From 8036eb5a3f322f29d22c205f140764ac8f871751 Mon Sep 17 00:00:00 2001 From: kempersc Date: Tue, 23 Dec 2025 21:17:45 +0100 Subject: [PATCH] enrich: logo enrichment for JP custodians (1490 processed, 10606 remaining) --- .../.logo_enrichment_crawl4ai_checkpoint.json | 144 +++++++++++++++++- data/custodian/JP-08-TSU-L-TCL.yaml | 36 ++++- data/custodian/JP-08-TSU-L-TIUL.yaml | 43 +++++- data/custodian/JP-08-TSU-L-TL.yaml | 40 ++++- ...ashiritsu_library_kandatsuchikubunkan.yaml | 27 ++++ data/custodian/JP-08-TSU-L-TLK.yaml | 19 +++ data/custodian/JP-08-TSU-L-TLM.yaml | 19 +++ data/custodian/JP-08-TSU-L-TLN.yaml | 27 ++++ data/custodian/JP-08-TSU-L-TLS.yaml | 27 ++++ data/custodian/JP-08-TSU-L-TLT.yaml | 27 ++++ ...TSU-L-TPL-tsukubamirai_public_library.yaml | 28 +++- data/custodian/JP-08-TSU-L-TPL.yaml | 33 ++++ data/custodian/JP-08-TSU-L-TUTLPHD.yaml | 19 +++ data/custodian/JP-08-TSU-L-TUTLPVD.yaml | 35 ++++- data/custodian/JP-08-TSU-L-UTLAPEL.yaml | 32 +++- data/custodian/JP-08-TSU-L-UTLCL.yaml | 19 +++ data/custodian/JP-08-TSU-L-UTLLLIS.yaml | 38 ++++- data/custodian/JP-08-TSU-L-UTLML.yaml | 32 +++- data/custodian/JP-08-TSU-M-IKESC.yaml | 19 +++ data/custodian/JP-08-TSU-M-TAM.yaml | 19 +++ data/custodian/JP-08-TSU-M-TBG.yaml | 25 +++ data/custodian/JP-08-TSU-M-TCM.yaml | 19 +++ data/custodian/JP-08-TSU-M-TEC.yaml | 25 +++ ...shiokunoshogaigakushusentatoshoshitsu.yaml | 19 +++ data/custodian/JP-08-USH-L-U.yaml | 19 +++ data/custodian/JP-08-USH-M-CKDKH.yaml | 49 +++++- data/custodian/JP-08-YOT-M-IAC.yaml | 19 +++ data/custodian/JP-08-YUK-L-YL.yaml | 19 +++ data/custodian/JP-08-YUK-L-YPL.yaml | 19 +++ data/custodian/JP-08-YUK-M-YMFHMH.yaml | 19 +++ data/custodian/JP-09-GER-M-JMGNH.yaml | 19 +++ data/custodian/JP-09-HAG-L-FMML.yaml | 19 +++ data/custodian/JP-09-HIR-M-HFM.yaml | 19 +++ data/custodian/JP-09-KAM-M-KAMH.yaml | 19 +++ data/custodian/JP-09-KAS-M-HSM.yaml | 25 +++ data/custodian/JP-09-KAW-M-GKASM.yaml | 25 +++ data/custodian/JP-09-MAG-M-TMM.yaml | 25 +++ data/custodian/JP-09-MIN-M-MYMF.yaml | 28 ++++ data/custodian/JP-09-MIN-M-OIFHMFMH.yaml | 19 +++ data/custodian/JP-09-OIC-M-HMAE.yaml | 34 +++++ data/custodian/JP-09-SEK-M-GSBMM.yaml | 25 +++ data/custodian/JP-09-SEK-M-SCSTAM.yaml | 19 +++ data/custodian/JP-09-TOM-M-TTM.yaml | 19 +++ data/custodian/JP-09-UED-M-MF.yaml | 25 +++ data/custodian/JP-09-YAM-M-SM.yaml | 19 +++ data/custodian/JP-10-AGA-L-KL.yaml | 27 ++++ data/custodian/JP-10-AGA-M-GAO.yaml | 19 +++ data/custodian/JP-10-AGA-M-NFHMM.yaml | 19 +++ data/custodian/JP-10-AGA-M-YTMM.yaml | 20 +++ data/custodian/JP-10-ANN-M-ASGFG.yaml | 19 +++ data/custodian/JP-10-AZU-M-TAM.yaml | 33 ++++ data/custodian/JP-10-FUJ-L-GLF.yaml | 19 +++ data/custodian/JP-10-HOD-M-MLCBT.yaml | 25 +++ ...P-10-ISE-L-IL-isesakishiazuma_library.yaml | 25 +++ ...P-10-ISE-L-IL-isesakishisakai_library.yaml | 25 +++ data/custodian/JP-10-ISE-L-IL.yaml | 25 +++ data/custodian/JP-10-ISE-M-AAM.yaml | 19 +++ data/custodian/JP-10-ITA-M-TCKNZMA.yaml | 19 +++ data/custodian/JP-10-IWA-M-GPMH.yaml | 28 ++++ data/custodian/JP-10-IWA-M-GSP.yaml | 25 +++ data/custodian/JP-10-KIR-L-GL.yaml | 19 +++ data/custodian/JP-10-KIR-L-KCL.yaml | 27 ++++ data/custodian/JP-10-KIR-M-KFNO.yaml | 27 ++++ data/custodian/JP-10-KIR-M-KZ.yaml | 19 +++ data/custodian/JP-10-KIT-L-YTL.yaml | 19 +++ data/custodian/JP-10-KIT-M-MESM.yaml | 19 +++ data/custodian/JP-10-MAE-L-GLI.yaml | 19 +++ data/custodian/JP-10-MAE-L-GLM.yaml | 19 +++ data/custodian/JP-10-MAE-L-GPL.yaml | 19 +++ data/custodian/JP-10-MAE-L-GPLES.yaml | 19 +++ data/custodian/JP-10-MAE-L-GUHWL.yaml | 19 +++ data/custodian/JP-10-MAE-L-LGPCHS.yaml | 25 +++ 72 files changed, 1794 insertions(+), 57 deletions(-) diff --git a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json index ec46522dd3..99ffdf8750 100644 --- a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json +++ b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json @@ -6876,7 +6876,147 @@ "JP-08-TSU-A-UTA-university_of_tsukuba_archives.yaml", "JP-08-TSU-A-UTA.yaml", "JP-08-TSU-L-AFFRITCTOA.yaml", - "JP-08-TSU-L-APIL.yaml" + "JP-08-TSU-L-APIL.yaml", + "JP-08-TSU-L-DILN.yaml", + "JP-08-TSU-L-FFPRI.yaml", + "JP-08-TSU-L-HEAROL.yaml", + "JP-08-TSU-L-JAEATL.yaml", + "JP-08-TSU-L-JIRCAS.yaml", + "JP-08-TSU-L-JSTJLT.yaml", + "JP-08-TSU-L-LGSIMLIT.yaml", + "JP-08-TSU-L-LGSJAL.yaml", + "JP-08-TSU-L-LNILIM.yaml", + "JP-08-TSU-L-NAFROCL.yaml", + "JP-08-TSU-L-NIAISTL.yaml", + "JP-08-TSU-L-NIES.yaml", + "JP-08-TSU-L-NIMSSIOL.yaml", + "JP-08-TSU-L-PWRI.yaml", + "JP-08-TSU-L-RPURL.yaml", + "JP-08-TSU-L-T-tsukubashikukizakikoryusentatoshoshitsu.yaml", + "JP-08-TSU-L-T-tsukubashionogawakoryusentatoshoshitsu.yaml", + "JP-08-TSU-L-T-tsukubashiyatabekoryusentatoshoshitsu.yaml", + "JP-08-TSU-L-T.yaml", + "JP-08-TSU-L-TCL.yaml", + "JP-08-TSU-L-TGUL.yaml", + "JP-08-TSU-L-TIUL.yaml", + "JP-08-TSU-L-TL.yaml", + "JP-08-TSU-L-TLK-tsuchiurashiritsu_library_kandatsuchikubunkan.yaml", + "JP-08-TSU-L-TLK.yaml", + "JP-08-TSU-L-TLM.yaml", + "JP-08-TSU-L-TLN.yaml", + "JP-08-TSU-L-TLS.yaml", + "JP-08-TSU-L-TLT.yaml", + "JP-08-TSU-L-TPL-tsukubamirai_public_library.yaml", + "JP-08-TSU-L-TPL.yaml", + "JP-08-TSU-L-TRIOC.yaml", + "JP-08-TSU-L-TUTLPHD.yaml", + "JP-08-TSU-L-TUTLPVD.yaml", + "JP-08-TSU-L-UTLAPEL.yaml", + "JP-08-TSU-L-UTLCL.yaml", + "JP-08-TSU-L-UTLLLIS.yaml", + "JP-08-TSU-L-UTLML.yaml", + "JP-08-TSU-M-GMGSJA.yaml", + "JP-08-TSU-M-IKESC.yaml", + "JP-08-TSU-M-MRMM.yaml", + "JP-08-TSU-M-TAM.yaml", + "JP-08-TSU-M-TBG.yaml", + "JP-08-TSU-M-TCM.yaml", + "JP-08-TSU-M-TEC.yaml", + "JP-08-TSU-M-TMAI.yaml", + "JP-08-USH-L-U-ushikushiokunoshogaigakushusentatoshoshitsu.yaml", + "JP-08-USH-L-U.yaml", + "JP-08-USH-L-UL.yaml", + "JP-08-USH-M-CKDKH.yaml", + "JP-08-YOT-M-IAC.yaml", + "JP-08-YUK-L-YL.yaml", + "JP-08-YUK-L-YPL.yaml", + "JP-08-YUK-M-YMFHMH.yaml", + "JP-08-YUK-M-YTTMM.yaml", + "JP-09-FUR-M-HCM.yaml", + "JP-09-GER-M-JMGNH.yaml", + "JP-09-HAG-L-FMML.yaml", + "JP-09-HIR-M-HFM.yaml", + "JP-09-KAM-M-KAMH.yaml", + "JP-09-KAS-M-HSM.yaml", + "JP-09-KAW-M-GKASM.yaml", + "JP-09-KOY-M-KMTMA.yaml", + "JP-09-MAG-M-TMM.yaml", + "JP-09-MIN-M-MYMF.yaml", + "JP-09-MIN-M-OIFHMFMH.yaml", + "JP-09-MIZ-M-MFM.yaml", + "JP-09-MIZ-M-MN.yaml", + "JP-09-OIC-M-HMAE.yaml", + "JP-09-SEK-M-GSBMM.yaml", + "JP-09-SEK-M-SCSTAM.yaml", + "JP-09-TAJ-L-GPGECLERR.yaml", + "JP-09-TAJ-M-CSPM.yaml", + "JP-09-TAK-M-FAM.yaml", + "JP-09-TOK-M-TCHMMC.yaml", + "JP-09-TOM-M-TTM.yaml", + "JP-09-UED-M-MF.yaml", + "JP-09-YAM-M-SM.yaml", + "JP-10-AGA-A-NMFHM-nakanojo_museum_of_folk_and_history_musee.yaml", + "JP-10-AGA-A-NMFHM.yaml", + "JP-10-AGA-L-H.yaml", + "JP-10-AGA-L-KL.yaml", + "JP-10-AGA-L-N-nakanojochoritsukunikominkantoshoshitsu.yaml", + "JP-10-AGA-L-N.yaml", + "JP-10-AGA-L-NL.yaml", + "JP-10-AGA-L-T.yaml", + "JP-10-AGA-L-TT.yaml", + "JP-10-AGA-M-GAO.yaml", + "JP-10-AGA-M-JKNMDHSDP.yaml", + "JP-10-AGA-M-NFHMM.yaml", + "JP-10-AGA-M-YTMM.yaml", + "JP-10-ANN-L-ACL.yaml", + "JP-10-ANN-L-AL.yaml", + "JP-10-ANN-M-ACMH.yaml", + "JP-10-ANN-M-ASGFG.yaml", + "JP-10-ANN-M-MSMA.yaml", + "JP-10-AZU-M-TAM.yaml", + "JP-10-FUJ-L-FCL.yaml", + "JP-10-FUJ-L-GLF.yaml", + "JP-10-FUJ-M-FR.yaml", + "JP-10-HOD-M-MLCBT.yaml", + "JP-10-ISE-L-GPEC.yaml", + "JP-10-ISE-L-IL-isesakishiakabori_library.yaml", + "JP-10-ISE-L-IL-isesakishiazuma_library.yaml", + "JP-10-ISE-L-IL-isesakishisakai_library.yaml", + "JP-10-ISE-L-IL.yaml", + "JP-10-ISE-L-JL.yaml", + "JP-10-ISE-L-TL.yaml", + "JP-10-ISE-M-AAM.yaml", + "JP-10-ISE-M-ISARMS.yaml", + "JP-10-ITA-M-TCKNZMA.yaml", + "JP-10-IWA-M-GPMH.yaml", + "JP-10-IWA-M-GSP.yaml", + "JP-10-KAN-L-KL.yaml", + "JP-10-KAN-L-N.yaml", + "JP-10-KAN-L-S.yaml", + "JP-10-KAN-M-AMK.yaml", + "JP-10-KAN-M-MHFKT.yaml", + "JP-10-KAN-M-SMHM.yaml", + "JP-10-KAN-M-SMNH.yaml", + "JP-10-KAN-M-THM.yaml", + "JP-10-KIR-L-GL.yaml", + "JP-10-KIR-L-KCL.yaml", + "JP-10-KIR-L-KL-kiryushiritsutenji_library.yaml", + "JP-10-KIR-L-KL.yaml", + "JP-10-KIR-L-TRIG.yaml", + "JP-10-KIR-M-ATMH.yaml", + "JP-10-KIR-M-GIW.yaml", + "JP-10-KIR-M-KFNO.yaml", + "JP-10-KIR-M-KZ.yaml", + "JP-10-KIR-M-OMA.yaml", + "JP-10-KIR-M-TRC.yaml", + "JP-10-KIT-L-MPMM.yaml", + "JP-10-KIT-L-S.yaml", + "JP-10-KIT-L-YTL.yaml", + "JP-10-KIT-M-FIMM.yaml", + "JP-10-KIT-M-MESM.yaml", + "JP-10-MAE-A-GPA.yaml", + "JP-10-MAE-L-GLI.yaml", + "JP-10-MAE-L-GLM.yaml" ], - "last_index": 9 + "last_index": 59 } \ No newline at end of file diff --git a/data/custodian/JP-08-TSU-L-TCL.yaml b/data/custodian/JP-08-TSU-L-TCL.yaml index 86e12049a3..332d310338 100644 --- a/data/custodian/JP-08-TSU-L-TCL.yaml +++ b/data/custodian/JP-08-TSU-L-TCL.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-TCL - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-TCL valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-TCL ghcid_numeric: 15985076264426679211 valid_from: '2025-12-06T23:38:42.042769+00:00' @@ -242,3 +243,30 @@ location: postal_code: 300-0045 street_address: 1-1 YAMATOCHO, Tsuchiura Shi, Ibaraki Ken, 300-0036 normalization_timestamp: '2025-12-09T10:56:34.639663+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T19:59:34.782062+00:00' + source_url: http://www.t-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.t-lib.jp/themes/lib_theme/images/logo.png + source_url: http://www.t-lib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-23T19:59:34.782062+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 土浦市立図書館 Tsuchiura City Library + - claim_type: favicon_url + claim_value: https://www.t-lib.jp/themes/lib_theme/favicon.ico + source_url: http://www.t-lib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-23T19:59:34.782062+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TIUL.yaml b/data/custodian/JP-08-TSU-L-TIUL.yaml index 09ebaeb49b..1b766f8958 100644 --- a/data/custodian/JP-08-TSU-L-TIUL.yaml +++ b/data/custodian/JP-08-TSU-L-TIUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-TIUL - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-TIUL valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-TIUL ghcid_numeric: 6074333871908067787 valid_from: '2025-12-06T23:38:54.523156+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tsukuba International University Library @@ -190,7 +191,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.ktt.ac.jp/tiu/campus/library.htm wikidata_official_website: http://www.ktt.ac.jp/tiu/campus/library.htm @@ -212,3 +214,30 @@ location: geonames_id: 6822099 geonames_name: Tsuchiura feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T19:59:50.472942+00:00' + source_url: http://www.ktt.ac.jp/tiu/campus/library.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ktt.ac.jp/tiu/favicon.ico + source_url: http://www.ktt.ac.jp/tiu/campus/library.htm + css_selector: '[document] > html.wf-biz-udgothic-n7-active.wf-biz-udgothic-n4-active + > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T19:59:50.472942+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.ico + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ktt.ac.jp/tiu/campus/images/library-image1.jpg + source_url: http://www.ktt.ac.jp/tiu/campus/library.htm + css_selector: '[document] > html.wf-biz-udgothic-n7-active.wf-biz-udgothic-n4-active + > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T19:59:50.472942+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TL.yaml b/data/custodian/JP-08-TSU-L-TL.yaml index 29102ebd39..39eb513e4e 100644 --- a/data/custodian/JP-08-TSU-L-TL.yaml +++ b/data/custodian/JP-08-TSU-L-TL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-TL - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-TL valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-TL ghcid_numeric: 4843233854099595654 valid_from: '2025-12-06T23:38:56.857111+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TSUKUBAKOKUSAITANKIDAIGAKU Library @@ -204,3 +205,30 @@ location: geonames_id: 6822099 geonames_name: Tsuchiura feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T19:59:59.044016+00:00' + source_url: http://www.ktt.ac.jp/tiu/campus/library.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ktt.ac.jp/tiu/favicon.ico + source_url: http://www.ktt.ac.jp/tiu/campus/library.htm + css_selector: '[document] > html.wf-biz-udgothic-n7-active.wf-biz-udgothic-n4-active + > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T19:59:59.044016+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.ico + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ktt.ac.jp/tiu/campus/images/library-image1.jpg + source_url: http://www.ktt.ac.jp/tiu/campus/library.htm + css_selector: '[document] > html.wf-biz-udgothic-n7-active.wf-biz-udgothic-n4-active + > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T19:59:59.044016+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TLK-tsuchiurashiritsu_library_kandatsuchikubunkan.yaml b/data/custodian/JP-08-TSU-L-TLK-tsuchiurashiritsu_library_kandatsuchikubunkan.yaml index 96c5fc75dd..7f4adb7615 100644 --- a/data/custodian/JP-08-TSU-L-TLK-tsuchiurashiritsu_library_kandatsuchikubunkan.yaml +++ b/data/custodian/JP-08-TSU-L-TLK-tsuchiurashiritsu_library_kandatsuchikubunkan.yaml @@ -205,3 +205,30 @@ wikidata_enrichment: wikidata_web: official_website: http://www.t-lib.jp/ wikidata_official_website: http://www.t-lib.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:00:09.223812+00:00' + source_url: http://www.t-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.t-lib.jp/themes/lib_theme/images/logo.png + source_url: http://www.t-lib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-23T20:00:09.223812+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 土浦市立図書館 Tsuchiura City Library + - claim_type: favicon_url + claim_value: https://www.t-lib.jp/themes/lib_theme/favicon.ico + source_url: http://www.t-lib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-23T20:00:09.223812+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TLK.yaml b/data/custodian/JP-08-TSU-L-TLK.yaml index 9884b7694f..802c352c58 100644 --- a/data/custodian/JP-08-TSU-L-TLK.yaml +++ b/data/custodian/JP-08-TSU-L-TLK.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://lib.city.tsukubamirai.lg.jp/index.html wikidata_official_website: http://lib.city.tsukubamirai.lg.jp/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:00:17.692385+00:00' + source_url: http://lib.city.tsukubamirai.lg.jp/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://lib.city.tsukubamirai.lg.jp/images/logo_01.png?1205 + source_url: http://lib.city.tsukubamirai.lg.jp/index.html + css_selector: '#main_header > div.wrap.flex_row > h1 > a > img' + retrieved_on: '2025-12-23T20:00:17.692385+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: つくばみらい市立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-08-TSU-L-TLM.yaml b/data/custodian/JP-08-TSU-L-TLM.yaml index 555fe10bba..850ab2db9c 100644 --- a/data/custodian/JP-08-TSU-L-TLM.yaml +++ b/data/custodian/JP-08-TSU-L-TLM.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://lib.city.tsukubamirai.lg.jp/ wikidata_official_website: http://lib.city.tsukubamirai.lg.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:00:26.039371+00:00' + source_url: http://lib.city.tsukubamirai.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://lib.city.tsukubamirai.lg.jp/images/logo_01.png?1205 + source_url: http://lib.city.tsukubamirai.lg.jp + css_selector: '#main_header > div.wrap.flex_row > h1 > a > img' + retrieved_on: '2025-12-23T20:00:26.039371+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: つくばみらい市立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-08-TSU-L-TLN.yaml b/data/custodian/JP-08-TSU-L-TLN.yaml index e7f3ddd25b..bbe1f35cb4 100644 --- a/data/custodian/JP-08-TSU-L-TLN.yaml +++ b/data/custodian/JP-08-TSU-L-TLN.yaml @@ -205,3 +205,30 @@ wikidata_enrichment: wikidata_web: official_website: http://www.t-lib.jp/ wikidata_official_website: http://www.t-lib.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:00:36.203107+00:00' + source_url: http://www.t-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.t-lib.jp/themes/lib_theme/images/logo.png + source_url: http://www.t-lib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-23T20:00:36.203107+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 土浦市立図書館 Tsuchiura City Library + - claim_type: favicon_url + claim_value: https://www.t-lib.jp/themes/lib_theme/favicon.ico + source_url: http://www.t-lib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-23T20:00:36.203107+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TLS.yaml b/data/custodian/JP-08-TSU-L-TLS.yaml index 9fc731b869..ffd5c05985 100644 --- a/data/custodian/JP-08-TSU-L-TLS.yaml +++ b/data/custodian/JP-08-TSU-L-TLS.yaml @@ -205,3 +205,30 @@ wikidata_enrichment: wikidata_web: official_website: http://www.t-lib.jp/ wikidata_official_website: http://www.t-lib.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:00:49.112168+00:00' + source_url: http://www.t-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.t-lib.jp/themes/lib_theme/images/logo.png + source_url: http://www.t-lib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-23T20:00:49.112168+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 土浦市立図書館 Tsuchiura City Library + - claim_type: favicon_url + claim_value: https://www.t-lib.jp/themes/lib_theme/favicon.ico + source_url: http://www.t-lib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-23T20:00:49.112168+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TLT.yaml b/data/custodian/JP-08-TSU-L-TLT.yaml index b028ab0b22..a7ea5d837c 100644 --- a/data/custodian/JP-08-TSU-L-TLT.yaml +++ b/data/custodian/JP-08-TSU-L-TLT.yaml @@ -205,3 +205,30 @@ wikidata_enrichment: wikidata_web: official_website: http://www.t-lib.jp/ wikidata_official_website: http://www.t-lib.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:00:59.082830+00:00' + source_url: http://www.t-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.t-lib.jp/themes/lib_theme/images/logo.png + source_url: http://www.t-lib.jp + css_selector: '#header_logo > a.active > img' + retrieved_on: '2025-12-23T20:00:59.082830+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 土浦市立図書館 Tsuchiura City Library + - claim_type: favicon_url + claim_value: https://www.t-lib.jp/themes/lib_theme/favicon.ico + source_url: http://www.t-lib.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-23T20:00:59.082830+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TPL-tsukubamirai_public_library.yaml b/data/custodian/JP-08-TSU-L-TPL-tsukubamirai_public_library.yaml index 93c8ec2850..8782ba58a5 100644 --- a/data/custodian/JP-08-TSU-L-TPL-tsukubamirai_public_library.yaml +++ b/data/custodian/JP-08-TSU-L-TPL-tsukubamirai_public_library.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-TPL-tsukubamirai_public_library - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-TPL-tsukubamirai_public_library valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-TPL-tsukubamirai_public_library ghcid_numeric: 17132519902273369305 valid_from: '2025-12-06T23:38:42.132826+00:00' @@ -239,3 +240,22 @@ location: postal_code: 300-2341 street_address: 623 FUKUDA, Tsukubamirai Shi, Ibaraki Ken, 300-2341 normalization_timestamp: '2025-12-09T10:56:34.999787+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:01:08.846453+00:00' + source_url: https://lib.city.tsukubamirai.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://lib.city.tsukubamirai.lg.jp/images/logo_01.png?1205 + source_url: https://lib.city.tsukubamirai.lg.jp + css_selector: '#main_header > div.wrap.flex_row > h1 > a > img' + retrieved_on: '2025-12-23T20:01:08.846453+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: つくばみらい市立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-08-TSU-L-TPL.yaml b/data/custodian/JP-08-TSU-L-TPL.yaml index 6d4a934095..df23ee4b82 100644 --- a/data/custodian/JP-08-TSU-L-TPL.yaml +++ b/data/custodian/JP-08-TSU-L-TPL.yaml @@ -254,3 +254,36 @@ location: postal_code: 305-0031 street_address: 2-8 AZUMA, Tsukuba Shi, Ibaraki Ken, 305-0031 normalization_timestamp: '2025-12-09T10:56:35.022020+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:01:18.726070+00:00' + source_url: http://www.city.tsukuba.lg.jp/kankobunka/bunka/toshokan/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.tsukuba.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.tsukuba.lg.jp/kankobunka/bunka/toshokan/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T20:01:18.726070+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: つくば市 City of Tsukuba + - claim_type: favicon_url + claim_value: http://www.city.tsukuba.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.tsukuba.lg.jp/kankobunka/bunka/toshokan/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:01:18.726070+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.tsukuba.lg.jp/material/images/group/1/MV1.png + source_url: http://www.city.tsukuba.lg.jp/kankobunka/bunka/toshokan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T20:01:18.726070+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-08-TSU-L-TUTLPHD.yaml b/data/custodian/JP-08-TSU-L-TUTLPHD.yaml index 9bcfe1434e..31994d8429 100644 --- a/data/custodian/JP-08-TSU-L-TUTLPHD.yaml +++ b/data/custodian/JP-08-TSU-L-TUTLPHD.yaml @@ -206,3 +206,22 @@ location: geonames_id: 2110681 geonames_name: Tsukuba feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:01:20.904151+00:00' + source_url: https://library.k.tsukuba-tech.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.k.tsukuba-tech.ac.jp/opac/images/cyan/favicon.ico + source_url: https://library.k.tsukuba-tech.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-23T20:01:20.904151+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-TUTLPVD.yaml b/data/custodian/JP-08-TSU-L-TUTLPVD.yaml index df103733e1..f1bee6d9cf 100644 --- a/data/custodian/JP-08-TSU-L-TUTLPVD.yaml +++ b/data/custodian/JP-08-TSU-L-TUTLPVD.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-TUTLPVD - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-TUTLPVD valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-TUTLPVD ghcid_numeric: 2415562980847147700 valid_from: '2025-12-06T23:38:53.233475+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tsukuba University of Technology Library for People with Visual Disability @@ -164,7 +165,8 @@ wikidata_enrichment: wikidata_labels: en: Tsukuba University of Technology Library for People with Visual Disability ja: 筑波技術大学視覚障害系図書館 - wikidata_label_en: Tsukuba University of Technology Library for People with Visual Disability + wikidata_label_en: Tsukuba University of Technology Library for People with Visual + Disability wikidata_label_ja: 筑波技術大学視覚障害系図書館 wikidata_classification: instance_of: &id004 @@ -204,3 +206,22 @@ location: geonames_id: 2110681 geonames_name: Tsukuba feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:01:27.502245+00:00' + source_url: https://library.k.tsukuba-tech.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.k.tsukuba-tech.ac.jp/opac/images/cyan/favicon.ico + source_url: https://library.k.tsukuba-tech.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-23T20:01:27.502245+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-UTLAPEL.yaml b/data/custodian/JP-08-TSU-L-UTLAPEL.yaml index 8d3170df40..ebf6c8fe7c 100644 --- a/data/custodian/JP-08-TSU-L-UTLAPEL.yaml +++ b/data/custodian/JP-08-TSU-L-UTLAPEL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-UTLAPEL - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-UTLAPEL valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-UTLAPEL ghcid_numeric: 5604560830902852942 valid_from: '2025-12-06T23:38:53.217409+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: University of Tsukuba Library Art and Physical Education Library @@ -204,3 +205,22 @@ location: geonames_id: 2110681 geonames_name: Tsukuba feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:01:35.009288+00:00' + source_url: http://www.tulips.tsukuba.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tulips.tsukuba.ac.jp/lib/sites/default/files/favicon-tulips.ico + source_url: http://www.tulips.tsukuba.ac.jp + css_selector: '[document] > html.front.js > head > link' + retrieved_on: '2025-12-23T20:01:35.009288+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-UTLCL.yaml b/data/custodian/JP-08-TSU-L-UTLCL.yaml index d67cfcf2a2..10d31458c6 100644 --- a/data/custodian/JP-08-TSU-L-UTLCL.yaml +++ b/data/custodian/JP-08-TSU-L-UTLCL.yaml @@ -205,3 +205,22 @@ location: geonames_id: 2110681 geonames_name: Tsukuba feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:01:43.710724+00:00' + source_url: http://www.tulips.tsukuba.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tulips.tsukuba.ac.jp/lib/sites/default/files/favicon-tulips.ico + source_url: http://www.tulips.tsukuba.ac.jp + css_selector: '[document] > html.front.js > head > link' + retrieved_on: '2025-12-23T20:01:43.710724+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-UTLLLIS.yaml b/data/custodian/JP-08-TSU-L-UTLLLIS.yaml index f99110151c..c33469ce2b 100644 --- a/data/custodian/JP-08-TSU-L-UTLLLIS.yaml +++ b/data/custodian/JP-08-TSU-L-UTLLLIS.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-UTLLLIS - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-UTLLLIS valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-UTLLLIS ghcid_numeric: 5258773043305655002 valid_from: '2025-12-06T23:38:53.223203+00:00' @@ -101,11 +102,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: University of Tsukuba Library Library on Library and Information Science + claim_value: University of Tsukuba Library Library on Library and Information + Science property_uri: skos:prefLabel provenance: namespace: glam @@ -164,7 +166,8 @@ wikidata_enrichment: wikidata_labels: en: University of Tsukuba Library Library on Library and Information Science ja: 筑波大学附属図書館図書館情報学図書館 - wikidata_label_en: University of Tsukuba Library Library on Library and Information Science + wikidata_label_en: University of Tsukuba Library Library on Library and Information + Science wikidata_label_ja: 筑波大学附属図書館図書館情報学図書館 wikidata_classification: instance_of: &id004 @@ -204,3 +207,22 @@ location: geonames_id: 2110681 geonames_name: Tsukuba feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:01:52.035776+00:00' + source_url: http://www.tulips.tsukuba.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tulips.tsukuba.ac.jp/lib/sites/default/files/favicon-tulips.ico + source_url: http://www.tulips.tsukuba.ac.jp + css_selector: '[document] > html.front.js > head > link' + retrieved_on: '2025-12-23T20:01:52.035776+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-L-UTLML.yaml b/data/custodian/JP-08-TSU-L-UTLML.yaml index 0181abf023..5b305da62f 100644 --- a/data/custodian/JP-08-TSU-L-UTLML.yaml +++ b/data/custodian/JP-08-TSU-L-UTLML.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-TSU-L-UTLML - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-TSU-L-UTLML valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-TSU-L-UTLML ghcid_numeric: 4233618454059642818 valid_from: '2025-12-06T23:38:53.220311+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: University of Tsukuba Library Medical Library @@ -204,3 +205,22 @@ location: geonames_id: 2110681 geonames_name: Tsukuba feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:02:00.389197+00:00' + source_url: http://www.tulips.tsukuba.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tulips.tsukuba.ac.jp/lib/sites/default/files/favicon-tulips.ico + source_url: http://www.tulips.tsukuba.ac.jp + css_selector: '[document] > html.front.js > head > link' + retrieved_on: '2025-12-23T20:02:00.389197+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-M-IKESC.yaml b/data/custodian/JP-08-TSU-M-IKESC.yaml index 8c35410646..f63673586e 100644 --- a/data/custodian/JP-08-TSU-M-IKESC.yaml +++ b/data/custodian/JP-08-TSU-M-IKESC.yaml @@ -208,3 +208,22 @@ wikidata_enrichment: wikidata_media: image: Ibaraki Kasumigaura Environmental Science Center Building.jpg wikidata_image: Ibaraki Kasumigaura Environmental Science Center Building.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:02:18.865184+00:00' + source_url: http://www.pref.ibaraki.jp/soshiki/seikatsukankyo/kasumigauraesc/index.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.pref.ibaraki.jp/soshiki/seikatsukankyo/kasumigauraesc/favicon.ico + source_url: http://www.pref.ibaraki.jp/soshiki/seikatsukankyo/kasumigauraesc/index.htm + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T20:02:18.865184+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-08-TSU-M-TAM.yaml b/data/custodian/JP-08-TSU-M-TAM.yaml index f7b7b9673e..94b7bf8875 100644 --- a/data/custodian/JP-08-TSU-M-TAM.yaml +++ b/data/custodian/JP-08-TSU-M-TAM.yaml @@ -236,3 +236,22 @@ wikidata_enrichment: wikidata_media: image: KamitakatsuKaizuka.jpg wikidata_image: KamitakatsuKaizuka.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:02:31.815145+00:00' + source_url: http://www.city.tsuchiura.lg.jp/section.php?code=44 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.tsuchiura.lg.jp/web_clip_icon.png + source_url: http://www.city.tsuchiura.lg.jp/section.php?code=44 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:02:31.815145+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-08-TSU-M-TBG.yaml b/data/custodian/JP-08-TSU-M-TBG.yaml index af7055c883..b5d1be4707 100644 --- a/data/custodian/JP-08-TSU-M-TBG.yaml +++ b/data/custodian/JP-08-TSU-M-TBG.yaml @@ -285,3 +285,28 @@ wikidata_enrichment: commons_category: Tsukuba Botanical Garden image: TBG entrance.jpg wikidata_image: TBG entrance.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:02:43.779834+00:00' + source_url: http://www.tbg.kahaku.go.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tbg.kahaku.go.jp/apple-touch-icon.png + source_url: http://www.tbg.kahaku.go.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:02:43.779834+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://tbg.kahaku.go.jp/ogp.png + source_url: http://www.tbg.kahaku.go.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T20:02:43.779834+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-08-TSU-M-TCM.yaml b/data/custodian/JP-08-TSU-M-TCM.yaml index 5cc80a7702..81819e29d9 100644 --- a/data/custodian/JP-08-TSU-M-TCM.yaml +++ b/data/custodian/JP-08-TSU-M-TCM.yaml @@ -238,3 +238,22 @@ wikidata_enrichment: image: Museum Tsuchiura 2.jpg commons_category: Tsuchiura City Museum wikidata_image: Museum Tsuchiura 2.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:02:52.239381+00:00' + source_url: https://www.city.tsuchiura.lg.jp/section.php?code=43 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.tsuchiura.lg.jp/web_clip_icon.png + source_url: https://www.city.tsuchiura.lg.jp/section.php?code=43 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:02:52.239381+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-08-TSU-M-TEC.yaml b/data/custodian/JP-08-TSU-M-TEC.yaml index bf88273183..4ff13bd68f 100644 --- a/data/custodian/JP-08-TSU-M-TEC.yaml +++ b/data/custodian/JP-08-TSU-M-TEC.yaml @@ -906,3 +906,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/lgrsBGYzYbw/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:02:59.858298+00:00' + source_url: http://www.expocenter.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.expocenter.or.jp/favicon.ico?v=1652767826 + source_url: http://www.expocenter.or.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T20:02:59.858298+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.expocenter.or.jp/files/user/images/ogplogo.png + source_url: http://www.expocenter.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T20:02:59.858298+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-08-USH-L-U-ushikushiokunoshogaigakushusentatoshoshitsu.yaml b/data/custodian/JP-08-USH-L-U-ushikushiokunoshogaigakushusentatoshoshitsu.yaml index 566e5feb42..47eca11a65 100644 --- a/data/custodian/JP-08-USH-L-U-ushikushiokunoshogaigakushusentatoshoshitsu.yaml +++ b/data/custodian/JP-08-USH-L-U-ushikushiokunoshogaigakushusentatoshoshitsu.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ushiku.lg.jp/page/page000492.html wikidata_official_website: http://www.city.ushiku.lg.jp/page/page000492.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:03:13.057033+00:00' + source_url: http://www.city.ushiku.lg.jp/page/page000492.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.ushiku.lg.jp/web_clip_icon.png + source_url: http://www.city.ushiku.lg.jp/page/page000492.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:03:13.057033+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-08-USH-L-U.yaml b/data/custodian/JP-08-USH-L-U.yaml index 7ff86774f0..5f610f4285 100644 --- a/data/custodian/JP-08-USH-L-U.yaml +++ b/data/custodian/JP-08-USH-L-U.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ushiku.lg.jp/page/page000491.html wikidata_official_website: http://www.city.ushiku.lg.jp/page/page000491.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:03:20.210475+00:00' + source_url: http://www.city.ushiku.lg.jp/page/page000491.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.ushiku.lg.jp/web_clip_icon.png + source_url: http://www.city.ushiku.lg.jp/page/page000491.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:03:20.210475+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-08-USH-M-CKDKH.yaml b/data/custodian/JP-08-USH-M-CKDKH.yaml index 517095a0e6..018d8ea0d5 100644 --- a/data/custodian/JP-08-USH-M-CKDKH.yaml +++ b/data/custodian/JP-08-USH-M-CKDKH.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-08-USH-M-CKDKH - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per ISO 3166-2:JP" + reason: Corrected region code from JP-IB (abbreviation) to JP-08 (Ibaraki) per + ISO 3166-2:JP - ghcid: JP-IB-USH-M-CKDKH valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IB-USH-M-CKDKH ghcid_numeric: 4524693118986719992 valid_from: '2025-12-06T23:38:31.658514+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: CHATEAU KAMIYA D.KAMIYA HALL @@ -195,7 +196,8 @@ wikidata_enrichment: heritage_designation: - id: Q1188622 label: Important Cultural Property of Japan - description: item judged by the Agency for Cultural Affairs to be of particular importance to the Japanese people + description: item judged by the Agency for Cultural Affairs to be of particular + importance to the Japanese people main_subject: - id: Q11590840 label: Kamiya Denbei @@ -246,3 +248,36 @@ location: geonames_id: 2110629 geonames_name: Ushiku feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:04:02.691922+00:00' + source_url: https://www.oenon.jp/ushiku-chateau/shop/memorial_hall + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.oenon.jp/ushiku-chateau/common/img/com_logo02.jpg + source_url: https://www.oenon.jp/ushiku-chateau/shop/memorial_hall + css_selector: '#siteTop > header > div.headerInner > h1.logo > img' + retrieved_on: '2025-12-23T20:04:02.691922+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日本遺産 + - claim_type: favicon_url + claim_value: https://www.oenon.jp/ushiku-chateau/webclip.png + source_url: https://www.oenon.jp/ushiku-chateau/shop/memorial_hall + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:04:02.691922+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.oenon.jp/common/img/ogp.png + source_url: https://www.oenon.jp/ushiku-chateau/shop/memorial_hall + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T20:04:02.691922+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-08-YOT-M-IAC.yaml b/data/custodian/JP-08-YOT-M-IAC.yaml index 08c689b8dd..9287fc5b73 100644 --- a/data/custodian/JP-08-YOT-M-IAC.yaml +++ b/data/custodian/JP-08-YOT-M-IAC.yaml @@ -414,3 +414,22 @@ location: geonames_id: 8991885 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:29.031738+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:06:29.721989+00:00' + source_url: http://www.ammonite-center.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.ammonite-center.jp/images/logobule.png + source_url: http://www.ammonite-center.jp + css_selector: '#header > div.logo > img' + retrieved_on: '2025-12-23T20:06:29.721989+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-08-YUK-L-YL.yaml b/data/custodian/JP-08-YUK-L-YL.yaml index b1084faa87..eaa80d9c60 100644 --- a/data/custodian/JP-08-YUK-L-YL.yaml +++ b/data/custodian/JP-08-YUK-L-YL.yaml @@ -225,3 +225,22 @@ wikidata_enrichment: wikidata_web: official_website: http://lib-yuki.city.yuki.lg.jp wikidata_official_website: http://lib-yuki.city.yuki.lg.jp +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:06:39.097204+00:00' + source_url: http://lib-yuki.city.yuki.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://lib-yuki.city.yuki.lg.jp/apple-touch-icon.png + source_url: http://lib-yuki.city.yuki.lg.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-23T20:06:39.097204+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-08-YUK-L-YPL.yaml b/data/custodian/JP-08-YUK-L-YPL.yaml index 7393c56e74..22c0a1af94 100644 --- a/data/custodian/JP-08-YUK-L-YPL.yaml +++ b/data/custodian/JP-08-YUK-L-YPL.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.ibaraki-yachiyo.lg.jp/page/page000588.html wikidata_official_website: http://www.town.ibaraki-yachiyo.lg.jp/page/page000588.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:06:47.318133+00:00' + source_url: http://www.town.ibaraki-yachiyo.lg.jp/page/page000588.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.ibaraki-yachiyo.lg.jp/page/web_clip_icon.png + source_url: http://www.town.ibaraki-yachiyo.lg.jp/page/page000588.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:06:47.318133+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-08-YUK-M-YMFHMH.yaml b/data/custodian/JP-08-YUK-M-YMFHMH.yaml index 0964d6e803..513c153081 100644 --- a/data/custodian/JP-08-YUK-M-YMFHMH.yaml +++ b/data/custodian/JP-08-YUK-M-YMFHMH.yaml @@ -213,3 +213,22 @@ location: postal_code: 300-3572 street_address: SUGENOYA, Yuki Gun Yachiyo Machi, Ibaraki Ken, 300-3572 normalization_timestamp: '2025-12-09T10:56:35.591211+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:06:54.704307+00:00' + source_url: http://www.town.ibaraki-yachiyo.lg.jp/page/dir000654.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.ibaraki-yachiyo.lg.jp/web_clip_icon.png + source_url: http://www.town.ibaraki-yachiyo.lg.jp/page/dir000654.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:06:54.704307+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-09-GER-M-JMGNH.yaml b/data/custodian/JP-09-GER-M-JMGNH.yaml index ddbb361a78..effe54da06 100644 --- a/data/custodian/JP-09-GER-M-JMGNH.yaml +++ b/data/custodian/JP-09-GER-M-JMGNH.yaml @@ -415,3 +415,22 @@ location: geonames_id: 1848055 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:29.151838+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:07:14.969823+00:00' + source_url: http://www.city.gero.lg.jp/departmentTop/node_1069/node_1149/node_27591 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.gero.lg.jp/apple-touch-icon.png + source_url: http://www.city.gero.lg.jp/departmentTop/node_1069/node_1149/node_27591 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:07:14.969823+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-09-HAG-L-FMML.yaml b/data/custodian/JP-09-HAG-L-FMML.yaml index 5059e2fdec..b07dd99943 100644 --- a/data/custodian/JP-09-HAG-L-FMML.yaml +++ b/data/custodian/JP-09-HAG-L-FMML.yaml @@ -338,3 +338,22 @@ wikidata_enrichment: wikidata_web: official_website: http://fuminomori.jp/ wikidata_official_website: http://fuminomori.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:07:27.539612+00:00' + source_url: http://fuminomori.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://fuminomori.jp/templates/motegilibrary/favicon.ico + source_url: http://fuminomori.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T20:07:27.539612+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-09-HIR-M-HFM.yaml b/data/custodian/JP-09-HIR-M-HFM.yaml index 54935990eb..e2347debfd 100644 --- a/data/custodian/JP-09-HIR-M-HFM.yaml +++ b/data/custodian/JP-09-HIR-M-HFM.yaml @@ -346,3 +346,22 @@ location: geonames_id: 1862454 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:29.270643+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:07:36.010034+00:00' + source_url: https://www.okuhida.or.jp/?s=%E5%B9%B3%E6%B9%AF%E6%B0%91%E4%BF%97%E9%A4%A8 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.okuhida.or.jp/wp-content/uploads/2016/06/favicon.ico + source_url: https://www.okuhida.or.jp/?s=%E5%B9%B3%E6%B9%AF%E6%B0%91%E4%BF%97%E9%A4%A8 + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T20:07:36.010034+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-09-KAM-M-KAMH.yaml b/data/custodian/JP-09-KAM-M-KAMH.yaml index c272f823e9..ab1623761d 100644 --- a/data/custodian/JP-09-KAM-M-KAMH.yaml +++ b/data/custodian/JP-09-KAM-M-KAMH.yaml @@ -387,3 +387,22 @@ location: geonames_id: 1860528 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:29.338280+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:07:44.602913+00:00' + source_url: https://www.city.kani.lg.jp/10014.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.kani.lg.jp/apple-touch-icon.png + source_url: https://www.city.kani.lg.jp/10014.htm + css_selector: '[document] > html > head > link.png:nth-of-type(22)' + retrieved_on: '2025-12-23T20:07:44.602913+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-09-KAS-M-HSM.yaml b/data/custodian/JP-09-KAS-M-HSM.yaml index a581509e1e..8ac6ebd09f 100644 --- a/data/custodian/JP-09-KAS-M-HSM.yaml +++ b/data/custodian/JP-09-KAS-M-HSM.yaml @@ -383,3 +383,28 @@ location: geonames_id: 1860008 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:29.402038+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:07:53.723706+00:00' + source_url: http://www.hakusekikan.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hakusekikan.co.jp/cms/wp-content/themes/original/img/common/animated_favicon1.gif + source_url: http://www.hakusekikan.co.jp + css_selector: '[document] > html.webp.webp-alpha > head > link:nth-of-type(11)' + retrieved_on: '2025-12-23T20:07:53.723706+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.hakusekikan.co.jp/cms/cms/wp-content/uploads/2023/03/ogp.jpg + source_url: http://www.hakusekikan.co.jp + css_selector: '[document] > html.webp.webp-alpha > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-23T20:07:53.723706+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-09-KAW-M-GKASM.yaml b/data/custodian/JP-09-KAW-M-GKASM.yaml index c9d81b8685..70b4153a27 100644 --- a/data/custodian/JP-09-KAW-M-GKASM.yaml +++ b/data/custodian/JP-09-KAW-M-GKASM.yaml @@ -725,3 +725,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/8DVB8_C3dOg/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:08:01.141615+00:00' + source_url: http://www.sorahaku.net + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.sorahaku.net/favicon.ico + source_url: http://www.sorahaku.net + css_selector: '[document] > html.fontReady > head > link' + retrieved_on: '2025-12-23T20:08:01.141615+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sorahaku.net/images/ogp.jpg + source_url: http://www.sorahaku.net + css_selector: '[document] > html.fontReady > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T20:08:01.141615+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-09-MAG-M-TMM.yaml b/data/custodian/JP-09-MAG-M-TMM.yaml index 844f3a5d38..07ad88b51b 100644 --- a/data/custodian/JP-09-MAG-M-TMM.yaml +++ b/data/custodian/JP-09-MAG-M-TMM.yaml @@ -386,3 +386,28 @@ location: geonames_id: 6698070 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:29.549570+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:08:18.731131+00:00' + source_url: http://toson.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://toson.jp/files/favicon.ico?cache=20251224042245 + source_url: http://toson.jp + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-23T20:08:18.731131+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://toson.jp/css/public/pc/image/ogimage.jpg + source_url: http://toson.jp + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T20:08:18.731131+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-09-MIN-M-MYMF.yaml b/data/custodian/JP-09-MIN-M-MYMF.yaml index 84b49e795b..8d23096aaf 100644 --- a/data/custodian/JP-09-MIN-M-MYMF.yaml +++ b/data/custodian/JP-09-MIN-M-MYMF.yaml @@ -333,3 +333,31 @@ location: geonames_id: 1857062 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:29.699280+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:08:29.050448+00:00' + source_url: http://www.city.mino.gifu.jp/pages/37513 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.mino.gifu.jp/common/images/logo01.svg + source_url: http://www.city.mino.gifu.jp/pages/37513 + css_selector: '#body--docs-1449 > div.l-wrapper > header.l-header > div.p-pc-header + > div.container > h1.p-pc-header__logo > a.p-pc-header__logo-link > img' + retrieved_on: '2025-12-23T20:08:29.050448+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 和紙とうだつのまち 美濃市 + - claim_type: favicon_url + claim_value: http://www.city.mino.gifu.jp/common/images/favicon.ico + source_url: http://www.city.mino.gifu.jp/pages/37513 + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T20:08:29.050448+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-09-MIN-M-OIFHMFMH.yaml b/data/custodian/JP-09-MIN-M-OIFHMFMH.yaml index 09500eb8b0..0d24c4c684 100644 --- a/data/custodian/JP-09-MIN-M-OIFHMFMH.yaml +++ b/data/custodian/JP-09-MIN-M-OIFHMFMH.yaml @@ -350,3 +350,22 @@ location: geonames_id: 1857062 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:29.837153+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:08:36.374874+00:00' + source_url: http://www.mino-city.jp/jp/tourist/construction01.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mino-city.jp/wp-content/uploads/2023/07/cropped-rect103685-180x180.png + source_url: http://www.mino-city.jp/jp/tourist/construction01.html + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-23T20:08:36.374874+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-09-OIC-M-HMAE.yaml b/data/custodian/JP-09-OIC-M-HMAE.yaml index ad39a0fc7b..51ede963bc 100644 --- a/data/custodian/JP-09-OIC-M-HMAE.yaml +++ b/data/custodian/JP-09-OIC-M-HMAE.yaml @@ -393,3 +393,37 @@ location: geonames_id: 1854523 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:30.089335+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:08:58.688889+00:00' + source_url: https://hiroshige-ena.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://hiroshige-ena.jp/wp-content/uploads/2025/03/アイキャッチ_本山1.png + source_url: https://hiroshige-ena.jp + css_selector: '#header-in > div.logo.logo-header > a.site-name.site-name-text-link + > span.site-name-text > img.site-logo-image.header-site-logo-image' + retrieved_on: '2025-12-23T20:08:58.688889+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 中山道広重美術館 + - claim_type: favicon_url + claim_value: https://hiroshige-ena.jp/wp-content/uploads/2024/10/cropped-favicon-180x180.png + source_url: https://hiroshige-ena.jp + css_selector: '[document] > html > head > link:nth-of-type(42)' + retrieved_on: '2025-12-23T20:08:58.688889+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://hiroshige-ena.jp/wp-content/uploads/2024/10/アイキャッチ1.jpg + source_url: https://hiroshige-ena.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T20:08:58.688889+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-09-SEK-M-GSBMM.yaml b/data/custodian/JP-09-SEK-M-GSBMM.yaml index 0c84085070..caa163e437 100644 --- a/data/custodian/JP-09-SEK-M-GSBMM.yaml +++ b/data/custodian/JP-09-SEK-M-GSBMM.yaml @@ -842,3 +842,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/c2R-Dos6GHA/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:09:13.706141+00:00' + source_url: https://sekigahara.pref.gifu.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sekigahara.pref.gifu.lg.jp/wp/wp-content/themes/standard/favicon.ico + source_url: https://sekigahara.pref.gifu.lg.jp + css_selector: '[document] > html.no-js.webkit > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T20:09:13.706141+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://sekigahara.pref.gifu.lg.jp/wp/wp-content/uploads/2020/09/ogp.png + source_url: https://sekigahara.pref.gifu.lg.jp + css_selector: '[document] > html.no-js.webkit > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T20:09:13.706141+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-09-SEK-M-SCSTAM.yaml b/data/custodian/JP-09-SEK-M-SCSTAM.yaml index fb94694459..537098348c 100644 --- a/data/custodian/JP-09-SEK-M-SCSTAM.yaml +++ b/data/custodian/JP-09-SEK-M-SCSTAM.yaml @@ -265,3 +265,22 @@ location: geonames_id: 1852775 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:30.191140+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:09:21.543883+00:00' + source_url: https://www.city.seki.lg.jp/0000000059.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.seki.lg.jp/css/img/apple-touch-icon.png + source_url: https://www.city.seki.lg.jp/0000000059.html + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T20:09:21.543883+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-09-TOM-M-TTM.yaml b/data/custodian/JP-09-TOM-M-TTM.yaml index cd367def72..16e355bb57 100644 --- a/data/custodian/JP-09-TOM-M-TTM.yaml +++ b/data/custodian/JP-09-TOM-M-TTM.yaml @@ -253,3 +253,22 @@ location: geonames_id: 13132758 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:30.419820+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:10:23.836151+00:00' + source_url: https://www.town.tomika.gifu.jp/docs/249.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.tomika.gifu.jp/img/favicon.ico + source_url: https://www.town.tomika.gifu.jp/docs/249.html + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T20:10:23.836151+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-09-UED-M-MF.yaml b/data/custodian/JP-09-UED-M-MF.yaml index 6900f2e11f..3610a590ce 100644 --- a/data/custodian/JP-09-UED-M-MF.yaml +++ b/data/custodian/JP-09-UED-M-MF.yaml @@ -230,3 +230,28 @@ location: geonames_id: 1849430 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:30.452937+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:10:31.465965+00:00' + source_url: https://www.minami-kanko.com/sightseeing/enjoy/post-7.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://minami-kanko.com/wp_7mamv9/wp-content/themes/minami-theme/assets/minami-kanko/images/common/favicon.ico + source_url: https://www.minami-kanko.com/sightseeing/enjoy/post-7.html + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-23T20:10:31.465965+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://minami-kanko.com/wp_7mamv9/wp-content/themes/minami-theme/assets/minami-kanko/images/common/ogp.jpg + source_url: https://www.minami-kanko.com/sightseeing/enjoy/post-7.html + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-23T20:10:31.465965+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-09-YAM-M-SM.yaml b/data/custodian/JP-09-YAM-M-SM.yaml index d4616582fd..1238c5fa71 100644 --- a/data/custodian/JP-09-YAM-M-SM.yaml +++ b/data/custodian/JP-09-YAM-M-SM.yaml @@ -270,3 +270,22 @@ location: geonames_id: 6822213 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:30.488553+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:10:41.031629+00:00' + source_url: http://www.sanko-museum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sanko-museum.or.jp/wp-content/themes/sanko-museum/img/favicon/safari-pinned-tab.svg + source_url: http://www.sanko-museum.or.jp + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-23T20:10:41.031629+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/JP-10-AGA-L-KL.yaml b/data/custodian/JP-10-AGA-L-KL.yaml index 78685774a4..dba9cb97e1 100644 --- a/data/custodian/JP-10-AGA-L-KL.yaml +++ b/data/custodian/JP-10-AGA-L-KL.yaml @@ -231,3 +231,30 @@ wikidata_enrichment: wikidata_media: image: Kusatsu-Onsen-Sta-Outside.jpg wikidata_image: Kusatsu-Onsen-Sta-Outside.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:11:00.732567+00:00' + source_url: https://www.town.kusatsu.gunma.jp/www/contents/1486453585239 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.kusatsu.gunma.jp/www/assets/images/common/logo-hd_sp.svg + source_url: https://www.town.kusatsu.gunma.jp/www/contents/1486453585239 + css_selector: '[document] > html.normal.load-done > body.page-home > div.l-frame-wrapper + > header.l-header.u-state-fade > div.l-header__in > div.l-header__logo > a > + picture > source > source > img' + retrieved_on: '2025-12-23T20:11:00.732567+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 草津町 + - claim_type: og_image_url + claim_value: https://www.town.kusatsu.gunma.jp/www/assets/images/og-image.jpg + source_url: https://www.town.kusatsu.gunma.jp/www/contents/1486453585239 + css_selector: '[document] > html.normal.load-done > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T20:11:00.732567+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-10-AGA-M-GAO.yaml b/data/custodian/JP-10-AGA-M-GAO.yaml index 5f6627ef5e..c2d476ca03 100644 --- a/data/custodian/JP-10-AGA-M-GAO.yaml +++ b/data/custodian/JP-10-AGA-M-GAO.yaml @@ -268,3 +268,22 @@ location: postal_code: 377-0702 street_address: NAKAYAMA, Agatsuma Gun Takayama Mura, Gumma Ken, 377-0702 normalization_timestamp: '2025-12-09T06:54:35.422641+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:11:17.539356+00:00' + source_url: http://www.astron.pref.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.astron.pref.gunma.jp/images/general/gaologo2025.jpg + source_url: http://www.astron.pref.gunma.jp + css_selector: '#titlelogo' + retrieved_on: '2025-12-23T20:11:17.539356+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: キーテクノロジー ぐんま天文台 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-10-AGA-M-NFHMM.yaml b/data/custodian/JP-10-AGA-M-NFHMM.yaml index 5f00022f47..838d9bcc5d 100644 --- a/data/custodian/JP-10-AGA-M-NFHMM.yaml +++ b/data/custodian/JP-10-AGA-M-NFHMM.yaml @@ -253,3 +253,22 @@ location: postal_code: 377-0424 street_address: NAKANOJOMACHI, Agatsuma Gun Nakanojo Machi, Gumma Ken, 377-0424 normalization_timestamp: '2025-12-09T06:54:35.468074+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:11:24.865962+00:00' + source_url: https://www.town.nakanojo.gunma.jp/musee + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.nakanojo.gunma.jp/apple-touch-icon.png + source_url: https://www.town.nakanojo.gunma.jp/musee + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:11:24.865962+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-10-AGA-M-YTMM.yaml b/data/custodian/JP-10-AGA-M-YTMM.yaml index ec253d5774..588c4bf744 100644 --- a/data/custodian/JP-10-AGA-M-YTMM.yaml +++ b/data/custodian/JP-10-AGA-M-YTMM.yaml @@ -255,3 +255,23 @@ location: postal_code: 377-1309 street_address: HAYASHI, Agatsuma Gun Naganohara Machi, Gumma Ken, 377-1309 normalization_timestamp: '2025-12-09T06:54:35.486709+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:11:37.676455+00:00' + source_url: https://www.town.naganohara.gunma.jp/www/yamba-museum + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.naganohara.gunma.jp/yamba/img/common/logo_pc.png + source_url: https://www.town.naganohara.gunma.jp/www/yamba-museum + css_selector: '[document] > html > body > div.wrap > header.header > div.inner.flex + > h1.header_logo > a > img' + retrieved_on: '2025-12-23T20:11:37.676455+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: やんば天明泥流ミュージアムロゴ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-10-ANN-M-ASGFG.yaml b/data/custodian/JP-10-ANN-M-ASGFG.yaml index e6c79811e2..3ad4649d2c 100644 --- a/data/custodian/JP-10-ANN-M-ASGFG.yaml +++ b/data/custodian/JP-10-ANN-M-ASGFG.yaml @@ -218,3 +218,22 @@ location: postal_code: 379-0123 street_address: KAMIMANITA, Annaka Shi, Gumma Ken, 379-0123 normalization_timestamp: '2025-12-09T06:54:35.551014+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:11:52.878792+00:00' + source_url: https://www.city.annaka.lg.jp/gakushuunomori + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.annaka.lg.jp/apple-touch-icon.png + source_url: https://www.city.annaka.lg.jp/gakushuunomori + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:11:52.878792+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-10-AZU-M-TAM.yaml b/data/custodian/JP-10-AZU-M-TAM.yaml index 8ba756100c..b2806d40ff 100644 --- a/data/custodian/JP-10-AZU-M-TAM.yaml +++ b/data/custodian/JP-10-AZU-M-TAM.yaml @@ -727,3 +727,36 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/mutTcGX1vn0/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:12:01.582721+00:00' + source_url: https://www.city.midori.gunma.jp/tomihiro + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.midori.gunma.jp/_template_/_site_/_default_/_res/tomihiro/images/header/tlogo.png?a + source_url: https://www.city.midori.gunma.jp/tomihiro + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T20:12:01.582721+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 富弘美術館 + - claim_type: favicon_url + claim_value: https://www.city.midori.gunma.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.midori.gunma.jp/tomihiro + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T20:12:01.582721+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.midori.gunma.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.midori.gunma.jp/tomihiro + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T20:12:01.582721+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-10-FUJ-L-GLF.yaml b/data/custodian/JP-10-FUJ-L-GLF.yaml index ea5b77110a..e0f3be10dc 100644 --- a/data/custodian/JP-10-FUJ-L-GLF.yaml +++ b/data/custodian/JP-10-FUJ-L-GLF.yaml @@ -205,3 +205,22 @@ location: geonames_id: 1864099 geonames_name: Fujioka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:12:11.251516+00:00' + source_url: http://www.shoken-gakuen.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.shoken-gakuen.ac.jp/favicon.ico + source_url: http://www.shoken-gakuen.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T20:12:11.251516+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-10-HOD-M-MLCBT.yaml b/data/custodian/JP-10-HOD-M-MLCBT.yaml index 8bdc4502d2..0c3f301066 100644 --- a/data/custodian/JP-10-HOD-M-MLCBT.yaml +++ b/data/custodian/JP-10-HOD-M-MLCBT.yaml @@ -299,3 +299,28 @@ location: geonames_id: 9182534 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:30.598864+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:12:20.971748+00:00' + source_url: https://bungaku.pref.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bungaku.pref.gunma.jp/tb2021/wp-content/themes/tb2021/assets/img/favicon.png + source_url: https://bungaku.pref.gunma.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:12:20.971748+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://bungaku.pref.gunma.jp/tb2021/wp-content/themes/tb2021/assets/img/ogp.jpg + source_url: https://bungaku.pref.gunma.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T20:12:20.971748+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-10-ISE-L-IL-isesakishiazuma_library.yaml b/data/custodian/JP-10-ISE-L-IL-isesakishiazuma_library.yaml index b30f18c24c..26baacf363 100644 --- a/data/custodian/JP-10-ISE-L-IL-isesakishiazuma_library.yaml +++ b/data/custodian/JP-10-ISE-L-IL-isesakishiazuma_library.yaml @@ -204,3 +204,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.isesaki.gunma.jp/ wikidata_official_website: http://www.library.isesaki.gunma.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:13:07.325372+00:00' + source_url: http://www.library.isesaki.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.library.isesaki.gunma.jp/css/img/apple-touch-icon.png + source_url: http://www.library.isesaki.gunma.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T20:13:07.325372+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.library.isesaki.gunma.jp/design_img/og_image.png + source_url: http://www.library.isesaki.gunma.jp + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T20:13:07.325372+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-10-ISE-L-IL-isesakishisakai_library.yaml b/data/custodian/JP-10-ISE-L-IL-isesakishisakai_library.yaml index ac2c8ccab8..3e858bd873 100644 --- a/data/custodian/JP-10-ISE-L-IL-isesakishisakai_library.yaml +++ b/data/custodian/JP-10-ISE-L-IL-isesakishisakai_library.yaml @@ -204,3 +204,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.isesaki.gunma.jp wikidata_official_website: http://www.library.isesaki.gunma.jp +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:13:15.460463+00:00' + source_url: http://www.library.isesaki.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.library.isesaki.gunma.jp/css/img/apple-touch-icon.png + source_url: http://www.library.isesaki.gunma.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T20:13:15.460463+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.library.isesaki.gunma.jp/design_img/og_image.png + source_url: http://www.library.isesaki.gunma.jp + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T20:13:15.460463+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-10-ISE-L-IL.yaml b/data/custodian/JP-10-ISE-L-IL.yaml index c7beba66c7..7f57fe652b 100644 --- a/data/custodian/JP-10-ISE-L-IL.yaml +++ b/data/custodian/JP-10-ISE-L-IL.yaml @@ -206,3 +206,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.isesaki.gunma.jp/ wikidata_official_website: http://www.library.isesaki.gunma.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:13:23.813213+00:00' + source_url: http://www.library.isesaki.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.library.isesaki.gunma.jp/css/img/apple-touch-icon.png + source_url: http://www.library.isesaki.gunma.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T20:13:23.813213+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.library.isesaki.gunma.jp/design_img/og_image.png + source_url: http://www.library.isesaki.gunma.jp + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T20:13:23.813213+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-10-ISE-M-AAM.yaml b/data/custodian/JP-10-ISE-M-AAM.yaml index becbd6cccb..7a72a45fb3 100644 --- a/data/custodian/JP-10-ISE-M-AAM.yaml +++ b/data/custodian/JP-10-ISE-M-AAM.yaml @@ -239,3 +239,22 @@ wikidata_enrichment: image: Aikawa Archaeological Museum.JPG commons_category: Aikawa Archaeological Museum wikidata_image: Aikawa Archaeological Museum.JPG +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:14:06.622415+00:00' + source_url: http://aam.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://aam.or.jp/wp-content/themes/aikawa/images/logo.png + source_url: http://aam.or.jp + css_selector: '#header > div.inner:nth-of-type(2) > h2 > a > img' + retrieved_on: '2025-12-23T20:14:06.622415+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 相川考古館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-10-ITA-M-TCKNZMA.yaml b/data/custodian/JP-10-ITA-M-TCKNZMA.yaml index 7d0e63b353..7a55c5eb4b 100644 --- a/data/custodian/JP-10-ITA-M-TCKNZMA.yaml +++ b/data/custodian/JP-10-ITA-M-TCKNZMA.yaml @@ -389,3 +389,22 @@ location: geonames_id: 1861315 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:30.715791+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:14:17.576045+00:00' + source_url: http://www.city.takasaki.gunma.jp/docs/2014010800114 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.takasaki.gunma.jp/apple-touch-icon.png + source_url: http://www.city.takasaki.gunma.jp/docs/2014010800114 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:14:17.576045+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-10-IWA-M-GPMH.yaml b/data/custodian/JP-10-IWA-M-GPMH.yaml index 70054cfcfd..cb05ea8bce 100644 --- a/data/custodian/JP-10-IWA-M-GPMH.yaml +++ b/data/custodian/JP-10-IWA-M-GPMH.yaml @@ -398,3 +398,31 @@ location: geonames_id: 1861228 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:30.777468+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:14:29.877698+00:00' + source_url: https://grekisi.pref.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://grekisi.pref.gunma.jp/wp/wp-content/themes/gunma-rekisi/img/common/logo_header.png + source_url: https://grekisi.pref.gunma.jp + css_selector: '#headarea > div.above > div.wrap:nth-of-type(2) > p.logo > a > + img' + retrieved_on: '2025-12-23T20:14:29.877698+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 群馬県立歴史博物館 + - claim_type: favicon_url + claim_value: https://grekisi.pref.gunma.jp/wp/wp-content/themes/gunma-rekisi/img/apple-touch-icon.png + source_url: https://grekisi.pref.gunma.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:14:29.877698+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-10-IWA-M-GSP.yaml b/data/custodian/JP-10-IWA-M-GSP.yaml index 2106c60503..1f0d087f49 100644 --- a/data/custodian/JP-10-IWA-M-GSP.yaml +++ b/data/custodian/JP-10-IWA-M-GSP.yaml @@ -1895,3 +1895,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/gKk40uuuMCE/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:14:40.881615+00:00' + source_url: https://www.safari.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://safari.co.jp/apple-touch-icon.png + source_url: https://www.safari.co.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T20:14:40.881615+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://safari.co.jp/wordpress/wp-content/themes/safari/dist/img/common/ogp.jpg + source_url: https://www.safari.co.jp + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T20:14:40.881615+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-10-KIR-L-GL.yaml b/data/custodian/JP-10-KIR-L-GL.yaml index 2568e12462..1a7bfec158 100644 --- a/data/custodian/JP-10-KIR-L-GL.yaml +++ b/data/custodian/JP-10-KIR-L-GL.yaml @@ -205,3 +205,22 @@ location: geonames_id: 1859405 geonames_name: Kiryū feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:15:21.720070+00:00' + source_url: http://www.media.gunma-u.ac.jp/guide/k + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.media.gunma-u.ac.jp/assets/templates/media/favicon.ico + source_url: http://www.media.gunma-u.ac.jp/guide/k + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:15:21.720070+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-10-KIR-L-KCL.yaml b/data/custodian/JP-10-KIR-L-KCL.yaml index 49f546c243..9360c36920 100644 --- a/data/custodian/JP-10-KIR-L-KCL.yaml +++ b/data/custodian/JP-10-KIR-L-KCL.yaml @@ -256,3 +256,30 @@ location: postal_code: 376-0022 street_address: 1-4 INARICHO, Kiryu Shi, Gumma Ken, 376-0022 normalization_timestamp: '2025-12-09T06:54:35.962227+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:15:31.467697+00:00' + source_url: https://www.city.kiryu.lg.jp/shisetsu/bunka/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.kiryu.lg.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.kiryu.lg.jp/shisetsu/bunka/library/index.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T20:15:31.467697+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 桐生市トップページ + - claim_type: favicon_url + claim_value: https://www.city.kiryu.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.kiryu.lg.jp/shisetsu/bunka/library/index.html + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T20:15:31.467697+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-10-KIR-M-KFNO.yaml b/data/custodian/JP-10-KIR-M-KFNO.yaml index eb09da8f55..edf96044ca 100644 --- a/data/custodian/JP-10-KIR-M-KFNO.yaml +++ b/data/custodian/JP-10-KIR-M-KFNO.yaml @@ -205,3 +205,30 @@ wikidata_enrichment: wikidata_web: official_website: https://www.city.kiryu.lg.jp/forest/index.html wikidata_official_website: https://www.city.kiryu.lg.jp/forest/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:15:54.289728+00:00' + source_url: https://www.city.kiryu.lg.jp/forest/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.kiryu.lg.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.kiryu.lg.jp/forest/index.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T20:15:54.289728+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 桐生市トップページ + - claim_type: favicon_url + claim_value: https://www.city.kiryu.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.kiryu.lg.jp/forest/index.html + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T20:15:54.289728+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-10-KIR-M-KZ.yaml b/data/custodian/JP-10-KIR-M-KZ.yaml index 9a1a675ea1..9da18d248c 100644 --- a/data/custodian/JP-10-KIR-M-KZ.yaml +++ b/data/custodian/JP-10-KIR-M-KZ.yaml @@ -254,3 +254,22 @@ location: postal_code: 376-0056 street_address: MIYAMOTOCHO, Kiryu Shi, Gumma Ken, 376-0056 normalization_timestamp: '2025-12-09T06:54:36.089273+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:16:03.137062+00:00' + source_url: http://www.city.kiryu.lg.jp/zoo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.kiryu.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: http://www.city.kiryu.lg.jp/zoo + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T20:16:03.137062+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-10-KIT-L-YTL.yaml b/data/custodian/JP-10-KIT-L-YTL.yaml index 6b55b8dbd2..9ae9fff64f 100644 --- a/data/custodian/JP-10-KIT-L-YTL.yaml +++ b/data/custodian/JP-10-KIT-L-YTL.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.library.yoshioka.gunma.jp/ wikidata_official_website: http://www.library.yoshioka.gunma.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:16:26.469578+00:00' + source_url: http://www.library.yoshioka.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.library.yoshioka.gunma.jp/images/header_logo.svg + source_url: http://www.library.yoshioka.gunma.jp + css_selector: '#index > header > div.block.clearfix > div.logo > a > img' + retrieved_on: '2025-12-23T20:16:26.469578+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 吉岡町図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-10-KIT-M-MESM.yaml b/data/custodian/JP-10-KIT-M-MESM.yaml index 878504e757..71d85b90d4 100644 --- a/data/custodian/JP-10-KIT-M-MESM.yaml +++ b/data/custodian/JP-10-KIT-M-MESM.yaml @@ -247,3 +247,22 @@ location: postal_code: 370-3502 street_address: YAMAKODA, Kitagumma Gun Shinto Mura, Gumma Ken, 370-3502 normalization_timestamp: '2025-12-09T06:54:36.201363+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:16:38.385098+00:00' + source_url: http://www.vill.shinto.gunma.jp/mimikazari/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.vill.shinto.gunma.jp/apple-touch-icon.png + source_url: http://www.vill.shinto.gunma.jp/mimikazari/index.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T20:16:38.385098+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-10-MAE-L-GLI.yaml b/data/custodian/JP-10-MAE-L-GLI.yaml index 5366aa783f..462dd06ef0 100644 --- a/data/custodian/JP-10-MAE-L-GLI.yaml +++ b/data/custodian/JP-10-MAE-L-GLI.yaml @@ -205,3 +205,22 @@ location: geonames_id: 1857843 geonames_name: Maebashi feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:16:49.675684+00:00' + source_url: http://www.media.gunma-u.ac.jp/guide/s + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.media.gunma-u.ac.jp/assets/templates/media/favicon.ico + source_url: http://www.media.gunma-u.ac.jp/guide/s + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T20:16:49.675684+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-10-MAE-L-GLM.yaml b/data/custodian/JP-10-MAE-L-GLM.yaml index 84dde34858..f7f20167b8 100644 --- a/data/custodian/JP-10-MAE-L-GLM.yaml +++ b/data/custodian/JP-10-MAE-L-GLM.yaml @@ -205,3 +205,22 @@ location: geonames_id: 1857843 geonames_name: Maebashi feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:16:57.378499+00:00' + source_url: http://www.shoken-gakuen.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.shoken-gakuen.ac.jp/favicon.ico + source_url: http://www.shoken-gakuen.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T20:16:57.378499+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-10-MAE-L-GPL.yaml b/data/custodian/JP-10-MAE-L-GPL.yaml index df15fbbfc5..a112aa8989 100644 --- a/data/custodian/JP-10-MAE-L-GPL.yaml +++ b/data/custodian/JP-10-MAE-L-GPL.yaml @@ -373,3 +373,22 @@ location: geonames_id: 1857843 feature_code: PPLA normalization_timestamp: '2025-12-09T06:53:30.978383+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:17:10.871626+00:00' + source_url: https://www.library.pref.gunma.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.pref.gunma.jp/nc_favicon.ico?1751936623 + source_url: https://www.library.pref.gunma.jp + css_selector: '[document] > html.ng-scope > head > link' + retrieved_on: '2025-12-23T20:17:10.871626+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: 2 diff --git a/data/custodian/JP-10-MAE-L-GPLES.yaml b/data/custodian/JP-10-MAE-L-GPLES.yaml index 14c3354313..a9a0ca6d50 100644 --- a/data/custodian/JP-10-MAE-L-GPLES.yaml +++ b/data/custodian/JP-10-MAE-L-GPLES.yaml @@ -209,3 +209,22 @@ location: geonames_id: 1857843 geonames_name: Maebashi feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:17:22.371745+00:00' + source_url: https://center.gsn.ed.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://center.gsn.ed.jp/nc_favicon.ico?1707660674 + source_url: https://center.gsn.ed.jp + css_selector: '[document] > html.ng-scope > head > link' + retrieved_on: '2025-12-23T20:17:22.371745+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-10-MAE-L-GUHWL.yaml b/data/custodian/JP-10-MAE-L-GUHWL.yaml index 16c9e736c1..b651941f26 100644 --- a/data/custodian/JP-10-MAE-L-GUHWL.yaml +++ b/data/custodian/JP-10-MAE-L-GUHWL.yaml @@ -219,3 +219,22 @@ location: geonames_id: 1857843 geonames_name: Maebashi feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:17:30.750585+00:00' + source_url: http://www.shoken-gakuen.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.shoken-gakuen.ac.jp/favicon.ico + source_url: http://www.shoken-gakuen.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T20:17:30.750585+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-10-MAE-L-LGPCHS.yaml b/data/custodian/JP-10-MAE-L-LGPCHS.yaml index 4f74b53908..2f5b9fd583 100644 --- a/data/custodian/JP-10-MAE-L-LGPCHS.yaml +++ b/data/custodian/JP-10-MAE-L-LGPCHS.yaml @@ -211,3 +211,28 @@ location: geonames_id: 1857843 geonames_name: Maebashi feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T20:17:39.216513+00:00' + source_url: http://gchs.opac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://gchs.opac.jp/common/images/op4-favicon.ico + source_url: http://gchs.opac.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T20:17:39.216513+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://gchs.opac.jp/common/images/ogp-image.jpg + source_url: http://gchs.opac.jp + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T20:17:39.216513+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