diff --git a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json index 04dca4b1e7..d05b043062 100644 --- a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json +++ b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json @@ -12202,7 +12202,327 @@ "JP-13-SHI-L-AIITL.yaml", "JP-13-SHI-L-AL.yaml", "JP-13-SHI-L-APCCUAL.yaml", - "JP-13-SHI-L-BGUL.yaml" + "JP-13-SHI-L-BGUL.yaml", + "JP-13-SHI-L-BMFJINF.yaml", + "JP-13-SHI-L-BPAJBCC.yaml", + "JP-13-SHI-L-CIMOL.yaml", + "JP-13-SHI-L-CLR.yaml", + "JP-13-SHI-L-DHT.yaml", + "JP-13-SHI-L-DMUL.yaml", + "JP-13-SHI-L-GIROJ.yaml", + "JP-13-SHI-L-GWSCL.yaml", + "JP-13-SHI-L-HL.yaml", + "JP-13-SHI-L-I-ippanzaidanhojinkokusaiigakujohosentatoshoshiryoka.yaml", + "JP-13-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai.yaml", + "JP-13-SHI-L-I.yaml", + "JP-13-SHI-L-ILOOJL.yaml", + "JP-13-SHI-L-IRTMG.yaml", + "JP-13-SHI-L-JACNNTL.yaml", + "JP-13-SHI-L-JBL.yaml", + "JP-13-SHI-L-JFICL.yaml", + "JP-13-SHI-L-JFOUYCL.yaml", + "JP-13-SHI-L-JICAL.yaml", + "JP-13-SHI-L-JJLS.yaml", + "JP-13-SHI-L-JMUL.yaml", + "JP-13-SHI-L-JPICL.yaml", + "JP-13-SHI-L-JRCCNL.yaml", + "JP-13-SHI-L-JSCEL.yaml", + "JP-13-SHI-L-JSME.yaml", + "JP-13-SHI-L-JTRIL.yaml", + "JP-13-SHI-L-JTSLIC.yaml", + "JP-13-SHI-L-K-kabushikigaishameidenshatoshoshitsu.yaml", + "JP-13-SHI-L-K-kabushikigaishanihonsogokenkyushochosabutoshoshits.yaml", + "JP-13-SHI-L-K.yaml", + "JP-13-SHI-L-KC.yaml", + "JP-13-SHI-L-KL.yaml", + "JP-13-SHI-L-KLS.yaml", + "JP-13-SHI-L-KUSMCKMML.yaml", + "JP-13-SHI-L-LDCOCOSBLL.yaml", + "JP-13-SHI-L-LKCCKE.yaml", + "JP-13-SHI-L-LKSF.yaml", + "JP-13-SHI-L-LNIID.yaml", + "JP-13-SHI-L-MACMHNIDS.yaml", + "JP-13-SHI-L-MCAMMMML.yaml", + "JP-13-SHI-L-MDLBN.yaml", + "JP-13-SHI-L-ML.yaml", + "JP-13-SHI-L-MTL.yaml", + "JP-13-SHI-L-MYGL.yaml", + "JP-13-SHI-L-N-nihonkodenkogyokabushikigaishasomubushiryoshitsu.yaml", + "JP-13-SHI-L-N-nyuzemmachiaokikominkantoshoshitsu.yaml", + "JP-13-SHI-L-N-nyuzemmachiiinokominkantoshoshitsu.yaml", + "JP-13-SHI-L-N-nyuzemmachikunugiyamakominkantoshoshitsu.yaml", + "JP-13-SHI-L-N.yaml", + "JP-13-SHI-L-NIC.yaml", + "JP-13-SHI-L-NIYE.yaml", + "JP-13-SHI-L-NL-nihommojinkairengotenji_library.yaml", + "JP-13-SHI-L-NL.yaml", + "JP-13-SHI-L-NNTT.yaml", + "JP-13-SHI-L-NTL.yaml", + "JP-13-SHI-L-PCCA.yaml", + "JP-13-SHI-L-PJITMIC.yaml", + "JP-13-SHI-L-PUIMIL.yaml", + "JP-13-SHI-L-S.yaml", + "JP-13-SHI-L-SELWU.yaml", + "JP-13-SHI-L-SFCL.yaml", + "JP-13-SHI-L-SL-seisenjoshidaigakufuzoku_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsuchuo_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsuhommachi_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsukomorebiowada_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsunishihara_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsurinsemminnano_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsusasazuka_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsusasazukakodomo_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsutomigaya_library.yaml", + "JP-13-SHI-L-SL-shibuyakuritsuyoyogi_library.yaml", + "JP-13-SHI-L-SL-shimotsukeshiritsuishibashi_library.yaml", + "JP-13-SHI-L-SL-shimotsukeshiritsukokubunji_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsuebara_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsufutaba_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsugenjimae_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsugotanda_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsuminamioi_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsuoi_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsuosaki_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsushinagawa_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsuyashio_library.yaml", + "JP-13-SHI-L-SL-shinagawakuritsuyutaka_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsuchuo_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsukitashinjuku_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsukodomo_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsunakamachi_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsunishiochiai_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsuokubo_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsutoyama_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsutsunohazu_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsutsurumaki_library.yaml", + "JP-13-SHI-L-SL-shinjukukuritsuyotsuya_library.yaml", + "JP-13-SHI-L-SL-shioyamachi_library.yaml", + "JP-13-SHI-L-SL.yaml", + "JP-13-SHI-L-SLJ.yaml", + "JP-13-SHI-L-SLMIACBN.yaml", + "JP-13-SHI-L-SMUL.yaml", + "JP-13-SHI-L-SS.yaml", + "JP-13-SHI-L-T.yaml", + "JP-13-SHI-L-TL-takarazukadaigakutokyoshinjukukyampasu_library.yaml", + "JP-13-SHI-L-TL-teikyotankidaigaku_library.yaml", + "JP-13-SHI-L-TL-tokyofujidaigaku_library.yaml", + "JP-13-SHI-L-TL-tokyoherenkerakyokaitenji_library.yaml", + "JP-13-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library.yaml", + "JP-13-SHI-L-TL-tokyorikadaigakukagurazaka_library.yaml", + "JP-13-SHI-L-TL-tokyotoritsusangyogijutsukotosemmongakkoshinagawak.yaml", + "JP-13-SHI-L-TL.yaml", + "JP-13-SHI-L-TLB.yaml", + "JP-13-SHI-L-TLK-tokyojoshiikadaigaku_library_kawadachobunshitsu.yaml", + "JP-13-SHI-L-TLK.yaml", + "JP-13-SHI-L-TLN.yaml", + "JP-13-SHI-L-TMAL.yaml", + "JP-13-SHI-L-TMUL.yaml", + "JP-13-SHI-L-TUYL.yaml", + "JP-13-SHI-L-TWSMUHHA.yaml", + "JP-13-SHI-L-TWSMUL.yaml", + "JP-13-SHI-L-TWSPL.yaml", + "JP-13-SHI-L-UNUL.yaml", + "JP-13-SHI-L-USHL.yaml", + "JP-13-SHI-L-W-wasedadaigakuchoshinkokusaigurupukinengakuseidokus.yaml", + "JP-13-SHI-L-W-wasedadaigakudaigakuinhogakukenkyukagakuseidokusho.yaml", + "JP-13-SHI-L-W-wasedadaigakuhogakubugakuseidokushoshitsu.yaml", + "JP-13-SHI-L-W-wasedadaigakukyoikugakubugakuseidokushoshitsu.yaml", + "JP-13-SHI-L-W-wasedadaigakukyoikugakukenkyukagakuseidokushoshits.yaml", + "JP-13-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush.yaml", + "JP-13-SHI-L-W-wasedadaigakuseijikeizaigakubugakuseidokushoshitsu.yaml", + "JP-13-SHI-L-W-wasedadaigakushakaikagakubugakuseidokushoshitsu.yaml", + "JP-13-SHI-L-W-wasedadaigakushakaikagakubukyointoshoshitsu.yaml", + "JP-13-SHI-L-W-wasedadaigakutsubochihakasekinenengekihakubutsukan.yaml", + "JP-13-SHI-L-W-wasedadaigakuzairyogijutsukenkyujotoshoshitsu.yaml", + "JP-13-SHI-L-W.yaml", + "JP-13-SHI-L-WIHL.yaml", + "JP-13-SHI-L-WIPE.yaml", + "JP-13-SHI-L-WL.yaml", + "JP-13-SHI-L-WLG.yaml", + "JP-13-SHI-L-WUFCL.yaml", + "JP-13-SHI-L-WUL.yaml", + "JP-13-SHI-L-WUSLSE.yaml", + "JP-13-SHI-L-WUSTMRL.yaml", + "JP-13-SHI-M-AM.yaml", + "JP-13-SHI-M-AMWU.yaml", + "JP-13-SHI-M-ATCAO.yaml", + "JP-13-SHI-M-BCC.yaml", + "JP-13-SHI-M-BGCM.yaml", + "JP-13-SHI-M-BM.yaml", + "JP-13-SHI-M-BMA.yaml", + "JP-13-SHI-M-CM.yaml", + "JP-13-SHI-M-CPS.yaml", + "JP-13-SHI-M-EM.yaml", + "JP-13-SHI-M-FM.yaml", + "JP-13-SHI-M-FMA.yaml", + "JP-13-SHI-M-GCCP.yaml", + "JP-13-SHI-M-GT.yaml", + "JP-13-SHI-M-HMSYYMRTWS.yaml", + "JP-13-SHI-M-IMA.yaml", + "JP-13-SHI-M-JOM-jade_ore_museum.yaml", + "JP-13-SHI-M-JOM.yaml", + "JP-13-SHI-M-KKCH.yaml", + "JP-13-SHI-M-KM.yaml", + "JP-13-SHI-M-KMMJWSU.yaml", + "JP-13-SHI-M-KMMM.yaml", + "JP-13-SHI-M-KSMM.yaml", + "JP-13-SHI-M-KUM.yaml", + "JP-13-SHI-M-MMHFMM.yaml", + "JP-13-SHI-M-MMM.yaml", + "JP-13-SHI-M-MMMH.yaml", + "JP-13-SHI-M-MMPG.yaml", + "JP-13-SHI-M-MMSDSPR.yaml", + "JP-13-SHI-M-MPC.yaml", + "JP-13-SHI-M-MPGHU.yaml", + "JP-13-SHI-M-MYB.yaml", + "JP-13-SHI-M-NFAM.yaml", + "JP-13-SHI-M-NICI.yaml", + "JP-13-SHI-M-NSMA.yaml", + "JP-13-SHI-M-NSMM.yaml", + "JP-13-SHI-M-OMMA.yaml", + "JP-13-SHI-M-SA.yaml", + "JP-13-SHI-M-SCM.yaml", + "JP-13-SHI-M-SFLSMM.yaml", + "JP-13-SHI-M-SFOMM.yaml", + "JP-13-SHI-M-SGNG.yaml", + "JP-13-SHI-M-SHM.yaml", + "JP-13-SHI-M-SMA-sompo_museum_of_art.yaml", + "JP-13-SHI-M-SMA-the_shoto_museum_of_art.yaml", + "JP-13-SHI-M-SUMBG.yaml", + "JP-13-SHI-M-TDHM.yaml", + "JP-13-SHI-M-TMA.yaml", + "JP-13-SHI-M-TMTMWU.yaml", + "JP-13-SHI-M-TTM.yaml", + "JP-13-SHI-M-TTMHF.yaml", + "JP-13-SHI-M-WIHLHML.yaml", + "JP-13-SHI-M-WK.yaml", + "JP-13-SHI-M-WWMCA.yaml", + "JP-13-SHI-M-YKM.yaml", + "JP-13-SHI-M-YMA.yaml", + "JP-13-SUG-L-ICSCTWSCU.yaml", + "JP-13-SUG-L-JUADL.yaml", + "JP-13-SUG-L-MLIL.yaml", + "JP-13-SUG-L-RIRC.yaml", + "JP-13-SUG-L-RL.yaml", + "JP-13-SUG-L-SL-suginamikuritsuasagaya_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsueifuku_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsuhonan_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsuimagawa_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsukakinoki_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsukoenji_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsuminamiogikubo_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsumiyamae_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsunarita_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsunishiogi_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsushimoigusa_library.yaml", + "JP-13-SUG-L-SL-suginamikuritsutakaido_library.yaml", + "JP-13-SUG-L-SL.yaml", + "JP-13-SUG-L-TRJCL.yaml", + "JP-13-SUG-L-TUL.yaml", + "JP-13-SUG-L-TWSCUL.yaml", + "JP-13-SUG-M-SHM.yaml", + "JP-13-SUM-L-ETML.yaml", + "JP-13-SUM-L-K.yaml", + "JP-13-SUM-L-SL-sumidakuritsuhikifune_library.yaml", + "JP-13-SUM-L-SL-sumidakuritsumidori_library.yaml", + "JP-13-SUM-L-SL-sumidakuritsuyahiro_library.yaml", + "JP-13-SUM-L-SL.yaml", + "JP-13-SUM-M-BM.yaml", + "JP-13-SUM-M-ETM.yaml", + "JP-13-SUM-M-GKEMM.yaml", + "JP-13-SUM-M-JSM.yaml", + "JP-13-SUM-M-PMJ.yaml", + "JP-13-SUM-M-SA.yaml", + "JP-13-SUM-M-SM.yaml", + "JP-13-SUM-M-TMTC.yaml", + "JP-13-SUM-M-TSM.yaml", + "JP-13-TAC-L-ISMLD.yaml", + "JP-13-TAC-L-JPRA.yaml", + "JP-13-TAC-L-KCML.yaml", + "JP-13-TAC-L-NIJL.yaml", + "JP-13-TAC-L-NIPRLROIS.yaml", + "JP-13-TAC-L-RLIURICNIH.yaml", + "JP-13-TAC-L-THUTL.yaml", + "JP-13-TAC-L-TL-tachikawashichuo_library.yaml", + "JP-13-TAC-L-TL-tachikawashikamisuna_library.yaml", + "JP-13-TAC-L-TL-tachikawashinishisuna_library.yaml", + "JP-13-TAC-L-TL-tachikawashisaiwai_library.yaml", + "JP-13-TAC-L-TL-tachikawashishibasaki_library.yaml", + "JP-13-TAC-L-TL-tachikawashitakamatsu_library.yaml", + "JP-13-TAC-L-TL-tachikawashitamagawa_library.yaml", + "JP-13-TAC-L-TL-tachikawashiwakaba_library.yaml", + "JP-13-TAC-L-TL.yaml", + "JP-13-TAC-M-GSCOKCM.yaml", + "JP-13-TAC-M-PM.yaml", + "JP-13-TAC-M-TCHFM.yaml", + "JP-13-TAI-L-ILCSLNDL.yaml", + "JP-13-TAI-L-ITEL.yaml", + "JP-13-TAI-L-JA.yaml", + "JP-13-TAI-L-MRRCMRFMTG.yaml", + "JP-13-TAI-L-NRICPT.yaml", + "JP-13-TAI-L-RICTNM.yaml", + "JP-13-TAI-L-RIJMHUGU.yaml", + "JP-13-TAI-L-RLNMWAT.yaml", + "JP-13-TAI-L-TBKML.yaml", + "JP-13-TAI-L-TL-taitokuritsuishihama_library.yaml", + "JP-13-TAI-L-TL-taitokuritsunegishi_library.yaml", + "JP-13-TAI-L-TL.yaml", + "JP-13-TAI-L-TLA.yaml", + "JP-13-TAI-L-TUAUUL.yaml", + "JP-13-TAI-L-UL.yaml", + "JP-13-TAI-L-UZL.yaml", + "JP-13-TAI-M-AMST.yaml", + "JP-13-TAI-M-CM.yaml", + "JP-13-TAI-M-IAINICHTNM.yaml", + "JP-13-TAI-M-MLI.yaml", + "JP-13-TAI-M-NMNS.yaml", + "JP-13-TAI-M-SM.yaml", + "JP-13-TAI-M-TMAM.yaml", + "JP-13-TAI-M-URM.yaml", + "JP-13-TAI-M-UZG.yaml", + "JP-13-TAI-M-YTMH.yaml", + "JP-13-TAK-L-I.yaml", + "JP-13-TAK-L-T-takaokashiritsufukutakominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsufutagamikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsufutazukakominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsuhigashigoikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsuhiramaikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsuishitsuzumikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsukawarakominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsukitahannyakominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsukizukominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsukofukominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsukoretokominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsukuniyoshikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsumakinokominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsumoriyamakominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsunishigoikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsunomurakominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsunoumachikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsusanokominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsuseibikominkantoshoshitsu.yaml", + "JP-13-TAK-L-T-takaokashiritsutatenokominkantoshoshitsu.yaml", + "JP-13-TAK-L-T.yaml", + "JP-13-TAK-L-TL-takaokahokadaigaku_library.yaml", + "JP-13-TAK-L-TL-takaokashiritsufukuoka_library.yaml", + "JP-13-TAK-L-TL-takaokashiritsufushiki_library.yaml", + "JP-13-TAK-L-TL-takaokashiritsunakada_library.yaml", + "JP-13-TAK-L-TL-takaokashiritsutoide_library.yaml", + "JP-13-TAK-L-TL.yaml", + "JP-13-TAK-L-UTADL.yaml", + "JP-13-TAK-M-AMAGTKHSTP.yaml", + "JP-13-TAK-M-FFFHAG.yaml", + "JP-13-TAK-M-FLMM.yaml", + "JP-13-TAK-M-KARC.yaml", + "JP-13-TAK-M-TAM.yaml", + "JP-13-TAK-M-TKPZ.yaml", + "JP-13-TAK-M-TMM.yaml", + "JP-13-TAM-L-KL.yaml", + "JP-13-TAM-L-KLJ.yaml", + "JP-13-TAM-L-N.yaml", + "JP-13-TAM-L-T.yaml", + "JP-13-TAM-L-TCCL.yaml", + "JP-13-TAM-L-TL-tamashiritsuhijirigaoka_library.yaml" ], - "last_index": 369 + "last_index": 189 } \ No newline at end of file diff --git a/data/custodian/JP-13-SHI-L-GWSCL.yaml b/data/custodian/JP-13-SHI-L-GWSCL.yaml index 0272e98ecc..6960156e3d 100644 --- a/data/custodian/JP-13-SHI-L-GWSCL.yaml +++ b/data/custodian/JP-13-SHI-L-GWSCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-GWSCL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-GWSCL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-GWSCL ghcid_numeric: 2073927055910298095 valid_from: '2025-12-06T23:38:55.420541+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: Gakushuin Women's College Library @@ -215,3 +216,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:00:52.527531+00:00' + source_url: http://www.gwc.gakushuin.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.gwc.gakushuin.ac.jp/cmn/icon/apple-touch-icon.png + source_url: http://www.gwc.gakushuin.ac.jp/library + css_selector: '[document] > html.js.supports > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T20:00:52.527531+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.gwc.gakushuin.ac.jp/cmn/img/ogimage.png + source_url: http://www.gwc.gakushuin.ac.jp/library + css_selector: '[document] > html.js.supports > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T20:00:52.527531+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai.yaml b/data/custodian/JP-13-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai.yaml index 1f24f832dd..f00891b889 100644 --- a/data/custodian/JP-13-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai.yaml +++ b/data/custodian/JP-13-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-I-ippanzaidanhojinnihonesuperantokyokai ghcid_numeric: 908938074059110531 valid_from: '2025-12-06T23:38:58.892903+00:00' @@ -106,8 +107,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: IPPANZAIDANHOJINNIHONESUPERANTOKYOKAI @@ -218,7 +219,8 @@ wikidata_enrichment: field_of_work: &id006 - id: Q108883098 label: radioisotope - description: isotope of given element that exhibits radioactivity and undergoes radioactive decay + description: isotope of given element that exhibits radioactivity and undergoes + radioactive decay wikidata_instance_of: *id005 wikidata_field_of_work: *id006 wikidata_location: @@ -259,3 +261,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:01:29.773117+00:00' + source_url: http://www.jei.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jei.or.jp/wp/wp-content/uploads/2020/08/cropped-JEI_SITEIMG-180x180.png + source_url: http://www.jei.or.jp + css_selector: '[document] > html.pc > head > link:nth-of-type(21)' + retrieved_on: '2025-12-25T20:01:29.773117+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-I.yaml b/data/custodian/JP-13-SHI-L-I.yaml index 06fdb2cedb..6d9e4e5cfe 100644 --- a/data/custodian/JP-13-SHI-L-I.yaml +++ b/data/custodian/JP-13-SHI-L-I.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-I - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-I valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-I ghcid_numeric: 13579733956564066065 valid_from: '2025-12-06T23:38:57.702787+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: IPPANZAIDANHOJINKEIRYOKEIKAKUKENKYUJOINOUEBUNKO @@ -151,3 +152,36 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:01:37.699979+00:00' + source_url: http://www.ibs.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.ibs.or.jp/wp-content/themes/ibswp/images/common/hd_logo.png + source_url: http://www.ibs.or.jp + css_selector: '#wrap > div.inner.clearfix > h1.hd_logo > a > img' + retrieved_on: '2025-12-25T20:01:37.699979+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: IBS計量計画研究所 + - claim_type: favicon_url + claim_value: https://www.ibs.or.jp/wp-content/uploads/2018/09/cropped-09e206f5750b6541346a7f1bf563bbe7-1-180x180.png + source_url: http://www.ibs.or.jp + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T20:01:37.699979+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ibs.or.jp/wp-content/themes/ibswp/images/fb-default.png + source_url: http://www.ibs.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:01:37.699979+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-ILOOJL.yaml b/data/custodian/JP-13-SHI-L-ILOOJL.yaml index 36a6a22a68..745e7a4059 100644 --- a/data/custodian/JP-13-SHI-L-ILOOJL.yaml +++ b/data/custodian/JP-13-SHI-L-ILOOJL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-ILOOJL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-ILOOJL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-ILOOJL ghcid_numeric: 9086109275483503289 valid_from: '2025-12-06T23:38:58.763295+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: International Labour Organization Office for Japan Library @@ -151,3 +152,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:01:44.462030+00:00' + source_url: http://www.ilo.org/tokyo/ilo-japan/office-for-japan/lang--ja/index.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ilo.org/themes/custom/ilo/node_modules/@ilo-org/brand-assets/dist/assets/favicon/safari-pinned-tab.svg + source_url: http://www.ilo.org/tokyo/ilo-japan/office-for-japan/lang--ja/index.htm + css_selector: '[document] > html.js > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T20:01:44.462030+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 6 diff --git a/data/custodian/JP-13-SHI-L-IRTMG.yaml b/data/custodian/JP-13-SHI-L-IRTMG.yaml index e2eb03c0f6..fce92d2109 100644 --- a/data/custodian/JP-13-SHI-L-IRTMG.yaml +++ b/data/custodian/JP-13-SHI-L-IRTMG.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:01:55.709047+00:00' + source_url: http://www.metro.tokyo.jp/POLICY/JOHO/BOOK/room.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.metro.tokyo.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.metro.tokyo.jp/POLICY/JOHO/BOOK/room.htm + css_selector: '[document] > html.ltr.yui3-js-enabled > head > link:nth-of-type(11)' + retrieved_on: '2025-12-25T20:01:55.709047+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.soumu.metro.tokyo.lg.jp/documents/158990/5052145/opg.png/3c79ba89-ab16-4589-4fad-b5b411615b25?version=1.1&t=1764164520819&imagePreview=1 + source_url: http://www.metro.tokyo.jp/POLICY/JOHO/BOOK/room.htm + css_selector: '[document] > html.ltr.yui3-js-enabled > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T20:01:55.709047+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-JACNNTL.yaml b/data/custodian/JP-13-SHI-L-JACNNTL.yaml index 52ab927776..4f6f13a04a 100644 --- a/data/custodian/JP-13-SHI-L-JACNNTL.yaml +++ b/data/custodian/JP-13-SHI-L-JACNNTL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-JACNNTL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-JACNNTL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-JACNNTL ghcid_numeric: 11890365984657398763 valid_from: '2025-12-06T23:38:58.917909+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Japan Arts Council National Noh Theatre Library @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:02:09.800985+00:00' + source_url: http://www.ntj.jac.go.jp/nou/lib.html#3 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ntj.jac.go.jp/assets/images/shared/apple-touch-icon.png + source_url: http://www.ntj.jac.go.jp/nou/lib.html#3 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:02:09.800985+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ntj.jac.go.jp/assets/images/shared/ogimage.png + source_url: http://www.ntj.jac.go.jp/nou/lib.html#3 + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:02:09.800985+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-JFOUYCL.yaml b/data/custodian/JP-13-SHI-L-JFOUYCL.yaml index 8b53056a44..711ef12840 100644 --- a/data/custodian/JP-13-SHI-L-JFOUYCL.yaml +++ b/data/custodian/JP-13-SHI-L-JFOUYCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-JFOUYCL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-JFOUYCL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-JFOUYCL ghcid_numeric: 7542575299194262143 valid_from: '2025-12-06T23:38:54.836717+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: J. F. Oberlin University Yotsuya Campus Library @@ -204,3 +205,20 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:02:31.980719+00:00' + source_url: http://www.obirin.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.obirin.ac.jp/common/img/base/ogp_image.png + source_url: http://www.obirin.ac.jp/library + css_selector: '#pagetop > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T20:02:31.980719+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-JJLS.yaml b/data/custodian/JP-13-SHI-L-JJLS.yaml index 486e09127c..396b6a18fe 100644 --- a/data/custodian/JP-13-SHI-L-JJLS.yaml +++ b/data/custodian/JP-13-SHI-L-JJLS.yaml @@ -205,3 +205,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:02:45.920171+00:00' + source_url: http://www.jissen.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.jissen.ac.jp/favicon.ico + source_url: http://www.jissen.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:02:45.920171+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-JPICL.yaml b/data/custodian/JP-13-SHI-L-JPICL.yaml index 11ae76e753..f67958a785 100644 --- a/data/custodian/JP-13-SHI-L-JPICL.yaml +++ b/data/custodian/JP-13-SHI-L-JPICL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-JPICL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-JPICL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-JPICL ghcid_numeric: 444209012839895188 valid_from: '2025-12-06T23:38:57.897057+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Japan Pharmaceutical Information Center Library @@ -151,3 +152,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:03:02.002632+00:00' + source_url: http://www.japic.or.jp/service/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.japic.or.jp/japic/Img/webopac.gif + source_url: http://www.japic.or.jp/service/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:03:02.002632+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-JRCCNL.yaml b/data/custodian/JP-13-SHI-L-JRCCNL.yaml index 3e5ca79ede..55fb7796cf 100644 --- a/data/custodian/JP-13-SHI-L-JRCCNL.yaml +++ b/data/custodian/JP-13-SHI-L-JRCCNL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-JRCCNL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-JRCCNL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-JRCCNL ghcid_numeric: 15710308027103382997 valid_from: '2025-12-06T23:38:55.396369+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: The Japanese Red Cross College of Nursing Library @@ -206,3 +207,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:03:09.277027+00:00' + source_url: https://www.redcross.ac.jp/research/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.redcross.ac.jp/wp/wp-content/themes/redcross/images/favicon/safari-pinned-tab.svg + source_url: https://www.redcross.ac.jp/research/library + css_selector: '[document] > html._device-pc._os-mac > body > link:nth-of-type(9)' + retrieved_on: '2025-12-25T20:03:09.277027+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.redcross.ac.jp/wp/wp-content/themes/redcross/images/common/ogp.jpg + source_url: https://www.redcross.ac.jp/research/library + css_selector: '[document] > html._device-pc._os-mac > body > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T20:03:09.277027+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 7 diff --git a/data/custodian/JP-13-SHI-L-JSCEL.yaml b/data/custodian/JP-13-SHI-L-JSCEL.yaml index 311ab98c49..7b70825e34 100644 --- a/data/custodian/JP-13-SHI-L-JSCEL.yaml +++ b/data/custodian/JP-13-SHI-L-JSCEL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-JSCEL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-JSCEL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-JSCEL ghcid_numeric: 9520054881437067399 valid_from: '2025-12-06T23:38:57.878635+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Japan Society of Civil Engineers Library @@ -151,3 +152,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:03:16.704308+00:00' + source_url: http://www.jsce.or.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.jsce.or.jp/images/liblogo.gif + source_url: http://www.jsce.or.jp/library + css_selector: '#wrapper > header > h1 > img' + retrieved_on: '2025-12-25T20:03:16.704308+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 土木学会附属土木図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-JSME.yaml b/data/custodian/JP-13-SHI-L-JSME.yaml index 3369f41fd4..254226b374 100644 --- a/data/custodian/JP-13-SHI-L-JSME.yaml +++ b/data/custodian/JP-13-SHI-L-JSME.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:03:32.227958+00:00' + source_url: http://www.jsme.or.jp/japanese/contents/08/07.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jsme.or.jp/jsme/uploads/2016/11/jsme-logo.png + source_url: http://www.jsme.or.jp/japanese/contents/08/07.html + css_selector: '[document] > html.no-js > head > link:nth-of-type(19)' + retrieved_on: '2025-12-25T20:03:32.227958+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://www.jsme.or.jp/jsme/wp-content/themes/jsme-template/img/jsme-logo.png + source_url: http://www.jsme.or.jp/japanese/contents/08/07.html + css_selector: '[document] > html.no-js > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T20:03:32.227958+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-JTRIL.yaml b/data/custodian/JP-13-SHI-L-JTRIL.yaml index 0d331a9a63..126673781b 100644 --- a/data/custodian/JP-13-SHI-L-JTRIL.yaml +++ b/data/custodian/JP-13-SHI-L-JTRIL.yaml @@ -228,3 +228,31 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:03:44.589425+00:00' + source_url: https://www.jtri.or.jp/library/about.php + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.jtri.or.jp/assets/images/global/header_logo01.png + source_url: https://www.jtri.or.jp/library/about.php + css_selector: '[document] > html > body > div.wrapper > header.gHeader > div.gHeader_inner + > div.gHeader_left > div.gHeader_logo > a > img' + retrieved_on: '2025-12-25T20:03:44.589425+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 公益財団法人日本税務研究センター + - claim_type: favicon_url + claim_value: https://www.jtri.or.jp/assets/favicon/favicon-SP.png + source_url: https://www.jtri.or.jp/library/about.php + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:03:44.589425+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-KL.yaml b/data/custodian/JP-13-SHI-L-KL.yaml index 69b5911b0b..25cad662cc 100644 --- a/data/custodian/JP-13-SHI-L-KL.yaml +++ b/data/custodian/JP-13-SHI-L-KL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-KL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-KL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-KL ghcid_numeric: 16724242296380404573 valid_from: '2025-12-06T23:38:54.883500+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: KOKUGAKUINDAIGAKU Library @@ -182,7 +183,8 @@ wikidata_enrichment: part_of: id: Q495330 label: Kokugakuin University - description: Private university, whose main campus is in Tokyo's Shibuya district., Japan + description: Private university, whose main campus is in Tokyo's Shibuya district., + Japan wikidata_web: official_website: https://www.kokugakuin.ac.jp/research/facility/library wikidata_official_website: https://www.kokugakuin.ac.jp/research/facility/library @@ -204,3 +206,38 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:04:08.082990+00:00' + source_url: https://www.kokugakuin.ac.jp/research/facility/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.kokugakuin.ac.jp/wp/wp-content/themes/kokugakuin-pc/img/logo-kokugakuin.svg + source_url: https://www.kokugakuin.ac.jp/research/facility/library + css_selector: '[document] > html.win10.chrome > body.lang-ja > div.l-wrapper:nth-of-type(2) + > header.l-header > div.header-content > div.header-inner > h1.header-logo > + a > span.header-logo-symbol > img' + retrieved_on: '2025-12-25T20:04:08.082990+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.kokugakuin.ac.jp/assets/img/touch-icon.png + source_url: https://www.kokugakuin.ac.jp/research/facility/library + css_selector: '[document] > html.win10.chrome > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T20:04:08.082990+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kokugakuin.ac.jp/assets/img/ogimg.png + source_url: https://www.kokugakuin.ac.jp/research/facility/library + css_selector: '[document] > html.win10.chrome > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T20:04:08.082990+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-KUSMCKMML.yaml b/data/custodian/JP-13-SHI-L-KUSMCKMML.yaml index 4884c78888..95bac46827 100644 --- a/data/custodian/JP-13-SHI-L-KUSMCKMML.yaml +++ b/data/custodian/JP-13-SHI-L-KUSMCKMML.yaml @@ -37,20 +37,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-KUSMCKMML - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-KUSMCKMML valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-KUSMCKMML ghcid_numeric: 3841359580709059291 valid_from: '2025-12-06T23:38:54.870312+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Keio University Shinanomachi Media Center ・ Kitasato Memorial Medical Library + claim_value: Keio University Shinanomachi Media Center ・ Kitasato Memorial Medical + Library source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -101,11 +103,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Keio University Shinanomachi Media Center ・ Kitasato Memorial Medical Library + claim_value: Keio University Shinanomachi Media Center ・ Kitasato Memorial Medical + Library property_uri: skos:prefLabel provenance: namespace: glam @@ -164,7 +167,8 @@ wikidata_enrichment: wikidata_labels: en: Keio University Shinanomachi Media Center ・ Kitasato Memorial Medical Library ja: 慶應義塾大学 信濃町メディアセンター・北里記念医学図書館 - wikidata_label_en: Keio University Shinanomachi Media Center ・ Kitasato Memorial Medical Library + wikidata_label_en: Keio University Shinanomachi Media Center ・ Kitasato Memorial + Medical Library wikidata_label_ja: 慶應義塾大学 信濃町メディアセンター・北里記念医学図書館 wikidata_classification: instance_of: &id004 @@ -204,3 +208,30 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:04:21.555226+00:00' + source_url: https://www.lib.keio.ac.jp/med/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.keio.ac.jp/assets/images/logo.png + source_url: https://www.lib.keio.ac.jp/med/index.html + css_selector: '#header > h1 > a > img' + retrieved_on: '2025-12-25T20:04:21.555226+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 慶応義塾大学 メディアセンター + - claim_type: favicon_url + claim_value: https://www.lib.keio.ac.jp/assets/images/favicon.ico + source_url: https://www.lib.keio.ac.jp/med/index.html + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:04:21.555226+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-LDCOCOSBLL.yaml b/data/custodian/JP-13-SHI-L-LDCOCOSBLL.yaml index 305b918114..357953f8b7 100644 --- a/data/custodian/JP-13-SHI-L-LDCOCOSBLL.yaml +++ b/data/custodian/JP-13-SHI-L-LDCOCOSBLL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-LDCOCOSBLL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-LDCOCOSBLL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-LDCOCOSBLL ghcid_numeric: 18295765553004357284 valid_from: '2025-12-06T23:38:58.980952+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: LIVING DESIGN CENTER OZONE CLUB OZONE SQUARE BUSINESS LOUNGE & LIBRARY @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:04:31.652158+00:00' + source_url: http://www.ozone.co.jp/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ozone.co.jp/images/common/apple-touch-icon.png + source_url: http://www.ozone.co.jp/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:04:31.652158+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.ozone.co.jp/images/common/ogp.png + source_url: http://www.ozone.co.jp/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T20:04:31.652158+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-LKCCKE.yaml b/data/custodian/JP-13-SHI-L-LKCCKE.yaml index 3315a35af1..e425c5f974 100644 --- a/data/custodian/JP-13-SHI-L-LKCCKE.yaml +++ b/data/custodian/JP-13-SHI-L-LKCCKE.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-LKCCKE - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-LKCCKE valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-LKCCKE ghcid_numeric: 11198899156336397467 valid_from: '2025-12-06T23:38:58.839148+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Library of Korean Cultural Center, Korean Embassy @@ -151,3 +152,32 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:04:46.531742+00:00' + source_url: http://koreaculture.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://koreaculture.jp/img/logo3.png + source_url: http://koreaculture.jp + css_selector: '#exp_alert > div.header-global-wrap > div.container.mt-0 > div.row + > div.header-global > div.header-theme > div.col > div.header-theme-title-wrap + > div.header-global-logo > a.header-theme-incheon > img' + retrieved_on: '2025-12-25T20:04:46.531742+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 駐日韓国文化院 ロゴ + - claim_type: favicon_url + claim_value: http://koreaculture.jp/img/favicon.ico + source_url: http://koreaculture.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:04:46.531742+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-LKSF.yaml b/data/custodian/JP-13-SHI-L-LKSF.yaml index 853ff011fa..15c3b37cb3 100644 --- a/data/custodian/JP-13-SHI-L-LKSF.yaml +++ b/data/custodian/JP-13-SHI-L-LKSF.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:04:56.185345+00:00' + source_url: http://www.korean-s-f.or.jp/05-04.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://d1lq8ke1ftufx1.cloudfront.net/4140f5f47018b87d2aa23f2e07e1f7e2/favicon/1/favicon_朝鮮奨学会10.png + source_url: http://www.korean-s-f.or.jp/05-04.htm + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:04:56.185345+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://d1lq8ke1ftufx1.cloudfront.net/4140f5f47018b87d2aa23f2e07e1f7e2/ogpimage/1/ogpimage.png + source_url: http://www.korean-s-f.or.jp/05-04.htm + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T20:04:56.185345+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-MCAMMMML.yaml b/data/custodian/JP-13-SHI-L-MCAMMMML.yaml index ba52c1fd65..2717ed3807 100644 --- a/data/custodian/JP-13-SHI-L-MCAMMMML.yaml +++ b/data/custodian/JP-13-SHI-L-MCAMMMML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-MCAMMMML - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-MCAMMMML valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-MCAMMMML ghcid_numeric: 16937512374504230162 valid_from: '2025-12-06T23:38:58.083211+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Min-On Concert Association Min-On Music Museum Music Library @@ -151,3 +152,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:05:22.224397+00:00' + source_url: http://museum.min-on.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://museum.min-on.or.jp/common/img/logo.gif + source_url: http://museum.min-on.or.jp + css_selector: '#logo > a.over > img.pc' + retrieved_on: '2025-12-25T20:05:22.224397+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 民音音楽博物館 MIN-ON MUSIC MUSEUM + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-MDLBN.yaml b/data/custodian/JP-13-SHI-L-MDLBN.yaml index bf6a180aed..5e199abc84 100644 --- a/data/custodian/JP-13-SHI-L-MDLBN.yaml +++ b/data/custodian/JP-13-SHI-L-MDLBN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-MDLBN - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-MDLBN valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-MDLBN ghcid_numeric: 2730034423663561018 valid_from: '2025-12-06T23:38:53.054961+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ministry of Defense Library, Branch of the NDL @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:05:29.906635+00:00' + source_url: https://www.mod.go.jp/j/profile/dal + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.mod.go.jp/j/assets/images/svg/logo.svg + source_url: https://www.mod.go.jp/j/profile/dal + css_selector: '[document] > html > body > header.pc-header.inner > div.header-content + > h1.logo > a > img' + retrieved_on: '2025-12-25T20:05:29.906635+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 防衛省・自衛隊 + - claim_type: favicon_url + claim_value: https://www.mod.go.jp/apple-touch-icon.png + source_url: https://www.mod.go.jp/j/profile/dal + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T20:05:29.906635+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 96x96 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-NIC.yaml b/data/custodian/JP-13-SHI-L-NIC.yaml index 3e55bc6ca8..83b01808ee 100644 --- a/data/custodian/JP-13-SHI-L-NIC.yaml +++ b/data/custodian/JP-13-SHI-L-NIC.yaml @@ -152,3 +152,38 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:06:35.336854+00:00' + source_url: http://www.ntticc.or.jp/About/index_j.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.ntticc.or.jp/assets/images/ICClogo.png + source_url: http://www.ntticc.or.jp/About/index_j.html + css_selector: '[document] > html.ua-windows_nt.ua-windows_nt-10 > body > header.header.header--global + > div.container.container--sp-hidden > div.header__brand > h1.header__brand__logo + > a.header__brand__logo__link.a-hover--alpha > img' + retrieved_on: '2025-12-25T20:06:35.336854+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: NTT ICC + - claim_type: favicon_url + claim_value: http://www.ntticc.or.jp/assets/icon.png + source_url: http://www.ntticc.or.jp/About/index_j.html + css_selector: '[document] > html.ua-windows_nt.ua-windows_nt-10 > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T20:06:35.336854+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ntticc.or.jp/assets/ogp.png + source_url: http://www.ntticc.or.jp/About/index_j.html + css_selector: '[document] > html.ua-windows_nt.ua-windows_nt-10 > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T20:06:35.336854+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-NL-nihommojinkairengotenji_library.yaml b/data/custodian/JP-13-SHI-L-NL-nihommojinkairengotenji_library.yaml index 59e44f398c..17ae0a0e99 100644 --- a/data/custodian/JP-13-SHI-L-NL-nihommojinkairengotenji_library.yaml +++ b/data/custodian/JP-13-SHI-L-NL-nihommojinkairengotenji_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-NL-nihommojinkairengotenji_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-NL-nihommojinkairengotenji_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-NL-nihommojinkairengotenji_library ghcid_numeric: 17357773876595444937 valid_from: '2025-12-06T23:38:59.533373+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NIHOMMOJINKAIRENGOTENJI Library @@ -151,3 +152,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:06:48.546961+00:00' + source_url: http://nichimou.org/morebooks/borrow + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://nichimou.org/wp-content/uploads/2017/02/cropped-logo-1-180x180.png + source_url: http://nichimou.org/morebooks/borrow + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T20:06:48.546961+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-NL.yaml b/data/custodian/JP-13-SHI-L-NL.yaml index 520b8a24e0..e8d0152474 100644 --- a/data/custodian/JP-13-SHI-L-NL.yaml +++ b/data/custodian/JP-13-SHI-L-NL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-NL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-NL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-NL ghcid_numeric: 5082532956432509917 valid_from: '2025-12-06T23:38:44.474256+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NYUZENCHORITSU Library @@ -153,3 +154,36 @@ location: geonames_id: 1854868 geonames_name: Nyūzen feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:06:57.876741+00:00' + source_url: https://www.town.nyuzen.toyama.jp/gyosei/tosho/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.nyuzen.toyama.jp/theme/base/img_common/sp_header_logo.png + source_url: https://www.town.nyuzen.toyama.jp/gyosei/tosho/index.html + css_selector: '#sp-header-logo > a > img' + retrieved_on: '2025-12-25T20:06:57.876741+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 入善町 NYUZEN MACHI + - claim_type: favicon_url + claim_value: https://www.town.nyuzen.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.nyuzen.toyama.jp/gyosei/tosho/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:06:57.876741+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.nyuzen.toyama.jp/material/images/group/0/sawasugi_winter.jpg + source_url: https://www.town.nyuzen.toyama.jp/gyosei/tosho/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T20:06:57.876741+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-NNTT.yaml b/data/custodian/JP-13-SHI-L-NNTT.yaml index 3da64ac379..46d3ffed0c 100644 --- a/data/custodian/JP-13-SHI-L-NNTT.yaml +++ b/data/custodian/JP-13-SHI-L-NNTT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-NNTT - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-NNTT valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-NNTT ghcid_numeric: 13717018555581456162 valid_from: '2025-12-06T23:38:58.799563+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NEW NATIONAL THEATRE, TOKYO @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:07:10.079473+00:00' + source_url: http://www.nntt.jac.go.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.nntt.jac.go.jp/apple-touch-icon-152x152.png + source_url: http://www.nntt.jac.go.jp/library + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:07:10.079473+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 152x152 + - claim_type: og_image_url + claim_value: https://www.nntt.jac.go.jp/common_files/images/ogp_logo01.gif + source_url: http://www.nntt.jac.go.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T20:07:10.079473+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 6 diff --git a/data/custodian/JP-13-SHI-L-PUIMIL.yaml b/data/custodian/JP-13-SHI-L-PUIMIL.yaml index 78039aed82..5736a347dd 100644 --- a/data/custodian/JP-13-SHI-L-PUIMIL.yaml +++ b/data/custodian/JP-13-SHI-L-PUIMIL.yaml @@ -209,3 +209,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:07:30.166106+00:00' + source_url: https://www.i-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://d28fv2wf8x8ap4.cloudfront.net/wp-content/uploads/2025/03/19192421/cropped-iu_favicon-180x180.png + source_url: https://www.i-u.ac.jp + css_selector: '[document] > html > body > link:nth-of-type(20)' + retrieved_on: '2025-12-25T20:07:30.166106+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.i-u.ac.jp/wp-content/themes/innovation_university/img/ogp.png + source_url: https://www.i-u.ac.jp + css_selector: '[document] > html > body > meta:nth-of-type(20)' + retrieved_on: '2025-12-25T20:07:30.166106+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-SL-seisenjoshidaigakufuzoku_library.yaml b/data/custodian/JP-13-SHI-L-SL-seisenjoshidaigakufuzoku_library.yaml index 7c4770161c..4c543696d5 100644 --- a/data/custodian/JP-13-SHI-L-SL-seisenjoshidaigakufuzoku_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-seisenjoshidaigakufuzoku_library.yaml @@ -220,3 +220,22 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:08:12.403091+00:00' + source_url: http://www.seisen-u.ac.jp/library/index.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.seisen-u.ac.jp/favicons.png + source_url: http://www.seisen-u.ac.jp/library/index.php + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:08:12.403091+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuchuo_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuchuo_library.yaml index 5c7272ce1a..5979153d89 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuchuo_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuchuo_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shibuyakuritsuchuo_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shibuyakuritsuchuo_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shibuyakuritsuchuo_library ghcid_numeric: 16440431237366545158 valid_from: '2025-12-06T23:38:43.347763+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUYAKURITSUCHUO Library @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:08:27.760254+00:00' + source_url: https://www.lib.city.shibuya.tokyo.jp/library/central + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/central + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:08:27.760254+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/central + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:08:27.760254+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuhommachi_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuhommachi_library.yaml index 71f1b53ea1..a6e22180ad 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuhommachi_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuhommachi_library.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shibuyakuritsuhommachi_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shibuyakuritsuhommachi_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shibuyakuritsuhommachi_library ghcid_numeric: 11562911049642748088 valid_from: '2025-12-06T23:38:43.357796+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUYAKURITSUHOMMACHI Library @@ -196,8 +197,9 @@ wikidata_enrichment: instance_of: &id004 - id: Q7075 label: library - description: institution charged with the care of a collection of literary, musical, artistic, or reference materials, - such as books, manuscripts, recordings, or films + description: institution charged with the care of a collection of literary, + musical, artistic, or reference materials, such as books, manuscripts, recordings, + or films wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -237,3 +239,28 @@ location: postal_code: 151-0071 street_address: 1-33-5 HOMMACHI, Shibuya Ku, Tokyo To, 151-0071 normalization_timestamp: '2025-12-09T12:22:18.229380+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:08:41.446440+00:00' + source_url: https://www.lib.city.shibuya.tokyo.jp/library/honmachi + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/honmachi + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:08:41.446440+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/honmachi + css_selector: '[document] > html.c-font-size--medium > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:08:41.446440+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsukomorebiowada_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsukomorebiowada_library.yaml index dfe1a2d6c2..e722a98917 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsukomorebiowada_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsukomorebiowada_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shibuyakuritsukomorebiowada_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shibuyakuritsukomorebiowada_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shibuyakuritsukomorebiowada_library ghcid_numeric: 16123062157196011198 valid_from: '2025-12-06T23:38:48.532314+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUYAKURITSUKOMOREBIOWADA Library @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:08:58.108637+00:00' + source_url: http://www.lib.city.shibuya.tokyo.jp/hp/intro_kan07/top/kan-oowada-top.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: http://www.lib.city.shibuya.tokyo.jp/hp/intro_kan07/top/kan-oowada-top.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:08:58.108637+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: http://www.lib.city.shibuya.tokyo.jp/hp/intro_kan07/top/kan-oowada-top.html + css_selector: '[document] > html.c-font-size--medium > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:08:58.108637+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsunishihara_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsunishihara_library.yaml index 71821b4a2e..69eac4e787 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsunishihara_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsunishihara_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shibuyakuritsunishihara_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shibuyakuritsunishihara_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shibuyakuritsunishihara_library ghcid_numeric: 17785388247656868893 valid_from: '2025-12-06T23:38:43.355242+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUYAKURITSUNISHIHARA Library @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:09:10.702259+00:00' + source_url: https://www.lib.city.shibuya.tokyo.jp/library/nishihara + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/nishihara + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:09:10.702259+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/nishihara + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:09:10.702259+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsurinsemminnano_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsurinsemminnano_library.yaml index 5dc0ca49e1..3ade73761a 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsurinsemminnano_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsurinsemminnano_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shibuyakuritsurinsemminnano_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shibuyakuritsurinsemminnano_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shibuyakuritsurinsemminnano_library ghcid_numeric: 12906667359869386042 valid_from: '2025-12-06T23:38:43.360485+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUYAKURITSURINSEMMINNANO Library @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:09:24.058936+00:00' + source_url: https://www.lib.city.shibuya.tokyo.jp/library/rinsen + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/rinsen + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:09:24.058936+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/rinsen + css_selector: '[document] > html.c-font-size--medium > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:09:24.058936+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazuka_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazuka_library.yaml index 360e29f361..074bad3779 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazuka_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazuka_library.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shibuyakuritsusasazuka_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shibuyakuritsusasazuka_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shibuyakuritsusasazuka_library ghcid_numeric: 8265421307880987084 valid_from: '2025-12-06T23:38:43.350036+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUYAKURITSUSASAZUKA Library @@ -206,8 +207,9 @@ wikidata_enrichment: instance_of: &id005 - id: Q7075 label: library - description: institution charged with the care of a collection of literary, musical, artistic, or reference materials, - such as books, manuscripts, recordings, or films + description: institution charged with the care of a collection of literary, + musical, artistic, or reference materials, such as books, manuscripts, recordings, + or films wikidata_instance_of: *id005 wikidata_location: country: &id006 @@ -247,3 +249,28 @@ location: postal_code: 151-0073 street_address: 1-47-1 SASAZUKA, Shibuya Ku, Tokyo To, 151-0073 normalization_timestamp: '2025-12-09T12:22:18.393035+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:09:37.365858+00:00' + source_url: https://www.lib.city.shibuya.tokyo.jp/library/sasaduka + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/sasaduka + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:09:37.365858+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/sasaduka + css_selector: '[document] > html.c-font-size--medium > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:09:37.365858+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazukakodomo_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazukakodomo_library.yaml index d4b472cf3b..47d713e430 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazukakodomo_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsusasazukakodomo_library.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:09:50.192853+00:00' + source_url: http://www.lib.city.shibuya.tokyo.jp/hp/intro_kan10/top/kan-sasako-top.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: http://www.lib.city.shibuya.tokyo.jp/hp/intro_kan10/top/kan-sasako-top.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:09:50.192853+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: http://www.lib.city.shibuya.tokyo.jp/hp/intro_kan10/top/kan-sasako-top.html + css_selector: '[document] > html.c-font-size--medium > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:09:50.192853+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuyoyogi_library.yaml b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuyoyogi_library.yaml index 004615e2a9..d250483f20 100644 --- a/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuyoyogi_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shibuyakuritsuyoyogi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shibuyakuritsuyoyogi_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shibuyakuritsuyoyogi_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shibuyakuritsuyoyogi_library ghcid_numeric: 7403354112903127291 valid_from: '2025-12-06T23:38:43.362817+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHIBUYAKURITSUYOYOGI Library @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:12:50.257572+00:00' + source_url: https://www.lib.city.shibuya.tokyo.jp/library/yoyogi + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/apple-icon-152x152.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/yoyogi + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T20:12:50.257572+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.city.shibuya.tokyo.jp/common/images/ogimage.png + source_url: https://www.lib.city.shibuya.tokyo.jp/library/yoyogi + css_selector: '[document] > html.c-font-size--medium > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:12:50.257572+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuebara_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuebara_library.yaml index 8757e4bbf7..79a2babd14 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuebara_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuebara_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsuebara_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuebara_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuebara_library ghcid_numeric: 9731767278111432749 valid_from: '2025-12-06T23:38:43.234443+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUEBARA Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:13:10.876217+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/148/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/148/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:13:10.876217+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/148/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:13:10.876217+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsufutaba_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsufutaba_library.yaml index ca7e7b7ffa..f52234b59e 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsufutaba_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsufutaba_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsufutaba_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsufutaba_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsufutaba_library ghcid_numeric: 11150668552583277524 valid_from: '2025-12-06T23:38:43.241388+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUFUTABA Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:13:17.766347+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/147/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/147/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:13:17.766347+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/147/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:13:17.766347+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugenjimae_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugenjimae_library.yaml index dcdcc4c632..b07fd94211 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugenjimae_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugenjimae_library.yaml @@ -152,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:17:37.461918+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/150/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/150/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:17:37.461918+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/150/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:17:37.461918+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugotanda_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugotanda_library.yaml index 047d891980..53525d0bba 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugotanda_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsugotanda_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsugotanda_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsugotanda_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsugotanda_library ghcid_numeric: 8884731610305891341 valid_from: '2025-12-06T23:38:43.248309+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUGOTANDA Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:17:47.129851+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/153/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/153/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:17:47.129851+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/153/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:17:47.129851+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuminamioi_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuminamioi_library.yaml index 5dac475500..ec5ca97035 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuminamioi_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuminamioi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsuminamioi_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuminamioi_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuminamioi_library ghcid_numeric: 13608119357687349101 valid_from: '2025-12-06T23:38:43.243725+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUMINAMIOI Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:17:54.055640+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/149/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/149/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:17:54.055640+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/149/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:17:54.055640+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuoi_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuoi_library.yaml index 9926c16fdc..e3801833f8 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuoi_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuoi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsuoi_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuoi_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuoi_library ghcid_numeric: 6492883629932343853 valid_from: '2025-12-06T23:38:43.236741+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUOI Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:18:02.097446+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/152/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/152/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:18:02.097446+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/152/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:18:02.097446+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuosaki_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuosaki_library.yaml index 773c184615..3b6561e4d6 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuosaki_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuosaki_library.yaml @@ -152,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:18:09.520292+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/154/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/154/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:18:09.520292+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/154/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:18:09.520292+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsushinagawa_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsushinagawa_library.yaml index c69f91100d..f50d621eb5 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsushinagawa_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsushinagawa_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsushinagawa_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsushinagawa_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsushinagawa_library ghcid_numeric: 15197828810019728155 valid_from: '2025-12-06T23:38:43.232009+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUSHINAGAWA Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:18:15.936741+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/146/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/146/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:18:15.936741+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/146/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:18:15.936741+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyashio_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyashio_library.yaml index 6eed4e048c..f5e59a8265 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyashio_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyashio_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsuyashio_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuyashio_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuyashio_library ghcid_numeric: 13818981413628739929 valid_from: '2025-12-06T23:38:43.253068+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUYASHIO Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:22:37.411723+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/155/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/155/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:22:37.411723+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/155/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:22:37.411723+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyutaka_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyutaka_library.yaml index 7203b33f5e..34252dd2ca 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyutaka_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinagawakuritsuyutaka_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinagawakuritsuyutaka_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuyutaka_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinagawakuritsuyutaka_library ghcid_numeric: 623680535122764625 valid_from: '2025-12-06T23:38:43.246028+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINAGAWAKURITSUYUTAKA Library @@ -151,3 +152,30 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:22:49.445564+00:00' + source_url: https://library.city.shinagawa.tokyo.jp/tabid/151/Default.aspx + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/Skins/SKL/images/title_logo2.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/151/Default.aspx + css_selector: '#dnn_dnnLOGO_imgLogo' + retrieved_on: '2025-12-25T20:22:49.445564+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立図書館 + - claim_type: favicon_url + claim_value: https://library.city.shinagawa.tokyo.jp/Portals/0/apple-touch-icon.png + source_url: https://library.city.shinagawa.tokyo.jp/tabid/151/Default.aspx + css_selector: '#Head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:22:49.445564+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuchuo_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuchuo_library.yaml index 218ce7cf35..54b4e2c2cc 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuchuo_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuchuo_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsuchuo_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsuchuo_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsuchuo_library ghcid_numeric: 4093451784235006471 valid_from: '2025-12-06T23:38:43.141794+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUCHUO Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:22:57.546722+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:22:57.546722+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:22:57.546722+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukitashinjuku_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukitashinjuku_library.yaml index 54e7a06090..e4cb83d676 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukitashinjuku_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukitashinjuku_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsukitashinjuku_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsukitashinjuku_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsukitashinjuku_library ghcid_numeric: 13836094622384941353 valid_from: '2025-12-06T23:38:43.155497+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUKITASHINJUKU Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:23:06.261036+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:23:06.261036+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:23:06.261036+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukodomo_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukodomo_library.yaml index bad608b8b8..190b249614 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukodomo_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsukodomo_library.yaml @@ -152,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:23:13.944377+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:23:13.944377+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:23:13.944377+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunakamachi_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunakamachi_library.yaml index c145bf407f..6fa24964f8 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunakamachi_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunakamachi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsunakamachi_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsunakamachi_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsunakamachi_library ghcid_numeric: 12724833914518660537 valid_from: '2025-12-06T23:38:43.157847+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUNAKAMACHI Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:23:21.534722+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:23:21.534722+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:23:21.534722+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunishiochiai_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunishiochiai_library.yaml index 78f3f5d3bb..bcdae0095e 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunishiochiai_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsunishiochiai_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsunishiochiai_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsunishiochiai_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsunishiochiai_library ghcid_numeric: 16480162703699215478 valid_from: '2025-12-06T23:38:43.153230+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUNISHIOCHIAI Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:35:31.960370+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:35:31.960370+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:35:31.960370+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuokubo_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuokubo_library.yaml index 206f62c9bb..d0bbd970bc 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuokubo_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuokubo_library.yaml @@ -152,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:35:39.625215+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:35:39.625215+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:35:39.625215+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutoyama_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutoyama_library.yaml index 3fec52890d..718b08318e 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutoyama_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutoyama_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsutoyama_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsutoyama_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsutoyama_library ghcid_numeric: 14402702814009396393 valid_from: '2025-12-06T23:38:43.150976+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUTOYAMA Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:35:47.352129+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:35:47.352129+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:35:47.352129+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsunohazu_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsunohazu_library.yaml index 08271cbab7..1b09c6b8d9 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsunohazu_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsunohazu_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsutsunohazu_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsutsunohazu_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsutsunohazu_library ghcid_numeric: 13346229056295438295 valid_from: '2025-12-06T23:38:43.160119+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUTSUNOHAZU Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:35:55.739880+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:35:55.739880+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:35:55.739880+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsurumaki_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsurumaki_library.yaml index cce5182460..0883159c8f 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsurumaki_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsutsurumaki_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsutsurumaki_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsutsurumaki_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsutsurumaki_library ghcid_numeric: 13525032014389989918 valid_from: '2025-12-06T23:38:43.148665+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUTSURUMAKI Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:36:03.320794+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:36:03.320794+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:36:03.320794+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuyotsuya_library.yaml b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuyotsuya_library.yaml index 82a1161cce..6ba3eeaea6 100644 --- a/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuyotsuya_library.yaml +++ b/data/custodian/JP-13-SHI-L-SL-shinjukukuritsuyotsuya_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SL-shinjukukuritsuyotsuya_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SL-shinjukukuritsuyotsuya_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SL-shinjukukuritsuyotsuya_library ghcid_numeric: 13778722674861452342 valid_from: '2025-12-06T23:38:43.146416+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKUKURITSUYOTSUYA Library @@ -151,3 +152,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:36:11.240020+00:00' + source_url: https://www.library.shinjuku.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.shinjuku.tokyo.jp/img/logo.png + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '#header > div.header_outer:nth-of-type(2) > div.header-body:nth-of-type(2) + > div.wrap > div.title > a > img.title__logo.title__logo--def' + retrieved_on: '2025-12-25T20:36:11.240020+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 新宿区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.shinjuku.tokyo.jp/favicon.ico + source_url: https://www.library.shinjuku.tokyo.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T20:36:11.240020+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-SLMIACBN.yaml b/data/custodian/JP-13-SHI-L-SLMIACBN.yaml index d70030bb3f..1b55888b34 100644 --- a/data/custodian/JP-13-SHI-L-SLMIACBN.yaml +++ b/data/custodian/JP-13-SHI-L-SLMIACBN.yaml @@ -1,5 +1,6 @@ original_entry: - name: Statistical Library of Ministry of Internal Affairs and Communications, Branch of the NDL + name: Statistical Library of Ministry of Internal Affairs and Communications, Branch + of the NDL institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -32,20 +33,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SLMIACBN - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SLMIACBN valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SLMIACBN ghcid_numeric: 641214978273751125 valid_from: '2025-12-06T23:38:53.024299+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Statistical Library of Ministry of Internal Affairs and Communications, Branch of the NDL + claim_value: Statistical Library of Ministry of Internal Affairs and Communications, + Branch of the NDL source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +99,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Statistical Library of Ministry of Internal Affairs and Communications, Branch of the NDL + claim_value: Statistical Library of Ministry of Internal Affairs and Communications, + Branch of the NDL property_uri: skos:prefLabel provenance: namespace: glam @@ -151,3 +155,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:37:50.928282+00:00' + source_url: https://www.stat.go.jp/library/index.htm + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.stat.go.jp/shared2/images/kyoutuu/logo_jp_side.png + source_url: https://www.stat.go.jp/library/index.htm + css_selector: '#header > div.header_logo > h1 > a > img' + retrieved_on: '2025-12-25T20:37:50.928282+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 総務省統計局 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-SMUL.yaml b/data/custodian/JP-13-SHI-L-SMUL.yaml index 5833504759..6c74df1ecc 100644 --- a/data/custodian/JP-13-SHI-L-SMUL.yaml +++ b/data/custodian/JP-13-SHI-L-SMUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-SMUL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-SMUL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-SMUL ghcid_numeric: 15123667337661058592 valid_from: '2025-12-06T23:38:54.983288+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: Showa Medical University Library @@ -204,3 +205,28 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:38:14.317349+00:00' + source_url: https://www.showa-u.ac.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.showa-u.ac.jp/apple-touch-icon.png + source_url: https://www.showa-u.ac.jp/lib + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T20:38:14.317349+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.showa-u.ac.jp/lib/ogp.png + source_url: https://www.showa-u.ac.jp/lib + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T20:38:14.317349+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-T.yaml b/data/custodian/JP-13-SHI-L-T.yaml index cf0e7d15fa..248f2afbed 100644 --- a/data/custodian/JP-13-SHI-L-T.yaml +++ b/data/custodian/JP-13-SHI-L-T.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-T - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-T valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-T ghcid_numeric: 15677519384413346759 valid_from: '2025-12-06T23:38:58.877386+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOKYOTOSHOHISEIKATSUSOGOSENTATOSHOSHIRYOSHITSU @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:38:27.473560+00:00' + source_url: https://www.shouhiseikatu.metro.tokyo.jp/manabitai/tosho + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.shouhiseikatu.metro.tokyo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.shouhiseikatu.metro.tokyo.jp/manabitai/tosho + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T20:38:27.473560+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.shouhiseikatu.metro.tokyo.lg.jp/shared/system/images/sns_logo.jpg + source_url: https://www.shouhiseikatu.metro.tokyo.jp/manabitai/tosho + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T20:38:27.473560+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-TL-tokyofujidaigaku_library.yaml b/data/custodian/JP-13-SHI-L-TL-tokyofujidaigaku_library.yaml index 30e2e28763..b12e83444f 100644 --- a/data/custodian/JP-13-SHI-L-TL-tokyofujidaigaku_library.yaml +++ b/data/custodian/JP-13-SHI-L-TL-tokyofujidaigaku_library.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-TL-tokyofujidaigaku_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-TL-tokyofujidaigaku_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-TL-tokyofujidaigaku_library ghcid_numeric: 12526019047227652240 valid_from: '2025-12-06T23:38:55.426628+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: TOKYOFUJIDAIGAKU Library @@ -215,3 +216,31 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:38:48.602089+00:00' + source_url: http://www.fuji.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.fuji.ac.jp/assets/images/common/logo.svg + source_url: http://www.fuji.ac.jp/library + css_selector: '[document] > html.is-chrome > body > div.l-page > header.l-header.js-header + > div.l-header__inner > div.l-header__wrap01 > h1 > a > img' + retrieved_on: '2025-12-25T20:38:48.602089+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.fuji.ac.jp/msup/wp-content/uploads/2025/12/fuji.png + source_url: http://www.fuji.ac.jp/library + css_selector: '[document] > html.is-chrome > head > link:nth-of-type(11)' + retrieved_on: '2025-12-25T20:38:48.602089+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library.yaml b/data/custodian/JP-13-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library.yaml index 2ca890812c..32f028e4de 100644 --- a/data/custodian/JP-13-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library.yaml +++ b/data/custodian/JP-13-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-TL-tokyoiryohokendaigakufuzokugotanda_library ghcid_numeric: 16934569386173860887 valid_from: '2025-12-06T23:38:55.442372+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: TOKYOIRYOHOKENDAIGAKUFUZOKUGOTANDA Library @@ -204,3 +205,20 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:39:09.930369+00:00' + source_url: http://www.thcu.ac.jp/facilities/library + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://thcu.ac.jp/img/asset/ogp.png + source_url: http://www.thcu.ac.jp/facilities/library + css_selector: '[document] > html.other > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T20:39:09.930369+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-TL.yaml b/data/custodian/JP-13-SHI-L-TL.yaml index 52cae6a4e1..f04601da44 100644 --- a/data/custodian/JP-13-SHI-L-TL.yaml +++ b/data/custodian/JP-13-SHI-L-TL.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-TL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-TL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-TL ghcid_numeric: 11354693265614078277 valid_from: '2025-12-06T23:38:42.254505+00:00' @@ -152,3 +153,36 @@ geocoding: resolved_place: Hoshakuji resolved_city: 'Shioya Gun ' timestamp: '2025-12-09T23:13:34.545009+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:52:59.549599+00:00' + source_url: https://www.library.takanezawa.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.takanezawa.tochigi.jp/assets/images/common/logo.svg?v=f368bfdef095b83dacd9490b33aadb85 + source_url: https://www.library.takanezawa.tochigi.jp + css_selector: '#header > div.header_top > h1.header_logo > a > img' + retrieved_on: '2025-12-25T20:52:59.549599+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + - claim_type: favicon_url + claim_value: https://www.library.takanezawa.tochigi.jp/favicon.ico + source_url: https://www.library.takanezawa.tochigi.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:52:59.549599+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.library.takanezawa.tochigi.jp/og.png + source_url: https://www.library.takanezawa.tochigi.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:52:59.549599+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-TLK-tokyojoshiikadaigaku_library_kawadachobunshitsu.yaml b/data/custodian/JP-13-SHI-L-TLK-tokyojoshiikadaigaku_library_kawadachobunshitsu.yaml index cf58cc481e..37d2232ff7 100644 --- a/data/custodian/JP-13-SHI-L-TLK-tokyojoshiikadaigaku_library_kawadachobunshitsu.yaml +++ b/data/custodian/JP-13-SHI-L-TLK-tokyojoshiikadaigaku_library_kawadachobunshitsu.yaml @@ -205,3 +205,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:53:20.532299+00:00' + source_url: http://www.twmu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.twmu.ac.jp/images/favicon.ico + source_url: http://www.twmu.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:53:20.532299+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-TLK.yaml b/data/custodian/JP-13-SHI-L-TLK.yaml index 0e0227ae56..d473cf2fe7 100644 --- a/data/custodian/JP-13-SHI-L-TLK.yaml +++ b/data/custodian/JP-13-SHI-L-TLK.yaml @@ -35,13 +35,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-TLK - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-TLK valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-TLK ghcid_numeric: 14933871631456830934 valid_from: '2025-12-06T23:38:42.259095+00:00' @@ -153,3 +154,36 @@ geocoding: resolved_place: Kamitakanezawa resolved_city: 'Shioya Gun ' timestamp: '2025-12-09T23:13:34.561373+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:53:29.258924+00:00' + source_url: https://www.library.takanezawa.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.takanezawa.tochigi.jp/assets/images/common/logo.svg?v=f368bfdef095b83dacd9490b33aadb85 + source_url: https://www.library.takanezawa.tochigi.jp + css_selector: '#header > div.header_top > h1.header_logo > a > img' + retrieved_on: '2025-12-25T20:53:29.258924+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: logo + - claim_type: favicon_url + claim_value: https://www.library.takanezawa.tochigi.jp/favicon.ico + source_url: https://www.library.takanezawa.tochigi.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T20:53:29.258924+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.library.takanezawa.tochigi.jp/og.png + source_url: https://www.library.takanezawa.tochigi.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:53:29.258924+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-TWSMUHHA.yaml b/data/custodian/JP-13-SHI-L-TWSMUHHA.yaml index d22a062a7b..05f8c13903 100644 --- a/data/custodian/JP-13-SHI-L-TWSMUHHA.yaml +++ b/data/custodian/JP-13-SHI-L-TWSMUHHA.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-TWSMUHHA - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-TWSMUHHA valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-TWSMUHHA ghcid_numeric: 7828166892621412157 valid_from: '2025-12-06T23:38:58.860476+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Women's Medical University Hospital Health Archives @@ -204,3 +205,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T21:09:07.741408+00:00' + source_url: http://www.twmu.ac.jp/info-twmu/karada-jyohoukan.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.twmu.ac.jp/info-twmu/data/favicons/site/apple-icon-180x180.png?v=121225011200 + source_url: http://www.twmu.ac.jp/info-twmu/karada-jyohoukan.html + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T21:09:07.741408+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.twmu.ac.jp/info-twmu/data/confs/1/71e2d3299dc414dc50dd32fb13ef0698-1741937892.png + source_url: http://www.twmu.ac.jp/info-twmu/karada-jyohoukan.html + css_selector: '[document] > html > head > meta:nth-of-type(23)' + retrieved_on: '2025-12-25T21:09:07.741408+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 28 diff --git a/data/custodian/JP-13-SHI-L-TWSMUL.yaml b/data/custodian/JP-13-SHI-L-TWSMUL.yaml index 23a8d61332..a2f5d31b32 100644 --- a/data/custodian/JP-13-SHI-L-TWSMUL.yaml +++ b/data/custodian/JP-13-SHI-L-TWSMUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-TWSMUL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-TWSMUL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-TWSMUL ghcid_numeric: 190510891469836913 valid_from: '2025-12-06T23:38:55.098948+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Women's Medical 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.twmu.ac.jp/library/ wikidata_official_website: http://www.twmu.ac.jp/library/ @@ -212,3 +214,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T21:09:15.394430+00:00' + source_url: http://www.twmu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.twmu.ac.jp/images/favicon.ico + source_url: http://www.twmu.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T21:09:15.394430+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-USHL.yaml b/data/custodian/JP-13-SHI-L-USHL.yaml index 79ccb5a2fd..f2015cb5e3 100644 --- a/data/custodian/JP-13-SHI-L-USHL.yaml +++ b/data/custodian/JP-13-SHI-L-USHL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-USHL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-USHL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-USHL ghcid_numeric: 6071458696063380244 valid_from: '2025-12-06T23:38:54.911951+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 the Sacred Heart 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.u-sacred-heart.ac.jp/library/index.html wikidata_official_website: http://www.u-sacred-heart.ac.jp/library/index.html @@ -212,3 +214,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T21:09:50.928633+00:00' + source_url: http://www.u-sacred-heart.ac.jp/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.u-sacred-heart.ac.jp/library/favicon.ico + source_url: http://www.u-sacred-heart.ac.jp/library/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T21:09:50.928633+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush.yaml b/data/custodian/JP-13-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush.yaml index c179920044..c6074e26b4 100644 --- a/data/custodian/JP-13-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush.yaml +++ b/data/custodian/JP-13-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-W-wasedadaigakunihongokyoikukenkyusentagakuseidokush ghcid_numeric: 13361711264574864142 valid_from: '2025-12-06T23:38:55.385688+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: WASEDADAIGAKUNIHONGOKYOIKUKENKYUSENTAGAKUSEIDOKUSHOSHITSU @@ -210,3 +211,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T21:10:24.256195+00:00' + source_url: https://www.waseda.jp/inst/cjl/about/support + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.waseda.jp/inst/cjl/assets/themes/waseda-template-engine-alt/img/icons/favicon_32.png + source_url: https://www.waseda.jp/inst/cjl/about/support + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T21:10:24.256195+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.waseda.jp/inst/cjl/assets/themes/waseda-template-engine-alt/img/og_image.png + source_url: https://www.waseda.jp/inst/cjl/about/support + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T21:10:24.256195+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-L-WIHL.yaml b/data/custodian/JP-13-SHI-L-WIHL.yaml index ce4d288546..deeafa8c1c 100644 --- a/data/custodian/JP-13-SHI-L-WIHL.yaml +++ b/data/custodian/JP-13-SHI-L-WIHL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-WIHL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-WIHL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-WIHL ghcid_numeric: 15212324872547790820 valid_from: '2025-12-06T23:38:59.934286+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Waseda International House of Literature @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:20:26.568469+00:00' + source_url: https://www.waseda.jp/culture/wihl + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.waseda.jp/culture/wihl/assets/themes/waseda-template-engine-alt/img/icons/favicon_32.png + source_url: https://www.waseda.jp/culture/wihl + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:20:26.568469+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.waseda.jp/culture/wihl/assets/themes/waseda-template-engine-alt/img/og_image.png + source_url: https://www.waseda.jp/culture/wihl + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:20:26.568469+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-L-WIPE.yaml b/data/custodian/JP-13-SHI-L-WIPE.yaml index 9fedecaca0..1927fe9837 100644 --- a/data/custodian/JP-13-SHI-L-WIPE.yaml +++ b/data/custodian/JP-13-SHI-L-WIPE.yaml @@ -205,3 +205,38 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:20:34.941423+00:00' + source_url: http://www.waseda.jp/fpse/winpec + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.waseda.jp/fpse/winpec/assets/uploads/2016/09/logo_winpec_unit.png + source_url: http://www.waseda.jp/fpse/winpec + css_selector: '[document] > html > body.is-home.not-ja > nav.l-spot-navigation + > div.o-container.l-spot-navigation__container:nth-of-type(2) > div.l-spot-navigation__header + > div.c-spot-title.l-spot-navigation__title > a.c-spot-title__logo > img.attachment-original.size-original' + retrieved_on: '2025-12-25T23:20:34.941423+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Waseda Institute of Political Economy + - claim_type: favicon_url + claim_value: https://www.waseda.jp/fpse/winpec/assets/themes/waseda-template-engine-alt-gen2/img/icons/favicon_32.png + source_url: http://www.waseda.jp/fpse/winpec + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:20:34.941423+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.waseda.jp/fpse/winpec/assets/themes/waseda-template-engine-alt-gen2/img/og_image.png + source_url: http://www.waseda.jp/fpse/winpec + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T23:20:34.941423+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-L-WUL.yaml b/data/custodian/JP-13-SHI-L-WUL.yaml index 4312589d86..061332a859 100644 --- a/data/custodian/JP-13-SHI-L-WUL.yaml +++ b/data/custodian/JP-13-SHI-L-WUL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-WUL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-WUL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-WUL ghcid_numeric: 6113101262943342763 valid_from: '2025-12-06T23:38:55.328727+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Waseda University Library @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:21:03.055800+00:00' + source_url: https://www.waseda.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.waseda.jp/library/assets/themes/waseda-template-engine-alt/img/icons/favicon_32.png + source_url: https://www.waseda.jp/library + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:21:03.055800+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.waseda.jp/library/assets/themes/waseda-template-engine-alt/img/og_image.png + source_url: https://www.waseda.jp/library + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:21:03.055800+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-M-AM.yaml b/data/custodian/JP-13-SHI-M-AM.yaml index d044cf069a..2f6d375519 100644 --- a/data/custodian/JP-13-SHI-M-AM.yaml +++ b/data/custodian/JP-13-SHI-M-AM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-AM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-AM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-AM ghcid_numeric: 2083682771591372140 valid_from: '2025-12-06T23:38:33.295983+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: O ART MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:21:24.908321+00:00' + source_url: https://www.shinagawa-culture.or.jp/o-art + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.shinagawa-culture.or.jp/common/img/favicon.ico + source_url: https://www.shinagawa-culture.or.jp/o-art + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:21:24.908321+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-AMWU.yaml b/data/custodian/JP-13-SHI-M-AMWU.yaml index 228052a28d..0b390bf9d7 100644 --- a/data/custodian/JP-13-SHI-M-AMWU.yaml +++ b/data/custodian/JP-13-SHI-M-AMWU.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-AMWU - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-AMWU valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-AMWU ghcid_numeric: 11497090365595640436 valid_from: '2025-12-06T23:38:33.130876+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: AIZU MUSEUM, WASEDA UNIVERSITY @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:21:35.788058+00:00' + source_url: https://www.waseda.jp/culture/aizu-museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.waseda.jp/culture/aizu-museum/assets/themes/waseda-template-engine-alt/img/icons/favicon_32.png + source_url: https://www.waseda.jp/culture/aizu-museum + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T23:21:35.788058+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.waseda.jp/culture/aizu-museum/assets/themes/waseda-template-engine-alt/img/og_image.png + source_url: https://www.waseda.jp/culture/aizu-museum + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:21:35.788058+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-M-ATCAO.yaml b/data/custodian/JP-13-SHI-M-ATCAO.yaml index 5793d1b91a..06e5f84862 100644 --- a/data/custodian/JP-13-SHI-M-ATCAO.yaml +++ b/data/custodian/JP-13-SHI-M-ATCAO.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-ATCAO - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-ATCAO valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-ATCAO ghcid_numeric: 15183089343750129698 valid_from: '2025-12-06T23:38:34.792013+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ASAHI TOWN CENTER FOR ARCHAEOLOGICAL OPERATIONS @@ -153,3 +154,36 @@ location: geonames_id: 2113077 geonames_name: Asahi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:21:43.548355+00:00' + source_url: https://www.town.asahi.toyama.jp/soshiki/maibunkan/1536212832856.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.asahi.toyama.jp/theme/base/img_common/header_logo.png + source_url: https://www.town.asahi.toyama.jp/soshiki/maibunkan/1536212832856.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-25T23:21:43.548355+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 富山県朝日町 + - claim_type: favicon_url + claim_value: https://www.town.asahi.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.asahi.toyama.jp/soshiki/maibunkan/1536212832856.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:21:43.548355+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.asahi.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.town.asahi.toyama.jp/soshiki/maibunkan/1536212832856.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T23:21:43.548355+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-BGCM.yaml b/data/custodian/JP-13-SHI-M-BGCM.yaml index edc5ba0b91..ad70fcd4bc 100644 --- a/data/custodian/JP-13-SHI-M-BGCM.yaml +++ b/data/custodian/JP-13-SHI-M-BGCM.yaml @@ -152,3 +152,38 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:21:54.478436+00:00' + source_url: http://museum.bunka.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://museum.bunka.ac.jp/wp/wp-content/themes/museum.bunka_2025/images/common/logo-jp.svg + source_url: http://museum.bunka.ac.jp + css_selector: '#head-top > h1 > a > img' + retrieved_on: '2025-12-25T23:21:54.478436+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 文化学園服飾博物館 + - claim_type: favicon_url + claim_value: http://museum.bunka.ac.jp/wp/wp-content/uploads/2022/01/favicon.ico + source_url: http://museum.bunka.ac.jp + css_selector: '[document] > html.wf-marcellus-n4-active.wf-notosanssc-n4-active + > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T23:21:54.478436+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://museum.bunka.ac.jp/wp/wp-content/themes/museum.bunka_2025/images/ogp.jpg + source_url: http://museum.bunka.ac.jp + css_selector: '[document] > html.wf-marcellus-n4-active.wf-notosanssc-n4-active + > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T23:21:54.478436+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-BM.yaml b/data/custodian/JP-13-SHI-M-BM.yaml index 1f79d57398..cbf108899f 100644 --- a/data/custodian/JP-13-SHI-M-BM.yaml +++ b/data/custodian/JP-13-SHI-M-BM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-BM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-BM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-BM ghcid_numeric: 5437912945417455583 valid_from: '2025-12-06T23:38:31.931417+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: BANDAI MUSEUM @@ -153,3 +154,22 @@ location: geonames_id: 1857379 geonames_name: Mibu feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:22:01.433875+00:00' + source_url: https://www.bandai-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bandai-museum.jp/images/favicon.ico + source_url: https://www.bandai-museum.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:22:01.433875+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-BMA.yaml b/data/custodian/JP-13-SHI-M-BMA.yaml index 1baea3c082..9758c16ea0 100644 --- a/data/custodian/JP-13-SHI-M-BMA.yaml +++ b/data/custodian/JP-13-SHI-M-BMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-BMA - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-BMA valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-BMA ghcid_numeric: 8555353921229259664 valid_from: '2025-12-06T23:38:33.426162+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Bunkamura Museum of Art @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:22:14.916540+00:00' + source_url: https://www.bunkamura.co.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.bunkamura.co.jp/common/images/favicon.ico + source_url: https://www.bunkamura.co.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T23:22:14.916540+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.bunkamura.co.jp/common/images/cardimage.png + source_url: https://www.bunkamura.co.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T23:22:14.916540+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-CM.yaml b/data/custodian/JP-13-SHI-M-CM.yaml index 36d0c9dcb7..a847804974 100644 --- a/data/custodian/JP-13-SHI-M-CM.yaml +++ b/data/custodian/JP-13-SHI-M-CM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-CM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-CM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-CM ghcid_numeric: 1303307277342219249 valid_from: '2025-12-06T23:38:33.388952+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: COLOR MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:22:22.643143+00:00' + source_url: https://color-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://color-museum.jp/wp-content/uploads/2025/02/cropped-MUSEUM-180x180.jpg + source_url: https://color-museum.jp + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-25T23:22:22.643143+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-M-CPS.yaml b/data/custodian/JP-13-SHI-M-CPS.yaml index 319d98ad4a..36519b3b01 100644 --- a/data/custodian/JP-13-SHI-M-CPS.yaml +++ b/data/custodian/JP-13-SHI-M-CPS.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:22:34.495988+00:00' + source_url: https://www.shibu-cul.jp/planetarium + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://shibu-cul.jp/cms/wp-content/themes/owada/images/apple-touch-icon.png + source_url: https://www.shibu-cul.jp/planetarium + css_selector: '[document] > html.fontM > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:22:34.495988+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://shibu-cul.jp/cms/wp-content/uploads/2022/07/ogp.png + source_url: https://www.shibu-cul.jp/planetarium + css_selector: '[document] > html.fontM > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-25T23:22:34.495988+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-EM.yaml b/data/custodian/JP-13-SHI-M-EM.yaml index 07c9e51be7..2532dce6e8 100644 --- a/data/custodian/JP-13-SHI-M-EM.yaml +++ b/data/custodian/JP-13-SHI-M-EM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-EM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-EM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-EM ghcid_numeric: 16322092273426354584 valid_from: '2025-12-06T23:38:33.394041+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: EMAUX MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:22:42.815351+00:00' + source_url: https://emaux.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://emaux.jp/wp/wp-content/themes/html5blank-stable/img/fav.ico + source_url: https://emaux.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:22:42.815351+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: https://emaux.jp/wp/wp-content/themes/html5blank-stable/img/ico + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-FM.yaml b/data/custodian/JP-13-SHI-M-FM.yaml index bf8a06bbed..e1ce5a9d2b 100644 --- a/data/custodian/JP-13-SHI-M-FM.yaml +++ b/data/custodian/JP-13-SHI-M-FM.yaml @@ -247,3 +247,28 @@ location: postal_code: 160-0004 street_address: YOTSUYA, Shinjuku Ku, Tokyo To, 160-0004 normalization_timestamp: '2025-12-09T12:22:22.046959+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:22:53.953544+00:00' + source_url: https://www.tfd.metro.tokyo.lg.jp/ts/museum.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tfd.metro.tokyo.lg.jp/content/000000003.png + source_url: https://www.tfd.metro.tokyo.lg.jp/ts/museum.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:22:53.953544+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.tfd.metro.tokyo.lg.jp/ts/サムネイル画像のURL + source_url: https://www.tfd.metro.tokyo.lg.jp/ts/museum.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T23:22:53.953544+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-M-GCCP.yaml b/data/custodian/JP-13-SHI-M-GCCP.yaml index 779a44e377..5c201395ee 100644 --- a/data/custodian/JP-13-SHI-M-GCCP.yaml +++ b/data/custodian/JP-13-SHI-M-GCCP.yaml @@ -152,3 +152,28 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:23:09.689962+00:00' + source_url: https://shinagawa-gotanda-planetarium.com + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://shinagawa-gotanda-planetarium.com/images/h_logo01.png + source_url: https://shinagawa-gotanda-planetarium.com + css_selector: '#hLogo > a > img' + retrieved_on: '2025-12-25T23:23:09.689962+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 品川区立五反田文化センター + - claim_type: og_image_url + claim_value: https://shinagawa-gotanda-planetarium.com/images/index/main_visual_01.png + source_url: https://shinagawa-gotanda-planetarium.com + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:23:09.689962+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-M-GT.yaml b/data/custodian/JP-13-SHI-M-GT.yaml index 83d676e8b6..1ce68a4360 100644 --- a/data/custodian/JP-13-SHI-M-GT.yaml +++ b/data/custodian/JP-13-SHI-M-GT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-GT - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-GT valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-GT ghcid_numeric: 13467446309830136506 valid_from: '2025-12-06T23:38:33.121152+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: GALERIE TAISEI @@ -151,3 +152,30 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:23:16.442795+00:00' + source_url: https://www.galerie-taisei.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.galerie-taisei.jp/assets/static/app-icon-512x512.png + source_url: https://www.galerie-taisei.jp + css_selector: '[document] > html.is-browser-chrome.is-browser-ver-135 > head > + link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:23:16.442795+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://galerie-taisei.jp/assets/static/ogp.jpg + source_url: https://www.galerie-taisei.jp + css_selector: '[document] > html.is-browser-chrome.is-browser-ver-135 > head > + meta:nth-of-type(11)' + retrieved_on: '2025-12-25T23:23:16.442795+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-HMSYYMRTWS.yaml b/data/custodian/JP-13-SHI-M-HMSYYMRTWS.yaml index a00310cd99..958f3053d9 100644 --- a/data/custodian/JP-13-SHI-M-HMSYYMRTWS.yaml +++ b/data/custodian/JP-13-SHI-M-HMSYYMRTWS.yaml @@ -1,5 +1,6 @@ original_entry: - name: HISTORICAL MATERIALS SECTION, YOSHIOKA YAYOI MEMORIAL ROOM TOKYO WOMEN'S MEDICAL UNIVERSITY + name: HISTORICAL MATERIALS SECTION, YOSHIOKA YAYOI MEMORIAL ROOM TOKYO WOMEN'S MEDICAL + UNIVERSITY institution_type: MUSEUM source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -39,20 +40,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-HMSYYMRTWS - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-HMSYYMRTWS valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-HMSYYMRTWS ghcid_numeric: 3676647472595533467 valid_from: '2025-12-06T23:38:33.114954+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: HISTORICAL MATERIALS SECTION, YOSHIOKA YAYOI MEMORIAL ROOM TOKYO WOMEN'S MEDICAL UNIVERSITY + claim_value: HISTORICAL MATERIALS SECTION, YOSHIOKA YAYOI MEMORIAL ROOM TOKYO WOMEN'S + MEDICAL UNIVERSITY source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -103,11 +106,12 @@ 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: HISTORICAL MATERIALS SECTION, YOSHIOKA YAYOI MEMORIAL ROOM TOKYO WOMEN'S MEDICAL UNIVERSITY + claim_value: HISTORICAL MATERIALS SECTION, YOSHIOKA YAYOI MEMORIAL ROOM TOKYO + WOMEN'S MEDICAL UNIVERSITY property_uri: skos:prefLabel provenance: namespace: glam @@ -169,8 +173,10 @@ wikidata_enrichment: wikidata_labels: ja: 東京女子医科大学史料室 吉岡彌生記念室 tr: Tokyo Kadın Tıp Üniversitesi Arşivleri - en: Historical Materials Section, Yoshioka Yayoi Memorial Room Tokyo Women's Medical University - wikidata_label_en: Historical Materials Section, Yoshioka Yayoi Memorial Room Tokyo Women's Medical University + en: Historical Materials Section, Yoshioka Yayoi Memorial Room Tokyo Women's Medical + University + wikidata_label_en: Historical Materials Section, Yoshioka Yayoi Memorial Room Tokyo + Women's Medical University wikidata_label_ja: 東京女子医科大学史料室 吉岡彌生記念室 wikidata_descriptions: tr: Tokyo'da müze @@ -178,8 +184,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance wikidata_instance_of: *id004 wikidata_location: coordinates: &id007 @@ -221,3 +227,28 @@ location: postal_code: 162-8666 street_address: KAWADACHO, Shinjuku Ku, Tokyo To, 162-8666 normalization_timestamp: '2025-12-09T12:22:22.259994+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:23:22.741142+00:00' + source_url: https://www.twmu.ac.jp/univ/about/yayoi.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.twmu.ac.jp/img/web_icon.png + source_url: https://www.twmu.ac.jp/univ/about/yayoi.php + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:23:22.741142+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.twmu.ac.jp/img/facebook.png + source_url: https://www.twmu.ac.jp/univ/about/yayoi.php + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:23:22.741142+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-JOM.yaml b/data/custodian/JP-13-SHI-M-JOM.yaml index 54f4f133c2..9a1376b12f 100644 --- a/data/custodian/JP-13-SHI-M-JOM.yaml +++ b/data/custodian/JP-13-SHI-M-JOM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-JOM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-JOM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-JOM ghcid_numeric: 7696966075453324061 valid_from: '2025-12-06T23:38:33.086294+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JAPAN OLYMPIC MUSEUM @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:23:39.785530+00:00' + source_url: https://japan-olympicmuseum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://japan-olympicmuseum.jp/apple-touch-icon.png + source_url: https://japan-olympicmuseum.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:23:39.785530+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://japan-olympicmuseum.jp/img/ogimg.png + source_url: https://japan-olympicmuseum.jp + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T23:23:39.785530+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-KKCH.yaml b/data/custodian/JP-13-SHI-M-KKCH.yaml index 9a5a84612e..f0ad6d8f08 100644 --- a/data/custodian/JP-13-SHI-M-KKCH.yaml +++ b/data/custodian/JP-13-SHI-M-KKCH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-KKCH - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-KKCH valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-KKCH ghcid_numeric: 4895139672748294116 valid_from: '2025-12-06T23:38:33.403732+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KODOMO KAGAKU CENTER HACHIRABO @@ -151,3 +152,37 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:23:49.684315+00:00' + source_url: https://www.city.shibuya.tokyo.jp/shisetsu/kosodate/hachirabo.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.shibuya.tokyo.jp/assets/image/logo.svg + source_url: https://www.city.shibuya.tokyo.jp/shisetsu/kosodate/hachirabo.html + css_selector: '#pageTop > header.is-fixed.is-lang-ja > div.header-content:nth-of-type(2) + > div.header-content-inner > div.sp-menu-head.u-is-sp > h1 > a > img' + retrieved_on: '2025-12-25T23:23:49.684315+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: ちがいをちからに変える街。渋谷区 + - claim_type: favicon_url + claim_value: https://www.city.shibuya.tokyo.jp/pwa/icon/apple-touch-icon-180x180.png + source_url: https://www.city.shibuya.tokyo.jp/shisetsu/kosodate/hachirabo.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:23:49.684315+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.shibuya.tokyo.jp/ogp.png + source_url: https://www.city.shibuya.tokyo.jp/shisetsu/kosodate/hachirabo.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T23:23:49.684315+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-KM.yaml b/data/custodian/JP-13-SHI-M-KM.yaml index 9098a37c7f..f337d1e6c3 100644 --- a/data/custodian/JP-13-SHI-M-KM.yaml +++ b/data/custodian/JP-13-SHI-M-KM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-KM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-KM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-KM ghcid_numeric: 467800503311037800 valid_from: '2025-12-06T23:38:33.128409+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KOREA MUSEUM @@ -151,3 +152,30 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:23:58.735177+00:00' + source_url: https://kouraihakubutsukan.org + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://kouraihakubutsukan.org/wp-content/uploads/images/logo.gif + source_url: https://kouraihakubutsukan.org + css_selector: '#logoarea > dl > dt > a > img' + retrieved_on: '2025-12-25T23:23:58.735177+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 高麗博物館 + - claim_type: favicon_url + claim_value: https://kouraihakubutsukan.org/wp-content/uploads/2020/08/cropped-icon-310x310-1-180x180.png + source_url: https://kouraihakubutsukan.org + css_selector: '[document] > html.js.svg > head > link:nth-of-type(25)' + retrieved_on: '2025-12-25T23:23:58.735177+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-M-KMMJWSU.yaml b/data/custodian/JP-13-SHI-M-KMMJWSU.yaml index 1b251bcde9..44d7c122ac 100644 --- a/data/custodian/JP-13-SHI-M-KMMJWSU.yaml +++ b/data/custodian/JP-13-SHI-M-KMMJWSU.yaml @@ -209,3 +209,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:24:06.352778+00:00' + source_url: https://www.jissen.ac.jp/kosetsu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jissen.ac.jp/favicon.ico + source_url: https://www.jissen.ac.jp/kosetsu + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:24:06.352778+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-KMMM.yaml b/data/custodian/JP-13-SHI-M-KMMM.yaml index 921debfffc..166f198d02 100644 --- a/data/custodian/JP-13-SHI-M-KMMM.yaml +++ b/data/custodian/JP-13-SHI-M-KMMM.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-KMMM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-KMMM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-KMMM ghcid_numeric: 11373810528957527316 valid_from: '2025-12-06T23:38:33.433753+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: KOGA MASAO MUSEUM OF MUSIC @@ -223,3 +224,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:24:14.068464+00:00' + source_url: http://www.koga.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.koga.or.jp/favicon.ico + source_url: http://www.koga.or.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:24:14.068464+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-KUM.yaml b/data/custodian/JP-13-SHI-M-KUM.yaml index 0f26494ada..b318611b1b 100644 --- a/data/custodian/JP-13-SHI-M-KUM.yaml +++ b/data/custodian/JP-13-SHI-M-KUM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-KUM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-KUM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-KUM ghcid_numeric: 12921501113247545313 valid_from: '2025-12-06T23:38:33.423713+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KOKUGAKUIN UNIVERSITY MUSEUM @@ -151,3 +152,36 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:24:27.521732+00:00' + source_url: http://museum.kokugakuin.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://museum.kokugakuin.ac.jp/files/user/images/common/logo.png?v=1448876254 + source_url: http://museum.kokugakuin.ac.jp + css_selector: '#nav_menu > div.logo > a > img' + retrieved_on: '2025-12-25T23:24:27.521732+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 國學院大學博物館 + - claim_type: favicon_url + claim_value: http://museum.kokugakuin.ac.jp/favicon.ico?v= + source_url: http://museum.kokugakuin.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T23:24:27.521732+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://museum.kokugakuin.ac.jp/files/user/images/common/ogp.png + source_url: http://museum.kokugakuin.ac.jp + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T23:24:27.521732+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-MMM.yaml b/data/custodian/JP-13-SHI-M-MMM.yaml index 954a7f681a..e072f563f7 100644 --- a/data/custodian/JP-13-SHI-M-MMM.yaml +++ b/data/custodian/JP-13-SHI-M-MMM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-MMM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-MMM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-MMM ghcid_numeric: 11374316570611590784 valid_from: '2025-12-06T23:38:33.100816+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MIN-ON MUSIC MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:24:39.259318+00:00' + source_url: https://museum.min-on.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://museum.min-on.or.jp/common/img/logo.gif + source_url: https://museum.min-on.or.jp + css_selector: '#logo > a.over > img.pc' + retrieved_on: '2025-12-25T23:24:39.259318+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 民音音楽博物館 MIN-ON MUSIC MUSEUM + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-M-MMMH.yaml b/data/custodian/JP-13-SHI-M-MMMH.yaml index 4751afe4a9..5db91fcafb 100644 --- a/data/custodian/JP-13-SHI-M-MMMH.yaml +++ b/data/custodian/JP-13-SHI-M-MMMH.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-MMMH - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-MMMH valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-MMMH ghcid_numeric: 4329749905644130487 valid_from: '2025-12-06T23:38:33.107037+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: MIYAGI MICHIO MEMORIAL HALL @@ -235,3 +236,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:24:43.916253+00:00' + source_url: https://www.miyagikai.gr.jp/kinenkan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://static.wixstatic.com/media/c9fe24_36cf7334c3d54722822c9c4c250013cd%7Emv2.png/v1/fill/w_180%2Ch_180%2Clg_1%2Cusm_0.66_1.00_0.01/c9fe24_36cf7334c3d54722822c9c4c250013cd%7Emv2.png + source_url: https://www.miyagikai.gr.jp/kinenkan + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:24:43.916253+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://static.wixstatic.com/media/c9fe24_062a37697b03424095534c3cd702dccf%7Emv2.jpg/v1/fit/w_2500,h_1330,al_c/c9fe24_062a37697b03424095534c3cd702dccf%7Emv2.jpg + source_url: https://www.miyagikai.gr.jp/kinenkan + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-25T23:24:43.916253+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-M-MYB.yaml b/data/custodian/JP-13-SHI-M-MYB.yaml index 3fcaa8cddd..b291f6d763 100644 --- a/data/custodian/JP-13-SHI-M-MYB.yaml +++ b/data/custodian/JP-13-SHI-M-MYB.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-MYB - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-MYB valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-MYB ghcid_numeric: 7970597598966946897 valid_from: '2025-12-06T23:38:33.428455+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MUSEUM OF YEBISU BEER @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:25:26.372616+00:00' + source_url: https://www.sapporobeer.jp/brewery/y_museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sapporobeer.jp/icon/icon.png + source_url: https://www.sapporobeer.jp/brewery/y_museum + css_selector: '[document] > html.webkit.chrome > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:25:26.372616+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sapporobeer.jp/common/img/og-image.jpg + source_url: https://www.sapporobeer.jp/brewery/y_museum + css_selector: '[document] > html.webkit.chrome > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T23:25:26.372616+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-NFAM.yaml b/data/custodian/JP-13-SHI-M-NFAM.yaml index 272b150cc3..c7cd72430e 100644 --- a/data/custodian/JP-13-SHI-M-NFAM.yaml +++ b/data/custodian/JP-13-SHI-M-NFAM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-NFAM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-NFAM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-NFAM ghcid_numeric: 14384303042717162102 valid_from: '2025-12-06T23:38:34.789469+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NIZAYAMA FOREST ART MUSEUM @@ -194,7 +195,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) heritage_designation: - id: Q11579194 label: Registered Tangible Cultural Property of Japan @@ -248,3 +250,36 @@ location: postal_code: 939-0631 street_address: NIZAYAMA, Shimoniikawa Gun Nyuzen Machi, Toyama Ken, 939-0631 normalization_timestamp: '2025-12-09T12:22:23.353905+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:25:35.675939+00:00' + source_url: https://www.town.nyuzen.toyama.jp/gyosei/bijutsukan/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.nyuzen.toyama.jp/theme/base/img_common/sp_header_logo.png + source_url: https://www.town.nyuzen.toyama.jp/gyosei/bijutsukan/index.html + css_selector: '#sp-header-logo > a > img' + retrieved_on: '2025-12-25T23:25:35.675939+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 入善町 NYUZEN MACHI + - claim_type: favicon_url + claim_value: https://www.town.nyuzen.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.nyuzen.toyama.jp/gyosei/bijutsukan/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:25:35.675939+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.nyuzen.toyama.jp/material/images/group/0/sawasugi_winter.jpg + source_url: https://www.town.nyuzen.toyama.jp/gyosei/bijutsukan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T23:25:35.675939+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-NICI.yaml b/data/custodian/JP-13-SHI-M-NICI.yaml index f33472510e..3525696cd5 100644 --- a/data/custodian/JP-13-SHI-M-NICI.yaml +++ b/data/custodian/JP-13-SHI-M-NICI.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-NICI - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-NICI valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-NICI ghcid_numeric: 9977725243162971483 valid_from: '2025-12-06T23:38:33.126117+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NTT INTERCOMMUNICATION CENTER [ICC] @@ -151,3 +152,38 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:25:41.570460+00:00' + source_url: https://www.ntticc.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.ntticc.or.jp/assets/images/ICClogo.png + source_url: https://www.ntticc.or.jp + css_selector: '[document] > html.ua-windows_nt.ua-windows_nt-10 > body > header.header.header--global + > div.container.container--sp-hidden > div.header__brand > h1.header__brand__logo + > a.header__brand__logo__link.a-hover--alpha > img' + retrieved_on: '2025-12-25T23:25:41.570460+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: NTT ICC + - claim_type: favicon_url + claim_value: https://www.ntticc.or.jp/assets/icon.png + source_url: https://www.ntticc.or.jp + css_selector: '[document] > html.ua-windows_nt.ua-windows_nt-10 > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T23:25:41.570460+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ntticc.or.jp/assets/ogp.png + source_url: https://www.ntticc.or.jp + css_selector: '[document] > html.ua-windows_nt.ua-windows_nt-10 > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T23:25:41.570460+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-NSMA.yaml b/data/custodian/JP-13-SHI-M-NSMA.yaml index a846887595..9c10397a79 100644 --- a/data/custodian/JP-13-SHI-M-NSMA.yaml +++ b/data/custodian/JP-13-SHI-M-NSMA.yaml @@ -152,3 +152,20 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:25:48.594509+00:00' + source_url: https://www.nakamuraya.co.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.nakamuraya.co.jp/museum/common/img/museum_thum.jpg + source_url: https://www.nakamuraya.co.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:25:48.594509+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-M-OMMA.yaml b/data/custodian/JP-13-SHI-M-OMMA.yaml index dcbb111996..d56ba9f891 100644 --- a/data/custodian/JP-13-SHI-M-OMMA.yaml +++ b/data/custodian/JP-13-SHI-M-OMMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-OMMA - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-OMMA valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-OMMA ghcid_numeric: 15945030423839162456 valid_from: '2025-12-06T23:38:33.384290+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTA MEMORIAL MUSEUM OF ART @@ -151,3 +152,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:26:11.714714+00:00' + source_url: http://www.ukiyoe-ota-muse.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ukiyoe-ota-muse.jp/wp-content/uploads/2020/08/cropped-slide01-180x180.png + source_url: http://www.ukiyoe-ota-muse.jp + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-25T23:26:11.714714+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-M-SA.yaml b/data/custodian/JP-13-SHI-M-SA.yaml index 4be873a2e1..6e255fbaa3 100644 --- a/data/custodian/JP-13-SHI-M-SA.yaml +++ b/data/custodian/JP-13-SHI-M-SA.yaml @@ -1132,3 +1132,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/Vkp4BMwwV3A/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:26:22.012896+00:00' + source_url: https://www.aquarium.gr.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.aquarium.gr.jp/wp-content/uploads/2023/11/cropped-shinagawa-favicon-180x180.png + source_url: https://www.aquarium.gr.jp + css_selector: '[document] > html > body > link:nth-of-type(25)' + retrieved_on: '2025-12-25T23:26:22.012896+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.aquarium.gr.jp/wp-content/themes/shinagawa-aquarium/assets/img/global/ogp.png?240311 + source_url: https://www.aquarium.gr.jp + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-25T23:26:22.012896+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-M-SGNG.yaml b/data/custodian/JP-13-SHI-M-SGNG.yaml index 3b2374fcf0..99ada58fc2 100644 --- a/data/custodian/JP-13-SHI-M-SGNG.yaml +++ b/data/custodian/JP-13-SHI-M-SGNG.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-SGNG - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-SGNG valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-SGNG ghcid_numeric: 14359450035441317812 valid_from: '2025-12-06T23:38:33.090474+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHINJUKU GYOEN NATIONAL GARDEN @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:26:50.739791+00:00' + source_url: https://www.env.go.jp/garden/shinjukugyoen + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.env.go.jp/garden/shinjukugyoen + source_url: https://www.env.go.jp/garden/shinjukugyoen + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:26:50.739791+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.env.go.jp/content/000078974.jpg + source_url: https://www.env.go.jp/garden/shinjukugyoen + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T23:26:50.739791+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-SMA-sompo_museum_of_art.yaml b/data/custodian/JP-13-SHI-M-SMA-sompo_museum_of_art.yaml index 399bda1abf..7451f078ea 100644 --- a/data/custodian/JP-13-SHI-M-SMA-sompo_museum_of_art.yaml +++ b/data/custodian/JP-13-SHI-M-SMA-sompo_museum_of_art.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-SMA-sompo_museum_of_art - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-SMA-sompo_museum_of_art valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-SMA-sompo_museum_of_art ghcid_numeric: 3552863885919592797 valid_from: '2025-12-06T23:38:33.098445+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Sompo Museum of Art @@ -151,3 +152,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:27:14.855897+00:00' + source_url: https://www.sompo-museum.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sompo-museum.org/apple-touch-icon.png + source_url: https://www.sompo-museum.org + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T23:27:14.855897+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.sompo-museum.org/assets/image/common/og.png + source_url: https://www.sompo-museum.org + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T23:27:14.855897+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-M-SMA-the_shoto_museum_of_art.yaml b/data/custodian/JP-13-SHI-M-SMA-the_shoto_museum_of_art.yaml index a2ea7a6bbd..87514e35a7 100644 --- a/data/custodian/JP-13-SHI-M-SMA-the_shoto_museum_of_art.yaml +++ b/data/custodian/JP-13-SHI-M-SMA-the_shoto_museum_of_art.yaml @@ -381,3 +381,36 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/H1xwPypW6eQ/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:27:23.464266+00:00' + source_url: https://shoto-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://shoto-museum.jp/wp-content/themes/shoto_museum/images/site_logo_mark.png + source_url: https://shoto-museum.jp + css_selector: '#site_header > h1 > a > img.has-retina.logo_mark' + retrieved_on: '2025-12-25T23:27:23.464266+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://shoto-museum.jp/wp-content/themes/shoto_museum/images/favicon/favicon.ico + source_url: https://shoto-museum.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:27:23.464266+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://shoto-museum.jp/wp-content/themes/shoto_museum/images/ogp_img.jpg + source_url: https://shoto-museum.jp + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T23:27:23.464266+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-SUMBG.yaml b/data/custodian/JP-13-SHI-M-SUMBG.yaml index ce79f5cf87..c9754849ab 100644 --- a/data/custodian/JP-13-SHI-M-SUMBG.yaml +++ b/data/custodian/JP-13-SHI-M-SUMBG.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-SUMBG - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-SUMBG valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-SUMBG ghcid_numeric: 947204767805275654 valid_from: '2025-12-06T23:38:33.305345+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Showa University Medicinal Botanical Garden @@ -151,3 +152,28 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:27:41.457525+00:00' + source_url: https://www.showa-u.ac.jp/education/pharm/facility/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.showa-u.ac.jp/apple-touch-icon.png + source_url: https://www.showa-u.ac.jp/education/pharm/facility/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:27:41.457525+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.showa-u.ac.jp/ogp.png + source_url: https://www.showa-u.ac.jp/education/pharm/facility/index.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T23:27:41.457525+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-M-TDHM.yaml b/data/custodian/JP-13-SHI-M-TDHM.yaml index c881c03a62..cfd8803db9 100644 --- a/data/custodian/JP-13-SHI-M-TDHM.yaml +++ b/data/custodian/JP-13-SHI-M-TDHM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-TDHM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-TDHM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-TDHM ghcid_numeric: 8307086761172309828 valid_from: '2025-12-06T23:38:33.070226+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TEIKOKU DATABANK HISTORICAL MUSEUM @@ -151,3 +152,29 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:27:50.777221+00:00' + source_url: https://tdb-muse.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://tdb-muse.jp/images/common/header_logo01.svg + source_url: https://tdb-muse.jp + css_selector: '#home > header > div.contents > div.logoarea > h1.h-logo > a > + img' + retrieved_on: '2025-12-25T23:27:50.777221+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: og_image_url + claim_value: https://www.tdb-muse.jp/images/common/ogp.jpg + source_url: https://tdb-muse.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T23:27:50.777221+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-M-TMA.yaml b/data/custodian/JP-13-SHI-M-TMA.yaml index b7e6fedcc7..e11f074c51 100644 --- a/data/custodian/JP-13-SHI-M-TMA.yaml +++ b/data/custodian/JP-13-SHI-M-TMA.yaml @@ -339,3 +339,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/01GbZriTg-4/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:27:58.869546+00:00' + source_url: http://www.toguri-museum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.toguri-museum.or.jp/image/webclip.png + source_url: http://www.toguri-museum.or.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:27:58.869546+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-TTM.yaml b/data/custodian/JP-13-SHI-M-TTM.yaml index 8c20c163f9..2068f0bf10 100644 --- a/data/custodian/JP-13-SHI-M-TTM.yaml +++ b/data/custodian/JP-13-SHI-M-TTM.yaml @@ -1857,3 +1857,37 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/nP4n3n9eO4s/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:28:11.583053+00:00' + source_url: https://art-play.or.jp/ttm + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://art-play.or.jp/ttm/assets/img/common/logo_01.svg + source_url: https://art-play.or.jp/ttm + css_selector: '[document] > html > body > header.header.hero > div.sp-header > + a.sp-header__logo > img' + retrieved_on: '2025-12-25T23:28:11.583053+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東京おもちゃ美術館 + - claim_type: favicon_url + claim_value: https://art-play.or.jp/ttm/assets/img/common/favicon.ico + source_url: https://art-play.or.jp/ttm + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:28:11.583053+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://art-play.or.jp/ttm/assets/img/common/img_ogp.png + source_url: https://art-play.or.jp/ttm + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:28:11.583053+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-WIHLHML.yaml b/data/custodian/JP-13-SHI-M-WIHLHML.yaml index fec2b51e8e..b0459aee46 100644 --- a/data/custodian/JP-13-SHI-M-WIHLHML.yaml +++ b/data/custodian/JP-13-SHI-M-WIHLHML.yaml @@ -153,3 +153,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:28:27.797679+00:00' + source_url: https://www.waseda.jp/culture/wihl + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.waseda.jp/culture/wihl/assets/themes/waseda-template-engine-alt/img/icons/favicon_32.png + source_url: https://www.waseda.jp/culture/wihl + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:28:27.797679+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.waseda.jp/culture/wihl/assets/themes/waseda-template-engine-alt/img/og_image.png + source_url: https://www.waseda.jp/culture/wihl + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T23:28:27.797679+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-M-WK.yaml b/data/custodian/JP-13-SHI-M-WK.yaml index 751d12e277..bd0f777357 100644 --- a/data/custodian/JP-13-SHI-M-WK.yaml +++ b/data/custodian/JP-13-SHI-M-WK.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-WK - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-WK valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-WK ghcid_numeric: 13694690612664537851 valid_from: '2025-12-06T23:38:31.941016+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Wake Kinenkan @@ -153,3 +154,28 @@ location: geonames_id: 1851959 geonames_name: Shioya feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:28:37.425088+00:00' + source_url: https://www.boubou.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://boubou.jp/wp/wp-content/themes/wakemuseum/favicon.ico + source_url: https://www.boubou.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:28:37.425088+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://boubou.jp/wp/wp-content/uploads/2019/11/ogimage.png + source_url: https://www.boubou.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T23:28:37.425088+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-M-WWMCA.yaml b/data/custodian/JP-13-SHI-M-WWMCA.yaml index 19e12513a7..d37b14c0de 100644 --- a/data/custodian/JP-13-SHI-M-WWMCA.yaml +++ b/data/custodian/JP-13-SHI-M-WWMCA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-WWMCA - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-WWMCA valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-WWMCA ghcid_numeric: 3243570898702909062 valid_from: '2025-12-06T23:38:33.391285+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: WATARI-UM, THE WATARI MUSEUM OF CONTEMPORARY ART @@ -151,3 +152,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:28:43.450228+00:00' + source_url: http://watarium.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://watarium.co.jp/2020/img/common/icon.png + source_url: http://watarium.co.jp + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T23:28:43.450228+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-YKM.yaml b/data/custodian/JP-13-SHI-M-YKM.yaml index 33f7b4b42e..19f40a252e 100644 --- a/data/custodian/JP-13-SHI-M-YKM.yaml +++ b/data/custodian/JP-13-SHI-M-YKM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-YKM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-YKM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-YKM ghcid_numeric: 4534191744148990280 valid_from: '2025-12-06T23:38:33.109984+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAYOI KUSAMA MUSEUM @@ -151,3 +152,36 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:28:50.188691+00:00' + source_url: https://yayoikusamamuseum.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://yayoikusamamuseum.jp/assets/images/logo.svg + source_url: https://yayoikusamamuseum.jp + css_selector: '#container > header.clearfix > div.top_header_logo > img' + retrieved_on: '2025-12-25T23:28:50.188691+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://yayoikusamamuseum.jp/assets/images/favicon/favicon.ico + source_url: https://yayoikusamamuseum.jp + css_selector: '[document] > html.js.svg > head > link' + retrieved_on: '2025-12-25T23:28:50.188691+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.yayoikusamamuseum.jp/assets/images/image/ogimage.png + source_url: https://yayoikusamamuseum.jp + css_selector: '[document] > html.js.svg > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T23:28:50.188691+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-M-YMA.yaml b/data/custodian/JP-13-SHI-M-YMA.yaml index 5ce8b80be2..5697ae1316 100644 --- a/data/custodian/JP-13-SHI-M-YMA.yaml +++ b/data/custodian/JP-13-SHI-M-YMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-M-YMA - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-M-YMA valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-M-YMA ghcid_numeric: 15465584477573009829 valid_from: '2025-12-06T23:38:33.398958+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YAMATANE MUSEUM OF ART @@ -151,3 +152,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:29:01.678478+00:00' + source_url: https://www.yamatane-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.yamatane-museum.jp/img/icon.ico + source_url: https://www.yamatane-museum.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T23:29:01.678478+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SUG-L-RIRC.yaml b/data/custodian/JP-13-SUG-L-RIRC.yaml index 368d832d4b..0203e77f8f 100644 --- a/data/custodian/JP-13-SUG-L-RIRC.yaml +++ b/data/custodian/JP-13-SUG-L-RIRC.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-RIRC - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-RIRC valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-RIRC ghcid_numeric: 13207269400803065640 valid_from: '2025-12-06T23:38:58.789972+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Religious Information Research Center @@ -151,3 +152,22 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:46:50.070967+00:00' + source_url: http://www.rirc.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.rirc.or.jp/favicon.ico + source_url: http://www.rirc.or.jp + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T23:46:50.070967+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SUG-L-RL.yaml b/data/custodian/JP-13-SUG-L-RL.yaml index 49084bb820..fdd0fe123f 100644 --- a/data/custodian/JP-13-SUG-L-RL.yaml +++ b/data/custodian/JP-13-SUG-L-RL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-RL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-RL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-RL ghcid_numeric: 4195359826046447467 valid_from: '2025-12-06T23:38:44.000818+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: RISSHOKOSEIKAIFUZOKUKOSEI Library @@ -151,3 +152,22 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:46:57.778447+00:00' + source_url: https://www.kosei-kai.or.jp/official/relation/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kosei-kai.or.jp/official/wp-content/themes/kosei-kai-s/images/common/apple-touch-icon-180x180.png + source_url: https://www.kosei-kai.or.jp/official/relation/library + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T23:46:57.778447+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-13-SUG-L-SL-suginamikuritsuasagaya_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuasagaya_library.yaml index b467c2e100..2398d2b7c3 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsuasagaya_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuasagaya_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsuasagaya_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsuasagaya_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsuasagaya_library ghcid_numeric: 10165707458489072125 valid_from: '2025-12-06T23:38:43.395742+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUASAGAYA Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:47:10.986083+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/asagaya.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/asagaya.html + css_selector: '#body--index > 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: '2025-12-25T23:47:10.986083+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/asagaya.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:47:10.986083+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-13-SUG-L-SL-suginamikuritsueifuku_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsueifuku_library.yaml index bafbf3b1c9..4e5215355a 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsueifuku_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsueifuku_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsueifuku_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsueifuku_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsueifuku_library ghcid_numeric: 2870554232597438212 valid_from: '2025-12-06T23:38:43.381718+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUEIFUKU Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:47:25.921756+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/eifuku.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/eifuku.html + css_selector: '#body--index > 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: '2025-12-25T23:47:25.921756+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/eifuku.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:47:25.921756+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-13-SUG-L-SL-suginamikuritsuhonan_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuhonan_library.yaml index 802ca0195e..b4235952cd 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsuhonan_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuhonan_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsuhonan_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsuhonan_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsuhonan_library ghcid_numeric: 4723643412594067018 valid_from: '2025-12-06T23:38:43.404952+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUHONAN Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:50:52.965405+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/hounan.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/hounan.html + css_selector: '#body--index > 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: '2025-12-25T23:50:52.965405+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/hounan.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:50:52.965405+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-13-SUG-L-SL-suginamikuritsuimagawa_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuimagawa_library.yaml index 61e7103ae9..bad09566bc 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsuimagawa_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuimagawa_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsuimagawa_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsuimagawa_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsuimagawa_library ghcid_numeric: 9713418915851587274 valid_from: '2025-12-06T23:38:43.407159+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUIMAGAWA Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:51:03.614636+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/imagawa.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/imagawa.html + css_selector: '#body--index > 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: '2025-12-25T23:51:03.614636+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/imagawa.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:51:03.614636+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-13-SUG-L-SL-suginamikuritsukakinoki_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsukakinoki_library.yaml index 245dc9e61f..2b923346d7 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsukakinoki_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsukakinoki_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsukakinoki_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsukakinoki_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsukakinoki_library ghcid_numeric: 16428946661860733882 valid_from: '2025-12-06T23:38:43.384017+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUKAKINOKI Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:51:16.702737+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/kakinoki.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/kakinoki.html + css_selector: '#body--index > 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: '2025-12-25T23:51:16.702737+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/kakinoki.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:51:16.702737+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-13-SUG-L-SL-suginamikuritsukoenji_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsukoenji_library.yaml index c882de5122..21b324d4fc 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsukoenji_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsukoenji_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsukoenji_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsukoenji_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsukoenji_library ghcid_numeric: 14418484037755624381 valid_from: '2025-12-06T23:38:43.386340+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUKOENJI Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:53:09.160866+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/kouenji.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/kouenji.html + css_selector: '#body--index > 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: '2025-12-25T23:53:09.160866+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/kouenji.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:53:09.160866+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-13-SUG-L-SL-suginamikuritsuminamiogikubo_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuminamiogikubo_library.yaml index 0ccbc14ced..251a69c7e1 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsuminamiogikubo_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsuminamiogikubo_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsuminamiogikubo_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsuminamiogikubo_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsuminamiogikubo_library ghcid_numeric: 3430398447578666959 valid_from: '2025-12-06T23:38:43.398024+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUMINAMIOGIKUBO Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:53:24.579100+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/minamiogikubo.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/minamiogikubo.html + css_selector: '#body--index > 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: '2025-12-25T23:53:24.579100+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/minamiogikubo.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:53:24.579100+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-13-SUG-L-SL-suginamikuritsumiyamae_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsumiyamae_library.yaml index 4f3b329a5a..5273a346aa 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsumiyamae_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsumiyamae_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsumiyamae_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsumiyamae_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsumiyamae_library ghcid_numeric: 12337871471170690030 valid_from: '2025-12-06T23:38:43.388610+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUMIYAMAE Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:53:35.669568+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/miyamae.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/miyamae.html + css_selector: '#body--index > 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: '2025-12-25T23:53:35.669568+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/miyamae.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:53:35.669568+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-13-SUG-L-SL-suginamikuritsunarita_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsunarita_library.yaml index 5c659f9c76..2eb297f54f 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsunarita_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsunarita_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsunarita_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsunarita_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsunarita_library ghcid_numeric: 6613387937265546957 valid_from: '2025-12-06T23:38:43.391004+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUNARITA Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:53:43.902354+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/narita.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/narita.html + css_selector: '#body--index > 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: '2025-12-25T23:53:43.902354+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/narita.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:53:43.902354+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-13-SUG-L-SL-suginamikuritsunishiogi_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsunishiogi_library.yaml index aa03415639..b41dc16f94 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsunishiogi_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsunishiogi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsunishiogi_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsunishiogi_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsunishiogi_library ghcid_numeric: 12213217574598834758 valid_from: '2025-12-06T23:38:43.393412+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUNISHIOGI Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:53:57.906661+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/nishiogi.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/nishiogi.html + css_selector: '#body--index > 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: '2025-12-25T23:53:57.906661+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/nishiogi.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:53:57.906661+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-13-SUG-L-SL-suginamikuritsushimoigusa_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsushimoigusa_library.yaml index e6812d07a6..b6b0d14a74 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsushimoigusa_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsushimoigusa_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsushimoigusa_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsushimoigusa_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsushimoigusa_library ghcid_numeric: 17647394243049588926 valid_from: '2025-12-06T23:38:43.400343+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUSHIMOIGUSA Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:54:08.024700+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/simoigusa.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/simoigusa.html + css_selector: '#body--index > 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: '2025-12-25T23:54:08.024700+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/simoigusa.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:54:08.024700+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-13-SUG-L-SL-suginamikuritsutakaido_library.yaml b/data/custodian/JP-13-SUG-L-SL-suginamikuritsutakaido_library.yaml index 44915c50ec..52988c756a 100644 --- a/data/custodian/JP-13-SUG-L-SL-suginamikuritsutakaido_library.yaml +++ b/data/custodian/JP-13-SUG-L-SL-suginamikuritsutakaido_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL-suginamikuritsutakaido_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL-suginamikuritsutakaido_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL-suginamikuritsutakaido_library ghcid_numeric: 7727176216525055227 valid_from: '2025-12-06T23:38:43.402662+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMIKURITSUTAKAIDO Library @@ -151,3 +152,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:54:24.137298+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/takaido.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/takaido.html + css_selector: '#body--index > 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: '2025-12-25T23:54:24.137298+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/takaido.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:54:24.137298+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-13-SUG-L-SL.yaml b/data/custodian/JP-13-SUG-L-SL.yaml index e9b9a3e405..b4d976cb57 100644 --- a/data/custodian/JP-13-SUG-L-SL.yaml +++ b/data/custodian/JP-13-SUG-L-SL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-SL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-SL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-SL ghcid_numeric: 2644995687597938113 valid_from: '2025-12-06T23:38:43.378856+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: SUGINAMIKURITSUCHUO Library @@ -200,12 +201,13 @@ wikidata_enrichment: instance_of: &id004 - id: Q7075 label: library - description: institution charged with the care of a collection of literary, musical, artistic, or reference materials, - such as books, manuscripts, recordings, or films + description: institution charged with the care of a collection of literary, + musical, artistic, or reference materials, such as books, manuscripts, recordings, + or films - id: Q28564 label: public library - description: free community resource offering access to books, media, and information, promoting literacy and education - for all ages + description: free community resource offering access to books, media, and information, + promoting literacy and education for all ages wikidata_instance_of: *id004 wikidata_location: country: &id006 @@ -258,3 +260,31 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:54:32.828405+00:00' + source_url: https://www.library.city.suginami.tokyo.jp/facilities/chuou.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/logo01.svg + source_url: https://www.library.city.suginami.tokyo.jp/facilities/chuou.html + css_selector: '#body--index > 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: '2025-12-25T23:54:32.828405+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 杉並区立図書館 + - claim_type: favicon_url + claim_value: https://www.library.city.suginami.tokyo.jp/common/images/favicon.ico + source_url: https://www.library.city.suginami.tokyo.jp/facilities/chuou.html + css_selector: '[document] > html.c-font-size--medium > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T23:54:32.828405+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-13-SUG-L-TRJCL.yaml b/data/custodian/JP-13-SUG-L-TRJCL.yaml index bc4b977cfc..7e938fe00d 100644 --- a/data/custodian/JP-13-SUG-L-TRJCL.yaml +++ b/data/custodian/JP-13-SUG-L-TRJCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-TRJCL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-TRJCL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-TRJCL ghcid_numeric: 1383261020996787552 valid_from: '2025-12-06T23:38:56.922091+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Rissho Junior College Library @@ -204,3 +205,28 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:54:42.429475+00:00' + source_url: http://www.tokyorissho.ac.jp/about/institution/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tokyorissho.ac.jp/user/common/images/i_icon.png + source_url: http://www.tokyorissho.ac.jp/about/institution/library + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T23:54:42.429475+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.tokyorissho.ac.jp/user/common/images/ogp_image.png + source_url: http://www.tokyorissho.ac.jp/about/institution/library + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T23:54:42.429475+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SUG-L-TUL.yaml b/data/custodian/JP-13-SUG-L-TUL.yaml index d5c39b8581..625f611d15 100644 --- a/data/custodian/JP-13-SUG-L-TUL.yaml +++ b/data/custodian/JP-13-SUG-L-TUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-L-TUL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-L-TUL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-L-TUL ghcid_numeric: 2772778370531107567 valid_from: '2025-12-06T23:38:55.007384+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: Takachiho 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.takachiho.jp/lib wikidata_official_website: http://www.takachiho.jp/lib @@ -212,3 +214,22 @@ location: geonames_id: 11836117 geonames_name: Suginami feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:54:53.918665+00:00' + source_url: http://www.takachiho.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.takachiho.jp/_public/favicon.ico?dummy=1749030777 + source_url: http://www.takachiho.jp/lib + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:54:53.918665+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SUG-M-SHM.yaml b/data/custodian/JP-13-SUG-M-SHM.yaml index e7442c31ef..a63e2a38e0 100644 --- a/data/custodian/JP-13-SUG-M-SHM.yaml +++ b/data/custodian/JP-13-SUG-M-SHM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUG-M-SHM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUG-M-SHM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUG-M-SHM ghcid_numeric: 10881678560356835583 valid_from: '2025-12-06T23:38:33.446601+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUGINAMI HISTORICAL MUSEUM @@ -242,3 +243,28 @@ location: postal_code: 168-0061 street_address: OMIYA, Suginami Ku, Tokyo To, 168-0061 normalization_timestamp: '2025-12-09T12:22:26.165019+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:55:14.449356+00:00' + source_url: https://www.city.suginami.tokyo.jp/histmus + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.suginami.tokyo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.suginami.tokyo.jp/histmus + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T23:55:14.449356+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.suginami.tokyo.jp/shared/images/sns/logo.jpg + source_url: https://www.city.suginami.tokyo.jp/histmus + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T23:55:14.449356+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SUM-L-ETML.yaml b/data/custodian/JP-13-SUM-L-ETML.yaml index 757025c51d..4f96b85c8a 100644 --- a/data/custodian/JP-13-SUM-L-ETML.yaml +++ b/data/custodian/JP-13-SUM-L-ETML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUM-L-ETML - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUM-L-ETML valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUM-L-ETML ghcid_numeric: 418847945960344618 valid_from: '2025-12-06T23:38:57.857811+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Edo-Tokyo Museum Library @@ -151,3 +152,28 @@ location: geonames_id: 1851454 geonames_name: Sumida feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:55:23.626674+00:00' + source_url: http://www.edo-tokyo-museum.or.jp/purpose/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.edo-tokyo-museum.or.jp/assets/common/img/favicon.ico + source_url: http://www.edo-tokyo-museum.or.jp/purpose/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:55:23.626674+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.edo-tokyo-museum.or.jp/assets/common/img/ogimage.png + source_url: http://www.edo-tokyo-museum.or.jp/purpose/library + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T23:55:23.626674+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SUM-M-BM.yaml b/data/custodian/JP-13-SUM-M-BM.yaml index df8fd18c1f..7bc88b36ea 100644 --- a/data/custodian/JP-13-SUM-M-BM.yaml +++ b/data/custodian/JP-13-SUM-M-BM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUM-M-BM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUM-M-BM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUM-M-BM ghcid_numeric: 10748703492400092997 valid_from: '2025-12-06T23:38:33.239623+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Brake Museum @@ -151,3 +152,22 @@ location: geonames_id: 1851454 geonames_name: Sumida feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:57:45.175513+00:00' + source_url: https://sasga.co.jp/brake_museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sasga.co.jp/apple-touch-icon.png + source_url: https://sasga.co.jp/brake_museum + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T23:57:45.175513+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SUM-M-ETM.yaml b/data/custodian/JP-13-SUM-M-ETM.yaml index 78d4c1a00b..cc21167bca 100644 --- a/data/custodian/JP-13-SUM-M-ETM.yaml +++ b/data/custodian/JP-13-SUM-M-ETM.yaml @@ -1830,3 +1830,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/c3jFhFF5lmM/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:58:01.632070+00:00' + source_url: http://edo-tokyo-museum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://edo-tokyo-museum.or.jp/assets/common/img/favicon.ico + source_url: http://edo-tokyo-museum.or.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:58:01.632070+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.edo-tokyo-museum.or.jp/assets/common/img/ogimage.png + source_url: http://edo-tokyo-museum.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T23:58:01.632070+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SUM-M-JSM.yaml b/data/custodian/JP-13-SUM-M-JSM.yaml index 3da57f74b0..0ed111c405 100644 --- a/data/custodian/JP-13-SUM-M-JSM.yaml +++ b/data/custodian/JP-13-SUM-M-JSM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUM-M-JSM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUM-M-JSM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUM-M-JSM ghcid_numeric: 12759261843282855817 valid_from: '2025-12-06T23:38:33.237284+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: THE JAPANESE SWORD MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 1851454 geonames_name: Sumida feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:58:19.827237+00:00' + source_url: https://www.touken.or.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.touken.or.jp/Portals/0/logo_museum.png + source_url: https://www.touken.or.jp/museum + css_selector: '#dnn_ctr407_HtmlModule_HtmlModule_lblContent > h1.logo > a > img' + retrieved_on: '2025-12-25T23:58:19.827237+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 刀剣博物館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SUM-M-PMJ.yaml b/data/custodian/JP-13-SUM-M-PMJ.yaml index 6ee424235a..5400e19d22 100644 --- a/data/custodian/JP-13-SUM-M-PMJ.yaml +++ b/data/custodian/JP-13-SUM-M-PMJ.yaml @@ -493,3 +493,20 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/EUFvnNWjsAw/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:58:53.756204+00:00' + source_url: https://www.postalmuseum.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.postalmuseum.jp/img/common/og_image.png + source_url: https://www.postalmuseum.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-25T23:58:53.756204+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SUM-M-SA.yaml b/data/custodian/JP-13-SUM-M-SA.yaml index ccc12d5a5c..f1190cb821 100644 --- a/data/custodian/JP-13-SUM-M-SA.yaml +++ b/data/custodian/JP-13-SUM-M-SA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUM-M-SA - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUM-M-SA valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUM-M-SA ghcid_numeric: 720102818627553456 valid_from: '2025-12-06T23:38:33.247176+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUMIDA AQUARIUM @@ -151,3 +152,28 @@ location: geonames_id: 1851454 geonames_name: Sumida feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:58:59.680970+00:00' + source_url: https://www.sumida-aquarium.com/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sumida-aquarium.com/img/common/favicon.ico + source_url: https://www.sumida-aquarium.com/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:58:59.680970+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sumida-aquarium.com/img/common/ogp.jpg + source_url: https://www.sumida-aquarium.com/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T23:58:59.680970+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SUM-M-SM.yaml b/data/custodian/JP-13-SUM-M-SM.yaml index 47f0a84965..930e88c8d4 100644 --- a/data/custodian/JP-13-SUM-M-SM.yaml +++ b/data/custodian/JP-13-SUM-M-SM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUM-M-SM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUM-M-SM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUM-M-SM ghcid_numeric: 6416286907207205092 valid_from: '2025-12-06T23:38:33.229289+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SUMO MUSEUM @@ -276,3 +277,28 @@ location: postal_code: 130-0015 street_address: YOKOAMI, Sumida Ku, Tokyo To, 130-0015 normalization_timestamp: '2025-12-09T12:22:26.743309+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:59:05.377402+00:00' + source_url: https://www.sumo.or.jp/KokugikanSumoMuseum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sumo.or.jp/crest.png + source_url: https://www.sumo.or.jp/KokugikanSumoMuseum + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T23:59:05.377402+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://www.sumo.or.jp/img/common/fb_logo.gif + source_url: https://www.sumo.or.jp/KokugikanSumoMuseum + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T23:59:05.377402+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SUM-M-TMTC.yaml b/data/custodian/JP-13-SUM-M-TMTC.yaml index f453ea9e9f..74508d2e1a 100644 --- a/data/custodian/JP-13-SUM-M-TMTC.yaml +++ b/data/custodian/JP-13-SUM-M-TMTC.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SUM-M-TMTC - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SUM-M-TMTC valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SUM-M-TMTC ghcid_numeric: 2389958956401817677 valid_from: '2025-12-06T23:38:33.241867+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOBU MUSEUM OF TRANSPORT & CULTURE @@ -151,3 +152,22 @@ location: geonames_id: 1851454 geonames_name: Sumida feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:59:12.523173+00:00' + source_url: https://www.tobu.co.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tobu.co.jp/museum/apple-touch-icon.png + source_url: https://www.tobu.co.jp/museum + css_selector: '[document] > html.js.opacity > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:59:12.523173+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SUM-M-TSM.yaml b/data/custodian/JP-13-SUM-M-TSM.yaml index e5235a1a06..635d7d9db3 100644 --- a/data/custodian/JP-13-SUM-M-TSM.yaml +++ b/data/custodian/JP-13-SUM-M-TSM.yaml @@ -624,3 +624,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/ypIDVU9gP-U/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:59:21.661873+00:00' + source_url: https://www.tabashio.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tabashio.jp/common/images/favicon.ico + source_url: https://www.tabashio.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T23:59:21.661873+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tabashio.jp/common/images/fb_logo.jpg + source_url: https://www.tabashio.jp + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T23:59:21.661873+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-TAC-L-ISMLD.yaml b/data/custodian/JP-13-TAC-L-ISMLD.yaml index f9de8c24a7..157aaba538 100644 --- a/data/custodian/JP-13-TAC-L-ISMLD.yaml +++ b/data/custodian/JP-13-TAC-L-ISMLD.yaml @@ -154,3 +154,22 @@ location: geonames_id: 11611487 geonames_name: Tachikawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:59:29.511477+00:00' + source_url: http://www.ism.ac.jp/library/index_j.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ism.ac.jp/ressources/img/share/favicon.ico + source_url: http://www.ism.ac.jp/library/index_j.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T23:59:29.511477+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-TAC-L-KCML.yaml b/data/custodian/JP-13-TAC-L-KCML.yaml index 2e312d32e4..5370d6ca2f 100644 --- a/data/custodian/JP-13-TAC-L-KCML.yaml +++ b/data/custodian/JP-13-TAC-L-KCML.yaml @@ -220,3 +220,37 @@ location: postal_code: 190-8520 street_address: 5-5-1 KASHIWACHO, Tachikawashi, Tokyo To, 190-8520 normalization_timestamp: '2025-12-09T12:22:27.045171+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:59:49.245621+00:00' + source_url: http://www.lib.kunitachi.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.kunitachi.ac.jp/wp-content/uploads/2023/06/logo5.png + source_url: http://www.lib.kunitachi.ac.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: '2025-12-25T23:59:49.245621+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 国立音楽大学附属図書館 + - claim_type: favicon_url + claim_value: https://www.lib.kunitachi.ac.jp/wp-content/uploads/2023/04/cropped-kamo9-180x180.png + source_url: http://www.lib.kunitachi.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(48)' + retrieved_on: '2025-12-25T23:59:49.245621+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.kunitachi.ac.jp/wp-content/uploads/2023/04/twittercard.png + source_url: http://www.lib.kunitachi.ac.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T23:59:49.245621+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-TAC-L-NIJL.yaml b/data/custodian/JP-13-TAC-L-NIJL.yaml index be6348bcdb..7de01be754 100644 --- a/data/custodian/JP-13-TAC-L-NIJL.yaml +++ b/data/custodian/JP-13-TAC-L-NIJL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAC-L-NIJL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAC-L-NIJL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAC-L-NIJL ghcid_numeric: 14292810362888772095 valid_from: '2025-12-06T23:38:57.535461+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: National Institute of Japanese Literature @@ -151,3 +152,28 @@ location: geonames_id: 11611487 geonames_name: Tachikawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T23:59:57.321309+00:00' + source_url: http://www.nijl.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.nijl.ac.jp/wp/wp-content/uploads/2025/10/apple-touch-icon.png + source_url: http://www.nijl.ac.jp + css_selector: '[document] > html._device-pc._os-mac > head > link:nth-of-type(28)' + retrieved_on: '2025-12-25T23:59:57.321309+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://www.nijl.ac.jp/wp/wp-content/themes/nijl/images/common/ogp.jpg + source_url: http://www.nijl.ac.jp + css_selector: '[document] > html._device-pc._os-mac > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T23:59:57.321309+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAC-L-NIPRLROIS.yaml b/data/custodian/JP-13-TAC-L-NIPRLROIS.yaml index 137b7e1d3f..f2524b7c5a 100644 --- a/data/custodian/JP-13-TAC-L-NIPRLROIS.yaml +++ b/data/custodian/JP-13-TAC-L-NIPRLROIS.yaml @@ -1,5 +1,6 @@ original_entry: - name: National Institute of Polar Research Library, Research Organization of Information and Systems + name: National Institute of Polar Research Library, Research Organization of Information + and Systems institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -32,20 +33,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAC-L-NIPRLROIS - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAC-L-NIPRLROIS valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAC-L-NIPRLROIS ghcid_numeric: 12619536097693835371 valid_from: '2025-12-06T23:38:57.539117+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: National Institute of Polar Research Library, Research Organization of Information and Systems + claim_value: National Institute of Polar Research Library, Research Organization + of Information and Systems source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +99,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: National Institute of Polar Research Library, Research Organization of Information and Systems + claim_value: National Institute of Polar Research Library, Research Organization + of Information and Systems property_uri: skos:prefLabel provenance: namespace: glam @@ -153,3 +157,22 @@ location: geonames_id: 11611487 geonames_name: Tachikawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:00:13.781526+00:00' + source_url: http://www.nipr.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.nipr.ac.jp/image/header-logo.png + source_url: http://www.nipr.ac.jp/library + css_selector: '#sp-header-inner > div.sp-title > a > img' + retrieved_on: '2025-12-26T00:00:13.781526+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 国立極地研究所 情報図書室 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-TAC-L-RLIURICNIH.yaml b/data/custodian/JP-13-TAC-L-RLIURICNIH.yaml index a5943422bd..bcae3aaf06 100644 --- a/data/custodian/JP-13-TAC-L-RLIURICNIH.yaml +++ b/data/custodian/JP-13-TAC-L-RLIURICNIH.yaml @@ -1,6 +1,6 @@ original_entry: - name: Research Library at the Inter-University Research Institute Corporation, National Institutes for the Humanities, National - Institute for Japanese Language and Linguistics + name: Research Library at the Inter-University Research Institute Corporation, National + Institutes for the Humanities, National Institute for Japanese Language and Linguistics institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -33,21 +33,23 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAC-L-RLIURICNIH - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAC-L-RLIURICNIH valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAC-L-RLIURICNIH ghcid_numeric: 6369189915400775987 valid_from: '2025-12-06T23:38:57.754271+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Research Library at the Inter-University Research Institute Corporation, National Institutes for the Humanities, - National Institute for Japanese Language and Linguistics + claim_value: Research Library at the Inter-University Research Institute Corporation, + National Institutes for the Humanities, National Institute for Japanese Language + and Linguistics source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -98,12 +100,13 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Research Library at the Inter-University Research Institute Corporation, National Institutes for the Humanities, - National Institute for Japanese Language and Linguistics + claim_value: Research Library at the Inter-University Research Institute Corporation, + National Institutes for the Humanities, National Institute for Japanese Language + and Linguistics property_uri: skos:prefLabel provenance: namespace: glam @@ -156,3 +159,28 @@ location: geonames_id: 11611487 geonames_name: Tachikawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:00:25.146171+00:00' + source_url: http://www.ninjal.ac.jp/info/aboutus/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ninjal.ac.jp/ninjal_wp/wp-content/uploads/2022/01/cropped-favicon-180x180.png + source_url: http://www.ninjal.ac.jp/info/aboutus/library + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-26T00:00:25.146171+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ninjal.ac.jp/ninjal_wp/wp-content/uploads/2022/01/top_OGP.jpg + source_url: http://www.ninjal.ac.jp/info/aboutus/library + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-26T00:00:25.146171+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-TAC-L-THUTL.yaml b/data/custodian/JP-13-TAC-L-THUTL.yaml index 97418b1178..57b615319f 100644 --- a/data/custodian/JP-13-TAC-L-THUTL.yaml +++ b/data/custodian/JP-13-TAC-L-THUTL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAC-L-THUTL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAC-L-THUTL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAC-L-THUTL ghcid_numeric: 14207913423546401956 valid_from: '2025-12-06T23:38:59.993239+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Healthcare University Tachikawa Library @@ -151,3 +152,20 @@ location: geonames_id: 11611487 geonames_name: Tachikawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:00:35.202949+00:00' + source_url: https://www.thcu.ac.jp/facilities/library + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://thcu.ac.jp/img/asset/ogp.png + source_url: https://www.thcu.ac.jp/facilities/library + css_selector: '[document] > html.other > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-26T00:00:35.202949+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAI-L-ILCSLNDL.yaml b/data/custodian/JP-13-TAI-L-ILCSLNDL.yaml index b84ed934e6..1aa56d27fb 100644 --- a/data/custodian/JP-13-TAI-L-ILCSLNDL.yaml +++ b/data/custodian/JP-13-TAI-L-ILCSLNDL.yaml @@ -152,3 +152,39 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:22:08.383169+00:00' + source_url: https://www.kodomo.go.jp/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: '[inline-svg]' + source_url: https://www.kodomo.go.jp/index.html + css_selector: '#__nuxt > div.layouts-global.is-light > header.global-header > + div.base-layout-row.is-hidden-mobile > div.global-header-left > a.router-link-active.router-link-exact-active + > h1.base-heading.is-image > svg.ui-parts-logo-service.global-header-brand' + retrieved_on: '2025-12-26T00:22:08.383169+00:00' + extraction_method: crawl4ai_svg_detection + detection_confidence: high + is_inline_svg: true + aria_label: '' + - claim_type: favicon_url + claim_value: https://www.kodomo.go.jp/assets/ilcl/favicon/favicon.ico + source_url: https://www.kodomo.go.jp/index.html + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-26T00:22:08.383169+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kodomo.go.jp/assets/ilcl/og.png + source_url: https://www.kodomo.go.jp/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-26T00:22:08.383169+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-TAI-L-ITEL.yaml b/data/custodian/JP-13-TAI-L-ITEL.yaml index 9c8c214c1a..427db7dec7 100644 --- a/data/custodian/JP-13-TAI-L-ITEL.yaml +++ b/data/custodian/JP-13-TAI-L-ITEL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-ITEL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-ITEL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-ITEL ghcid_numeric: 9773096727714678097 valid_from: '2025-12-06T23:38:59.849548+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Institute of Transportation Economics Library @@ -151,3 +152,28 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:22:29.931907+00:00' + source_url: https://www.itej.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.itej.or.jp/cp/wp-content/themes/itej/image/common/favicon.ico + source_url: https://www.itej.or.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T00:22:29.931907+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.itej.or.jp/cp/wp-content/themes/itej/image/common/ogp_image-top.png + source_url: https://www.itej.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-26T00:22:29.931907+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-TAI-L-JA.yaml b/data/custodian/JP-13-TAI-L-JA.yaml index c70d4b6d29..5a0cfe9067 100644 --- a/data/custodian/JP-13-TAI-L-JA.yaml +++ b/data/custodian/JP-13-TAI-L-JA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-JA - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-JA valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-JA ghcid_numeric: 17129158918314684917 valid_from: '2025-12-06T23:38:58.900155+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Japan Academy @@ -151,3 +152,22 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:38:01.264821+00:00' + source_url: http://www.japan-acad.go.jp/japanese/about/material.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.japan-acad.go.jp/common/images/header-logo.jpg + source_url: http://www.japan-acad.go.jp/japanese/about/material.html + css_selector: '#hd > header > div.headerarea > h1.fleft > a > img' + retrieved_on: '2025-12-26T00:38:01.264821+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日本学士院 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-TAI-L-NRICPT.yaml b/data/custodian/JP-13-TAI-L-NRICPT.yaml index fbed8473ea..e76164ffc3 100644 --- a/data/custodian/JP-13-TAI-L-NRICPT.yaml +++ b/data/custodian/JP-13-TAI-L-NRICPT.yaml @@ -341,3 +341,30 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/fLj519Wnw-E/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:38:19.393561+00:00' + source_url: http://www.tobunken.go.jp/~joho/japanese/library/library.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tobunken.go.jp/joho/japanese/library/image/logo-blue.svg + source_url: http://www.tobunken.go.jp/~joho/japanese/library/library.html + css_selector: '#logo-sp > a > img' + retrieved_on: '2025-12-26T00:38:19.393561+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 資料閲覧室サイトのロゴ + - claim_type: favicon_url + claim_value: https://www.tobunken.go.jp/image/ico/apple-touch-icon-180x180.png + source_url: http://www.tobunken.go.jp/~joho/japanese/library/library.html + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-26T00:38:19.393561+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 13 diff --git a/data/custodian/JP-13-TAI-L-RICTNM.yaml b/data/custodian/JP-13-TAI-L-RICTNM.yaml index 00cf96739a..d2fc625b2a 100644 --- a/data/custodian/JP-13-TAI-L-RICTNM.yaml +++ b/data/custodian/JP-13-TAI-L-RICTNM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-RICTNM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-RICTNM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-RICTNM ghcid_numeric: 25818348829309832 valid_from: '2025-12-06T23:38:58.087783+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Research and Information Center of Tokyo National Museum @@ -151,3 +152,28 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:38:40.997803+00:00' + source_url: https://www.tnm.jp/modules/r_free_page/index.php?id=138&lang=ja + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tnm.jp/themes/tnm2022/image/apple-touch-icon.png + source_url: https://www.tnm.jp/modules/r_free_page/index.php?id=138&lang=ja + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-26T00:38:40.997803+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tnm.jp/jp/exhibition/images/tmp/ogp/TNM_ogp.jpg + source_url: https://www.tnm.jp/modules/r_free_page/index.php?id=138&lang=ja + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-26T00:38:40.997803+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-TAI-L-RLNMWAT.yaml b/data/custodian/JP-13-TAI-L-RLNMWAT.yaml index 0e9cd09762..e4185da4ac 100644 --- a/data/custodian/JP-13-TAI-L-RLNMWAT.yaml +++ b/data/custodian/JP-13-TAI-L-RLNMWAT.yaml @@ -1736,3 +1736,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/5iily3Fg_8w/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:54:12.233568+00:00' + source_url: http://www.nmwa.go.jp/jp/education/library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.nmwa.go.jp/common2/img/common/favicon.ico + source_url: http://www.nmwa.go.jp/jp/education/library.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T00:54:12.233568+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.nmwa.go.jp/jp/img/thumb_facebook.png + source_url: http://www.nmwa.go.jp/jp/education/library.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-26T00:54:12.233568+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-TAI-L-TBKML.yaml b/data/custodian/JP-13-TAI-L-TBKML.yaml index 1f177478a3..07ed5ff4eb 100644 --- a/data/custodian/JP-13-TAI-L-TBKML.yaml +++ b/data/custodian/JP-13-TAI-L-TBKML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-TBKML - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-TBKML valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-TBKML ghcid_numeric: 3280679913192073616 valid_from: '2025-12-06T23:38:58.336351+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Bunka Kaikan Music Library @@ -151,3 +152,22 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:54:20.479966+00:00' + source_url: http://www.t-bunka.jp/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.t-bunka.jp/common/img/common/logo.jpg + source_url: http://www.t-bunka.jp/library/index.html + css_selector: '#header > h1 > a > img.headerH' + retrieved_on: '2025-12-26T00:54:20.479966+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東京文化会館 | Tokyo Bunka Kaikan + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-TAI-L-TL-taitokuritsuishihama_library.yaml b/data/custodian/JP-13-TAI-L-TL-taitokuritsuishihama_library.yaml index d8fda55c92..392480bd2b 100644 --- a/data/custodian/JP-13-TAI-L-TL-taitokuritsuishihama_library.yaml +++ b/data/custodian/JP-13-TAI-L-TL-taitokuritsuishihama_library.yaml @@ -152,3 +152,30 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:54:29.020160+00:00' + source_url: https://www.city.taito.lg.jp/library/lib-annai/ishihama/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.taito.lg.jp/images/lib_h_logo.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/ishihama/index.html + css_selector: '#header_logo > a > img' + retrieved_on: '2025-12-26T00:54:29.020160+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 台東区 + - claim_type: favicon_url + claim_value: https://www.city.taito.lg.jp/images/apple-touch-icon.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/ishihama/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T00:54:29.020160+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-TAI-L-TL-taitokuritsunegishi_library.yaml b/data/custodian/JP-13-TAI-L-TL-taitokuritsunegishi_library.yaml index c9743cb150..4f1f4a62f0 100644 --- a/data/custodian/JP-13-TAI-L-TL-taitokuritsunegishi_library.yaml +++ b/data/custodian/JP-13-TAI-L-TL-taitokuritsunegishi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-TL-taitokuritsunegishi_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-TL-taitokuritsunegishi_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-TL-taitokuritsunegishi_library ghcid_numeric: 17790133257439022131 valid_from: '2025-12-06T23:38:43.193377+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAITOKURITSUNEGISHI Library @@ -151,3 +152,30 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:54:35.369518+00:00' + source_url: https://www.city.taito.lg.jp/library/lib-annai/negishi/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.taito.lg.jp/images/lib_h_logo.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/negishi/index.html + css_selector: '#header_logo > a > img' + retrieved_on: '2025-12-26T00:54:35.369518+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 台東区 + - claim_type: favicon_url + claim_value: https://www.city.taito.lg.jp/images/apple-touch-icon.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/negishi/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T00:54:35.369518+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-TAI-L-TL.yaml b/data/custodian/JP-13-TAI-L-TL.yaml index 7c259b13c6..7bc7615b6a 100644 --- a/data/custodian/JP-13-TAI-L-TL.yaml +++ b/data/custodian/JP-13-TAI-L-TL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-TL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-TL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-TL ghcid_numeric: 17188375486791999739 valid_from: '2025-12-06T23:38:43.188612+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAITOKURITSUCHUO Library @@ -151,3 +152,30 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:54:41.465636+00:00' + source_url: https://www.city.taito.lg.jp/library/lib-annai/chuo/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.taito.lg.jp/images/lib_h_logo.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/chuo/index.html + css_selector: '#header_logo > a > img' + retrieved_on: '2025-12-26T00:54:41.465636+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 台東区 + - claim_type: favicon_url + claim_value: https://www.city.taito.lg.jp/images/apple-touch-icon.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/chuo/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T00:54:41.465636+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-TAI-L-TLA.yaml b/data/custodian/JP-13-TAI-L-TLA.yaml index 75cc7cb638..7227d2d4aa 100644 --- a/data/custodian/JP-13-TAI-L-TLA.yaml +++ b/data/custodian/JP-13-TAI-L-TLA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-TLA - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-TLA valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-TLA ghcid_numeric: 5177949797421546386 valid_from: '2025-12-06T23:38:43.196216+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAITOKURITSUCHUO Library ASAKUSABASHIBUNSHITSU @@ -151,3 +152,30 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:54:47.750836+00:00' + source_url: https://www.city.taito.lg.jp/library/lib-annai/asakusabashi/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.taito.lg.jp/images/lib_h_logo.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/asakusabashi/index.html + css_selector: '#header_logo > a > img' + retrieved_on: '2025-12-26T00:54:47.750836+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 台東区 + - claim_type: favicon_url + claim_value: https://www.city.taito.lg.jp/images/apple-touch-icon.png + source_url: https://www.city.taito.lg.jp/library/lib-annai/asakusabashi/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T00:54:47.750836+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-TAI-L-TUAUUL.yaml b/data/custodian/JP-13-TAI-L-TUAUUL.yaml index 6d2dc3b27a..966568cf13 100644 --- a/data/custodian/JP-13-TAI-L-TUAUUL.yaml +++ b/data/custodian/JP-13-TAI-L-TUAUUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-L-TUAUUL - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-L-TUAUUL valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-L-TUAUUL ghcid_numeric: 4215762235681227521 valid_from: '2025-12-06T23:38:53.359698+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo University of the Arts University Ueno Library @@ -204,3 +205,22 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:54:56.045125+00:00' + source_url: http://www.lib.geidai.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.geidai.ac.jp/static/icon_512.png + source_url: http://www.lib.geidai.ac.jp + css_selector: '[document] > html.pc.chrome > head > link:nth-of-type(7)' + retrieved_on: '2025-12-26T00:54:56.045125+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 512x512 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-TAI-M-IAINICHTNM.yaml b/data/custodian/JP-13-TAI-M-IAINICHTNM.yaml index 70ab57ccc8..eb70fce301 100644 --- a/data/custodian/JP-13-TAI-M-IAINICHTNM.yaml +++ b/data/custodian/JP-13-TAI-M-IAINICHTNM.yaml @@ -155,3 +155,28 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:55:27.230452+00:00' + source_url: https://www.tnm.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tnm.jp/themes/tnm2022/image/apple-touch-icon.png + source_url: https://www.tnm.jp + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-26T00:55:27.230452+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tnm.jp/jp/exhibition/images/tmp/ogp/TNM_ogp.jpg + source_url: https://www.tnm.jp + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-26T00:55:27.230452+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-TAI-M-MLI.yaml b/data/custodian/JP-13-TAI-M-MLI.yaml index e87d79555c..95ac01f615 100644 --- a/data/custodian/JP-13-TAI-M-MLI.yaml +++ b/data/custodian/JP-13-TAI-M-MLI.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-M-MLI - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-M-MLI valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-M-MLI ghcid_numeric: 759615220902283115 valid_from: '2025-12-06T23:38:33.215853+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MUSEUM OF LEATHER INDUSTRY @@ -151,3 +152,23 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:55:37.595114+00:00' + source_url: https://www.taito-sangyo.jp/05-kensyu/center_museum.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://taito-sangyo.jp/assets/img/logo.png + source_url: https://www.taito-sangyo.jp/05-kensyu/center_museum.html + css_selector: '[document] > html > body.is-pageTopHide.is-scrollUp > header.l-header + > div.inner > h1.l-header__logo > a.hasImg.is-loaded > img' + retrieved_on: '2025-12-26T00:55:37.595114+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-TAI-M-NMNS.yaml b/data/custodian/JP-13-TAI-M-NMNS.yaml index da02e843d5..5c6f3263f1 100644 --- a/data/custodian/JP-13-TAI-M-NMNS.yaml +++ b/data/custodian/JP-13-TAI-M-NMNS.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-M-NMNS - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-M-NMNS valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-M-NMNS ghcid_numeric: 5294571433937412280 valid_from: '2025-12-06T23:38:33.213545+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NATIONAL MUSEUM OF NATURE AND SCIENCE @@ -151,3 +152,28 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:56:04.531978+00:00' + source_url: https://www.kahaku.go.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kahaku.go.jp/apple-touch-icon.png + source_url: https://www.kahaku.go.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T00:56:04.531978+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kahaku.go.jp/ogp.png + source_url: https://www.kahaku.go.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-26T00:56:04.531978+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-TAI-M-TMAM.yaml b/data/custodian/JP-13-TAI-M-TMAM.yaml index eeab1e8af0..e01fe7b7a6 100644 --- a/data/custodian/JP-13-TAI-M-TMAM.yaml +++ b/data/custodian/JP-13-TAI-M-TMAM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-M-TMAM - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-M-TMAM valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-M-TMAM ghcid_numeric: 4396059256998395168 valid_from: '2025-12-06T23:38:33.192044+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOKYO METROPOLITAN ART MUSEUM @@ -151,3 +152,37 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:56:21.557973+00:00' + source_url: https://www.tobikan.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tobikan.jp/common/img/logo.png + source_url: https://www.tobikan.jp + css_selector: '#header > div.header-line > div.container.pv10:nth-of-type(2) > + h1.header-logo > a > img' + retrieved_on: '2025-12-26T00:56:21.557973+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東京都美術館 + - claim_type: favicon_url + claim_value: https://www.tobikan.jp/android-icon.png + source_url: https://www.tobikan.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T00:56:21.557973+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 152x152 + - claim_type: og_image_url + claim_value: https://tobikan.jp/common/img/icon_social_snap.png + source_url: https://www.tobikan.jp + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-26T00:56:21.557973+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAI-M-URM.yaml b/data/custodian/JP-13-TAI-M-URM.yaml index 93447fb651..18249e59c8 100644 --- a/data/custodian/JP-13-TAI-M-URM.yaml +++ b/data/custodian/JP-13-TAI-M-URM.yaml @@ -1194,3 +1194,20 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/pGmdQ45m_Gc/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:56:28.474701+00:00' + source_url: https://www.ueno-mori.org + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.ueno-mori.org/mod/homes/ogpphoto.jpg + source_url: https://www.ueno-mori.org + css_selector: '[document] > html.js.desktop > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-26T00:56:28.474701+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAI-M-YTMH.yaml b/data/custodian/JP-13-TAI-M-YTMH.yaml index 49a154f547..fd20d1d540 100644 --- a/data/custodian/JP-13-TAI-M-YTMH.yaml +++ b/data/custodian/JP-13-TAI-M-YTMH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAI-M-YTMH - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAI-M-YTMH valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAI-M-YTMH ghcid_numeric: 456006813127444200 valid_from: '2025-12-06T23:38:33.195110+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: YOKOYAMA-TAIKAN MEMORIAL HALL @@ -151,3 +152,23 @@ location: geonames_id: 11790369 geonames_name: Taito feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-26T00:56:53.806468+00:00' + source_url: http://taikan.tokyo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://taikan.tokyo/wp/wp-content/themes/ytk/assets/img/favicon.png + source_url: http://taikan.tokyo + css_selector: '[document] > html.wf-source-han-sans-japanese-n7-active.wf-source-han-sans-japanese-n4-active + > head > link:nth-of-type(5)' + retrieved_on: '2025-12-26T00:56:53.806468+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-TAK-L-TL-takaokashiritsufukuoka_library.yaml b/data/custodian/JP-13-TAK-L-TL-takaokashiritsufukuoka_library.yaml index 383a0764ea..fc3174e564 100644 --- a/data/custodian/JP-13-TAK-L-TL-takaokashiritsufukuoka_library.yaml +++ b/data/custodian/JP-13-TAK-L-TL-takaokashiritsufukuoka_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-L-TL-takaokashiritsufukuoka_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-L-TL-takaokashiritsufukuoka_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-L-TL-takaokashiritsufukuoka_library ghcid_numeric: 17338200293911298541 valid_from: '2025-12-06T23:38:44.424774+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAOKASHIRITSUFUKUOKA Library @@ -151,3 +152,36 @@ location: geonames_id: 1851032 geonames_name: Takaoka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:00:06.465348+00:00' + source_url: https://www.city.takaoka.toyama.jp/library/8/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/s-library/img_common/header_logo.png + source_url: https://www.city.takaoka.toyama.jp/library/8/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-26T01:00:06.465348+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 高岡市立図書館 + - claim_type: favicon_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.takaoka.toyama.jp/library/8/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T01:00:06.465348+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.takaoka.toyama.jp/library/8/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-26T01:00:06.465348+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAK-L-TL-takaokashiritsufushiki_library.yaml b/data/custodian/JP-13-TAK-L-TL-takaokashiritsufushiki_library.yaml index 453eafc7b6..6a02562dc2 100644 --- a/data/custodian/JP-13-TAK-L-TL-takaokashiritsufushiki_library.yaml +++ b/data/custodian/JP-13-TAK-L-TL-takaokashiritsufushiki_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-L-TL-takaokashiritsufushiki_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-L-TL-takaokashiritsufushiki_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-L-TL-takaokashiritsufushiki_library ghcid_numeric: 7347111181245033197 valid_from: '2025-12-06T23:38:44.422515+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAOKASHIRITSUFUSHIKI Library @@ -151,3 +152,36 @@ location: geonames_id: 1851032 geonames_name: Takaoka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:00:13.913875+00:00' + source_url: https://www.city.takaoka.toyama.jp/library/7/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/s-library/img_common/header_logo.png + source_url: https://www.city.takaoka.toyama.jp/library/7/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-26T01:00:13.913875+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 高岡市立図書館 + - claim_type: favicon_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.takaoka.toyama.jp/library/7/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T01:00:13.913875+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.takaoka.toyama.jp/library/7/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-26T01:00:13.913875+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAK-L-TL-takaokashiritsunakada_library.yaml b/data/custodian/JP-13-TAK-L-TL-takaokashiritsunakada_library.yaml index 07f17546e4..35a9e33859 100644 --- a/data/custodian/JP-13-TAK-L-TL-takaokashiritsunakada_library.yaml +++ b/data/custodian/JP-13-TAK-L-TL-takaokashiritsunakada_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-L-TL-takaokashiritsunakada_library - valid_from: "2025-12-10T09:44:12Z" + valid_from: '2025-12-10T09:44:12Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-L-TL-takaokashiritsunakada_library valid_from: null - valid_to: "2025-12-10T09:44:12Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:12Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-L-TL-takaokashiritsunakada_library ghcid_numeric: 16130147011297313471 valid_from: '2025-12-06T23:38:44.417986+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAOKASHIRITSUNAKADA Library @@ -151,3 +152,36 @@ location: geonames_id: 1851032 geonames_name: Takaoka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:00:21.439721+00:00' + source_url: https://www.city.takaoka.toyama.jp/library/6/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/s-library/img_common/header_logo.png + source_url: https://www.city.takaoka.toyama.jp/library/6/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-26T01:00:21.439721+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 高岡市立図書館 + - claim_type: favicon_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.takaoka.toyama.jp/library/6/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T01:00:21.439721+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.takaoka.toyama.jp/library/6/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-26T01:00:21.439721+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAK-L-TL-takaokashiritsutoide_library.yaml b/data/custodian/JP-13-TAK-L-TL-takaokashiritsutoide_library.yaml index 21a07daf4f..d7e170420e 100644 --- a/data/custodian/JP-13-TAK-L-TL-takaokashiritsutoide_library.yaml +++ b/data/custodian/JP-13-TAK-L-TL-takaokashiritsutoide_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-L-TL-takaokashiritsutoide_library - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-L-TL-takaokashiritsutoide_library valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-L-TL-takaokashiritsutoide_library ghcid_numeric: 4202901821150873957 valid_from: '2025-12-06T23:38:44.420269+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAOKASHIRITSUTOIDE Library @@ -151,3 +152,36 @@ location: geonames_id: 1851032 geonames_name: Takaoka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:00:28.950222+00:00' + source_url: https://www.city.takaoka.toyama.jp/library/3/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/s-library/img_common/header_logo.png + source_url: https://www.city.takaoka.toyama.jp/library/3/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-26T01:00:28.950222+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 高岡市立図書館 + - claim_type: favicon_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.takaoka.toyama.jp/library/3/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T01:00:28.950222+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.takaoka.toyama.jp/library/3/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-26T01:00:28.950222+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAK-L-TL.yaml b/data/custodian/JP-13-TAK-L-TL.yaml index 566553ccf7..511f0d9843 100644 --- a/data/custodian/JP-13-TAK-L-TL.yaml +++ b/data/custodian/JP-13-TAK-L-TL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-L-TL - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-L-TL valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-L-TL ghcid_numeric: 179505174549660129 valid_from: '2025-12-06T23:38:44.415460+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAKAOKASHIRITSUCHUO Library @@ -151,3 +152,36 @@ location: geonames_id: 1851032 geonames_name: Takaoka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:00:36.875518+00:00' + source_url: https://www.city.takaoka.toyama.jp/library/5/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/s-library/img_common/header_logo.png + source_url: https://www.city.takaoka.toyama.jp/library/5/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-26T01:00:36.875518+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 高岡市立図書館 + - claim_type: favicon_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.takaoka.toyama.jp/library/5/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-26T01:00:36.875518+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.takaoka.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.takaoka.toyama.jp/library/5/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-26T01:00:36.875518+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAK-L-UTADL.yaml b/data/custodian/JP-13-TAK-L-UTADL.yaml index 9278c49d94..970802744d 100644 --- a/data/custodian/JP-13-TAK-L-UTADL.yaml +++ b/data/custodian/JP-13-TAK-L-UTADL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-L-UTADL - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-L-UTADL valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-L-UTADL ghcid_numeric: 4971662745217485228 valid_from: '2025-12-06T23:38:53.451649+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 Toyama Art and Design Library @@ -204,3 +205,22 @@ location: geonames_id: 1851032 geonames_name: Takaoka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:00:45.044391+00:00' + source_url: http://www.lib.u-toyama.ac.jp/art/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.u-toyama.ac.jp/wp/wp-content/themes/library/assets/favicon/apple-touch-icon.png + source_url: http://www.lib.u-toyama.ac.jp/art/index.html + css_selector: '[document] > html.no-js.no-svg > head > link' + retrieved_on: '2025-12-26T01:00:45.044391+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-TAK-M-AMAGTKHSTP.yaml b/data/custodian/JP-13-TAK-M-AMAGTKHSTP.yaml index b0fcf50c41..c96a827853 100644 --- a/data/custodian/JP-13-TAK-M-AMAGTKHSTP.yaml +++ b/data/custodian/JP-13-TAK-M-AMAGTKHSTP.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-M-AMAGTKHSTP - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-M-AMAGTKHSTP valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-M-AMAGTKHSTP ghcid_numeric: 674662263572123776 valid_from: '2025-12-06T23:38:34.681117+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: AOI MEMORIAL ART GALLERY TAKAOKA KOGEI HIGH SCHOOL TOYAMA PREFECTURE @@ -151,3 +152,22 @@ location: geonames_id: 1851032 geonames_name: Takaoka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:00:55.849381+00:00' + source_url: http://kogei-h.el.tym.ed.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kogei-h.tym.ed.jp/wp-content/uploads/2016/11/cropped-school_mark_512-512-180x180.jpg + source_url: http://kogei-h.el.tym.ed.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-26T01:00:55.849381+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-TAK-M-FFFHAG.yaml b/data/custodian/JP-13-TAK-M-FFFHAG.yaml index bd25febba3..699176d743 100644 --- a/data/custodian/JP-13-TAK-M-FFFHAG.yaml +++ b/data/custodian/JP-13-TAK-M-FFFHAG.yaml @@ -283,3 +283,36 @@ location: postal_code: 933-0056 street_address: NAKAGAWA, Takaoka Shi, Toyama Ken, 933-0056 normalization_timestamp: '2025-12-09T12:22:29.983384+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:01:07.768854+00:00' + source_url: https://fujiko-artgallery.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://fujiko-artgallery.jp/img/common/logo.png + source_url: https://fujiko-artgallery.jp + css_selector: '#logo > a > img' + retrieved_on: '2025-12-26T01:01:07.768854+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 高岡市藤子・F・不二雄ふるさとギャラリー + - claim_type: favicon_url + claim_value: https://fujiko-artgallery.jp/img/favicon.ico + source_url: https://fujiko-artgallery.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T01:01:07.768854+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://fujiko-artgallery.jp/img/sns.png + source_url: https://fujiko-artgallery.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-26T01:01:07.768854+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-TAK-M-TAM.yaml b/data/custodian/JP-13-TAK-M-TAM.yaml index df3337a4fe..9d7366cba6 100644 --- a/data/custodian/JP-13-TAK-M-TAM.yaml +++ b/data/custodian/JP-13-TAK-M-TAM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAK-M-TAM - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAK-M-TAM valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAK-M-TAM ghcid_numeric: 3144587597285561967 valid_from: '2025-12-06T23:38:34.673756+00:00' @@ -80,7 +81,8 @@ provenance: extraction_method: 'Created from CH-Annotator file: japan_complete_ch_annotator.yaml' confidence_score: 0.98 notes: - - Removed incorrect wikidata_enrichment on 2025-12-08T08:18:48.779731+00:00. Re-enrichment required with proper matching. + - Removed incorrect wikidata_enrichment on 2025-12-08T08:18:48.779731+00:00. Re-enrichment + required with proper matching. - Canonical location normalized on 2025-12-09T12:22:30Z ch_annotator: convention_id: ch_annotator-v1_7_0 @@ -109,8 +111,8 @@ 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: TAKAOKA ART MUSEUM @@ -220,7 +222,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) wikidata_instance_of: *id005 wikidata_location: country: &id006 @@ -280,3 +283,28 @@ location: postal_code: 933-0056 street_address: NAKAGAWA, Takaoka Shi, Toyama Ken, 933-0056 normalization_timestamp: '2025-12-09T12:22:30.072151+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:01:26.127705+00:00' + source_url: https://www.e-tam.info + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.e-tam.info/images/favicon.png + source_url: https://www.e-tam.info + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T01:01:26.127705+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.e-tam.info/images/no-images.jpg + source_url: https://www.e-tam.info + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-26T01:01:26.127705+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-TAM-L-KL.yaml b/data/custodian/JP-13-TAM-L-KL.yaml index d9661e8aa5..7570535733 100644 --- a/data/custodian/JP-13-TAM-L-KL.yaml +++ b/data/custodian/JP-13-TAM-L-KL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-KL - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-KL valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-KL ghcid_numeric: 6755030136860546648 valid_from: '2025-12-06T23:38:55.399036+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: KEISENJOGAKUENDAIGAKU Library @@ -215,3 +216,37 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:01:56.549386+00:00' + source_url: http://www.keisen.ac.jp/institution/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.keisen.ac.jp/assets/img/common/main_logo.svg + source_url: http://www.keisen.ac.jp/institution/library + css_selector: '#header > div.headerMiddle.inner:nth-of-type(2) > h1.mainLogo > + a > img' + retrieved_on: '2025-12-26T01:01:56.549386+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 恵泉女学園大学 + - claim_type: favicon_url + claim_value: http://www.keisen.ac.jp/favicon.ico + source_url: http://www.keisen.ac.jp/institution/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-26T01:01:56.549386+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.keisen.ac.jp/images/ogp/default.jpg + source_url: http://www.keisen.ac.jp/institution/library + css_selector: '[document] > html > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-26T01:01:56.549386+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-TAM-L-KLJ.yaml b/data/custodian/JP-13-TAM-L-KLJ.yaml index 39970ed0c5..604ebcc217 100644 --- a/data/custodian/JP-13-TAM-L-KLJ.yaml +++ b/data/custodian/JP-13-TAM-L-KLJ.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-KLJ - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-KLJ valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-KLJ ghcid_numeric: 3507992790720166576 valid_from: '2025-12-06T23:38:54.896645+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: KOKUSHIKANDAIGAKUTAMA Library ・JOHOMEDEIASENTA @@ -204,3 +205,28 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:03.279145+00:00' + source_url: https://www.kokushikan.ac.jp/education/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kokushikan.ac.jp/favicon.ico + source_url: https://www.kokushikan.ac.jp/education/library + css_selector: '[document] > html.is-scroll.is-loaded > head > link:nth-of-type(2)' + retrieved_on: '2025-12-26T01:02:03.279145+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kokushikan.ac.jp/assets/img/common/ogp_image.jpg + source_url: https://www.kokushikan.ac.jp/education/library + css_selector: '[document] > html.is-scroll.is-loaded > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-26T01:02:03.279145+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-TAM-L-T.yaml b/data/custodian/JP-13-TAM-L-T.yaml index e8062ec3ea..a2b79b3351 100644 --- a/data/custodian/JP-13-TAM-L-T.yaml +++ b/data/custodian/JP-13-TAM-L-T.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-T - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-T valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-T ghcid_numeric: 9298495610496457384 valid_from: '2025-12-06T23:38:43.931154+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAMASHIGYOSEISHIRYOSHITSU @@ -151,3 +152,20 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:13.060021+00:00' + source_url: https://www.library.tama.tokyo.jp/contents?12&pid=343 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.tama.tokyo.jp/images/ogimage.png + source_url: https://www.library.tama.tokyo.jp/contents?12&pid=343 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T01:02:13.060021+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAM-L-TCCL.yaml b/data/custodian/JP-13-TAM-L-TCCL.yaml index 23994966bc..44cccb4227 100644 --- a/data/custodian/JP-13-TAM-L-TCCL.yaml +++ b/data/custodian/JP-13-TAM-L-TCCL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-TCCL - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-TCCL valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-TCCL ghcid_numeric: 17104641203600538395 valid_from: '2025-12-06T23:38:43.917168+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tama City Central Library @@ -151,3 +152,20 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:19.689612+00:00' + source_url: https://www.library.tama.tokyo.jp/index?6 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.tama.tokyo.jp/images/ogimage.png + source_url: https://www.library.tama.tokyo.jp/index?6 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T01:02:19.689612+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAM-L-TL-tamashiritsuhijirigaoka_library.yaml b/data/custodian/JP-13-TAM-L-TL-tamashiritsuhijirigaoka_library.yaml index 35b7ced6ae..17f863edfb 100644 --- a/data/custodian/JP-13-TAM-L-TL-tamashiritsuhijirigaoka_library.yaml +++ b/data/custodian/JP-13-TAM-L-TL-tamashiritsuhijirigaoka_library.yaml @@ -152,3 +152,20 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:25.982496+00:00' + source_url: https://www.library.tama.tokyo.jp/contents?10&pid=337 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.tama.tokyo.jp/images/ogimage.png + source_url: https://www.library.tama.tokyo.jp/contents?10&pid=337 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T01:02:25.982496+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAM-L-TL-tamashiritsukarakida_library.yaml b/data/custodian/JP-13-TAM-L-TL-tamashiritsukarakida_library.yaml index f122721f2f..ff9688fe6a 100644 --- a/data/custodian/JP-13-TAM-L-TL-tamashiritsukarakida_library.yaml +++ b/data/custodian/JP-13-TAM-L-TL-tamashiritsukarakida_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-TL-tamashiritsukarakida_library - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-TL-tamashiritsukarakida_library valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-TL-tamashiritsukarakida_library ghcid_numeric: 18235409836794372978 valid_from: '2025-12-06T23:38:48.617089+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAMASHIRITSUKARAKIDA Library @@ -151,3 +152,20 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:32.462194+00:00' + source_url: https://www.library.tama.tokyo.jp/contents;jsessionid=9C40C892477779A1C9DDF78A8B390787?0&pid=341 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.tama.tokyo.jp/images/ogimage.png + source_url: https://www.library.tama.tokyo.jp/contents;jsessionid=9C40C892477779A1C9DDF78A8B390787?0&pid=341 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T01:02:32.462194+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAM-L-TL-tamashiritsunagayama_library.yaml b/data/custodian/JP-13-TAM-L-TL-tamashiritsunagayama_library.yaml index 1801593251..799ef8943c 100644 --- a/data/custodian/JP-13-TAM-L-TL-tamashiritsunagayama_library.yaml +++ b/data/custodian/JP-13-TAM-L-TL-tamashiritsunagayama_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-TL-tamashiritsunagayama_library - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-TL-tamashiritsunagayama_library valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-TL-tamashiritsunagayama_library ghcid_numeric: 13650731474907999477 valid_from: '2025-12-06T23:38:43.928892+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAMASHIRITSUNAGAYAMA Library @@ -151,3 +152,20 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:38.990095+00:00' + source_url: https://www.library.tama.tokyo.jp/contents?11&pid=339 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.tama.tokyo.jp/images/ogimage.png + source_url: https://www.library.tama.tokyo.jp/contents?11&pid=339 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T01:02:38.990095+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAM-L-TL-tamashiritsusekido_library.yaml b/data/custodian/JP-13-TAM-L-TL-tamashiritsusekido_library.yaml index ae32fd89b9..5b0534abec 100644 --- a/data/custodian/JP-13-TAM-L-TL-tamashiritsusekido_library.yaml +++ b/data/custodian/JP-13-TAM-L-TL-tamashiritsusekido_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-TL-tamashiritsusekido_library - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-TL-tamashiritsusekido_library valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-TL-tamashiritsusekido_library ghcid_numeric: 17791696175084366492 valid_from: '2025-12-06T23:38:43.924348+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAMASHIRITSUSEKIDO Library @@ -151,3 +152,20 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:45.163445+00:00' + source_url: https://www.library.tama.tokyo.jp/contents?9&pid=335 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.tama.tokyo.jp/images/ogimage.png + source_url: https://www.library.tama.tokyo.jp/contents?9&pid=335 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T01:02:45.163445+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-TAM-L-TL-tamashiritsutoyogaoka_library.yaml b/data/custodian/JP-13-TAM-L-TL-tamashiritsutoyogaoka_library.yaml index 2f242ed5c7..0227933262 100644 --- a/data/custodian/JP-13-TAM-L-TL-tamashiritsutoyogaoka_library.yaml +++ b/data/custodian/JP-13-TAM-L-TL-tamashiritsutoyogaoka_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-TAM-L-TL-tamashiritsutoyogaoka_library - valid_from: "2025-12-10T09:44:13Z" + valid_from: '2025-12-10T09:44:13Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-TAM-L-TL-tamashiritsutoyogaoka_library valid_from: null - valid_to: "2025-12-10T09:44:13Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:13Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-TAM-L-TL-tamashiritsutoyogaoka_library ghcid_numeric: 15347009190247122022 valid_from: '2025-12-06T23:38:43.921619+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TAMASHIRITSUTOYOGAOKA Library @@ -151,3 +152,20 @@ location: geonames_id: 6822129 geonames_name: Tama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-26T01:02:51.359829+00:00' + source_url: https://www.library.tama.tokyo.jp/contents?8&pid=333 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.tama.tokyo.jp/images/ogimage.png + source_url: https://www.library.tama.tokyo.jp/contents?8&pid=333 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-26T01:02:51.359829+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0