-L-OKT.yaml index 9ff149b661..d40ec1b61c 100644 --- a/data/custodian/CZ-53-TRE-L-OKT.yaml +++ b/data/custodian/CZ-53-TRE-L-OKT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-TRE-L-OKT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-TRE-L-OKT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-TRE-L-OKT ghcid_numeric: 12313047830208036363 valid_from: '2025-12-06T23:37:41.034814+00:00' @@ -202,3 +203,22 @@ location: postal_code: 561 24 street_address: Třebovice 238 normalization_timestamp: '2025-12-09T10:53:40.893049+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:38.264484+00:00' + source_url: http://trebovice.knihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://trebovice.knihovna.cz/favicon.svg + source_url: http://trebovice.knihovna.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T18:52:38.264484+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-53-TRH-L-OKVTK.yaml b/data/custodian/CZ-53-TRH-L-OKVTK.yaml index ecc7e88627..f4ec60a444 100644 --- a/data/custodian/CZ-53-TRH-L-OKVTK.yaml +++ b/data/custodian/CZ-53-TRH-L-OKVTK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-TRH-L-OKVTK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-TRH-L-OKVTK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-TRH-L-OKVTK ghcid_numeric: 4780985329104752967 valid_from: '2025-12-06T23:37:23.027596+00:00' @@ -203,3 +204,22 @@ location: postal_code: 539 52 street_address: 5. května 45 normalization_timestamp: '2025-12-09T10:53:40.921212+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:44.218229+00:00' + source_url: https://www.trhovakamenice.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.trhovakamenice.cz/html/images/favicon.ico + source_url: https://www.trhovakamenice.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T18:52:44.218229+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-53-TRO-L-OKVT.yaml b/data/custodian/CZ-53-TRO-L-OKVT.yaml index 94b6e6624b..3f21867c7a 100644 --- a/data/custodian/CZ-53-TRO-L-OKVT.yaml +++ b/data/custodian/CZ-53-TRO-L-OKVT.yaml @@ -206,3 +206,22 @@ location: postal_code: 538 33 street_address: Trojovice 77 normalization_timestamp: '2025-12-09T10:53:40.946979+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:48.985521+00:00' + source_url: https://www.trojovice.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.trojovice.cz/favicon.svg + source_url: https://www.trojovice.cz/knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T18:52:48.985521+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-53-TRP-L-OKVT.yaml b/data/custodian/CZ-53-TRP-L-OKVT.yaml index 01efd41d20..c94ed9080d 100644 --- a/data/custodian/CZ-53-TRP-L-OKVT.yaml +++ b/data/custodian/CZ-53-TRP-L-OKVT.yaml @@ -209,3 +209,22 @@ location: postal_code: 569 74 street_address: Trpín 55 normalization_timestamp: '2025-12-09T10:53:40.975414+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:52:54.311636+00:00' + source_url: https://knihovna-trpin.webnode.cz/katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna-trpin.webnode.cz/favicon.svg + source_url: https://knihovna-trpin.webnode.cz/katalog + css_selector: '[document] > html.dk_fouc.js > head > link' + retrieved_on: '2025-12-26T18:52:54.311636+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-53-TRS-L-OKVT.yaml b/data/custodian/CZ-53-TRS-L-OKVT.yaml index 3750989f2b..43824e512c 100644 --- a/data/custodian/CZ-53-TRS-L-OKVT.yaml +++ b/data/custodian/CZ-53-TRS-L-OKVT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-TRS-L-OKVT - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-TRS-L-OKVT valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-TRS-L-OKVT ghcid_numeric: 17640260810147290682 valid_from: '2025-12-06T23:37:40.782254+00:00' @@ -212,3 +213,22 @@ location: postal_code: 569 57 street_address: Trstěnice 238 normalization_timestamp: '2025-12-09T10:53:40.999432+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:53:02.537515+00:00' + source_url: https://tritius.booksy.cz/library/trstenice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/trstenice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T18:53:02.537515+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-53-TRZ-L-MKVT.yaml b/data/custodian/CZ-53-TRZ-L-MKVT.yaml index 980e4c5548..9b38e160d0 100644 --- a/data/custodian/CZ-53-TRZ-L-MKVT.yaml +++ b/data/custodian/CZ-53-TRZ-L-MKVT.yaml @@ -206,3 +206,22 @@ location: postal_code: 570 01 street_address: Tržek 21 normalization_timestamp: '2025-12-09T10:53:41.027025+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:53:07.944398+00:00' + source_url: http://www.trzek.cz/mistni-knihovna/oteviraci-doba + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.trzek.cz/favicon.ico + source_url: http://www.trzek.cz/mistni-knihovna/oteviraci-doba + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:53:07.944398+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-53-UHR-L-OKVU.yaml b/data/custodian/CZ-53-UHR-L-OKVU.yaml index 61c6218540..ad2b4a31d3 100644 --- a/data/custodian/CZ-53-UHR-L-OKVU.yaml +++ b/data/custodian/CZ-53-UHR-L-OKVU.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-UHR-L-OKVU - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-UHR-L-OKVU valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-UHR-L-OKVU ghcid_numeric: 2138399927702071474 valid_from: '2025-12-08T11:21:24.182597+00:00' @@ -210,3 +211,22 @@ location: postal_code: 538 32 street_address: Úhřetice 36 normalization_timestamp: '2025-12-09T10:53:41.099055+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:53:28.005533+00:00' + source_url: https://uhretice.cz/knihovna-obce-a20 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://uhretice.cz/favicon.ico + source_url: https://uhretice.cz/knihovna-obce-a20 + css_selector: '[document] > html.js.canvas > head > link' + retrieved_on: '2025-12-26T18:53:28.005533+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-53-UNO-M-MMUNO.yaml b/data/custodian/CZ-53-UNO-M-MMUNO.yaml index 9f2ef05f85..cdd8f77919 100644 --- a/data/custodian/CZ-53-UNO-M-MMUNO.yaml +++ b/data/custodian/CZ-53-UNO-M-MMUNO.yaml @@ -232,3 +232,39 @@ location: youtube_status: NOT_FOUND youtube_search_query: Městské muzeum Ústí nad Orlicí official youtube_search_timestamp: '2025-12-09T09:34:28.959947+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:53:35.427677+00:00' + source_url: https://www.muzeum-uo.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.muzeum-uo.cz/wp-content/uploads/2023/09/logo_muzeum_uo.png + source_url: https://www.muzeum-uo.cz + css_selector: '[document] > html > body.home.wp-singular > header.elementor.elementor-2604 + > div.elementor-element.elementor-element-14cbd5e > div.e-con-inner > div.elementor-element.elementor-element-964caa0 + > div.elementor-element.elementor-element-bb484e6 > div.elementor-widget-container + > a > img.attachment-full.size-full' + retrieved_on: '2025-12-26T18:53:35.427677+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo Muzeum UO + - claim_type: favicon_url + claim_value: https://www.muzeum-uo.cz/wp-content/uploads/2024/07/cropped-log2-180x180.jpg + source_url: https://www.muzeum-uo.cz + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-26T18:53:35.427677+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.muzeum-uo.cz/wp-content/uploads/2024/01/van1-1024x639.jpg + source_url: https://www.muzeum-uo.cz + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T18:53:35.427677+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/CZ-53-UST-L-MKUNOPK.yaml b/data/custodian/CZ-53-UST-L-MKUNOPK.yaml index a632abdb24..1b322deb2f 100644 --- a/data/custodian/CZ-53-UST-L-MKUNOPK.yaml +++ b/data/custodian/CZ-53-UST-L-MKUNOPK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-UST-L-MKUNOPK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-UST-L-MKUNOPK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-UST-L-MKUNOPK ghcid_numeric: 11401983816985136768 valid_from: '2025-12-08T11:21:32.225584+00:00' @@ -216,3 +217,22 @@ location: postal_code: 562 01 street_address: Knapovec 8 normalization_timestamp: '2025-12-09T10:53:41.124085+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:53:40.196845+00:00' + source_url: https://vufind.knihovna-uo.cz/knapovec + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/knapovec/themes/bootprint3Rbit-knapovec/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/knapovec + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:53:40.196845+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-53-UST-L-NPKSONOK.yaml b/data/custodian/CZ-53-UST-L-NPKSONOK.yaml index a5d545ee14..6fd4fa7dc3 100644 --- a/data/custodian/CZ-53-UST-L-NPKSONOK.yaml +++ b/data/custodian/CZ-53-UST-L-NPKSONOK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-UST-L-NPKSONOK - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-UST-L-NPKSONOK valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-UST-L-NPKSONOK ghcid_numeric: 14333411450537917838 valid_from: '2025-12-06T23:37:20.514801+00:00' @@ -216,3 +217,32 @@ location: postal_code: 562 18 street_address: tř. Čs. armády 1076 normalization_timestamp: '2025-12-09T10:53:41.149105+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:53:46.427916+00:00' + source_url: https://knihovna.nempk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovna.nempk.cz/custom/design/logo.png + source_url: https://knihovna.nempk.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 > div > a > img' + retrieved_on: '2025-12-26T18:53:46.427916+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://knihovna.nempk.cz/favicon.png?v=2.3.0-32050 + source_url: https://knihovna.nempk.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T18:53:46.427916+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-53-UST-L-OKOPR.yaml b/data/custodian/CZ-53-UST-L-OKOPR.yaml index e70e8a2886..fba1341c3b 100644 --- a/data/custodian/CZ-53-UST-L-OKOPR.yaml +++ b/data/custodian/CZ-53-UST-L-OKOPR.yaml @@ -209,3 +209,22 @@ location: postal_code: 562 01 street_address: Rviště 24 normalization_timestamp: '2025-12-09T10:53:41.200571+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:53:55.817778+00:00' + source_url: https://rviste.katalog.kruo.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rviste.katalog.kruo.cz/themes/root/images/vufind-favicon.ico + source_url: https://rviste.katalog.kruo.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T18:53:55.817778+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-53-UST-L-OKVS.yaml b/data/custodian/CZ-53-UST-L-OKVS.yaml index 3396f0713e..291a9f0f85 100644 --- a/data/custodian/CZ-53-UST-L-OKVS.yaml +++ b/data/custodian/CZ-53-UST-L-OKVS.yaml @@ -206,3 +206,22 @@ location: postal_code: 562 01 street_address: Velká Skrovnice 30 normalization_timestamp: '2025-12-09T10:53:41.224512+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T18:54:00.709771+00:00' + source_url: https://vufind.knihovna-uo.cz/vskrovnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vufind.knihovna-uo.cz/vskrovnice/themes/bootprint3Rbit-vskrovnice/images/favicon.ico + source_url: https://vufind.knihovna-uo.cz/vskrovnice + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T18:54:00.709771+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-53-UST-O-SOAVHKSOAU.yaml b/data/custodian/CZ-53-UST-O-SOAVHKSOAU.yaml index 83b813c55b..d48510ab00 100644 --- a/data/custodian/CZ-53-UST-O-SOAVHKSOAU.yaml +++ b/data/custodian/CZ-53-UST-O-SOAVHKSOAU.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-UST-O-SOAVHKSOAU - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-UST-O-SOAVHKSOAU valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-UST-O-SOAVHKSOAU ghcid_numeric: 9783445674982916569 valid_from: '2025-12-08T11:21:35.322834+00:00' @@ -226,3 +227,33 @@ location: postal_code: 562 03 street_address: Pivovarská 137/II normalization_timestamp: '2025-12-09T10:53:41.308684+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T19:09:17.979198+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: '2025-12-26T19:09:17.981046+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: '2025-12-26T19:09:17.981046+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-53-VAL-L-OKVNL.yaml b/data/custodian/CZ-53-VAL-L-OKVNL.yaml index b228294802..ac8cf54198 100644 --- a/data/custodian/CZ-53-VAL-L-OKVNL.yaml +++ b/data/custodian/CZ-53-VAL-L-OKVNL.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-VAL-L-OKVNL - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-VAL-L-OKVNL valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-VAL-L-OKVNL ghcid_numeric: 9363927712970481712 valid_from: '2025-12-06T23:37:40.419727+00:00' @@ -205,3 +206,22 @@ location: postal_code: 535 01 street_address: Sportovní 152 normalization_timestamp: '2025-12-09T10:53:41.340213+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T19:09:24.449481+00:00' + source_url: https://www.valynadlabem.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.valynadlabem.cz/image.php?nid=935&oid=6970705 + source_url: https://www.valynadlabem.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-26T19:09:24.449481+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-53-VAP-L-OKP.yaml b/data/custodian/CZ-53-VAP-L-OKP.yaml index f8cb791fc6..ed9dc43dae 100644 --- a/data/custodian/CZ-53-VAP-L-OKP.yaml +++ b/data/custodian/CZ-53-VAP-L-OKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-VAP-L-OKP - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-VAP-L-OKP valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-VAP-L-OKP ghcid_numeric: 1543626275138123106 valid_from: '2025-12-06T23:37:40.431215+00:00' @@ -205,3 +206,22 @@ location: postal_code: 533 16 street_address: Přepychy 45 normalization_timestamp: '2025-12-09T10:53:41.390277+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T19:09:34.443047+00:00' + source_url: https://prepychy.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prepychy.cz/favicon/apple-icon-180x180.png + source_url: https://prepychy.cz/knihovna + css_selector: '[document] > html.js > head > link:nth-of-type(9)' + retrieved_on: '2025-12-26T19:09:34.443047+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-53-VCE-L-OKV.yaml b/data/custodian/CZ-53-VCE-L-OKV.yaml index 42a508676c..592ded2145 100644 --- a/data/custodian/CZ-53-VCE-L-OKV.yaml +++ b/data/custodian/CZ-53-VCE-L-OKV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-VCE-L-OKV - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-VCE-L-OKV valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-VCE-L-OKV ghcid_numeric: 9873702178981654543 valid_from: '2025-12-06T23:37:40.197412+00:00' @@ -205,3 +206,22 @@ location: postal_code: 539 57 street_address: Škroupovo náměstí 55 normalization_timestamp: '2025-12-09T10:53:41.505706+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T19:09:47.510996+00:00' + source_url: https://vcelakov-katalog.region-chrudim.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vcelakov-katalog.region-chrudim.cz/themes/root/images/vufind-favicon.ico + source_url: https://vcelakov-katalog.region-chrudim.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T19:09:47.510996+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-53-VIT-L-OKVV.yaml b/data/custodian/CZ-53-VIT-L-OKVV.yaml index ca2c0b77e2..0ef041b167 100644 --- a/data/custodian/CZ-53-VIT-L-OKVV.yaml +++ b/data/custodian/CZ-53-VIT-L-OKVV.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-53-VIT-L-OKVV - valid_from: "2025-12-10T09:47:07Z" + valid_from: '2025-12-10T09:47:07Z' valid_to: null - reason: "Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-PA to CZ-53 (Pardubice (Pardubický)) per + ISO 3166-2:CZ - ghcid: CZ-PA-VIT-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:07Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-PA-VIT-L-OKVV ghcid_numeric: 8249745795761465718 valid_from: '2025-12-06T23:37:40.801930+00:00' @@ -208,3 +209,22 @@ location: postal_code: 569 06 street_address: Vítějeves 65 normalization_timestamp: '2025-12-09T10:53:41.550715+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T19:09:57.851609+00:00' + source_url: https://tritius.booksy.cz/library/vitejeves + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.booksy.cz/apple-touch-icon-180x180.png + source_url: https://tritius.booksy.cz/library/vitejeves + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-26T19:09:57.851609+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-53-VMV-M-RMVVM.yaml b/data/custodian/CZ-53-VMV-M-RMVVM.yaml index 20fdecf156..aac7d083bc 100644 --- a/data/custodian/CZ-53-VMV-M-RMVVM.yaml +++ b/data/custodian/CZ-53-VMV-M-RMVVM.yaml @@ -237,3 +237,36 @@ location: youtube_status: NOT_FOUND youtube_search_query: Regionální muzeum ve Vysokém Mýtě official youtube_search_timestamp: '2025-12-09T09:34:29.625237+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T19:10:03.552055+00:00' + source_url: http://www.muzeum-myto.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.muzeum-myto.cz/src/Frontend/Themes/muzeum/Core/Layout/img/logo.svg + source_url: http://www.muzeum-myto.cz + css_selector: '#header > div.center > a.logo > img' + retrieved_on: '2025-12-26T19:10:03.552055+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: muzeum-myto.cz + - claim_type: favicon_url + claim_value: http://www.muzeum-myto.cz/src/Frontend/Themes/muzeum/Core/Layout/img/favicon/safari-pinned-tab.svg + source_url: http://www.muzeum-myto.cz + css_selector: '[document] > html.js > head > link:nth-of-type(6)' + retrieved_on: '2025-12-26T19:10:03.552055+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.muzeum-myto.cz//src/Frontend/Themes/muzeum/Core/Layout/img/fb-poster.jpg + source_url: http://www.muzeum-myto.cz + css_selector: '[document] > html.js > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-26T19:10:03.552055+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-53-VRA-L-OKVVL.yaml b/data/custodian/CZ-53-VRA-L-OKVVL.yaml index f1f727dafa..38abc3bb97 100644 --- a/data/custodian/CZ-53-VRA-L-OKVVL.yaml +++ b/data/custodian/CZ-53-VRA-L-OKVVL.yaml @@ -206,3 +206,22 @@ location: postal_code: 569 46 street_address: Vranová Lhota 34 normalization_timestamp: '2025-12-09T10:53:41.615578+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T19:10:26.389665+00:00' + source_url: https://vranovalhota-katalog.mkmt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://vranovalhota-katalog.mkmt.cz/themes/root/images/vufind-favicon.ico + source_url: https://vranovalhota-katalog.mkmt.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T19:10:26.389665+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/NL-NH-HEE-S-HKH.yaml b/data/custodian/NL-NH-HEE-S-HKH.yaml index 6ae6a006c8..9fa3a5a65c 100644 --- a/data/custodian/NL-NH-HEE-S-HKH.yaml +++ b/data/custodian/NL-NH-HEE-S-HKH.yaml @@ -453,127 +453,323 @@ location: cleanup_date: '2025-12-13T10:46:05.951755+00:00' cleanup_removed: 15 person_observations: - staff: - - person_id: nl-nh-hee-s-hkh_0001_l_van_dijk - person_name: L. van Dijk - role_title: Board member (Lid Worden) - heritage_relevant: true - heritage_type: S - current: true - affiliation_provenance: - source_url: https://www.historischekringheemskerk.nl/contact-en-links/ - retrieved_on: "2025-12-17T00:00:00Z" - retrieval_agent: exa_crawling - linkedin_profile_url: null - linkedin_profile_path: data/custodian/person/entity/l_van_dijk_20251217T000000Z.json - web_claims: - - claim_type: full_name - claim_value: L. van Dijk - source_url: https://www.historischekringheemskerk.nl/contact-en-links/ - retrieved_on: 2025-12-17T00:00:00Z - retrieval_agent: exa_crawling - xpath: /html/body/div[@class='contact-info']/p[1] - xpath_match_score: 1.0 - - person_id: nl-nh-hee-s-hkh_0002_aswv_de_jonge + source_metadata: + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + page_title: Bestuursleden – Historische Kring Heemskerk + board_members: + # 1. Voorzitter (Chair) + - person_id: nl-nh-hee-s-hkh_0001_aswv_de_jonge person_name: A.S.W.V. de Jonge - role_title: Board member (Lid Worden) + role_title: Voorzitter + role_title_en: Chair heritage_relevant: true heritage_type: S current: true + timespan: + begin_of_the_begin: '2024-04-01T00:00:00Z' + source_text: vanaf april 2024 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2024/02/foto-274x300.jpg + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[1]/td[1]/img[1] affiliation_provenance: - source_url: https://www.historischekringheemskerk.nl/contact-en-links/ - retrieved_on: "2025-12-17T00:00:00Z" - retrieval_agent: exa_crawling - linkedin_profile_url: null - linkedin_profile_path: data/custodian/person/entity/aswv_de_jonge_20251217T000100Z.json + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/aswv_de_jonge_20251226T124215Z.json web_claims: - claim_type: full_name claim_value: A.S.W.V. de Jonge - source_url: https://www.historischekringheemskerk.nl/contact-en-links/ - retrieved_on: 2025-12-17T00:00:00Z - retrieval_agent: exa_crawling - xpath: /html/body/div[@class='contact-info']/p[2] + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[1]/td[2] xpath_match_score: 1.0 - - person_id: nl-nh-hee-s-hkh_0003_o_lievers - person_name: O. Lievers - role_title: Candidate secretary (Kandidaat secretaris) + - claim_type: role_title + claim_value: Voorzitter + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[1]/td[2]/strong[1] + xpath_match_score: 1.0 + # 2. Secretaris (Secretary) + - person_id: nl-nh-hee-s-hkh_0002_l_van_dijk + person_name: L. van Dijk + role_title: Secretaris + role_title_en: Secretary heritage_relevant: true heritage_type: S current: true + timespan: + begin_of_the_begin: '2016-04-01T00:00:00Z' + source_text: bestuurslid vanaf april 2016 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2016/04/libbevandijk-233x300.jpg + image_alt: libbevandijk + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[2]/td[1]/strong[1]/img[1] affiliation_provenance: - source_url: https://www.historischekringheemskerk.nl/contact-en-links/ - retrieved_on: "2025-12-17T00:01:00Z" - retrieval_agent: exa_crawling - linkedin_profile_url: null - linkedin_profile_path: data/custodian/person/entity/o_lievers_20251217T000100Z.json + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/l_van_dijk_20251226T124215Z.json + web_claims: + - claim_type: full_name + claim_value: L. van Dijk + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[2]/td[2] + xpath_match_score: 1.0 + - claim_type: role_title + claim_value: Secretaris + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[2]/td[2]/span[1]/strong[1] + xpath_match_score: 1.0 + # 3. Kandidaat secretaris (Candidate Secretary) + - person_id: nl-nh-hee-s-hkh_0003_o_lievers + person_name: O. Lievers + role_title: Kandidaat secretaris + role_title_en: Candidate Secretary + heritage_relevant: true + heritage_type: S + current: true + timespan: + begin_of_the_begin: '2025-04-01T00:00:00Z' + source_text: bestuurslid vanaf april 2025 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2025/07/olga-mosselveld-lievers-255x300.jpg + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[3]/td[1]/span[1]/strong[1]/img[1] + affiliation_provenance: + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/o_lievers_20251226T124215Z.json web_claims: - claim_type: full_name claim_value: O. Lievers - source_url: https://www.historischekringheemskerk.nl/contact-en-links/ - retrieved_on: 2025-12-17T00:01:00Z" - retrieval_agent: exa_crawling - xpath: /html/body/div[@class='contact-info']/p[3] + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[3]/td[2] xpath_match_score: 1.0 - - person_id: nl-nh-hee-s-hkh_0004_mevr_kranendonk - person_name: Mevr. J.J. Kranendonk - role_title: Board member (Bestuurslid vanaf november 2007) - heritage_relevant: true - heritage_type: S - current: true - affiliation_provenance: - source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ - retrieved_on: "2025-12-17T00:02:00Z" - retrieval_agent: exa_crawling - linkedin_profile_url: null - linkedin_profile_path: data/custodian/person/entity/mevr_kranendonk_20251217T000200Z.json - web_claims: - - claim_type: full_name - claim_value: Mevr. J.J. Kranendonk + - claim_type: role_title + claim_value: Kandidaat secretaris source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ - retrieved_on: 2025-12-17T00:02:00Z" - retrieval_agent: exa_crawling - xpath: null - xpath_match_score: null - - person_id: nl-nh-hee-s-hkh_0005_pv_zwieten - person_name: P. van Zwieten - role_title: Board member (Bestuurslid vanaf november 2004) - heritage_relevant: true - heritage_type: S - current: true - affiliation_provenance: - source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ - retrieved_on: "2025-12-17T00:03:00Z" - retrieval_agent: exa_crawling - linkedin_profile_url: null - linkedin_profile_path: data/custodian/person/entity/pv_zwieten_20251217T000300Z.json - web_claims: - - claim_type: full_name - claim_value: P. van Zwieten - source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ - retrieved_on: 2025-12-17T00:03:00Z" - retrieval_agent: exa_crawling - xpath: null - xpath_match_score: null - - person_id: nl-nh-hee-s-hkh_0006_j_daas + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[3]/td[2]/strong[1] + xpath_match_score: 1.0 + # 4. Penningmeester (Treasurer) + - person_id: nl-nh-hee-s-hkh_0004_j_daas person_name: J. Daas - role_title: Board member (Bestuurslid vanaf april 2023) + role_title: Penningmeester + role_title_en: Treasurer heritage_relevant: true heritage_type: S current: true + timespan: + begin_of_the_begin: '2023-04-01T00:00:00Z' + source_text: bestuurslid vanaf april 2023 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2023/07/jan-daas-216x300.jpg + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[4]/td[1]/img[1] affiliation_provenance: source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ - retrieved_on: "2025-12-17T00:03:00Z" - retrieval_agent: exa_crawling - linkedin_profile_url: null - linkedin_profile_path: data/custodian/person/entity/j_daas_20251217T000300Z.json + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/j_daas_20251226T124215Z.json web_claims: - claim_type: full_name claim_value: J. Daas source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ - retrieved_on: 2025-12-17T00:03:00Z" - retrieval_agent: exa_crawling - xpath: null - xpath_match_score: null + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[4]/td[2] + xpath_match_score: 1.0 + - claim_type: role_title + claim_value: Penningmeester + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[4]/td[2]/strong[1] + xpath_match_score: 1.0 + # 5. Bestuurslid (Board Member) - Mevr. J.J. Kranendonk + - person_id: nl-nh-hee-s-hkh_0005_jj_kranendonk + person_name: Mevr. J.J. Kranendonk + role_title: Bestuurslid + role_title_en: Board Member + heritage_relevant: true + heritage_type: S + current: true + timespan: + begin_of_the_begin: '2007-11-01T00:00:00Z' + source_text: bestuurslid vanaf november 2007 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2013/11/Kranendonk.jpg + image_alt: Kranendonk + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[5]/td[1]/strong[1]/img[1] + affiliation_provenance: + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/jj_kranendonk_20251226T124215Z.json + web_claims: + - claim_type: full_name + claim_value: Mevr. J.J. Kranendonk + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[5]/td[2] + xpath_match_score: 1.0 + - claim_type: role_title + claim_value: Bestuurslid + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[5]/td[2]/strong[1] + xpath_match_score: 1.0 + # 6. Bestuurslid (Board Member) - P. van Zwieten + - person_id: nl-nh-hee-s-hkh_0006_p_van_zwieten + person_name: P. van Zwieten + role_title: Bestuurslid + role_title_en: Board Member + heritage_relevant: true + heritage_type: S + current: true + timespan: + begin_of_the_begin: '2014-11-01T00:00:00Z' + source_text: bestuurslid vanaf november 2014 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2014/11/pasfoto-PvZ.jpg + image_alt: pasfoto PvZ + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[6]/td[1]/img[1] + affiliation_provenance: + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/p_van_zwieten_20251226T124215Z.json + web_claims: + - claim_type: full_name + claim_value: P. van Zwieten + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[6]/td[2] + xpath_match_score: 1.0 + - claim_type: role_title + claim_value: Bestuurslid + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[6]/td[2]/strong[1] + xpath_match_score: 1.0 + # 7. Bestuurslid (Board Member) - J.D.W.M. Bos + - person_id: nl-nh-hee-s-hkh_0007_jdwm_bos + person_name: J.D.W.M. Bos + role_title: Bestuurslid + role_title_en: Board Member + heritage_relevant: true + heritage_type: S + current: true + timespan: + begin_of_the_begin: '2025-04-01T00:00:00Z' + source_text: bestuurslid vanaf april 2025 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2025/07/j.d.w.m.-bos-260x300.jpg + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[7]/td[1]/img[1] + affiliation_provenance: + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/jdwm_bos_20251226T124215Z.json + web_claims: + - claim_type: full_name + claim_value: J.D.W.M. Bos + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[7]/td[2] + xpath_match_score: 1.0 + - claim_type: role_title + claim_value: Bestuurslid + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[7]/td[2]/strong[1] + xpath_match_score: 1.0 + # 8. Ledenadministratie en bezorging (Membership Admin & Delivery) + - person_id: nl-nh-hee-s-hkh_0008_r_groen + person_name: R. Groen + role_title: Ledenadministratie en bezorging + role_title_en: Membership Administration & Delivery + heritage_relevant: true + heritage_type: S + current: true + timespan: + begin_of_the_begin: '2011-11-01T00:00:00Z' + source_text: vanaf november 2011 + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2013/11/groen.jpg + image_alt: groen + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[8]/td[1]/strong[1]/img[1] + affiliation_provenance: + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/r_groen_20251226T124215Z.json + web_claims: + - claim_type: full_name + claim_value: R. Groen + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[8]/td[2] + xpath_match_score: 1.0 + - claim_type: role_title + claim_value: Ledenadministratie en bezorging + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[8]/td[2]/strong[1] + xpath_match_score: 1.0 + # 9. Webmaster + - person_id: nl-nh-hee-s-hkh_0009_hphr_niesten + person_name: H.Ph.R. Niesten + role_title: Webmaster + role_title_en: Webmaster + heritage_relevant: true + heritage_type: S + current: true + timespan: + begin_of_the_begin: null + source_text: null + profile_image: + image_url: https://www.historischekringheemskerk.nl/wp-content/uploads/2014/04/webmaster-300x300.jpg + image_alt: webmaster + image_xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[9]/td[1]/strong[1]/img[1] + affiliation_provenance: + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + person_entity_path: data/custodian/person/entity/hphr_niesten_20251226T124215Z.json + web_claims: + - claim_type: full_name + claim_value: H.Ph.R. Niesten + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[9]/td[2] + xpath_match_score: 1.0 + - claim_type: role_title + claim_value: Webmaster + source_url: https://www.historischekringheemskerk.nl/bestuursleden-2/ + retrieved_on: '2025-12-26T12:42:15Z' + retrieval_agent: playwright + xpath: /html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[9]/td[2]/strong[1] + xpath_match_score: 1.0 cleanup_v2_removed: 12 crawl4ai_enrichment: retrieval_timestamp: '2025-12-14T18:02:12.861546+00:00' diff --git a/data/custodian/person/entity/aswv_de_jonge_20251226T124215Z.json b/data/custodian/person/entity/aswv_de_jonge_20251226T124215Z.json new file mode 100644 index 0000000000..03cfdf3fb6 --- /dev/null +++ b/data/custodian/person/entity/aswv_de_jonge_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0001_aswv_de_jonge", + "foaf:name": "A.S.W.V. de Jonge", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2024/02/foto-274x300.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Voorzitter", + "schema:jobTitle": "Voorzitter", + "schema:jobTitle@en": "Chair", + "org:headOf": true, + "timespan": { + "crm:P82a_begin_of_the_begin": "2024-04-01T00:00:00Z", + "source_text": "vanaf april 2024" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[1]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[1]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/hphr_niesten_20251226T124215Z.json b/data/custodian/person/entity/hphr_niesten_20251226T124215Z.json new file mode 100644 index 0000000000..af19dd7b52 --- /dev/null +++ b/data/custodian/person/entity/hphr_niesten_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0009_hphr_niesten", + "foaf:name": "H.Ph.R. Niesten", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2014/04/webmaster-300x300.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Webmaster", + "schema:jobTitle": "Webmaster", + "schema:jobTitle@en": "Webmaster", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": null, + "source_text": "not specified on source page" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[9]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[9]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/j_daas_20251226T124215Z.json b/data/custodian/person/entity/j_daas_20251226T124215Z.json new file mode 100644 index 0000000000..92fc35e749 --- /dev/null +++ b/data/custodian/person/entity/j_daas_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0004_j_daas", + "foaf:name": "J. Daas", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2023/07/jan-daas-216x300.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Penningmeester", + "schema:jobTitle": "Penningmeester", + "schema:jobTitle@en": "Treasurer", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": "2023-04-01T00:00:00Z", + "source_text": "vanaf april 2023" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[4]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[4]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/jdwm_bos_20251226T124215Z.json b/data/custodian/person/entity/jdwm_bos_20251226T124215Z.json new file mode 100644 index 0000000000..976badc00c --- /dev/null +++ b/data/custodian/person/entity/jdwm_bos_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0007_jdwm_bos", + "foaf:name": "J.D.W.M. Bos", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2025/07/j.d.w.m.-bos-260x300.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Bestuurslid", + "schema:jobTitle": "Bestuurslid", + "schema:jobTitle@en": "Board Member", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": "2025-04-01T00:00:00Z", + "source_text": "vanaf april 2025" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[7]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[7]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/jj_kranendonk_20251226T124215Z.json b/data/custodian/person/entity/jj_kranendonk_20251226T124215Z.json new file mode 100644 index 0000000000..e78a952b69 --- /dev/null +++ b/data/custodian/person/entity/jj_kranendonk_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0005_jj_kranendonk", + "foaf:name": "Mevr. J.J. Kranendonk", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2013/11/Kranendonk.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Bestuurslid", + "schema:jobTitle": "Bestuurslid", + "schema:jobTitle@en": "Board Member", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": "2007-11-01T00:00:00Z", + "source_text": "vanaf november 2007" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[5]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[5]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/l_van_dijk_20251226T124215Z.json b/data/custodian/person/entity/l_van_dijk_20251226T124215Z.json new file mode 100644 index 0000000000..1d0ff67209 --- /dev/null +++ b/data/custodian/person/entity/l_van_dijk_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0002_l_van_dijk", + "foaf:name": "L. van Dijk", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2016/04/libbevandijk-233x300.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Secretaris", + "schema:jobTitle": "Secretaris", + "schema:jobTitle@en": "Secretary", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": "2016-04-01T00:00:00Z", + "source_text": "vanaf april 2016" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[2]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[2]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/o_lievers_20251226T124215Z.json b/data/custodian/person/entity/o_lievers_20251226T124215Z.json new file mode 100644 index 0000000000..27911e3d5b --- /dev/null +++ b/data/custodian/person/entity/o_lievers_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0003_o_lievers", + "foaf:name": "O. Lievers", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2025/07/olga-mosselveld-lievers-255x300.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Kandidaat secretaris", + "schema:jobTitle": "Kandidaat secretaris", + "schema:jobTitle@en": "Candidate Secretary", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": "2025-04-01T00:00:00Z", + "source_text": "vanaf april 2025" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[3]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[3]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/p_van_zwieten_20251226T124215Z.json b/data/custodian/person/entity/p_van_zwieten_20251226T124215Z.json new file mode 100644 index 0000000000..113f4c3227 --- /dev/null +++ b/data/custodian/person/entity/p_van_zwieten_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0006_p_van_zwieten", + "foaf:name": "P. van Zwieten", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2014/11/pasfoto-PvZ.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Bestuurslid", + "schema:jobTitle": "Bestuurslid", + "schema:jobTitle@en": "Board Member", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": "2014-11-01T00:00:00Z", + "source_text": "vanaf november 2014" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[6]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[6]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/data/custodian/person/entity/r_groen_20251226T124215Z.json b/data/custodian/person/entity/r_groen_20251226T124215Z.json new file mode 100644 index 0000000000..c2676cd196 --- /dev/null +++ b/data/custodian/person/entity/r_groen_20251226T124215Z.json @@ -0,0 +1,40 @@ +{ + "@context": { + "foaf": "http://xmlns.com/foaf/0.1/", + "org": "http://www.w3.org/ns/org#", + "schema": "https://schema.org/", + "prov": "http://www.w3.org/ns/prov#", + "crm": "http://www.cidoc-crm.org/cidoc-crm/" + }, + "person_id": "nl-nh-hee-s-hkh_0008_r_groen", + "foaf:name": "R. Groen", + "foaf:img": "https://www.historischekringheemskerk.nl/wp-content/uploads/2013/11/groen.jpg", + "affiliations": [ + { + "org:organization": { + "id": "https://glam.example.org/custodian/nl-nh-hee-s-hkh", + "name": "Historische Kring Heemskerk" + }, + "org:role": "Ledenadministratie en bezorging", + "schema:jobTitle": "Ledenadministratie en bezorging", + "schema:jobTitle@en": "Membership Administration & Delivery", + "org:headOf": false, + "timespan": { + "crm:P82a_begin_of_the_begin": "2011-11-01T00:00:00Z", + "source_text": "vanaf november 2011" + } + } + ], + "prov:wasAttributedTo": { + "source_url": "https://www.historischekringheemskerk.nl/bestuursleden-2/", + "xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[8]/td[2]", + "image_xpath": "/html[1]/body[1]/div[3]/div[1]/div[1]/div[2]/div[1]/div[1]/table[1]/tbody[1]/tr[8]/td[1]/img[1]", + "retrieved_on": "2025-12-26T12:42:15Z", + "retrieval_agent": "playwright" + }, + "extraction_metadata": { + "extraction_date": "2025-12-26T12:42:15Z", + "extraction_method": "playwright_browser_scrape", + "extraction_agent": "claude-opus-4" + } +} diff --git a/scripts/index_persons_qdrant.py b/scripts/index_persons_qdrant.py index 34cac9acc8..3284219960 100644 --- a/scripts/index_persons_qdrant.py +++ b/scripts/index_persons_qdrant.py @@ -379,16 +379,60 @@ def extract_metadata(data: dict[str, Any], filepath: Path) -> dict[str, Any]: if "heritage_relevant" not in metadata: metadata["heritage_relevant"] = False - # Current affiliations - affiliations = data.get("custodian_affiliations", []) + # Current affiliations and custodian information for filtering + # Try both "affiliations" (correct key) and "custodian_affiliations" (legacy key) + affiliations = data.get("affiliations", []) or data.get("custodian_affiliations", []) current_affiliations = [] + custodian_slugs = [] + custodian_names = [] + for aff in affiliations: - if isinstance(aff, dict) and aff.get("current"): + if isinstance(aff, dict): custodian_name = aff.get("custodian_name", "") + custodian_slug = aff.get("custodian_slug", "") + is_current = aff.get("current", False) + if custodian_name: - current_affiliations.append(custodian_name) + custodian_names.append(custodian_name) + if is_current: + current_affiliations.append(custodian_name) + + if custodian_slug: + custodian_slugs.append(custodian_slug) + + # Also check source_staff_info for custodian data + source_staff = data.get("source_staff_info", {}) + if source_staff: + staff_custodian = source_staff.get("custodian", "") + staff_slug = source_staff.get("custodian_slug", "") + if staff_custodian and staff_custodian not in custodian_names: + custodian_names.append(staff_custodian) + if staff_slug and staff_slug not in custodian_slugs: + custodian_slugs.append(staff_slug) + + # Store all custodian information for filtering if current_affiliations: metadata["current_affiliations"] = current_affiliations + if custodian_names: + metadata["custodian_names"] = custodian_names + # Also store primary custodian (first one, usually current) + metadata["custodian_name"] = custodian_names[0] + if custodian_slugs: + metadata["custodian_slugs"] = custodian_slugs + # Also store primary custodian slug for simple filtering + metadata["custodian_slug"] = custodian_slugs[0] + + # Generate custodian_slug from custodian_name if not available + # This allows text-based filtering when slug is missing + if "custodian_slug" not in metadata and custodian_names: + # Create a simple slug from the name (lowercase, hyphenated) + import re + name = custodian_names[0] + slug = re.sub(r'[^a-z0-9\s-]', '', name.lower()) + slug = re.sub(r'[\s_]+', '-', slug) + slug = re.sub(r'-+', '-', slug).strip('-') + if slug: + metadata["custodian_slug"] = slug # Extraction metadata if extraction: