diff --git a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json index a49531a8ae..3059e7790c 100644 --- a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json +++ b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json @@ -5946,7 +5946,567 @@ "JP-01-SAP-L-KLH.yaml", "JP-01-SAP-L-LDICHPUSP.yaml", "JP-01-SAP-L-LFEGSEHU.yaml", - "JP-01-SAP-L-LFEHU.yaml" + "JP-01-SAP-L-LFEHU.yaml", + "JP-01-SAP-L-LFHSHU.yaml", + "JP-01-SAP-L-LFLHU.yaml", + "JP-01-SAP-L-LFPSHU.yaml", + "JP-01-SAP-L-LFSGSSSSHU.yaml", + "JP-01-SAP-L-LGSAHU.yaml", + "JP-01-SAP-L-LGSEHU.yaml", + "JP-01-SAP-L-LGSVMHU.yaml", + "JP-01-SAP-L-LIAAHROITR.yaml", + "JP-01-SAP-L-LILTSHU.yaml", + "JP-01-SAP-L-LNCHU.yaml", + "JP-01-SAP-L-LSDHU.yaml", + "JP-01-SAP-L-LSERCHU.yaml", + "JP-01-SAP-L-LSMHU.yaml", + "JP-01-SAP-L-MSBCLMSRIS.yaml", + "JP-01-SAP-L-N.yaml", + "JP-01-SAP-L-NIAISTHC.yaml", + "JP-01-SAP-L-O.yaml", + "JP-01-SAP-L-OHAL.yaml", + "JP-01-SAP-L-S-sapporoshishichokakushogaishajohosenta.yaml", + "JP-01-SAP-L-S-shingyorengyorentoshoshiryoshitsu.yaml", + "JP-01-SAP-L-S.yaml", + "JP-01-SAP-L-SACRS.yaml", + "JP-01-SAP-L-SAL-sapporo_akebono_library.yaml", + "JP-01-SAP-L-SAL.yaml", + "JP-01-SAP-L-SCAL.yaml", + "JP-01-SAP-L-SCLSCU.yaml", + "JP-01-SAP-L-SET.yaml", + "JP-01-SAP-L-SGULS.yaml", + "JP-01-SAP-L-SHL.yaml", + "JP-01-SAP-L-SKL.yaml", + "JP-01-SAP-L-SL.yaml", + "JP-01-SAP-L-SMCL.yaml", + "JP-01-SAP-L-SML.yaml", + "JP-01-SAP-L-SMLIC.yaml", + "JP-01-SAP-L-SMUSCC.yaml", + "JP-01-SAP-L-SNL.yaml", + "JP-01-SAP-L-SOUJCSOUL.yaml", + "JP-01-SAP-L-SSL-sapporo_sumikawa_library.yaml", + "JP-01-SAP-L-SSL.yaml", + "JP-01-SAP-L-SUHSL.yaml", + "JP-01-SAP-L-SUL.yaml", + "JP-01-SAP-L-SYL.yaml", + "JP-01-SAP-L-TCL.yaml", + "JP-01-SAP-L-TULSL.yaml", + "JP-01-SAP-M-ALM.yaml", + "JP-01-SAP-M-AMSU.yaml", + "JP-01-SAP-M-BGFSCNBHU.yaml", + "JP-01-SAP-M-CSM.yaml", + "JP-01-SAP-M-HLMH.yaml", + "JP-01-SAP-M-HM.yaml", + "JP-01-SAP-M-HML.yaml", + "JP-01-SAP-M-HMMA.yaml", + "JP-01-SAP-M-HSMMSS.yaml", + "JP-01-SAP-M-HUM.yaml", + "JP-01-SAP-M-MLM.yaml", + "JP-01-SAP-M-MSBM.yaml", + "JP-01-SAP-M-SA.yaml", + "JP-01-SAP-M-SAM.yaml", + "JP-01-SAP-M-SBM.yaml", + "JP-01-SAP-M-SCT.yaml", + "JP-01-SAP-M-SGBGGC.yaml", + "JP-01-SAP-M-SIUM.yaml", + "JP-01-SAP-M-SMAC.yaml", + "JP-01-SAP-M-SMTMM.yaml", + "JP-01-SAP-M-SMZ.yaml", + "JP-01-SAP-M-SOM.yaml", + "JP-01-SAP-M-SSSM.yaml", + "JP-01-SAP-M-SWM.yaml", + "JP-01-SAP-M-WJML.yaml", + "JP-01-SAP-M-YM.yaml", + "JP-01-SAR-L-BL.yaml", + "JP-01-SAR-L-HLK.yaml", + "JP-01-SAR-M-BTNACM.yaml", + "JP-01-SAR-M-HMM.yaml", + "JP-01-SAR-M-HMSR.yaml", + "JP-01-SAR-M-HMTLM.yaml", + "JP-01-SET-L-I.yaml", + "JP-01-SET-M-NHSP.yaml", + "JP-01-SHA-L-CL.yaml", + "JP-01-SHA-L-KL.yaml", + "JP-01-SHA-L-S.yaml", + "JP-01-SHA-L-SL.yaml", + "JP-01-SHA-M-AAMN.yaml", + "JP-01-SHA-M-SM.yaml", + "JP-01-SHI-L-NL.yaml", + "JP-01-SHI-L-S-shiranukachokominkantoshoshitsu.yaml", + "JP-01-SHI-L-S.yaml", + "JP-01-SHI-L-SL-shiraoichoritsu_library.yaml", + "JP-01-SHI-L-SL.yaml", + "JP-01-SHI-L-SLA.yaml", + "JP-01-SHI-L-STL.yaml", + "JP-01-SHI-M-APAM.yaml", + "JP-01-SHI-M-SCM.yaml", + "JP-01-SHI-M-SCPRP.yaml", + "JP-01-SOR-L-K.yaml", + "JP-01-SOR-L-KL.yaml", + "JP-01-SOR-L-M.yaml", + "JP-01-SOR-L-N.yaml", + "JP-01-SOR-L-NL-nakafuranocho_library.yaml", + "JP-01-SOR-L-NL.yaml", + "JP-01-SOR-M-GSM.yaml", + "JP-01-SOR-M-HF.yaml", + "JP-01-SOR-M-MSTW.yaml", + "JP-01-SOR-M-NK.yaml", + "JP-01-SOY-L-S.yaml", + "JP-01-SUN-L-SL.yaml", + "JP-01-SUN-M-SCLMH.yaml", + "JP-01-SUT-L-K.yaml", + "JP-01-SUT-L-S.yaml", + "JP-01-SUT-M-KBFM.yaml", + "JP-01-TAK-L-KL.yaml", + "JP-01-TAK-M-TMANH.yaml", + "JP-01-TAK-M-TSM-takikawa_sky_museum.yaml", + "JP-01-TAK-M-TSM.yaml", + "JP-01-TAT-M-AJM.yaml", + "JP-01-TES-L-E.yaml", + "JP-01-TES-L-H-horonobechotoikambetsushogaigakushusentatoshoshits.yaml", + "JP-01-TES-L-H.yaml", + "JP-01-TES-L-T-toyotomichotoshoshitsu.yaml", + "JP-01-TES-L-T.yaml", + "JP-01-TES-M-HCMLM.yaml", + "JP-01-TES-M-HMTR.yaml", + "JP-01-TES-M-KSCM.yaml", + "JP-01-TOK-L-C.yaml", + "JP-01-TOK-L-KL.yaml", + "JP-01-TOK-L-OL.yaml", + "JP-01-TOK-L-SL.yaml", + "JP-01-TOK-L-UL.yaml", + "JP-01-TOK-M-HMU.yaml", + "JP-01-TOK-M-KHM.yaml", + "JP-01-TOK-M-TCFM.yaml", + "JP-01-TOM-L-H.yaml", + "JP-01-TOM-L-HUL.yaml", + "JP-01-TOM-L-S.yaml", + "JP-01-TOM-L-T.yaml", + "JP-01-TOM-L-TCL.yaml", + "JP-01-TOM-L-TNCTL.yaml", + "JP-01-TOM-M-HCLHH.yaml", + "JP-01-TOM-M-LUSNC.yaml", + "JP-01-TOM-M-TK.yaml", + "JP-01-TOM-M-TSM.yaml", + "JP-01-TOM-M-YMH.yaml", + "JP-01-TOY-L-TL-toyokawashichuo_library.yaml", + "JP-01-URA-L-UL.yaml", + "JP-01-URA-M-UCLM.yaml", + "JP-01-URA-M-UFAM.yaml", + "JP-01-URY-L-CL.yaml", + "JP-01-URY-L-H.yaml", + "JP-01-URY-L-HL.yaml", + "JP-01-URY-L-MCT.yaml", + "JP-01-URY-L-NL.yaml", + "JP-01-URY-L-U.yaml", + "JP-01-URY-M-CLM.yaml", + "JP-01-URY-M-MTLM.yaml", + "JP-01-URY-M-NAM.yaml", + "JP-01-USU-L-S.yaml", + "JP-01-USU-M-SCHMKMH.yaml", + "JP-01-UTA-L-UCL.yaml", + "JP-01-UTA-M-UCLMY.yaml", + "JP-01-WAK-L-HROFRDWFRI.yaml", + "JP-01-WAK-L-IUL.yaml", + "JP-01-WAK-L-WCL.yaml", + "JP-01-WAK-M-WKM.yaml", + "JP-01-WAK-M-WMNMH.yaml", + "JP-01-WAK-M-WNA.yaml", + "JP-01-WAK-M-WYCSM.yaml", + "JP-01-YAM-L-OL.yaml", + "JP-01-YAM-L-TL.yaml", + "JP-01-YOI-L-A.yaml", + "JP-01-YOI-L-N.yaml", + "JP-01-YOI-L-YTL.yaml", + "JP-01-YOI-M-YFM.yaml", + "JP-01-YOI-M-YSM.yaml", + "JP-01-YUB-L-KTL.yaml", + "JP-01-YUB-L-NPL.yaml", + "JP-01-YUB-L-Y-yubarishitoshokona.yaml", + "JP-01-YUB-L-Y.yaml", + "JP-01-YUB-M-CMMY.yaml", + "JP-01-YUB-M-KK.yaml", + "JP-01-YUF-L-A-abirachohayakitakominkantoshoshitsu.yaml", + "JP-01-YUF-L-A-atsumachokominkantoshoshitsu.yaml", + "JP-01-YUF-L-A.yaml", + "JP-01-YUF-L-ML.yaml", + "JP-01-YUF-L-S.yaml", + "JP-01-YUF-M-HLM.yaml", + "JP-01-YUF-M-HM.yaml", + "JP-02-AKI-M-AKMKTM.yaml", + "JP-02-AOM-L-A-aomorikenshikakushogaishajohosenta.yaml", + "JP-02-AOM-L-A.yaml", + "JP-02-AOM-L-AAJCL.yaml", + "JP-02-AOM-L-ACGUACJCLI.yaml", + "JP-02-AOM-L-ACL.yaml", + "JP-02-AOM-L-ALH.yaml", + "JP-02-AOM-L-ALS.yaml", + "JP-02-AOM-L-APARDL.yaml", + "JP-02-AOM-L-APGEC.yaml", + "JP-02-AOM-L-APUL.yaml", + "JP-02-AOM-L-AUHWL.yaml", + "JP-02-AOM-M-ACACAPU.yaml", + "JP-02-AOM-M-ACMHH.yaml", + "JP-02-AOM-M-AMH.yaml", + "JP-02-AOM-M-APAA.yaml", + "JP-02-AOM-M-APM.yaml", + "JP-02-AOM-M-EKAWO.yaml", + "JP-02-AOM-M-KSPMJMKK.yaml", + "JP-02-AOM-M-MHBGBGTU.yaml", + "JP-02-AOM-M-MHSMM.yaml", + "JP-02-AOM-M-MMAL.yaml", + "JP-02-AOM-M-SMJCC.yaml", + "JP-02-GOS-L-GCL.yaml", + "JP-02-GOS-L-GLK.yaml", + "JP-02-GOS-L-GLS.yaml", + "JP-02-GOS-M-ODMHS.yaml", + "JP-02-GOS-M-SMHH.yaml", + "JP-02-GOS-M-TSH.yaml", + "JP-02-HAC-L-H.yaml", + "JP-02-HAC-L-HCPL.yaml", + "JP-02-HAC-L-HITL.yaml", + "JP-02-HAC-L-HL-hachinohekogyokotosemmongakko_library.yaml", + "JP-02-HAC-L-LHGUHGJC.yaml", + "JP-02-HAC-M-HAM.yaml", + "JP-02-HAC-M-HCMM.yaml", + "JP-02-HAC-M-HCSSM.yaml", + "JP-02-HAC-M-HHM.yaml", + "JP-02-HAC-M-HPKLHBG.yaml", + "JP-02-HAC-M-KAI.yaml", + "JP-02-HAC-M-NFHMH.yaml", + "JP-02-HAC-M-SM.yaml", + "JP-02-HIG-L-APITRCFFPR.yaml", + "JP-02-HIG-L-HL.yaml", + "JP-02-HIG-L-I.yaml", + "JP-02-HIG-L-S-sotogahamamachimimmayakominkantoshoshitsu.yaml", + "JP-02-HIG-L-S.yaml", + "JP-02-HIG-L-Y.yaml", + "JP-02-HIG-M-HMFHMH.yaml", + "JP-02-HIR-L-H.yaml", + "JP-02-HIR-L-HCPL.yaml", + "JP-02-HIR-L-HGUL.yaml", + "JP-02-HIR-L-HL-hirakawashihiraka_library.yaml", + "JP-02-HIR-L-HL-hirakawashionoe_library.yaml", + "JP-02-HIR-L-HL-hirosakiiryofukushidaigakusogo_library.yaml", + "JP-02-HIR-L-HL.yaml", + "JP-02-HIR-L-HLE.yaml", + "JP-02-HIR-L-HLS.yaml", + "JP-02-HIR-L-HUL.yaml", + "JP-02-HIR-L-HUML.yaml", + "JP-02-HIR-L-SGUL.yaml", + "JP-02-HIR-L-TWSJCL.yaml", + "JP-02-HIR-M-HLLM.yaml", + "JP-02-HIR-M-HSLMH.yaml", + "JP-02-HIR-M-HUM.yaml", + "JP-02-HIR-M-THMHC.yaml", + "JP-02-HIR-M-YI.yaml", + "JP-02-KAM-L-NTL.yaml", + "JP-02-KAM-L-O.yaml", + "JP-02-KAM-L-OML.yaml", + "JP-02-KAM-L-RL.yaml", + "JP-02-KAM-L-RLC-rokkashosommin_library_chitosetaichikukominkambunk.yaml", + "JP-02-KAM-L-RLC.yaml", + "JP-02-KAM-L-RLT.yaml", + "JP-02-KAM-L-RVL.yaml", + "JP-02-KAM-L-S.yaml", + "JP-02-KAM-L-SL.yaml", + "JP-02-KAM-L-TL.yaml", + "JP-02-KAM-L-TLO.yaml", + "JP-02-KAM-L-YL.yaml", + "JP-02-KAM-M-NMLFHMH.yaml", + "JP-02-KAM-M-OAK.yaml", + "JP-02-KAM-M-OSMH.yaml", + "JP-02-KAM-M-RM.yaml", + "JP-02-KAM-M-RTLMH.yaml", + "JP-02-KAM-M-TMFHMH.yaml", + "JP-02-KAM-M-UTMMA.yaml", + "JP-02-KAN-M-APM.yaml", + "JP-02-KAN-M-BGMMK.yaml", + "JP-02-KIT-L-ATIL.yaml", + "JP-02-KIT-L-NL.yaml", + "JP-02-KIT-L-T.yaml", + "JP-02-KIT-M-LMHIT.yaml", + "JP-02-KIT-M-NM.yaml", + "JP-02-KUR-L-K.yaml", + "JP-02-KUR-L-KCL.yaml", + "JP-02-KUR-M-AUMH.yaml", + "JP-02-KUR-M-TKH.yaml", + "JP-02-MIN-L-FLT.yaml", + "JP-02-MIN-L-I.yaml", + "JP-02-MIN-L-O.yaml", + "JP-02-MIN-L-T.yaml", + "JP-02-MIN-M-IBCPC.yaml", + "JP-02-MIN-M-IM.yaml", + "JP-02-MIS-L-ML.yaml", + "JP-02-MIS-M-MASMA.yaml", + "JP-02-MIS-M-MCMHFC.yaml", + "JP-02-MIS-M-MHF.yaml", + "JP-02-MUT-L-ML.yaml", + "JP-02-MUT-L-MLK.yaml", + "JP-02-MUT-L-MLO.yaml", + "JP-02-MUT-L-MLW.yaml", + "JP-02-NAK-L-N.yaml", + "JP-02-NIB-M-NFM.yaml", + "JP-02-NIK-M-SAEMM.yaml", + "JP-02-NIS-L-D.yaml", + "JP-02-NIS-L-N.yaml", + "JP-02-NIS-M-PMOM.yaml", + "JP-02-SAN-L-APL.yaml", + "JP-02-SAN-L-GTL.yaml", + "JP-02-SAN-L-HH.yaml", + "JP-02-SAN-L-N-nambuchoritsunagawachugakkotoshoshitsuikkai.yaml", + "JP-02-SAN-L-N.yaml", + "JP-02-SAN-L-SL.yaml", + "JP-02-SAN-L-TL.yaml", + "JP-02-SAN-M-SMLFHMH.yaml", + "JP-02-SEN-L-ALM.yaml", + "JP-02-SEN-M-AMA.yaml", + "JP-02-SEN-M-ASMA.yaml", + "JP-02-SEN-M-SHM.yaml", + "JP-02-SHI-L-K.yaml", + "JP-02-SHI-L-KU.yaml", + "JP-02-SHI-L-O.yaml", + "JP-02-SHI-L-S.yaml", + "JP-02-SHI-M-KMK.yaml", + "JP-02-SHI-M-SCM.yaml", + "JP-02-TEN-M-OCM.yaml", + "JP-02-TOG-M-OAG.yaml", + "JP-02-TOW-L-CLT.yaml", + "JP-02-TOW-L-KUSVML.yaml", + "JP-02-TOW-M-HMTCS.yaml", + "JP-02-TOW-M-NMM.yaml", + "JP-02-TOW-M-TCFM.yaml", + "JP-02-TOW-M-TCTLFHMH.yaml", + "JP-02-TSU-L-T-tsugarushimoritakominkantoshoshitsu.yaml", + "JP-02-TSU-L-T-tsugarushiushigatakominkantoshoshitsu.yaml", + "JP-02-TSU-L-T.yaml", + "JP-02-TSU-L-TCL.yaml", + "JP-02-TSU-L-TIHC.yaml", + "JP-02-TSU-M-MBD.yaml", + "JP-02-YAN-M-AMMA.yaml", + "JP-03-DOT-M-HMCA.yaml", + "JP-03-FUJ-L-APL.yaml", + "JP-03-FUK-M-ET.yaml", + "JP-03-HAC-L-H-hachimantaishiritsuarayakomyuniteisentatoshoshitsu.yaml", + "JP-03-HAC-L-H.yaml", + "JP-03-HAC-L-HCL.yaml", + "JP-03-HAC-M-HCM.yaml", + "JP-03-HAC-M-HMAM.yaml", + "JP-03-HAC-M-KK.yaml", + "JP-03-HAN-L-FL.yaml", + "JP-03-HAN-L-HIL.yaml", + "JP-03-HAN-L-HL-hanamakishiritsuohasama_library.yaml", + "JP-03-HAN-L-HL.yaml", + "JP-03-HAN-L-HTL.yaml", + "JP-03-HAN-M-HCCHC.yaml", + "JP-03-HAN-M-HCM.yaml", + "JP-03-HAN-M-HNM.yaml", + "JP-03-HAN-M-IFHM.yaml", + "JP-03-HAN-M-MKM.yaml", + "JP-03-HAN-M-TKM.yaml", + "JP-03-HAN-M-YTMMA.yaml", + "JP-03-ICH-L-HL.yaml", + "JP-03-ICH-L-IL-ichinosekikogyokotosemmongakko_library.yaml", + "JP-03-ICH-L-IL-ichinosekishiritsudaito_library.yaml", + "JP-03-ICH-L-IL-ichinosekishiritsufujisawa_library.yaml", + "JP-03-ICH-L-IL-ichinosekishiritsuhanaizumi_library.yaml", + "JP-03-ICH-L-IL-ichinosekishiritsuhigashiyama_library.yaml", + "JP-03-ICH-L-IL-ichinosekishiritsukawasaki_library.yaml", + "JP-03-ICH-L-IL-ichinosekishiritsumurone_library.yaml", + "JP-03-ICH-L-IL-ichinosekishiritsusemmaya_library.yaml", + "JP-03-ICH-L-IL.yaml", + "JP-03-ICH-L-SJCL.yaml", + "JP-03-ICH-M-ATMM.yaml", + "JP-03-ICH-M-ICFM.yaml", + "JP-03-ICH-M-ICM.yaml", + "JP-03-ICH-M-ISP.yaml", + "JP-03-ICH-M-OCM.yaml", + "JP-03-ISA-L-KL.yaml", + "JP-03-ISA-M-GR.yaml", + "JP-03-ISA-M-KSHC.yaml", + "JP-03-IWA-L-ITL.yaml", + "JP-03-IWA-L-K.yaml", + "JP-03-IWA-L-STL.yaml", + "JP-03-IWA-M-GKAM.yaml", + "JP-03-IWA-M-IMA.yaml", + "JP-03-IWA-M-STMHF.yaml", + "JP-03-KAM-L-KL.yaml", + "JP-03-KAM-M-KCISHM.yaml", + "JP-03-KAM-M-KHMD.yaml", + "JP-03-KES-L-S.yaml", + "JP-03-KES-M-FMST.yaml", + "JP-03-KIT-L-KL-kitakamishiritsuezuriko_library.yaml", + "JP-03-KIT-L-KL-kitakamishiritsuwaga_library.yaml", + "JP-03-KIT-L-KL.yaml", + "JP-03-KIT-L-MCJPTH.yaml", + "JP-03-KIT-M-HSMH.yaml", + "JP-03-KIT-M-IPAFPASM.yaml", + "JP-03-KIT-M-KCTKAM.yaml", + "JP-03-KIT-M-KOM.yaml", + "JP-03-KUJ-L-KCPL.yaml", + "JP-03-KUJ-L-KL.yaml", + "JP-03-KUJ-M-KAM.yaml", + "JP-03-KUJ-M-MJMG.yaml", + "JP-03-KUN-L-HL-hironochoritsuono_library.yaml", + "JP-03-KUN-L-HL.yaml", + "JP-03-KUN-L-K.yaml", + "JP-03-KUN-L-KL.yaml", + "JP-03-KUN-L-NL.yaml", + "JP-03-KUN-M-HCTHFM.yaml", + "JP-03-KUN-M-KTMHF.yaml", + "JP-03-KUN-M-MAEF.yaml", + "JP-03-MAT-M-ACSC.yaml", + "JP-03-MAT-M-MSMMA.yaml", + "JP-03-MAY-M-HCM.yaml", + "JP-03-MIY-L-IL.yaml", + "JP-03-MIY-L-ML.yaml", + "JP-03-MIY-L-MLK.yaml", + "JP-03-MIY-L-MLN.yaml", + "JP-03-MIY-L-MLT.yaml", + "JP-03-MIY-M-IPFSM.yaml", + "JP-03-MIY-M-MKHDFM.yaml", + "JP-03-MIY-M-SSMJMAM.yaml", + "JP-03-MOR-L-A.yaml", + "JP-03-MOR-L-FFPRITRC.yaml", + "JP-03-MOR-L-IIRI.yaml", + "JP-03-MOR-L-IMUL.yaml", + "JP-03-MOR-L-IPAL.yaml", + "JP-03-MOR-L-IPCVHI.yaml", + "JP-03-MOR-L-IPL.yaml", + "JP-03-MOR-L-IUL.yaml", + "JP-03-MOR-L-K.yaml", + "JP-03-MOR-L-M-moriokashichuokominkantoshoshitsu.yaml", + "JP-03-MOR-L-M-moriokashiuedakominkantoshoshitsu.yaml", + "JP-03-MOR-L-M.yaml", + "JP-03-MOR-L-MCL.yaml", + "JP-03-MOR-L-ML-moriokashishibutami_library.yaml", + "JP-03-MOR-L-ML.yaml", + "JP-03-MOR-L-O.yaml", + "JP-03-MOR-L-S.yaml", + "JP-03-MOR-M-BGIU.yaml", + "JP-03-MOR-M-HKMM.yaml", + "JP-03-MOR-M-HMAE.yaml", + "JP-03-MOR-M-IMA.yaml", + "JP-03-MOR-M-IPM.yaml", + "JP-03-MOR-M-ITMM.yaml", + "JP-03-MOR-M-IUM.yaml", + "JP-03-MOR-M-KFFFM.yaml", + "JP-03-MOR-M-MCPHPER.yaml", + "JP-03-MOR-M-MCSMS.yaml", + "JP-03-MOR-M-MHCM.yaml", + "JP-03-MOR-M-MMMGP.yaml", + "JP-03-MOR-M-MSMAS.yaml", + "JP-03-MOR-M-MTHFM-morioka_tamayama_history_and_folklore_museum.yaml", + "JP-03-MOR-M-MTHFM.yaml", + "JP-03-MOR-M-MZP.yaml", + "JP-03-MOT-M-HCBG.yaml", + "JP-03-NIN-L-ITPL.yaml", + "JP-03-NIN-L-N.yaml", + "JP-03-NIN-L-NCPL.yaml", + "JP-03-NIN-M-GJM.yaml", + "JP-03-NIN-M-MHFJ.yaml", + "JP-03-NIN-M-NCCCTAMSM.yaml", + "JP-03-NIN-M-NMHF.yaml", + "JP-03-NIS-L-HPL.yaml", + "JP-03-NIS-M-HCHC.yaml", + "JP-03-NIS-M-HMCH.yaml", + "JP-03-NIS-M-HWHIC.yaml", + "JP-03-NIS-M-MTH.yaml", + "JP-03-NIS-M-TAC.yaml", + "JP-03-OFU-L-OL.yaml", + "JP-03-OFU-M-OCM.yaml", + "JP-03-OSH-L-K.yaml", + "JP-03-OSH-L-OCEL.yaml", + "JP-03-OSH-L-OL-oshushiritsuisawa_library.yaml", + "JP-03-OSH-L-OL-oshushiritsumaesawa_library.yaml", + "JP-03-OSH-L-OL.yaml", + "JP-03-OSH-M-CM.yaml", + "JP-03-OSH-M-CTMH.yaml", + "JP-03-OSH-M-ENDCM.yaml", + "JP-03-OSH-M-ILM.yaml", + "JP-03-OSH-M-OCARC.yaml", + "JP-03-OSH-M-OSEM.yaml", + "JP-03-OSH-M-SGMH.yaml", + "JP-03-OSH-M-SMMH.yaml", + "JP-03-RIK-L-N.yaml", + "JP-03-RIK-L-RCL.yaml", + "JP-03-RIK-L-RLK.yaml", + "JP-03-RIK-M-ITMM.yaml", + "JP-03-RIK-M-RTCM.yaml", + "JP-03-SAB-M-STM.yaml", + "JP-03-SAM-M-HMSH.yaml", + "JP-03-SAN-M-AMA.yaml", + "JP-03-SEK-M-MSM.yaml", + "JP-03-SHI-L-A.yaml", + "JP-03-SHI-L-F.yaml", + "JP-03-SHI-L-IL.yaml", + "JP-03-SHI-L-IMULBL.yaml", + "JP-03-SHI-L-IPFTC.yaml", + "JP-03-SHI-L-SPL.yaml", + "JP-03-SHI-L-YL.yaml", + "JP-03-SHI-L-YPHL.yaml", + "JP-03-SHI-M-ACFM.yaml", + "JP-03-SHI-M-KANM.yaml", + "JP-03-SHI-M-TMM.yaml", + "JP-03-SHI-M-YCFHMH.yaml", + "JP-03-SHI-M-YCSMWO.yaml", + "JP-03-TAK-L-ICNL.yaml", + "JP-03-TAK-L-IPUMC.yaml", + "JP-03-TAK-L-ML.yaml", + "JP-03-TAK-L-RL.yaml", + "JP-03-TAK-L-TL.yaml", + "JP-03-TON-L-TCL.yaml", + "JP-03-TON-L-TLB.yaml", + "JP-03-TON-M-TFV.yaml", + "JP-03-TON-M-TMM.yaml", + "JP-03-WAG-L-N.yaml", + "JP-03-WAG-M-HM.yaml", + "JP-03-WAG-M-NKMDH.yaml", + "JP-03-WAG-M-NMFHMH.yaml", + "JP-03-WAG-M-YLH.yaml", + "JP-04-ABI-M-ACMB.yaml", + "JP-04-CHI-M-CCMA.yaml", + "JP-04-FUN-M-ILM.yaml", + "JP-04-KAI-M-THSPM.yaml", + "JP-04-KEM-M-ESMPSGSPSU.yaml", + "JP-04-MIN-L-ILK.yaml", + "JP-04-NAG-M-NMM.yaml", + "JP-04-NAR-L-NLB.yaml", + "JP-04-OMA-M-ICZ.yaml", + "JP-04-SAK-M-OSH.yaml", + "JP-04-SAK-M-SCMA.yaml", + "JP-04-SAW-M-ITM.yaml", + "JP-04-SHI-M-SATHM.yaml", + "JP-04-USU-M-IMIHF.yaml", + "JP-04-YAM-M-AWR.yaml", + "JP-04-YOT-M-CZP.yaml", + "JP-04-YOT-M-KSM.yaml", + "JP-05-AKI-A-APA.yaml", + "JP-05-AKI-L-AITC.yaml", + "JP-05-AKI-L-AIUL.yaml", + "JP-05-AKI-L-AL-akitakentenji_library.yaml", + "JP-05-AKI-L-AL-akitashiritsutsuchizaki_library.yaml", + "JP-05-AKI-L-AL-akitashiritsuyuwa_library.yaml", + "JP-05-AKI-L-AL.yaml", + "JP-05-AKI-L-ALA.yaml", + "JP-05-AKI-L-ALM-akitashiritsuchuo_library_meitokukambunkofuontebun.yaml", + "JP-05-AKI-L-ALM-akitashiritsuchuo_library_meitokukankawabebunkan.yaml", + "JP-05-AKI-L-ANCTL.yaml", + "JP-05-AKI-L-APAL.yaml", + "JP-05-AKI-L-APUL.yaml", + "JP-05-AKI-L-AUAL.yaml", + "JP-05-AKI-L-AUL.yaml", + "JP-05-AKI-L-AUMSL.yaml", + "JP-05-AKI-L-JRCACNLJRC.yaml", + "JP-05-AKI-L-MGJCL.yaml", + "JP-05-AKI-L-NAUL.yaml", + "JP-05-AKI-L-SWSJC.yaml", + "JP-05-AKI-M-ACFPAHC.yaml", + "JP-05-AKI-M-ACHMAFR.yaml", + "JP-05-AKI-M-AO.yaml", + "JP-05-AKI-M-APCH.yaml", + "JP-05-AKI-M-MIMAU.yaml", + "JP-05-AKI-M-NSLC.yaml" ], - "last_index": 59 + "last_index": 9 } \ No newline at end of file diff --git a/data/custodian/AT-3-WNE-L-KUKWESB.yaml b/data/custodian/AT-3-WNE-L-KUKWESB.yaml index 840ff10f9a..66f4f273f0 100644 --- a/data/custodian/AT-3-WNE-L-KUKWESB.yaml +++ b/data/custodian/AT-3-WNE-L-KUKWESB.yaml @@ -120,6 +120,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.150421+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Konvent der Unbeschuhten Karmeliten in Wien | Edith Stein Bibliothek + description: Discalced Carmelite convent library in Wiener Neustadt, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bibliothek im Zentrum - Hochschul- & Stadtbibliothek Wiener Neustadt diff --git a/data/custodian/AT-3-WNE-L-MUVB.yaml b/data/custodian/AT-3-WNE-L-MUVB.yaml index 143ed98db6..69a85f7b19 100644 --- a/data/custodian/AT-3-WNE-L-MUVB.yaml +++ b/data/custodian/AT-3-WNE-L-MUVB.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.356480+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q872071 + wikidata_url: https://www.wikidata.org/wiki/Q872071 + label: Modul University Vienna + description: private university in Vienna, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bibliothek im Zentrum - Hochschul- & Stadtbibliothek Wiener Neustadt diff --git a/data/custodian/AT-3-WNE-L-OBSGMBH.yaml b/data/custodian/AT-3-WNE-L-OBSGMBH.yaml index 1dac36740b..01d25e3a1d 100644 --- a/data/custodian/AT-3-WNE-L-OBSGMBH.yaml +++ b/data/custodian/AT-3-WNE-L-OBSGMBH.yaml @@ -124,6 +124,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.378209+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q108928882 + wikidata_url: https://www.wikidata.org/wiki/Q108928882 + label: Austrian Library Network and Service Ltd + description: head office and service provider of the Austrian Library Network OBV + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry for this library network service organization google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Österreichische Bibliothekenverbund und Service Ges.m.b.H. diff --git a/data/custodian/AT-3-WNE-L-OOB.yaml b/data/custodian/AT-3-WNE-L-OOB.yaml index 753e9811a5..a23ac5b5d5 100644 --- a/data/custodian/AT-3-WNE-L-OOB.yaml +++ b/data/custodian/AT-3-WNE-L-OOB.yaml @@ -222,6 +222,13 @@ google_maps_enrichment: agent: glm-4.6 verified: true ch_annotator_version: ch_annotator-v1_7_0 +wikidata_enrichment: + wikidata_id: null + label: Österreichische Ordenskonferenz | Bibliothek + description: Austrian Conference of Religious Orders library in Wiener Neustadt, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: SUCCESS youtube_status: NOT_FOUND youtube_search_query: Österreichische Ordenskonferenz | Bibliothek official diff --git a/data/custodian/AT-3-WNE-L-OOFIEB.yaml b/data/custodian/AT-3-WNE-L-OOFIEB.yaml index 5e27d91354..6d581fe65c 100644 --- a/data/custodian/AT-3-WNE-L-OOFIEB.yaml +++ b/data/custodian/AT-3-WNE-L-OOFIEB.yaml @@ -226,6 +226,14 @@ google_maps_enrichment: agent: glm-4.6 verified: true ch_annotator_version: ch_annotator-v1_7_0 +wikidata_enrichment: + wikidata_id: Q301949 + wikidata_url: https://www.wikidata.org/wiki/Q301949 + label: Österreichische Forschungsstiftung für Internationale Entwicklung + description: research foundation for international development in Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: SUCCESS youtube_status: NOT_FOUND youtube_search_query: ÖFSE − Österreichische Forschungsstiftung für Internationale diff --git a/data/custodian/AT-3-WNE-L-PP.yaml b/data/custodian/AT-3-WNE-L-PP.yaml index faa21418bb..8c5ad379bc 100644 --- a/data/custodian/AT-3-WNE-L-PP.yaml +++ b/data/custodian/AT-3-WNE-L-PP.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.424212+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q106527445 + wikidata_url: https://www.wikidata.org/wiki/Q106527445 + label: Parliament Library + description: library in Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Austrian Parliament diff --git a/data/custodian/AT-3-WNE-L-SFPWB.yaml b/data/custodian/AT-3-WNE-L-SFPWB.yaml index 19f47e2004..7f36dc7e8c 100644 --- a/data/custodian/AT-3-WNE-L-SFPWB.yaml +++ b/data/custodian/AT-3-WNE-L-SFPWB.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.480011+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q2157899 + wikidata_url: https://www.wikidata.org/wiki/Q2157899 + label: Sigmund Freud Privatuniversität Wien + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bibliothek im Zentrum - Hochschul- & Stadtbibliothek Wiener Neustadt diff --git a/data/custodian/AT-3-WNE-L-SMRGOB.yaml b/data/custodian/AT-3-WNE-L-SMRGOB.yaml index 709d2207d7..d3b30c47a1 100644 --- a/data/custodian/AT-3-WNE-L-SMRGOB.yaml +++ b/data/custodian/AT-3-WNE-L-SMRGOB.yaml @@ -126,6 +126,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.491869+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Souveräner Malteser Ritterorden, Großpriorat von Österreich | Bibliothek + description: library in Vienna, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Souveräner Malteser-Ritter-Orden - Großpriorat von Österreich diff --git a/data/custodian/AT-3-WNE-O-B-bundesdenkmalamt.yaml b/data/custodian/AT-3-WNE-O-B-bundesdenkmalamt.yaml index c9d058129b..863224e1b9 100644 --- a/data/custodian/AT-3-WNE-O-B-bundesdenkmalamt.yaml +++ b/data/custodian/AT-3-WNE-O-B-bundesdenkmalamt.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.167079+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q876452 + wikidata_url: https://www.wikidata.org/wiki/Q876452 + label: Bundesdenkmalamt + description: österreichische Behörde für Denkmalschutz und Denkmalpflege + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bundesdenkmalamt diff --git a/data/custodian/AT-3-WNE-O-B.yaml b/data/custodian/AT-3-WNE-O-B.yaml index bcd210429d..3cd3a859b6 100644 --- a/data/custodian/AT-3-WNE-O-B.yaml +++ b/data/custodian/AT-3-WNE-O-B.yaml @@ -213,6 +213,14 @@ google_maps_enrichment: agent: glm-4.6 verified: true ch_annotator_version: ch_annotator-v1_7_0 +wikidata_enrichment: + wikidata_id: Q876452 + wikidata_url: https://www.wikidata.org/wiki/Q876452 + label: Bundesdenkmalamt + description: österreichische Behörde für Denkmalschutz und Denkmalpflege + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this institution google_maps_status: SUCCESS youtube_status: NOT_FOUND youtube_search_query: Bundesdenkmalamt official diff --git a/data/custodian/AT-3-WNE-R-VZFEBSTIM.yaml b/data/custodian/AT-3-WNE-R-VZFEBSTIM.yaml index 1c62f62467..41d802b9cc 100644 --- a/data/custodian/AT-3-WNE-R-VZFEBSTIM.yaml +++ b/data/custodian/AT-3-WNE-R-VZFEBSTIM.yaml @@ -120,6 +120,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.352025+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Verein zur Förderung der Erforschung und Bildung sozialer und technischer Innovationen - metalab + description: hackerspace in Vienna, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Metalab diff --git a/data/custodian/AT-3-WNE-U-BBFSS-bundesministerium_fur_bildung_und_frauen_schulbuch.yaml b/data/custodian/AT-3-WNE-U-BBFSS-bundesministerium_fur_bildung_und_frauen_schulbuch.yaml index 3511344f8c..4ca0d971a5 100644 --- a/data/custodian/AT-3-WNE-U-BBFSS-bundesministerium_fur_bildung_und_frauen_schulbuch.yaml +++ b/data/custodian/AT-3-WNE-U-BBFSS-bundesministerium_fur_bildung_und_frauen_schulbuch.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.189815+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q606227 + wikidata_url: https://www.wikidata.org/wiki/Q606227 + label: Bundesministerium für Bildung + description: für das Schulwesen und die Universitäten zuständige Bundesministerium der Republik Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the Schulbuch- und Schulschriftensammlung google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bundesministerium für Bildung, Wissenschaft und Forschung diff --git a/data/custodian/AT-3-WNE-U-BBFSS.yaml b/data/custodian/AT-3-WNE-U-BBFSS.yaml index 715bf48dbf..16042a255a 100644 --- a/data/custodian/AT-3-WNE-U-BBFSS.yaml +++ b/data/custodian/AT-3-WNE-U-BBFSS.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.100767+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q606227 + wikidata_url: https://www.wikidata.org/wiki/Q606227 + label: Bundesministerium für Bildung + description: für das Schulwesen und die Universitäten zuständige Bundesministerium der Republik Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the Schulbuch- und Schulschriftensammlung google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bundesministerium für Bildung, Wissenschaft und Forschung diff --git a/data/custodian/AT-3-WNE-U-BJ-bundesministerium_fur_justiz.yaml b/data/custodian/AT-3-WNE-U-BJ-bundesministerium_fur_justiz.yaml index da2251c707..49d29721e2 100644 --- a/data/custodian/AT-3-WNE-U-BJ-bundesministerium_fur_justiz.yaml +++ b/data/custodian/AT-3-WNE-U-BJ-bundesministerium_fur_justiz.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.185456+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q872203 + wikidata_url: https://www.wikidata.org/wiki/Q872203 + label: Bundesministerium für Justiz + description: Justizministerium Österreichs + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bundesministerium für Verfassung, Reformen, Deregulierung und Justiz diff --git a/data/custodian/AT-3-WNE-U-BJ.yaml b/data/custodian/AT-3-WNE-U-BJ.yaml index 4ebe112d9f..754ca7336d 100644 --- a/data/custodian/AT-3-WNE-U-BJ.yaml +++ b/data/custodian/AT-3-WNE-U-BJ.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.098230+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q872203 + wikidata_url: https://www.wikidata.org/wiki/Q872203 + label: Bundesministerium für Justiz + description: Justizministerium Österreichs + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bundesministerium für Verfassung, Reformen, Deregulierung und Justiz diff --git a/data/custodian/AT-3-WNE-U-LPCVVFSASG-liechtenstein_the_princely_collections_vaduzvienna.yaml b/data/custodian/AT-3-WNE-U-LPCVVFSASG-liechtenstein_the_princely_collections_vaduzvienna.yaml index 990235cfb8..1b95277425 100644 --- a/data/custodian/AT-3-WNE-U-LPCVVFSASG-liechtenstein_the_princely_collections_vaduzvienna.yaml +++ b/data/custodian/AT-3-WNE-U-LPCVVFSASG-liechtenstein_the_princely_collections_vaduzvienna.yaml @@ -130,6 +130,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.269297+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1824069 + wikidata_url: https://www.wikidata.org/wiki/Q1824069 + label: Fürstliche Sammlungen (Liechtenstein) + description: Kunstmuseum in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Gartenpalais Liechtenstein diff --git a/data/custodian/AT-3-WNE-U-LPCVVFSASG.yaml b/data/custodian/AT-3-WNE-U-LPCVVFSASG.yaml index d5d2edd0c7..40bdf40ba9 100644 --- a/data/custodian/AT-3-WNE-U-LPCVVFSASG.yaml +++ b/data/custodian/AT-3-WNE-U-LPCVVFSASG.yaml @@ -233,6 +233,14 @@ google_maps_enrichment: agent: glm-4.6 verified: true ch_annotator_version: ch_annotator-v1_7_0 +wikidata_enrichment: + wikidata_id: Q1824069 + wikidata_url: https://www.wikidata.org/wiki/Q1824069 + label: Fürstliche Sammlungen (Liechtenstein) + description: Kunstmuseum in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this institution google_maps_status: SUCCESS youtube_status: NOT_FOUND youtube_search_query: Liechtenstein. The Princely Collections, Vaduz–Vienna. Fürstliche diff --git a/data/custodian/AT-3-WNE-U-MPL-max_perutz_library.yaml b/data/custodian/AT-3-WNE-U-MPL-max_perutz_library.yaml index 5a75d13ce0..4a27527a1a 100644 --- a/data/custodian/AT-3-WNE-U-MPL-max_perutz_library.yaml +++ b/data/custodian/AT-3-WNE-U-MPL-max_perutz_library.yaml @@ -127,6 +127,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.304823+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Max Perutz Library + description: library in Vienna, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Max Perutz Library diff --git a/data/custodian/AT-3-WNE-U-MPL.yaml b/data/custodian/AT-3-WNE-U-MPL.yaml index fbed22f5ce..7293da2542 100644 --- a/data/custodian/AT-3-WNE-U-MPL.yaml +++ b/data/custodian/AT-3-WNE-U-MPL.yaml @@ -127,6 +127,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.222347+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Max Perutz Library + description: library in Wiener Neustadt, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Max Perutz Library diff --git a/data/custodian/AT-3-WNE-U-OVNAH.yaml b/data/custodian/AT-3-WNE-U-OVNAH.yaml index 6f56b02e01..2ce19bd54a 100644 --- a/data/custodian/AT-3-WNE-U-OVNAH.yaml +++ b/data/custodian/AT-3-WNE-U-OVNAH.yaml @@ -126,6 +126,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.419185+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Österreichischer Verbundkatalog für Nachlässe, Autographen, Handschriften + description: union catalog in Wiener Neustadt, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NOT_FOUND google_maps_search_query: Österreichischer Verbundkatalog für Nachlässe, Autographen, Handschriften, Wiener Neustadt diff --git a/data/custodian/AT-3-WNE-U-SRR.yaml b/data/custodian/AT-3-WNE-U-SRR.yaml index f50604155e..a6463895e9 100644 --- a/data/custodian/AT-3-WNE-U-SRR.yaml +++ b/data/custodian/AT-3-WNE-U-SRR.yaml @@ -120,6 +120,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.484402+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: SK Rapid | Rapideum + description: sports museum in Wiener Neustadt, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: SK Rapid diff --git a/data/custodian/AT-3-WNE-U-VBKV.yaml b/data/custodian/AT-3-WNE-U-VBKV.yaml index a5c94e8146..01f7ee5f9f 100644 --- a/data/custodian/AT-3-WNE-U-VBKV.yaml +++ b/data/custodian/AT-3-WNE-U-VBKV.yaml @@ -120,6 +120,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.589126+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Verbund für Bildung und Kultur Verbundzentrale + description: education and culture organization in Wiener Neustadt, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Educational Center St. Bernard diff --git a/data/custodian/AT-3-WNE-U-VN.yaml b/data/custodian/AT-3-WNE-U-VN.yaml index 8d6a5ab4fa..27820ddfb8 100644 --- a/data/custodian/AT-3-WNE-U-VN.yaml +++ b/data/custodian/AT-3-WNE-U-VN.yaml @@ -120,6 +120,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.364361+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Villa North + description: institution in Wiener Neustadt, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Villa North diff --git a/data/custodian/AT-4-ATT-A-SAP-stadtarchiv_attnang_puchheim.yaml b/data/custodian/AT-4-ATT-A-SAP-stadtarchiv_attnang_puchheim.yaml index 6775f426f8..9338869b6d 100644 --- a/data/custodian/AT-4-ATT-A-SAP-stadtarchiv_attnang_puchheim.yaml +++ b/data/custodian/AT-4-ATT-A-SAP-stadtarchiv_attnang_puchheim.yaml @@ -137,6 +137,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.125731+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Stadtarchiv Attnang-Puchheim + description: city archive in Attnang-Puchheim, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bücherei der Stadtgemeinde Attnang-Puchheim diff --git a/data/custodian/AT-4-ATT-A-SAP.yaml b/data/custodian/AT-4-ATT-A-SAP.yaml index a256b9c7bb..3f7a8a7261 100644 --- a/data/custodian/AT-4-ATT-A-SAP.yaml +++ b/data/custodian/AT-4-ATT-A-SAP.yaml @@ -139,6 +139,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:13.984755+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Stadtarchiv Attnang-Puchheim + description: city archive in Attnang-Puchheim, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_enrichment: place_id: ChIJATY_9vgHdEcR6XKjdapDY6Q name: Bücherei der Stadtgemeinde Attnang-Puchheim diff --git a/data/custodian/AT-4-LAM-L-BLB.yaml b/data/custodian/AT-4-LAM-L-BLB.yaml index 23f80fc53c..e37883a4a5 100644 --- a/data/custodian/AT-4-LAM-L-BLB.yaml +++ b/data/custodian/AT-4-LAM-L-BLB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.517063+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q129792585 + wikidata_url: https://www.wikidata.org/wiki/Q129792585 + label: Stiftsbibliothek Lambach + description: Bibliothek des Benediktinerstifts Lambach + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Direct Wikidata entry for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Lambach Abbey diff --git a/data/custodian/AT-4-LIN-L-ABPB-anton_bruckner_privatuniversitat_bibliothek.yaml b/data/custodian/AT-4-LIN-L-ABPB-anton_bruckner_privatuniversitat_bibliothek.yaml index b756302ade..4a9beb9676 100644 --- a/data/custodian/AT-4-LIN-L-ABPB-anton_bruckner_privatuniversitat_bibliothek.yaml +++ b/data/custodian/AT-4-LIN-L-ABPB-anton_bruckner_privatuniversitat_bibliothek.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.144208+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q461551 + wikidata_url: https://www.wikidata.org/wiki/Q461551 + label: Anton Bruckner Privatuniversität + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Anton Bruckner Privatuniversität diff --git a/data/custodian/AT-4-LIN-L-ABPB.yaml b/data/custodian/AT-4-LIN-L-ABPB.yaml index 5c910d49f0..a65a49d5ee 100644 --- a/data/custodian/AT-4-LIN-L-ABPB.yaml +++ b/data/custodian/AT-4-LIN-L-ABPB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.045368+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q461551 + wikidata_url: https://www.wikidata.org/wiki/Q461551 + label: Anton Bruckner Privatuniversität + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJn5T0RSuYc0cR9hlih7VZaX0 name: Anton Bruckner Privatuniversität diff --git a/data/custodian/AT-4-LIN-L-KKODLWB-katholische_kirche_in_oberosterreich_diozese_linz_.yaml b/data/custodian/AT-4-LIN-L-KKODLWB-katholische_kirche_in_oberosterreich_diozese_linz_.yaml index 1b499e4fcb..a67193a0e8 100644 --- a/data/custodian/AT-4-LIN-L-KKODLWB-katholische_kirche_in_oberosterreich_diozese_linz_.yaml +++ b/data/custodian/AT-4-LIN-L-KKODLWB-katholische_kirche_in_oberosterreich_diozese_linz_.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.216992+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q701832 + wikidata_url: https://www.wikidata.org/wiki/Q701832 + label: Diözese Linz + description: römisch-katholische Diözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Diocese of Linz), not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Diözese Linz - Bischöfliches Ordinariat diff --git a/data/custodian/AT-4-LIN-L-KKODLWB.yaml b/data/custodian/AT-4-LIN-L-KKODLWB.yaml index 43616c18da..9dee0b2da6 100644 --- a/data/custodian/AT-4-LIN-L-KKODLWB.yaml +++ b/data/custodian/AT-4-LIN-L-KKODLWB.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.139995+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q701832 + wikidata_url: https://www.wikidata.org/wiki/Q701832 + label: Diözese Linz + description: römisch-katholische Diözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Diocese of Linz), not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Diözese Linz - Bischöfliches Ordinariat diff --git a/data/custodian/AT-4-LIN-L-KLU.yaml b/data/custodian/AT-4-LIN-L-KLU.yaml index 7d04794293..033383e306 100644 --- a/data/custodian/AT-4-LIN-L-KLU.yaml +++ b/data/custodian/AT-4-LIN-L-KLU.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.547180+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1516259 + wikidata_url: https://www.wikidata.org/wiki/Q1516259 + label: Universität für künstlerische und industrielle Gestaltung Linz + description: Universität in Linz, Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Kunstuniversität Linz), not specifically for the library google_maps_enrichment: place_id: ChIJAQAQ0yqYc0cRyWEq4azw5z4 name: Kunstuniversität Linz Bibliothek diff --git a/data/custodian/AT-4-LIN-L-KPLDUD-katholische_privatuniversitat_linz_diozesan_und_un.yaml b/data/custodian/AT-4-LIN-L-KPLDUD-katholische_privatuniversitat_linz_diozesan_und_un.yaml index ff8f770e5e..95c8c7fb44 100644 --- a/data/custodian/AT-4-LIN-L-KPLDUD-katholische_privatuniversitat_linz_diozesan_und_un.yaml +++ b/data/custodian/AT-4-LIN-L-KPLDUD-katholische_privatuniversitat_linz_diozesan_und_un.yaml @@ -125,6 +125,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.296340+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q179640 + wikidata_url: https://www.wikidata.org/wiki/Q179640 + label: Katholische Privat-Universität Linz + description: Universität in Linz, Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Katholische Privatuniversität Linz), not specifically for the library google_maps_enrichment: place_id: ChIJvcqXk4WXc0cR-eoJPhfjkYY name: Catholic Private University Linz diff --git a/data/custodian/AT-4-LIN-L-KPLDUD.yaml b/data/custodian/AT-4-LIN-L-KPLDUD.yaml index ee5afc1eff..5b0762ae49 100644 --- a/data/custodian/AT-4-LIN-L-KPLDUD.yaml +++ b/data/custodian/AT-4-LIN-L-KPLDUD.yaml @@ -125,6 +125,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.215441+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q179640 + wikidata_url: https://www.wikidata.org/wiki/Q179640 + label: Katholische Privat-Universität Linz + description: Universität in Linz, Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Katholische Privatuniversität Linz), not specifically for the library google_maps_enrichment: place_id: ChIJvcqXk4WXc0cR-eoJPhfjkYY name: Catholic Private University Linz diff --git a/data/custodian/AT-4-LIN-O-OLKG.yaml b/data/custodian/AT-4-LIN-O-OLKG.yaml index 6bec82e362..f9e250f6b7 100644 --- a/data/custodian/AT-4-LIN-O-OLKG.yaml +++ b/data/custodian/AT-4-LIN-O-OLKG.yaml @@ -120,6 +120,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.344318+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: OÖ Landes-Kultur GmbH + description: official institution in Linz, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: OK Center for Contemporary Art Austria diff --git a/data/custodian/AT-5-MAT-A-CMA-collegiatstift_mattsee_archiv.yaml b/data/custodian/AT-5-MAT-A-CMA-collegiatstift_mattsee_archiv.yaml index 2d188bdc6f..e7a43548c2 100644 --- a/data/custodian/AT-5-MAT-A-CMA-collegiatstift_mattsee_archiv.yaml +++ b/data/custodian/AT-5-MAT-A-CMA-collegiatstift_mattsee_archiv.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.147673+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1600414 + wikidata_url: https://www.wikidata.org/wiki/Q1600414 + label: Stift Mattsee + description: ehemaliges Kloster der Benediktiner (OSB), jetziges Kollegiatstift in Mattsee, Salzburg (128484) + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Stift Mattsee), not specifically for the archive google_maps_enrichment: place_id: ChIJp5S33oondEcRp56A7jt87bw name: Kloster / Stift Mattsee diff --git a/data/custodian/AT-5-MAT-A-CMA.yaml b/data/custodian/AT-5-MAT-A-CMA.yaml index 8fba4fb0fb..2eebe298c1 100644 --- a/data/custodian/AT-5-MAT-A-CMA.yaml +++ b/data/custodian/AT-5-MAT-A-CMA.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.047586+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1600414 + wikidata_url: https://www.wikidata.org/wiki/Q1600414 + label: Stift Mattsee + description: ehemaliges Kloster der Benediktiner (OSB), jetziges Kollegiatstift in Mattsee, Salzburg (128484) + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Stift Mattsee), not specifically for the archive google_maps_enrichment: place_id: ChIJp5S33oondEcRp56A7jt87bw name: Kloster / Stift Mattsee diff --git a/data/custodian/AT-5-SAL-A-BESPSBAM.yaml b/data/custodian/AT-5-SAL-A-BESPSBAM.yaml index 522f7c912d..4115525748 100644 --- a/data/custodian/AT-5-SAL-A-BESPSBAM.yaml +++ b/data/custodian/AT-5-SAL-A-BESPSBAM.yaml @@ -124,6 +124,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.519052+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q675735 + wikidata_url: https://www.wikidata.org/wiki/Q675735 + label: Stift Sankt Peter + description: Kloster in Salzburg + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Stift Sankt Peter), not specifically for the library/archive google_maps_enrichment: place_id: ChIJf0zTqWGQdkcRLclzz6-fLmY name: St. Peter's Abbey diff --git a/data/custodian/AT-5-SAL-H-ISMBM.yaml b/data/custodian/AT-5-SAL-H-ISMBM.yaml index 315b11866e..b6ae96fd6a 100644 --- a/data/custodian/AT-5-SAL-H-ISMBM.yaml +++ b/data/custodian/AT-5-SAL-H-ISMBM.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.354214+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q683865 + wikidata_url: https://www.wikidata.org/wiki/Q683865 + label: Internationale Stiftung Mozarteum + description: Non-Profit-Organisation mit Sitz in der österreichischen Stadt Salzburg + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Internationale Stiftung Mozarteum), not specifically for Bibliotheca Mozartiana google_maps_status: NO_MATCH google_maps_rejected: candidate_name: International Mozarteum Foundation diff --git a/data/custodian/AT-5-SAL-L-BLS.yaml b/data/custodian/AT-5-SAL-L-BLS.yaml index c6a1226281..51737f8e0e 100644 --- a/data/custodian/AT-5-SAL-L-BLS.yaml +++ b/data/custodian/AT-5-SAL-L-BLS.yaml @@ -154,6 +154,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.463753+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q2496333 + wikidata_url: https://www.wikidata.org/wiki/Q2496333 + label: Universitätsbibliothek Salzburg + description: Bibliothek in Salzburg + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for Universitätsbibliothek Salzburg, which is the main component of Bibliotheken des Landes Salzburg google_maps_enrichment: place_id: ChIJZYODTGGQdkcRdQBsD8TfQ4s name: University Library Salzburg diff --git a/data/custodian/AT-5-SAL-L-BLSAASL.yaml b/data/custodian/AT-5-SAL-L-BLSAASL.yaml index 2b873f36eb..e0ebd4287e 100644 --- a/data/custodian/AT-5-SAL-L-BLSAASL.yaml +++ b/data/custodian/AT-5-SAL-L-BLSAASL.yaml @@ -126,6 +126,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.466134+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Bibliotheken des Landes Salzburg | Amtsbibliothek, Amt der Salzburger Landesregierung + description: Government office library in Salzburg, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this specific library branch google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Amt der Salzburger Landesregierung diff --git a/data/custodian/AT-5-SAL-L-BLSSLV.yaml b/data/custodian/AT-5-SAL-L-BLSSLV.yaml index 6eea4507a0..491e9874e3 100644 --- a/data/custodian/AT-5-SAL-L-BLSSLV.yaml +++ b/data/custodian/AT-5-SAL-L-BLSSLV.yaml @@ -128,6 +128,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.471314+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Bibliotheken des Landes Salzburg | Salzburger Landesinstitut für Volkskunde + description: Folklore/ethnology research institute library in Salzburg, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this specific institute library google_maps_enrichment: place_id: ChIJQ2QoRgCRdkcRQ5UizazKoHU name: Salzburger Landesinstitut für Volkskunde diff --git a/data/custodian/AT-5-SAL-L-FSB-fachhochschule_salzburg_bibliothek.yaml b/data/custodian/AT-5-SAL-L-FSB-fachhochschule_salzburg_bibliothek.yaml index e83eddc935..9e5833da4e 100644 --- a/data/custodian/AT-5-SAL-L-FSB-fachhochschule_salzburg_bibliothek.yaml +++ b/data/custodian/AT-5-SAL-L-FSB-fachhochschule_salzburg_bibliothek.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.251668+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q701554 + wikidata_url: https://www.wikidata.org/wiki/Q701554 + label: Fachhochschule Salzburg + description: 1995 gegründete Fachhochschule + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Fachhochschule Salzburg), not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: FH Salzburg diff --git a/data/custodian/AT-5-SAL-L-FSB.yaml b/data/custodian/AT-5-SAL-L-FSB.yaml index 66ddc22e3c..c45d92a459 100644 --- a/data/custodian/AT-5-SAL-L-FSB.yaml +++ b/data/custodian/AT-5-SAL-L-FSB.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.172968+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q701554 + wikidata_url: https://www.wikidata.org/wiki/Q701554 + label: Fachhochschule Salzburg + description: 1995 gegründete Fachhochschule + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: FH Salzburg diff --git a/data/custodian/AT-5-SAL-L-PHSB.yaml b/data/custodian/AT-5-SAL-L-PHSB.yaml index 5426fa46e5..949d3df38c 100644 --- a/data/custodian/AT-5-SAL-L-PHSB.yaml +++ b/data/custodian/AT-5-SAL-L-PHSB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.442885+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q22693409 + wikidata_url: https://www.wikidata.org/wiki/Q22693409 + label: Pädagogische Hochschule Salzburg + description: Zentrum der Aus-, Fort- und Weiterbildung für Lehrer in Salzburg in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJw4q9vPKQdkcRfgMU17IAWCM name: University of Education Salzburg diff --git a/data/custodian/AT-5-SAL-L-PMPB.yaml b/data/custodian/AT-5-SAL-L-PMPB.yaml index 7b5f494105..49bd41e21a 100644 --- a/data/custodian/AT-5-SAL-L-PMPB.yaml +++ b/data/custodian/AT-5-SAL-L-PMPB.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.454809+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1476364 + wikidata_url: https://www.wikidata.org/wiki/Q1476364 + label: Paracelsus Medizinische Privatuniversität + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Paracelsus Medical University diff --git a/data/custodian/AT-5-SAW-L-PSSB.yaml b/data/custodian/AT-5-SAW-L-PSSB.yaml index c683304535..c91e15c857 100644 --- a/data/custodian/AT-5-SAW-L-PSSB.yaml +++ b/data/custodian/AT-5-SAW-L-PSSB.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.457086+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1624003 + wikidata_url: https://www.wikidata.org/wiki/Q1624003 + label: Privatuniversität Schloss Seeburg + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Seeburg Castle University diff --git a/data/custodian/AT-5-STR-L-BEBB-bundesinstitut_fur_erwachsenenbildung_bifeb_biblio.yaml b/data/custodian/AT-5-STR-L-BEBB-bundesinstitut_fur_erwachsenenbildung_bifeb_biblio.yaml index d0c8dc9732..8f025a2880 100644 --- a/data/custodian/AT-5-STR-L-BEBB-bundesinstitut_fur_erwachsenenbildung_bifeb_biblio.yaml +++ b/data/custodian/AT-5-STR-L-BEBB-bundesinstitut_fur_erwachsenenbildung_bifeb_biblio.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.170725+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q52606734 + wikidata_url: https://www.wikidata.org/wiki/Q52606734 + label: Bundesministerium für Bildung und Frauen, Bundesinstitut für Erwachsenenbildung + description: Academic publisher based in Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJrVD-wXmxdkcRA0ItYvkwcuA name: Federal Institute for Adult Education diff --git a/data/custodian/AT-5-STR-L-BEBB.yaml b/data/custodian/AT-5-STR-L-BEBB.yaml index 6e9343b211..0d1ea9ee41 100644 --- a/data/custodian/AT-5-STR-L-BEBB.yaml +++ b/data/custodian/AT-5-STR-L-BEBB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.082755+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q52606734 + wikidata_url: https://www.wikidata.org/wiki/Q52606734 + label: Bundesministerium für Bildung und Frauen, Bundesinstitut für Erwachsenenbildung + description: Academic publisher based in Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJrVD-wXmxdkcRA0ItYvkwcuA name: Federal Institute for Adult Education diff --git a/data/custodian/AT-6-GRA-A-DGSD-diozese_graz_seckau_diozesanarchiv.yaml b/data/custodian/AT-6-GRA-A-DGSD-diozese_graz_seckau_diozesanarchiv.yaml index 5bd8794d02..b14b889a19 100644 --- a/data/custodian/AT-6-GRA-A-DGSD-diozese_graz_seckau_diozesanarchiv.yaml +++ b/data/custodian/AT-6-GRA-A-DGSD-diozese_graz_seckau_diozesanarchiv.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.200607+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q259933 + wikidata_url: https://www.wikidata.org/wiki/Q259933 + label: Diözese Graz-Seckau + description: römisch-katholische Diözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (diocese), not specifically for the diocesan archive google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Diözese Graz-Seckau - Bischöfliches Ordinariat diff --git a/data/custodian/AT-6-GRA-A-DGSD.yaml b/data/custodian/AT-6-GRA-A-DGSD.yaml index be3c655c73..b6197611f9 100644 --- a/data/custodian/AT-6-GRA-A-DGSD.yaml +++ b/data/custodian/AT-6-GRA-A-DGSD.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.111775+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q259933 + wikidata_url: https://www.wikidata.org/wiki/Q259933 + label: Diözese Graz-Seckau + description: römisch-katholische Diözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (diocese), not specifically for the diocesan archive google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Diözese Graz-Seckau - Bischöfliches Ordinariat diff --git a/data/custodian/AT-6-GRA-A-UMDKGU.yaml b/data/custodian/AT-6-GRA-A-UMDKGU.yaml index 631a351ea8..1078ff977e 100644 --- a/data/custodian/AT-6-GRA-A-UMDKGU.yaml +++ b/data/custodian/AT-6-GRA-A-UMDKGU.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.531528+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q875147 + wikidata_url: https://www.wikidata.org/wiki/Q875147 + label: Universität für Musik und darstellende Kunst Graz + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (university), not specifically for the university archive google_maps_enrichment: place_id: ChIJy0SFq39KbkcR3ZQDMYHpazQ name: Kunst-Universität Graz diff --git a/data/custodian/AT-6-GRA-L-FJB-fh_joanneum_bibliothek.yaml b/data/custodian/AT-6-GRA-L-FJB-fh_joanneum_bibliothek.yaml index f57700f7a1..0b52777d59 100644 --- a/data/custodian/AT-6-GRA-L-FJB-fh_joanneum_bibliothek.yaml +++ b/data/custodian/AT-6-GRA-L-FJB-fh_joanneum_bibliothek.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.239452+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1388308 + wikidata_url: https://www.wikidata.org/wiki/Q1388308 + label: FH Joanneum + description: Fachhochschule in der Steiermark, Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (university of applied sciences), not specifically for the library google_maps_enrichment: place_id: ChIJhcGXRk81bkcRLCVt1FFrpnE name: FH JOANNEUM Library diff --git a/data/custodian/AT-6-GRA-L-FJB.yaml b/data/custodian/AT-6-GRA-L-FJB.yaml index 428e43e3bd..2a260d5b06 100644 --- a/data/custodian/AT-6-GRA-L-FJB.yaml +++ b/data/custodian/AT-6-GRA-L-FJB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.165930+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1388308 + wikidata_url: https://www.wikidata.org/wiki/Q1388308 + label: FH Joanneum + description: Fachhochschule in der Steiermark, Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (university of applied sciences), not specifically for the library google_maps_enrichment: place_id: ChIJhcGXRk81bkcRLCVt1FFrpnE name: FH JOANNEUM Library diff --git a/data/custodian/AT-6-GRA-L-MUGB.yaml b/data/custodian/AT-6-GRA-L-MUGB.yaml index 4c03932eb9..29c6e13635 100644 --- a/data/custodian/AT-6-GRA-L-MUGB.yaml +++ b/data/custodian/AT-6-GRA-L-MUGB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.561645+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q872543 + wikidata_url: https://www.wikidata.org/wiki/Q872543 + label: Medizinische Universität Graz + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (medical university), not specifically for the library google_maps_enrichment: place_id: ChIJEfjXaW5KbkcRAZPz-k3aT30 name: Library Medical University of Graz diff --git a/data/custodian/AT-6-GRA-L-PHSB-padagogische_hochschule_steiermark_bibliothek.yaml b/data/custodian/AT-6-GRA-L-PHSB-padagogische_hochschule_steiermark_bibliothek.yaml index db845c2b72..39e477f005 100644 --- a/data/custodian/AT-6-GRA-L-PHSB-padagogische_hochschule_steiermark_bibliothek.yaml +++ b/data/custodian/AT-6-GRA-L-PHSB-padagogische_hochschule_steiermark_bibliothek.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.444924+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q2120206 + wikidata_url: https://www.wikidata.org/wiki/Q2120206 + label: Pädagogische Hochschule Steiermark + description: Schule in Graz (56874) + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJsfR1eJo1bkcRJgnRrx1ibvU name: Pädagogische Hochschule Steiermark diff --git a/data/custodian/AT-6-GRA-L-UMDKGU.yaml b/data/custodian/AT-6-GRA-L-UMDKGU.yaml index 5de6d61283..5861084ccf 100644 --- a/data/custodian/AT-6-GRA-L-UMDKGU.yaml +++ b/data/custodian/AT-6-GRA-L-UMDKGU.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.556871+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q875147 + wikidata_url: https://www.wikidata.org/wiki/Q875147 + label: Universität für Musik und darstellende Kunst Graz + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJZXAEcX9KbkcRA-PoNVL5ehg name: Bibliothek der Universität für Musik und darstellende Kunst diff --git a/data/custodian/AT-6-GRA-U-VZFI.yaml b/data/custodian/AT-6-GRA-U-VZFI.yaml index 2187ab5639..f1fd0d1e9e 100644 --- a/data/custodian/AT-6-GRA-U-VZFI.yaml +++ b/data/custodian/AT-6-GRA-U-VZFI.yaml @@ -127,6 +127,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.591304+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Verein zur Förderung der Informationswissenschaft + description: society in Graz, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Österreichischer Integrationsfonds - Integrationszentrum Steiermark diff --git a/data/custodian/AT-6-MUR-A-SSAM.yaml b/data/custodian/AT-6-MUR-A-SSAM.yaml index 10d1cb4b5b..6854089fca 100644 --- a/data/custodian/AT-6-MUR-A-SSAM.yaml +++ b/data/custodian/AT-6-MUR-A-SSAM.yaml @@ -136,6 +136,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.461440+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q668150 + wikidata_url: https://www.wikidata.org/wiki/Q668150 + label: Schwarzenberg + description: fränkisches und böhmisches Adelsgeschlecht + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for the Schwarzenberg noble family who own the archive google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Schloss Murau diff --git a/data/custodian/AT-6-WIE-L-IOOBMWSSP-institut_osterreichischer_orden_bibliothek_der_mar.yaml b/data/custodian/AT-6-WIE-L-IOOBMWSSP-institut_osterreichischer_orden_bibliothek_der_mar.yaml index 0f5b5f1f31..8d86c7fdf6 100644 --- a/data/custodian/AT-6-WIE-L-IOOBMWSSP-institut_osterreichischer_orden_bibliothek_der_mar.yaml +++ b/data/custodian/AT-6-WIE-L-IOOBMWSSP-institut_osterreichischer_orden_bibliothek_der_mar.yaml @@ -151,6 +151,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.193031+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q19971297 + wikidata_url: https://www.wikidata.org/wiki/Q19971297 + label: Mary Ward Privatgymnasium und Oberstufenrealgymnasium St. Pölten + description: Schule in St. Pölten (20597) + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent school institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Mary Ward Schulen diff --git a/data/custodian/AT-6-WIE-L-IOOBMWSSP.yaml b/data/custodian/AT-6-WIE-L-IOOBMWSSP.yaml index 226621b606..d4331d77c1 100644 --- a/data/custodian/AT-6-WIE-L-IOOBMWSSP.yaml +++ b/data/custodian/AT-6-WIE-L-IOOBMWSSP.yaml @@ -151,6 +151,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.103279+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q19971297 + wikidata_url: https://www.wikidata.org/wiki/Q19971297 + label: Mary Ward Privatgymnasium und Oberstufenrealgymnasium St. Pölten + description: Schule in St. Pölten (20597) + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent school institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Mary Ward Schulen diff --git a/data/custodian/AT-7-INN-A-DID-diozese_innsbruck_diozesanarchiv.yaml b/data/custodian/AT-7-INN-A-DID-diozese_innsbruck_diozesanarchiv.yaml index 441e5991a4..d9fb86dc8f 100644 --- a/data/custodian/AT-7-INN-A-DID-diozese_innsbruck_diozesanarchiv.yaml +++ b/data/custodian/AT-7-INN-A-DID-diozese_innsbruck_diozesanarchiv.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.203615+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q278471 + wikidata_url: https://www.wikidata.org/wiki/Q278471 + label: Diözese Innsbruck + description: römisch-katholische Diözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Diocese), not specifically for the Diocesan Archive google_maps_enrichment: place_id: ChIJH_ntGvdrnUcR56KIN-3_nJ0 name: Diözese Innsbruck diff --git a/data/custodian/AT-7-INN-A-DID.yaml b/data/custodian/AT-7-INN-A-DID.yaml index 23aa4ae4d7..eeb04762c8 100644 --- a/data/custodian/AT-7-INN-A-DID.yaml +++ b/data/custodian/AT-7-INN-A-DID.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.116369+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q278471 + wikidata_url: https://www.wikidata.org/wiki/Q278471 + label: Diözese Innsbruck + description: römisch-katholische Diözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Diocese), not specifically for the Diocesan Archive google_maps_enrichment: place_id: ChIJH_ntGvdrnUcR56KIN-3_nJ0 name: Diözese Innsbruck diff --git a/data/custodian/AT-7-INN-A-FRIA-freiwillige_rettung_innsbruck_archiv.yaml b/data/custodian/AT-7-INN-A-FRIA-freiwillige_rettung_innsbruck_archiv.yaml index 32f487ba65..c247d10b92 100644 --- a/data/custodian/AT-7-INN-A-FRIA-freiwillige_rettung_innsbruck_archiv.yaml +++ b/data/custodian/AT-7-INN-A-FRIA-freiwillige_rettung_innsbruck_archiv.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.150244+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q108280972 + wikidata_url: https://www.wikidata.org/wiki/Q108280972 + label: Österreichisches Rotes Kreuz – Freiwillige Rettung Innsbruck + description: Bezirksstelle des Österreichischen Roten Kreuzes – Landesverband Tirol + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Red Cross branch), not specifically for the Archive google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Rotes Kreuz Innsbruck diff --git a/data/custodian/AT-7-INN-A-FRIA.yaml b/data/custodian/AT-7-INN-A-FRIA.yaml index 946575c581..bd68c898c8 100644 --- a/data/custodian/AT-7-INN-A-FRIA.yaml +++ b/data/custodian/AT-7-INN-A-FRIA.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.049715+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q108280972 + wikidata_url: https://www.wikidata.org/wiki/Q108280972 + label: Österreichisches Rotes Kreuz – Freiwillige Rettung Innsbruck + description: Bezirksstelle des Österreichischen Roten Kreuzes – Landesverband Tirol + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Red Cross branch), not specifically for the Archive google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Rotes Kreuz Innsbruck diff --git a/data/custodian/AT-7-INN-L-ATLL.yaml b/data/custodian/AT-7-INN-L-ATLL.yaml index 61adcaa18c..5b5bbe76e2 100644 --- a/data/custodian/AT-7-INN-L-ATLL.yaml +++ b/data/custodian/AT-7-INN-L-ATLL.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.521302+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q2436245 + wikidata_url: https://www.wikidata.org/wiki/Q2436245 + label: Tiroler Landesregierung + description: oberstes Organ der Vollziehung des Landes Tirol + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Tyrolean State Government), not specifically for the State Library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Amt der Tiroler Landesregierung - Unser Land Tirol diff --git a/data/custodian/AT-8-BRE-A-AJB-archiv_der_jugendarbeit_bregenz.yaml b/data/custodian/AT-8-BRE-A-AJB-archiv_der_jugendarbeit_bregenz.yaml index 3ea949f932..c2987ce1fe 100644 --- a/data/custodian/AT-8-BRE-A-AJB-archiv_der_jugendarbeit_bregenz.yaml +++ b/data/custodian/AT-8-BRE-A-AJB-archiv_der_jugendarbeit_bregenz.yaml @@ -136,6 +136,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.153526+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Archiv der Jugendarbeit Bregenz + description: archive in Bregenz, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Offene Jugend- und Kulturarbeit Bregenz diff --git a/data/custodian/AT-8-BRE-A-AJB.yaml b/data/custodian/AT-8-BRE-A-AJB.yaml index 8872115238..f561f354e0 100644 --- a/data/custodian/AT-8-BRE-A-AJB.yaml +++ b/data/custodian/AT-8-BRE-A-AJB.yaml @@ -139,6 +139,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.057273+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Archiv der Jugendarbeit Bregenz + description: archive in Bregenz, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Offene Jugend- und Kulturarbeit Bregenz diff --git a/data/custodian/AT-8-BRE-A-SB.yaml b/data/custodian/AT-8-BRE-A-SB.yaml index c195885252..2e14ab88b6 100644 --- a/data/custodian/AT-8-BRE-A-SB.yaml +++ b/data/custodian/AT-8-BRE-A-SB.yaml @@ -139,6 +139,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.496252+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Stadtarchiv Bregenz + description: municipal archive in Bregenz, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Stadtarchiv diff --git a/data/custodian/AT-8-FEL-L-ASFS-amt_der_stadt_feldkirch_stadtbibliothek.yaml b/data/custodian/AT-8-FEL-L-ASFS-amt_der_stadt_feldkirch_stadtbibliothek.yaml index 02cd34ef16..38dce0d343 100644 --- a/data/custodian/AT-8-FEL-L-ASFS-amt_der_stadt_feldkirch_stadtbibliothek.yaml +++ b/data/custodian/AT-8-FEL-L-ASFS-amt_der_stadt_feldkirch_stadtbibliothek.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.139416+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q183104 + wikidata_url: https://www.wikidata.org/wiki/Q183104 + label: Feldkirch + description: Bezirkshauptstadt in Vorarlberg + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (city of Feldkirch), not specifically for the library google_maps_enrichment: place_id: ChIJ_xNo_Zs5m0cRRs0c7FbVhWc name: Stadtbibliothek Feldkirch diff --git a/data/custodian/AT-8-FEL-L-ASFS.yaml b/data/custodian/AT-8-FEL-L-ASFS.yaml index 3d82fd9d3c..9bc44a094c 100644 --- a/data/custodian/AT-8-FEL-L-ASFS.yaml +++ b/data/custodian/AT-8-FEL-L-ASFS.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.026895+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q183104 + wikidata_url: https://www.wikidata.org/wiki/Q183104 + label: Feldkirch + description: Bezirkshauptstadt in Vorarlberg + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (city of Feldkirch), not specifically for the library google_maps_enrichment: place_id: ChIJ_xNo_Zs5m0cRRs0c7FbVhWc name: Stadtbibliothek Feldkirch diff --git a/data/custodian/AT-8-FEL-L-FVB-fachhochschule_vorarlberg_bibliothek.yaml b/data/custodian/AT-8-FEL-L-FVB-fachhochschule_vorarlberg_bibliothek.yaml index 50d29c60a7..5f1494e8b9 100644 --- a/data/custodian/AT-8-FEL-L-FVB-fachhochschule_vorarlberg_bibliothek.yaml +++ b/data/custodian/AT-8-FEL-L-FVB-fachhochschule_vorarlberg_bibliothek.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.256527+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1391237 + wikidata_url: https://www.wikidata.org/wiki/Q1391237 + label: FHV - Vorarlberg University of Applied Sciences + description: österreichische Hochschule + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Fachhochschule Vorarlberg), not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Bibliothek der Fachhochschule Vorarlberg diff --git a/data/custodian/AT-8-FEL-L-FVB.yaml b/data/custodian/AT-8-FEL-L-FVB.yaml index 992fae4a07..4db172dac5 100644 --- a/data/custodian/AT-8-FEL-L-FVB.yaml +++ b/data/custodian/AT-8-FEL-L-FVB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.179624+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1391237 + wikidata_url: https://www.wikidata.org/wiki/Q1391237 + label: FHV - Vorarlberg University of Applied Sciences + description: österreichische Hochschule + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Fachhochschule Vorarlberg), not specifically for the library google_maps_enrichment: place_id: ChIJIYkzADdrm0cRIKjrMOL-pL4 name: Bibliothek der Fachhochschule Vorarlberg diff --git a/data/custodian/AT-8-FEL-L-PHVB.yaml b/data/custodian/AT-8-FEL-L-PHVB.yaml index fc6fdb46c1..748069031f 100644 --- a/data/custodian/AT-8-FEL-L-PHVB.yaml +++ b/data/custodian/AT-8-FEL-L-PHVB.yaml @@ -122,6 +122,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.448928+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q2120218 + wikidata_url: https://www.wikidata.org/wiki/Q2120218 + label: Pädagogische Hochschule Vorarlberg + description: österreichische Hochschule + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJAfhZB5A5m0cRjElnHGIg570 name: Vorarlberg Teaching University diff --git a/data/custodian/AT-8-FEL-O-LV.yaml b/data/custodian/AT-8-FEL-O-LV.yaml index bb2d4295c5..4781f268f3 100644 --- a/data/custodian/AT-8-FEL-O-LV.yaml +++ b/data/custodian/AT-8-FEL-O-LV.yaml @@ -120,6 +120,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.339539+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1411271 + wikidata_url: https://www.wikidata.org/wiki/Q1411271 + label: Stella Vorarlberg Privathochschule für Musik + description: österreichisches Konservatorium + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry reflects current name (Stella Vorarlberg), formerly Landeskonservatorium für Vorarlberg google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Stella Vorarlberg Privathochschule für Musik diff --git a/data/custodian/AT-9-WIE-A-UBWUU.yaml b/data/custodian/AT-9-WIE-A-UBWUU.yaml index 7582b4429f..f7ac959082 100644 --- a/data/custodian/AT-9-WIE-A-UBWUU.yaml +++ b/data/custodian/AT-9-WIE-A-UBWUU.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.542497+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q876520 + wikidata_url: https://www.wikidata.org/wiki/Q876520 + label: Universität für Bodenkultur Wien + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (BOKU), not specifically for the library/archive google_maps_enrichment: place_id: ChIJrdL1vIAIbUcRPM2GZmnbwow name: Universitätsbibliothek der Universität für Bodenkultur Wien diff --git a/data/custodian/AT-9-WIE-A-WV.yaml b/data/custodian/AT-9-WIE-A-WV.yaml index e04f2eee2d..1ca2cdeb05 100644 --- a/data/custodian/AT-9-WIE-A-WV.yaml +++ b/data/custodian/AT-9-WIE-A-WV.yaml @@ -126,6 +126,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.612871+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Wirtschaftsarchiv Vorarlberg + description: archive in Wien, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Wirtschaftsarchiv Vorarlberg diff --git a/data/custodian/AT-9-WIE-A-WWIHSVBA.yaml b/data/custodian/AT-9-WIE-A-WWIHSVBA.yaml index 52dd5c8c62..4c14d2a590 100644 --- a/data/custodian/AT-9-WIE-A-WWIHSVBA.yaml +++ b/data/custodian/AT-9-WIE-A-WWIHSVBA.yaml @@ -129,6 +129,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.610734+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1748556 + wikidata_url: https://www.wikidata.org/wiki/Q1748556 + label: Wiener Wiesenthal Institut für Holocaust-Studien + description: Forschungsinstitut + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (VWI), not specifically for the library/archive google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Vienna Wiesenthal Institute for Holocaust Studies (VWI) diff --git a/data/custodian/AT-9-WIE-L-CFWB-campus_02_fachhochschule_der_wirtschaft_bibliothek.yaml b/data/custodian/AT-9-WIE-L-CFWB-campus_02_fachhochschule_der_wirtschaft_bibliothek.yaml index b69f1db6f2..12c2f9961d 100644 --- a/data/custodian/AT-9-WIE-L-CFWB-campus_02_fachhochschule_der_wirtschaft_bibliothek.yaml +++ b/data/custodian/AT-9-WIE-L-CFWB-campus_02_fachhochschule_der_wirtschaft_bibliothek.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.260595+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1031662 + wikidata_url: https://www.wikidata.org/wiki/Q1031662 + label: Campus 02 Fachhochschule der Wirtschaft + description: Fachhochschule in Graz, Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: CAMPUS 02 diff --git a/data/custodian/AT-9-WIE-L-CFWB.yaml b/data/custodian/AT-9-WIE-L-CFWB.yaml index dbaf09d10d..0dfa48d50a 100644 --- a/data/custodian/AT-9-WIE-L-CFWB.yaml +++ b/data/custodian/AT-9-WIE-L-CFWB.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.182056+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1031662 + wikidata_url: https://www.wikidata.org/wiki/Q1031662 + label: Campus 02 Fachhochschule der Wirtschaft + description: Fachhochschule in Graz, Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: CAMPUS 02 diff --git a/data/custodian/AT-9-WIE-L-DNOLB.yaml b/data/custodian/AT-9-WIE-L-DNOLB.yaml index f2e0fdb7aa..a0cd4286ee 100644 --- a/data/custodian/AT-9-WIE-L-DNOLB.yaml +++ b/data/custodian/AT-9-WIE-L-DNOLB.yaml @@ -132,6 +132,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.337184+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1988801 + wikidata_url: https://www.wikidata.org/wiki/Q1988801 + label: Niederösterreichische Landesbibliothek + description: wissenschaftliche Allgemeinbibliothek des Landes Niederösterreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: null google_maps_enrichment: place_id: ChIJm0YOyYwHbUcRihEtzxcVRUI name: Dokumentationsstelle F Neuere Österreichische Literatur Im Literaturhaus diff --git a/data/custodian/AT-9-WIE-L-EWWB-erzdiozese_wien_wissenschaftliche_bibliotheken.yaml b/data/custodian/AT-9-WIE-L-EWWB-erzdiozese_wien_wissenschaftliche_bibliotheken.yaml index ac4d520ef2..9835eaddec 100644 --- a/data/custodian/AT-9-WIE-L-EWWB-erzdiozese_wien_wissenschaftliche_bibliotheken.yaml +++ b/data/custodian/AT-9-WIE-L-EWWB-erzdiozese_wien_wissenschaftliche_bibliotheken.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.213900+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q262623 + wikidata_url: https://www.wikidata.org/wiki/Q262623 + label: Erzdiözese Wien + description: römisch-katholische Erzdiözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Archdiocese), not specifically for the libraries google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Erzdiözese Wien diff --git a/data/custodian/AT-9-WIE-L-EWWB.yaml b/data/custodian/AT-9-WIE-L-EWWB.yaml index 3b9b2c8513..ff95b6970d 100644 --- a/data/custodian/AT-9-WIE-L-EWWB.yaml +++ b/data/custodian/AT-9-WIE-L-EWWB.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.134593+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q262623 + wikidata_url: https://www.wikidata.org/wiki/Q262623 + label: Erzdiözese Wien + description: römisch-katholische Erzdiözese in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Archdiocese), not specifically for the libraries google_maps_enrichment: place_id: ChIJ_Zx3PZ4HbUcR2HfqxzXcFH4 name: Kirchliches Bibliothekswerk diff --git a/data/custodian/AT-9-WIE-L-FBWB-fachhochschule_des_bfi_wien_bibliothek.yaml b/data/custodian/AT-9-WIE-L-FBWB-fachhochschule_des_bfi_wien_bibliothek.yaml index 4415b34b75..d52a6a85af 100644 --- a/data/custodian/AT-9-WIE-L-FBWB-fachhochschule_des_bfi_wien_bibliothek.yaml +++ b/data/custodian/AT-9-WIE-L-FBWB-fachhochschule_des_bfi_wien_bibliothek.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.233971+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1391261 + wikidata_url: https://www.wikidata.org/wiki/Q1391261 + label: Fachhochschule des BFI Wien + description: Hochschule in Wien + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: University of Applied Sciences BFI Vienna diff --git a/data/custodian/AT-9-WIE-L-FBWB.yaml b/data/custodian/AT-9-WIE-L-FBWB.yaml index caf6d0d59a..71b532dd32 100644 --- a/data/custodian/AT-9-WIE-L-FBWB.yaml +++ b/data/custodian/AT-9-WIE-L-FBWB.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.160180+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1391261 + wikidata_url: https://www.wikidata.org/wiki/Q1391261 + label: Fachhochschule des BFI Wien + description: Hochschule in Wien + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: University of Applied Sciences BFI Vienna diff --git a/data/custodian/AT-9-WIE-L-FTWB-fachhochschule_technikum_wien_bibliothek.yaml b/data/custodian/AT-9-WIE-L-FTWB-fachhochschule_technikum_wien_bibliothek.yaml index 19abb8287f..7421c177c4 100644 --- a/data/custodian/AT-9-WIE-L-FTWB-fachhochschule_technikum_wien_bibliothek.yaml +++ b/data/custodian/AT-9-WIE-L-FTWB-fachhochschule_technikum_wien_bibliothek.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.272583+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q971426 + wikidata_url: https://www.wikidata.org/wiki/Q971426 + label: Fachhochschule Technikum Wien + description: Technische Fachhochschule in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: University of Applied Sciences Technikum Wien diff --git a/data/custodian/AT-9-WIE-L-FTWB.yaml b/data/custodian/AT-9-WIE-L-FTWB.yaml index d57da48eb6..a39f20f500 100644 --- a/data/custodian/AT-9-WIE-L-FTWB.yaml +++ b/data/custodian/AT-9-WIE-L-FTWB.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.196302+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q971426 + wikidata_url: https://www.wikidata.org/wiki/Q971426 + label: Fachhochschule Technikum Wien + description: Technische Fachhochschule in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJz3HZbk8GbUcRnS-xuzjH_pk name: University of Applied Sciences Technikum Wien diff --git a/data/custodian/AT-9-WIE-L-FWB-fhwien_der_wkw_bibliothek.yaml b/data/custodian/AT-9-WIE-L-FWB-fhwien_der_wkw_bibliothek.yaml index 26d15449ee..53af11c766 100644 --- a/data/custodian/AT-9-WIE-L-FWB-fhwien_der_wkw_bibliothek.yaml +++ b/data/custodian/AT-9-WIE-L-FWB-fhwien_der_wkw_bibliothek.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.263652+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1388299 + wikidata_url: https://www.wikidata.org/wiki/Q1388299 + label: FHWien der WKW + description: Fachhochschule für Management und Kommunikation in Wien + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: FHWien of WKW diff --git a/data/custodian/AT-9-WIE-L-FWB.yaml b/data/custodian/AT-9-WIE-L-FWB.yaml index a86a54e5bf..c380d216fd 100644 --- a/data/custodian/AT-9-WIE-L-FWB.yaml +++ b/data/custodian/AT-9-WIE-L-FWB.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.184914+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1388299 + wikidata_url: https://www.wikidata.org/wiki/Q1388299 + label: FHWien der WKW + description: Fachhochschule für Management und Kommunikation in Wien + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: FHWien of WKW diff --git a/data/custodian/AT-9-WIE-L-GAWB-gesellschaft_der_arzte_in_wien_bibliothek.yaml b/data/custodian/AT-9-WIE-L-GAWB-gesellschaft_der_arzte_in_wien_bibliothek.yaml index e480171c06..96acb608a5 100644 --- a/data/custodian/AT-9-WIE-L-GAWB-gesellschaft_der_arzte_in_wien_bibliothek.yaml +++ b/data/custodian/AT-9-WIE-L-GAWB-gesellschaft_der_arzte_in_wien_bibliothek.yaml @@ -136,6 +136,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.276781+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1518401 + wikidata_url: https://www.wikidata.org/wiki/Q1518401 + label: Gesellschaft der Ärzte in Wien + description: Organisation + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (medical society), not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Gesellschaft der Ärzte in Wien – Billrothhaus diff --git a/data/custodian/AT-9-WIE-L-GAWB.yaml b/data/custodian/AT-9-WIE-L-GAWB.yaml index 6568139bf2..5b9b1b80a8 100644 --- a/data/custodian/AT-9-WIE-L-GAWB.yaml +++ b/data/custodian/AT-9-WIE-L-GAWB.yaml @@ -136,6 +136,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.198765+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1518401 + wikidata_url: https://www.wikidata.org/wiki/Q1518401 + label: Gesellschaft der Ärzte in Wien + description: Organisation + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (medical society), not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Gesellschaft der Ärzte in Wien – Billrothhaus diff --git a/data/custodian/AT-9-WIE-L-HAWCWHBM-hochschule_fur_angewandte_wissenschaften_campus_wi.yaml b/data/custodian/AT-9-WIE-L-HAWCWHBM-hochschule_fur_angewandte_wissenschaften_campus_wi.yaml index 164e8da74b..39bfaf7e8e 100644 --- a/data/custodian/AT-9-WIE-L-HAWCWHBM-hochschule_fur_angewandte_wissenschaften_campus_wi.yaml +++ b/data/custodian/AT-9-WIE-L-HAWCWHBM-hochschule_fur_angewandte_wissenschaften_campus_wi.yaml @@ -130,6 +130,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.236818+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1388304 + wikidata_url: https://www.wikidata.org/wiki/Q1388304 + label: Hochschule Campus Wien + description: Größte Fachhochschule in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJzTYeHGupbUcRkpM-V58MBLw name: Bibliothek Hochschule Campus Wien diff --git a/data/custodian/AT-9-WIE-L-HAWCWHBM.yaml b/data/custodian/AT-9-WIE-L-HAWCWHBM.yaml index c5db6ef3e5..8fb756b82a 100644 --- a/data/custodian/AT-9-WIE-L-HAWCWHBM.yaml +++ b/data/custodian/AT-9-WIE-L-HAWCWHBM.yaml @@ -130,6 +130,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.163082+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q1388304 + wikidata_url: https://www.wikidata.org/wiki/Q1388304 + label: Hochschule Campus Wien + description: Größte Fachhochschule in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_enrichment: place_id: ChIJzTYeHGupbUcRkpM-V58MBLw name: Bibliothek Hochschule Campus Wien diff --git a/data/custodian/AT-9-WIE-L-HMB-heeresgeschichtliches_museum_bibliothek.yaml b/data/custodian/AT-9-WIE-L-HMB-heeresgeschichtliches_museum_bibliothek.yaml index 5338fde045..107c11fc5e 100644 --- a/data/custodian/AT-9-WIE-L-HMB-heeresgeschichtliches_museum_bibliothek.yaml +++ b/data/custodian/AT-9-WIE-L-HMB-heeresgeschichtliches_museum_bibliothek.yaml @@ -132,6 +132,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.300314+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q700751 + wikidata_url: https://www.wikidata.org/wiki/Q700751 + label: Heeresgeschichtliches Museum + description: Museum in Wien + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (museum), not specifically for the library google_maps_enrichment: place_id: ChIJJSoU-t6pbUcRJXTZ_tcG-7g name: Museum of Military History diff --git a/data/custodian/AT-9-WIE-L-HMB.yaml b/data/custodian/AT-9-WIE-L-HMB.yaml index a0d72aeace..9647961ed2 100644 --- a/data/custodian/AT-9-WIE-L-HMB.yaml +++ b/data/custodian/AT-9-WIE-L-HMB.yaml @@ -132,6 +132,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:34:14.217576+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q700751 + wikidata_url: https://www.wikidata.org/wiki/Q700751 + label: Heeresgeschichtliches Museum + description: Museum in Wien + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (museum), not specifically for the library google_maps_enrichment: place_id: ChIJJSoU-t6pbUcRJXTZ_tcG-7g name: Museum of Military History diff --git a/data/custodian/AT-9-WIE-L-MKPSWB.yaml b/data/custodian/AT-9-WIE-L-MKPSWB.yaml index 47f8ae9736..22a6e4f5cb 100644 --- a/data/custodian/AT-9-WIE-L-MKPSWB.yaml +++ b/data/custodian/AT-9-WIE-L-MKPSWB.yaml @@ -126,6 +126,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.326472+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q876640 + wikidata_url: https://www.wikidata.org/wiki/Q876640 + label: Musik und Kunst Privatuniversität der Stadt Wien + description: Universität in Österreich + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: MUK - Music and Arts Private University of Vienna diff --git a/data/custodian/AT-9-WIE-L-OGBRCB.yaml b/data/custodian/AT-9-WIE-L-OGBRCB.yaml index 354a47abbc..bae505c52b 100644 --- a/data/custodian/AT-9-WIE-L-OGBRCB.yaml +++ b/data/custodian/AT-9-WIE-L-OGBRCB.yaml @@ -132,6 +132,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.414134+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q303139 + wikidata_url: https://www.wikidata.org/wiki/Q303139 + label: Belvedere Wien + description: Kunstmuseum im gleichnamigen Schloss + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution (Belvedere museum), not specifically for the research center/library google_maps_enrichment: place_id: ChIJ04RSknkHbUcRgpRWVwtwqeE name: Belvedere Research Center diff --git a/data/custodian/AT-9-WIE-L-PHWB.yaml b/data/custodian/AT-9-WIE-L-PHWB.yaml index fe31468b7d..1a310936ef 100644 --- a/data/custodian/AT-9-WIE-L-PHWB.yaml +++ b/data/custodian/AT-9-WIE-L-PHWB.yaml @@ -127,6 +127,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.451553+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Pädagogische Hochschule Wien | Bibliothek + description: library of teacher education university in Vienna, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for state Pädagogische Hochschule Wien (only Kirchliche + PH Wien/NÖ Q1718503 exists, which is a different church-affiliated institution) google_maps_enrichment: place_id: ChIJF4m-TbmpbUcRWuXz8iQvxZw name: University College of Teacher Education in Vienna diff --git a/data/custodian/AT-9-WIE-L-VUWU.yaml b/data/custodian/AT-9-WIE-L-VUWU.yaml index 42988cac56..83350c808f 100644 --- a/data/custodian/AT-9-WIE-L-VUWU.yaml +++ b/data/custodian/AT-9-WIE-L-VUWU.yaml @@ -127,6 +127,15 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.578581+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q877421 + wikidata_url: https://www.wikidata.org/wiki/Q877421 + label: Veterinärmedizinische Universität Wien + description: Universität in Wien und zugleich die älteste im deutschsprachigen Raum + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the university + library google_maps_enrichment: place_id: ChIJQSRFKpgGbUcR4UqKObOnpWI name: Universitätsbibliothek der Vetmeduni Vienna diff --git a/data/custodian/AT-9-WIE-L-WWB-wirtschaftskammer_wien_bibliothek.yaml b/data/custodian/AT-9-WIE-L-WWB-wirtschaftskammer_wien_bibliothek.yaml index 12711975f7..224fa16221 100644 --- a/data/custodian/AT-9-WIE-L-WWB-wirtschaftskammer_wien_bibliothek.yaml +++ b/data/custodian/AT-9-WIE-L-WWB-wirtschaftskammer_wien_bibliothek.yaml @@ -131,6 +131,14 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.620514+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q14859362 + wikidata_url: https://www.wikidata.org/wiki/Q14859362 + label: Wirtschaftskammer Wien + description: chamber of commerce in Vienna, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry is for parent institution, not specifically for the library google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Wirtschaftskammer Wien diff --git a/data/custodian/AT-9-WIE-M-AMKKB.yaml b/data/custodian/AT-9-WIE-M-AMKKB.yaml index db09e1f7d5..c2610115a3 100644 --- a/data/custodian/AT-9-WIE-M-AMKKB.yaml +++ b/data/custodian/AT-9-WIE-M-AMKKB.yaml @@ -126,6 +126,13 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.624207+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: null + label: Afrika Museum | Kollektion Kabassu-Babu + description: private African art collection/museum in Vienna, Austria + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this private collection google_maps_status: NOT_FOUND google_maps_search_query: Afrika Museum | Kollektion Kabassu-Babu google_maps_search_timestamp: '2025-12-08T20:51:53.566277+00:00' diff --git a/data/custodian/AT-9-WIE-R-FPHS.yaml b/data/custodian/AT-9-WIE-R-FPHS.yaml index e5e0f20037..9984fd663a 100644 --- a/data/custodian/AT-9-WIE-R-FPHS.yaml +++ b/data/custodian/AT-9-WIE-R-FPHS.yaml @@ -126,6 +126,15 @@ ch_annotator: created_from: austria_complete_ch_annotator.yaml creation_date: '2025-12-06T23:36:14.615905+00:00' creation_method: create_custodian_from_ch_annotator.py +wikidata_enrichment: + wikidata_id: Q135095290 + wikidata_url: https://www.wikidata.org/wiki/Q135095290 + label: Forschungsinstitut für Politisch-Historische Studien + description: research institute in Austria (Dr.-Wilfried-Haslauer-Bibliothek Salzburg) + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: Wikidata entry found but has no label/description in Wikidata; institute + operates the Dr.-Wilfried-Haslauer-Bibliothek in Salzburg google_maps_status: NO_MATCH google_maps_rejected: candidate_name: Forschungsinstitut für Politische Wissenschaft und Europäische Fragen diff --git a/data/custodian/JP-01-SAP-L-LGSVMHU.yaml b/data/custodian/JP-01-SAP-L-LGSVMHU.yaml index cb48488a17..803c05eb0c 100644 --- a/data/custodian/JP-01-SAP-L-LGSVMHU.yaml +++ b/data/custodian/JP-01-SAP-L-LGSVMHU.yaml @@ -207,3 +207,29 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:28:07.559639+00:00' + source_url: https://www.lib.hokudai.ac.jp/vet + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lib.hokudai.ac.jp/uploads/2021/01/logo_white_350x59.png + source_url: https://www.lib.hokudai.ac.jp/vet + css_selector: '#masthead > div.custom-header:nth-of-type(2) > div.site-branding:nth-of-type(2) + > a.custom-logo-link > img.custom-logo' + retrieved_on: '2025-12-23T12:28:07.559639+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Hokkaido University Library + - claim_type: og_image_url + claim_value: https://www.lib.hokudai.ac.jp/uploads/2020/03/hulib_og_1200x630.jpg + source_url: https://www.lib.hokudai.ac.jp/vet + css_selector: '[document] > html.js.svg > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:28:07.559639+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-01-SAP-L-SAL-sapporo_akebono_library.yaml b/data/custodian/JP-01-SAP-L-SAL-sapporo_akebono_library.yaml index fca6c8d4df..ef68281df0 100644 --- a/data/custodian/JP-01-SAP-L-SAL-sapporo_akebono_library.yaml +++ b/data/custodian/JP-01-SAP-L-SAL-sapporo_akebono_library.yaml @@ -207,3 +207,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/akebono/akebono.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/akebono/akebono.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:31:37.500715+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/akebono/akebono.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/akebono/akebono.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:31:37.500715+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/akebono/akebono.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:31:37.500715+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-01-SAP-L-SAL.yaml b/data/custodian/JP-01-SAP-L-SAL.yaml index 368a251ba2..a838e020e6 100644 --- a/data/custodian/JP-01-SAP-L-SAL.yaml +++ b/data/custodian/JP-01-SAP-L-SAL.yaml @@ -208,3 +208,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/atubetu/atubetu.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/atubetu/atubetu.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:31:43.266913+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/atubetu/atubetu.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/atubetu/atubetu.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:31:43.266913+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/atubetu/atubetu.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:31:43.266913+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-01-SAP-L-SCLSCU.yaml b/data/custodian/JP-01-SAP-L-SCLSCU.yaml index cedbe84192..286a0966c8 100644 --- a/data/custodian/JP-01-SAP-L-SCLSCU.yaml +++ b/data/custodian/JP-01-SAP-L-SCLSCU.yaml @@ -207,3 +207,22 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:31:57.764463+00:00' + source_url: http://www.lib.scu.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.scu.ac.jp/wp-content/themes/202304scu/assets/images/apple-touch-icon152.png + source_url: http://www.lib.scu.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T12:31:57.764463+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 152x152 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-01-SAP-L-SET.yaml b/data/custodian/JP-01-SAP-L-SET.yaml index be165c8890..89aa704ad5 100644 --- a/data/custodian/JP-01-SAP-L-SET.yaml +++ b/data/custodian/JP-01-SAP-L-SET.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/ehon/index.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/ehon/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:32:03.529881+00:00' + source_url: http://www.city.sapporo.jp/toshokan/ehon/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/ehon/index.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:03.529881+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/ehon/index.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:03.529881+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-01-SAP-L-SHL.yaml b/data/custodian/JP-01-SAP-L-SHL.yaml index 51f6d6914e..b5a3b435b0 100644 --- a/data/custodian/JP-01-SAP-L-SHL.yaml +++ b/data/custodian/JP-01-SAP-L-SHL.yaml @@ -202,3 +202,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/h-sapporo/h-sapporo.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/h-sapporo/h-sapporo.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:32:12.478829+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/h-sapporo/h-sapporo.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/h-sapporo/h-sapporo.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:12.478829+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/h-sapporo/h-sapporo.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:12.478829+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-01-SAP-L-SKL.yaml b/data/custodian/JP-01-SAP-L-SKL.yaml index 5e847c6b74..512cff852a 100644 --- a/data/custodian/JP-01-SAP-L-SKL.yaml +++ b/data/custodian/JP-01-SAP-L-SKL.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/kiyota/kiyota.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/kiyota/kiyota.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:32:18.391090+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/kiyota/kiyota.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/kiyota/kiyota.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:18.391090+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/kiyota/kiyota.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:18.391090+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-01-SAP-L-SL.yaml b/data/custodian/JP-01-SAP-L-SL.yaml index 401c108236..91183a1786 100644 --- a/data/custodian/JP-01-SAP-L-SL.yaml +++ b/data/custodian/JP-01-SAP-L-SL.yaml @@ -222,3 +222,37 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:32:33.133590+00:00' + source_url: http://www.siu.ac.jp/04organ/lim/2799.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.siu.ac.jp/assets/main/img/common/logo.svg + source_url: http://www.siu.ac.jp/04organ/lim/2799.html + css_selector: '#wrap > header.header > div.header_inner > h1.header_logo > a > + img.svg_img' + retrieved_on: '2025-12-23T12:32:33.133590+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 札幌国際大学 + - claim_type: favicon_url + claim_value: http://www.siu.ac.jp/assets/main/img/favicon.ico + source_url: http://www.siu.ac.jp/04organ/lim/2799.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:32:33.133590+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.siu.ac.jp/assets/main/img/common/og.png + source_url: http://www.siu.ac.jp/04organ/lim/2799.html + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T12:32:33.133590+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-01-SAP-L-SML.yaml b/data/custodian/JP-01-SAP-L-SML.yaml index f1ca1e2739..a8da8890e5 100644 --- a/data/custodian/JP-01-SAP-L-SML.yaml +++ b/data/custodian/JP-01-SAP-L-SML.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/motomati/motomati.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/motomati/motomati.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:32:41.136695+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/motomati/motomati.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/motomati/motomati.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:41.136695+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/motomati/motomati.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:32:41.136695+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-01-SAP-L-SNL.yaml b/data/custodian/JP-01-SAP-L-SNL.yaml index 8344d3992e..a1b83d4531 100644 --- a/data/custodian/JP-01-SAP-L-SNL.yaml +++ b/data/custodian/JP-01-SAP-L-SNL.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/nisioka/nisioka.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/nisioka/nisioka.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:33:22.516626+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/nisioka/nisioka.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/nisioka/nisioka.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:33:22.516626+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/nisioka/nisioka.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:33:22.516626+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-01-SAP-L-SSL-sapporo_sumikawa_library.yaml b/data/custodian/JP-01-SAP-L-SSL-sapporo_sumikawa_library.yaml index e471599ac5..9b34685809 100644 --- a/data/custodian/JP-01-SAP-L-SSL-sapporo_sumikawa_library.yaml +++ b/data/custodian/JP-01-SAP-L-SSL-sapporo_sumikawa_library.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/sumikawa/sumikawa.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/sumikawa/sumikawa.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:34:02.255212+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/sumikawa/sumikawa.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/sumikawa/sumikawa.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:34:02.255212+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/sumikawa/sumikawa.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:34:02.255212+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-01-SAP-L-SSL.yaml b/data/custodian/JP-01-SAP-L-SSL.yaml index a9282c977e..8f5de6b1f8 100644 --- a/data/custodian/JP-01-SAP-L-SSL.yaml +++ b/data/custodian/JP-01-SAP-L-SSL.yaml @@ -207,3 +207,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/ wikidata_official_website: http://www.city.sapporo.jp/toshokan/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:34:09.427795+00:00' + source_url: http://www.city.sapporo.jp/toshokan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-23T12:34:09.427795+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:34:09.427795+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-01-SAP-L-SUHSL.yaml b/data/custodian/JP-01-SAP-L-SUHSL.yaml index 3a5931fe21..32c1e8d8d9 100644 --- a/data/custodian/JP-01-SAP-L-SUHSL.yaml +++ b/data/custodian/JP-01-SAP-L-SUHSL.yaml @@ -222,3 +222,28 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:36:36.306923+00:00' + source_url: http://www.sapporo-hokeniryou-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sapporo-hokeniryou-u.ac.jp/assets/img/common/mask-icon.svg + source_url: http://www.sapporo-hokeniryou-u.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T12:36:36.306923+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sapporo-hokeniryou-u.ac.jp/assets/img/common/fb_icon.jpg + source_url: http://www.sapporo-hokeniryou-u.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-23T12:36:36.306923+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/JP-01-SAP-L-SUL.yaml b/data/custodian/JP-01-SAP-L-SUL.yaml index 8daea8a42d..136a1b8ad0 100644 --- a/data/custodian/JP-01-SAP-L-SUL.yaml +++ b/data/custodian/JP-01-SAP-L-SUL.yaml @@ -216,3 +216,22 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:36:48.713301+00:00' + source_url: http://www.sapporo-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.sapporo-u.ac.jp/common/img/favicon.ico?ver=20240227 + source_url: http://www.sapporo-u.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:36:48.713301+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-01-SAP-L-SYL.yaml b/data/custodian/JP-01-SAP-L-SYL.yaml index a7d35766cc..3a832a47b3 100644 --- a/data/custodian/JP-01-SAP-L-SYL.yaml +++ b/data/custodian/JP-01-SAP-L-SYL.yaml @@ -207,3 +207,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.sapporo.jp/toshokan/sisetu/yamanote/yamanote.html wikidata_official_website: http://www.city.sapporo.jp/toshokan/sisetu/yamanote/yamanote.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:36:55.635313+00:00' + source_url: http://www.city.sapporo.jp/toshokan/sisetu/yamanote/yamanote.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: http://www.city.sapporo.jp/toshokan/sisetu/yamanote/yamanote.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T12:36:55.635313+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: http://www.city.sapporo.jp/toshokan/sisetu/yamanote/yamanote.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T12:36:55.635313+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-01-SAP-L-TCL.yaml b/data/custodian/JP-01-SAP-L-TCL.yaml index ad31feb94a..01ad0efcb4 100644 --- a/data/custodian/JP-01-SAP-L-TCL.yaml +++ b/data/custodian/JP-01-SAP-L-TCL.yaml @@ -218,3 +218,22 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:37:06.317086+00:00' + source_url: http://www.tenshi.ac.jp/lib/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tenshi.ac.jp/assets/images/common/favicon.ico + source_url: http://www.tenshi.ac.jp/lib/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:37:06.317086+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-01-SAP-M-AMSU.yaml b/data/custodian/JP-01-SAP-M-AMSU.yaml index 6d35362507..15d27b76fc 100644 --- a/data/custodian/JP-01-SAP-M-AMSU.yaml +++ b/data/custodian/JP-01-SAP-M-AMSU.yaml @@ -219,3 +219,22 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:37:55.594721+00:00' + source_url: https://www.sapporo-u.ac.jp/univ-guide/campus/museum.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sapporo-u.ac.jp/common/img/favicon.ico?ver=20240227 + source_url: https://www.sapporo-u.ac.jp/univ-guide/campus/museum.html + css_selector: '[document] > html > body > link' + retrieved_on: '2025-12-23T12:37:55.594721+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-01-SAP-M-BGFSCNBHU.yaml b/data/custodian/JP-01-SAP-M-BGFSCNBHU.yaml index 48890171c3..62d6f5ac45 100644 --- a/data/custodian/JP-01-SAP-M-BGFSCNBHU.yaml +++ b/data/custodian/JP-01-SAP-M-BGFSCNBHU.yaml @@ -319,3 +319,36 @@ location: postal_code: 060-0003 street_address: KITA3-JONISHI, Sapporo Shi Chuo Ku, Hokkaido, 060-0003 normalization_timestamp: '2025-12-09T06:54:54.027449+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:38:08.315161+00:00' + source_url: https://www.hokudai.ac.jp/fsc/bg + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.fsc.hokudai.ac.jp/wp-content/themes/fsc/images/common/logo.png + source_url: https://www.hokudai.ac.jp/fsc/bg + css_selector: '#headerCon > h1.logo > a > img' + retrieved_on: '2025-12-23T12:38:08.315161+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 国立大学法人北海道大学 北方生物圏フィールド科学センター FSC Field Science Center for Northern Biosphere + - claim_type: favicon_url + claim_value: https://www.fsc.hokudai.ac.jp/wp-content/uploads/2019/10/cropped-smc-180x180.png + source_url: https://www.hokudai.ac.jp/fsc/bg + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-23T12:38:08.315161+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.fsc.hokudai.ac.jp/wp-content/uploads/2019/10/cropped-smc.png + source_url: https://www.hokudai.ac.jp/fsc/bg + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-23T12:38:08.315161+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-01-SAP-M-CSM.yaml b/data/custodian/JP-01-SAP-M-CSM.yaml index 09df27887a..fdd3b5622b 100644 --- a/data/custodian/JP-01-SAP-M-CSM.yaml +++ b/data/custodian/JP-01-SAP-M-CSM.yaml @@ -210,3 +210,28 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:38:20.051022+00:00' + source_url: http://www.nipponseishu.co.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nipponseishu.co.jp/wordpress/wp-content/themes/nihonseishu/assets/images/apple-touch-icon.png + source_url: http://www.nipponseishu.co.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:38:20.051022+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://nipponseishu.co.jp/wordpress/wp-content/themes/nihonseishu/assets/images/ogp_chitosetsuru.png + source_url: http://www.nipponseishu.co.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-23T12:38:20.051022+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-01-SAP-M-HML.yaml b/data/custodian/JP-01-SAP-M-HML.yaml index c6204b3dda..7595710efe 100644 --- a/data/custodian/JP-01-SAP-M-HML.yaml +++ b/data/custodian/JP-01-SAP-M-HML.yaml @@ -272,3 +272,28 @@ location: postal_code: 064-0931 street_address: NAKAJIMAKOEN, Sapporo Shi Chuo Ku, Hokkaido, 064-0931 normalization_timestamp: '2025-12-09T08:40:37.360722+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:38:41.863019+00:00' + source_url: http://www.h-bungaku.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.h-bungaku.or.jp/images/favicon.ico + source_url: http://www.h-bungaku.or.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:38:41.863019+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/favicon.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.h-bungaku.or.jp/images/ogp_thumbnail.jpg + source_url: http://www.h-bungaku.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:38:41.863019+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-01-SAP-M-HUM.yaml b/data/custodian/JP-01-SAP-M-HUM.yaml index 123f934273..e760bf66dc 100644 --- a/data/custodian/JP-01-SAP-M-HUM.yaml +++ b/data/custodian/JP-01-SAP-M-HUM.yaml @@ -288,3 +288,30 @@ location: postal_code: 060-0810 street_address: KITA10-JONISHI, Sapporo Shi Kita Ku, Hokkaido, 060-0810 normalization_timestamp: '2025-12-09T06:54:54.306718+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:46:56.694903+00:00' + source_url: https://www.museum.hokudai.ac.jp/english + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.museum.hokudai.ac.jp/english/wp-content/themes/museum-en_2403/images/logo.png + source_url: https://www.museum.hokudai.ac.jp/english + css_selector: '#logo' + retrieved_on: '2025-12-23T12:46:56.694903+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: The Hokkaido University Museum + - claim_type: favicon_url + claim_value: https://www.museum.hokudai.ac.jp/english/wp-content/uploads/sites/2/2020/09/fabicon-1.png + source_url: https://www.museum.hokudai.ac.jp/english + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-23T12:46:56.694903+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-01-SAP-M-MSBM.yaml b/data/custodian/JP-01-SAP-M-MSBM.yaml index ee4ccc12ec..c6299b9b67 100644 --- a/data/custodian/JP-01-SAP-M-MSBM.yaml +++ b/data/custodian/JP-01-SAP-M-MSBM.yaml @@ -213,3 +213,28 @@ location: geonames_id: 2128295 geonames_name: Sapporo feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:47:11.534209+00:00' + source_url: http://www.meg-snow.com/fun/factory/sapporo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.meg-snow.com/favicon.ico + source_url: http://www.meg-snow.com/fun/factory/sapporo + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T12:47:11.534209+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.meg-snow.com/fun/factory/assets/ogp/sapporo.png + source_url: http://www.meg-snow.com/fun/factory/sapporo + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T12:47:11.534209+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-01-SAP-M-SA.yaml b/data/custodian/JP-01-SAP-M-SA.yaml index 0d421d7e67..71b9685b9b 100644 --- a/data/custodian/JP-01-SAP-M-SA.yaml +++ b/data/custodian/JP-01-SAP-M-SA.yaml @@ -246,3 +246,28 @@ location: postal_code: 004-0052 street_address: ATSUBETSUCHUO 2-JO, Sapporo Shi Atsubetsu Ku, Hokkaido, 004-0052 normalization_timestamp: '2025-12-09T06:54:54.394965+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:47:25.312075+00:00' + source_url: http://www.sunpiazza-aquarium.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.sunpiazza-aquarium.com/apple-touch-icon.png + source_url: http://www.sunpiazza-aquarium.com + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T12:47:25.312075+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sunpiazza-aquarium.com/ogp.jpg + source_url: http://www.sunpiazza-aquarium.com + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:47:25.312075+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-01-SAP-M-SAM.yaml b/data/custodian/JP-01-SAP-M-SAM.yaml index 8ea1820f44..7497526ebb 100644 --- a/data/custodian/JP-01-SAP-M-SAM.yaml +++ b/data/custodian/JP-01-SAP-M-SAM.yaml @@ -293,3 +293,28 @@ location: postal_code: 005-0864 street_address: GEIJUTSUNOMORI, Sapporo Shi Minami Ku, Hokkaido, 005-0864 normalization_timestamp: '2025-12-09T06:54:54.426737+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:47:34.581184+00:00' + source_url: https://artpark.or.jp/shisetsu/sapporo-art-museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://artpark.or.jp/apple-touch-icon.png + source_url: https://artpark.or.jp/shisetsu/sapporo-art-museum + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:47:34.581184+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://artpark.or.jp/ogp.png + source_url: https://artpark.or.jp/shisetsu/sapporo-art-museum + css_selector: '[document] > html > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-23T12:47:34.581184+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-01-SAP-M-SBM.yaml b/data/custodian/JP-01-SAP-M-SBM.yaml index 5e5b91864f..6da8df33a9 100644 --- a/data/custodian/JP-01-SAP-M-SBM.yaml +++ b/data/custodian/JP-01-SAP-M-SBM.yaml @@ -292,3 +292,28 @@ location: postal_code: 065-8633 street_address: KITA7-JOHIGASHI, Sapporo Shi Higashi Ku, Hokkaido, 065-8633 normalization_timestamp: '2025-12-09T06:54:54.462526+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:47:45.095190+00:00' + source_url: https://www.sapporobeer.jp/brewery/s_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/s_museum + css_selector: '[document] > html.webkit.chrome > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:47:45.095190+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/s_museum + css_selector: '[document] > html.webkit.chrome > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T12:47:45.095190+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-01-SAP-M-SIUM.yaml b/data/custodian/JP-01-SAP-M-SIUM.yaml index b82a51be20..dd8539b463 100644 --- a/data/custodian/JP-01-SAP-M-SIUM.yaml +++ b/data/custodian/JP-01-SAP-M-SIUM.yaml @@ -225,3 +225,22 @@ location: postal_code: 004-8602 street_address: KIYOTA 4-JO, Sapporo Shi Kiyota Ku, Hokkaido, 004-8602 normalization_timestamp: '2025-12-09T06:54:54.565528+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:48:16.199763+00:00' + source_url: https://www.siu.ac.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.siu.ac.jp/favicon.ico + source_url: https://www.siu.ac.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:48:16.199763+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-01-SAP-M-SMAC.yaml b/data/custodian/JP-01-SAP-M-SMAC.yaml index 9ced6701db..7a00b63b60 100644 --- a/data/custodian/JP-01-SAP-M-SMAC.yaml +++ b/data/custodian/JP-01-SAP-M-SMAC.yaml @@ -239,3 +239,28 @@ location: postal_code: 062-0935 street_address: HIRAGISHI 5-JO, Sapporo Shi Toyohira Ku, Hokkaido, 062-0935 normalization_timestamp: '2025-12-09T06:54:54.605256+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:48:24.007882+00:00' + source_url: https://www.city.sapporo.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.sapporo.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-23T12:48:24.007882+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: https://www.city.sapporo.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T12:48:24.007882+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-01-SAP-M-SMZ.yaml b/data/custodian/JP-01-SAP-M-SMZ.yaml index b2ad824d7f..8480c8e7f6 100644 --- a/data/custodian/JP-01-SAP-M-SMZ.yaml +++ b/data/custodian/JP-01-SAP-M-SMZ.yaml @@ -245,3 +245,28 @@ wikidata_enrichment: commons_category: Sapporo Maruyama Zoo image: Sapporo Maruyama Zoo Main Gate.JPG wikidata_image: Sapporo Maruyama Zoo Main Gate.JPG +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:48:33.429522+00:00' + source_url: https://www.city.sapporo.jp/zoo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sapporo.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.sapporo.jp/zoo + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-23T12:48:33.429522+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sapporo.jp/shared/system/images/municipal_emblem.jpg + source_url: https://www.city.sapporo.jp/zoo + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:48:33.429522+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-01-SAP-M-SWM.yaml b/data/custodian/JP-01-SAP-M-SWM.yaml index 3c80c18eb5..f9500d364a 100644 --- a/data/custodian/JP-01-SAP-M-SWM.yaml +++ b/data/custodian/JP-01-SAP-M-SWM.yaml @@ -252,3 +252,22 @@ location: postal_code: 064-0942 street_address: FUSHIMI, Sapporo Shi Chuo Ku, Hokkaido, 064-0942 normalization_timestamp: '2025-12-09T06:54:54.789242+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:48:59.868966+00:00' + source_url: https://www.swsa.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.swsa.jp/common/img/logo.png + source_url: https://www.swsa.jp/museum + css_selector: '#header > h1.big_img > a > img.mt10.photo-left0' + retrieved_on: '2025-12-23T12:48:59.868966+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 札幌市水道記念館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-01-SAP-M-WJML.yaml b/data/custodian/JP-01-SAP-M-WJML.yaml index 836629413e..96b5730a0c 100644 --- a/data/custodian/JP-01-SAP-M-WJML.yaml +++ b/data/custodian/JP-01-SAP-M-WJML.yaml @@ -226,3 +226,22 @@ location: postal_code: 064-0912 street_address: MINAMI12-JONISHI, Sapporo Shi Chuo Ku, Hokkaido, 064-0912 normalization_timestamp: '2025-12-09T06:54:54.823404+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:49:09.113032+00:00' + source_url: http://watanabe-museum.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://watanabe-museum.com/img/favicon.png + source_url: http://watanabe-museum.com + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:49:09.113032+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-01-SAR-L-BL.yaml b/data/custodian/JP-01-SAR-L-BL.yaml index bfe5df644a..daf76cf819 100644 --- a/data/custodian/JP-01-SAR-L-BL.yaml +++ b/data/custodian/JP-01-SAR-L-BL.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.biratori.hokkaido.jp/kyouiku/gakkou_library/ wikidata_official_website: http://www.town.biratori.hokkaido.jp/kyouiku/gakkou_library/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:49:26.999480+00:00' + source_url: http://www.town.biratori.hokkaido.jp/kyouiku/gakkou_library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.biratori.hokkaido.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.biratori.hokkaido.jp/kyouiku/gakkou_library + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:49:26.999480+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.biratori.hokkaido.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.biratori.hokkaido.jp/kyouiku/gakkou_library + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:49:26.999480+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-01-SAR-M-BTNACM.yaml b/data/custodian/JP-01-SAR-M-BTNACM.yaml index ef65cf2ec6..1dc6f26392 100644 --- a/data/custodian/JP-01-SAR-M-BTNACM.yaml +++ b/data/custodian/JP-01-SAR-M-BTNACM.yaml @@ -291,3 +291,28 @@ location: postal_code: 055-0101 street_address: NIBUTANI, Saru Gun Biratori Cho, Hokkaido, 055-0101 normalization_timestamp: '2025-12-09T06:54:54.905852+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:49:38.723793+00:00' + source_url: http://www.town.biratori.hokkaido.jp/biratori/nibutani + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.biratori.hokkaido.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.biratori.hokkaido.jp/biratori/nibutani + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:49:38.723793+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.biratori.hokkaido.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.biratori.hokkaido.jp/biratori/nibutani + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:49:38.723793+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-01-SAR-M-HMM.yaml b/data/custodian/JP-01-SAR-M-HMM.yaml index d75f33cfd6..90383ec0a2 100644 --- a/data/custodian/JP-01-SAR-M-HMM.yaml +++ b/data/custodian/JP-01-SAR-M-HMM.yaml @@ -267,3 +267,28 @@ location: postal_code: 055-2301 street_address: HONCHOHIGASHI, Saru Gun Hidaka Cho, Hokkaido, 055-2301 normalization_timestamp: '2025-12-09T06:54:54.925484+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:49:47.218921+00:00' + source_url: http://www.town.hidaka.hokkaido.jp/site/hmc + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.hidaka.hokkaido.jp/favicon.svg + source_url: http://www.town.hidaka.hokkaido.jp/site/hmc + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:49:47.218921+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + - claim_type: og_image_url + claim_value: https://www.town.hidaka.hokkaido.jp/assets/images/og-image.jpg + source_url: http://www.town.hidaka.hokkaido.jp/site/hmc + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:49:47.218921+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-01-SAR-M-HMSR.yaml b/data/custodian/JP-01-SAR-M-HMSR.yaml index 018fe8e547..452e030889 100644 --- a/data/custodian/JP-01-SAR-M-HMSR.yaml +++ b/data/custodian/JP-01-SAR-M-HMSR.yaml @@ -268,3 +268,28 @@ location: postal_code: 055-0101 street_address: NIBUTANI, Saru Gun Biratori Cho, Hokkaido, 055-0101 normalization_timestamp: '2025-12-09T06:54:54.944014+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:49:56.376563+00:00' + source_url: http://www.town.biratori.hokkaido.jp/kankou/bunka/bunka9 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.biratori.hokkaido.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.biratori.hokkaido.jp/kankou/bunka/bunka9 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:49:56.376563+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.biratori.hokkaido.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.biratori.hokkaido.jp/kankou/bunka/bunka9 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:49:56.376563+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-01-SHA-L-CL.yaml b/data/custodian/JP-01-SHA-L-CL.yaml index df7dc2d1a1..708ca54825 100644 --- a/data/custodian/JP-01-SHA-L-CL.yaml +++ b/data/custodian/JP-01-SHA-L-CL.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.koshimizu.hokkaido.jp/library/ wikidata_official_website: http://www.town.koshimizu.hokkaido.jp/library/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:50:30.412636+00:00' + source_url: http://www.town.koshimizu.hokkaido.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.koshimizu.hokkaido.jp/icon.png + source_url: http://www.town.koshimizu.hokkaido.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:50:30.412636+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-01-SHA-L-KL.yaml b/data/custodian/JP-01-SHA-L-KL.yaml index 1bd51359d1..379d3f0e05 100644 --- a/data/custodian/JP-01-SHA-L-KL.yaml +++ b/data/custodian/JP-01-SHA-L-KL.yaml @@ -200,3 +200,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.kiyosato.hokkaido.jp/soshiki_shigoto/kyouikuiinkai/library/ wikidata_official_website: http://www.town.kiyosato.hokkaido.jp/soshiki_shigoto/kyouikuiinkai/library/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:50:42.493515+00:00' + source_url: http://www.town.kiyosato.hokkaido.jp/soshiki_shigoto/kyouikuiinkai/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.kiyosato.hokkaido.jp/apple-touch-icon.png + source_url: http://www.town.kiyosato.hokkaido.jp/soshiki_shigoto/kyouikuiinkai/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:50:42.493515+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.town.kiyosato.hokkaido.jp/assets/images/og-image.jpg + source_url: http://www.town.kiyosato.hokkaido.jp/soshiki_shigoto/kyouikuiinkai/library + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:50:42.493515+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-01-SHA-L-SL.yaml b/data/custodian/JP-01-SHA-L-SL.yaml index b93b2c677b..a2c6afbacf 100644 --- a/data/custodian/JP-01-SHA-L-SL.yaml +++ b/data/custodian/JP-01-SHA-L-SL.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: https://www.town.shari.hokkaido.jp/05institution/10kyouiku_bunka/catetemp3_institution/2017-0129-1216-46.html wikidata_official_website: https://www.town.shari.hokkaido.jp/05institution/10kyouiku_bunka/catetemp3_institution/2017-0129-1216-46.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:50:57.396894+00:00' + source_url: https://www.town.shari.hokkaido.jp/05institution/10kyouiku_bunka/catetemp3_institution/2017-0129-1216-46.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.shari.hokkaido.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.town.shari.hokkaido.jp/05institution/10kyouiku_bunka/catetemp3_institution/2017-0129-1216-46.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T12:50:57.396894+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 斜里町 Shari town Hokkaido + - claim_type: favicon_url + claim_value: https://www.town.shari.hokkaido.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.shari.hokkaido.jp/05institution/10kyouiku_bunka/catetemp3_institution/2017-0129-1216-46.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:50:57.396894+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.shari.hokkaido.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.town.shari.hokkaido.jp/05institution/10kyouiku_bunka/catetemp3_institution/2017-0129-1216-46.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T12:50:57.396894+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-01-SHA-M-AAMN.yaml b/data/custodian/JP-01-SHA-M-AAMN.yaml index be09038b0a..7197612fb8 100644 --- a/data/custodian/JP-01-SHA-M-AAMN.yaml +++ b/data/custodian/JP-01-SHA-M-AAMN.yaml @@ -212,3 +212,22 @@ location: geonames_id: 2111135 geonames_name: Shari feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:51:03.422107+00:00' + source_url: http://www.alp-museum.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.alp-museum.org/logo/favicon1.png + source_url: http://www.alp-museum.org + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:51:03.422107+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-01-SHI-L-S-shiranukachokominkantoshoshitsu.yaml b/data/custodian/JP-01-SHI-L-S-shiranukachokominkantoshoshitsu.yaml index 525c34d3ef..ca1b5e5874 100644 --- a/data/custodian/JP-01-SHI-L-S-shiranukachokominkantoshoshitsu.yaml +++ b/data/custodian/JP-01-SHI-L-S-shiranukachokominkantoshoshitsu.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.shiranuka.lg.jp/section/kyoiku/shakai/qvum4j00000002mp.html wikidata_official_website: http://www.town.shiranuka.lg.jp/section/kyoiku/shakai/qvum4j00000002mp.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:51:23.429823+00:00' + source_url: http://www.town.shiranuka.lg.jp/section/kyoiku/shakai/qvum4j00000002mp.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.shiranuka.lg.jp/favicon.ico + source_url: http://www.town.shiranuka.lg.jp/section/kyoiku/shakai/qvum4j00000002mp.html + css_selector: '[document] > html.no-touchevents.flexbox > head > link' + retrieved_on: '2025-12-23T12:51:23.429823+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.ico + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.shiranuka.lg.jp/section/kyoiku/shakai/qvum4j00000002mp-img/qvum4j00000002r0.jpg + source_url: http://www.town.shiranuka.lg.jp/section/kyoiku/shakai/qvum4j00000002mp.html + css_selector: '[document] > html.no-touchevents.flexbox > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:51:23.429823+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-01-SHI-L-S.yaml b/data/custodian/JP-01-SHI-L-S.yaml index 64a831073a..7072ff6ef8 100644 --- a/data/custodian/JP-01-SHI-L-S.yaml +++ b/data/custodian/JP-01-SHI-L-S.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.ikuhaku.com/mains/systemdetail/hokkaido/shimamaki_mura/27491/ wikidata_official_website: http://www.ikuhaku.com/mains/systemdetail/hokkaido/shimamaki_mura/27491/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:51:36.550526+00:00' + source_url: http://www.ikuhaku.com/mains/systemdetail/hokkaido/shimamaki_mura/27491 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.ikuhaku.com/images/common/logo.gif + source_url: http://www.ikuhaku.com/mains/systemdetail/hokkaido/shimamaki_mura/27491 + css_selector: '#header > div.header_top > div.header_top_in > p.h_logo > a > img' + retrieved_on: '2025-12-23T12:51:36.550526+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 育児助成金白書（イクハクTOP） + - claim_type: favicon_url + claim_value: https://www.ikuhaku.com/apple-touch-icon-152x152.png + source_url: http://www.ikuhaku.com/mains/systemdetail/hokkaido/shimamaki_mura/27491 + css_selector: '[document] > html.js.svg > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T12:51:36.550526+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 152x152 + - claim_type: og_image_url + claim_value: https://www.ikuhaku.com/share.png + source_url: http://www.ikuhaku.com/mains/systemdetail/hokkaido/shimamaki_mura/27491 + css_selector: '[document] > html.js.svg > head > meta:nth-of-type(21)' + retrieved_on: '2025-12-23T12:51:36.550526+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/JP-01-SHI-L-SL-shiraoichoritsu_library.yaml b/data/custodian/JP-01-SHI-L-SL-shiraoichoritsu_library.yaml index 6ee443af1d..471be23689 100644 --- a/data/custodian/JP-01-SHI-L-SL-shiraoichoritsu_library.yaml +++ b/data/custodian/JP-01-SHI-L-SL-shiraoichoritsu_library.yaml @@ -219,3 +219,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.shiraoi.hokkaido.jp/bunya/tosyokan/ wikidata_official_website: http://www.town.shiraoi.hokkaido.jp/bunya/tosyokan/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:51:47.259345+00:00' + source_url: http://www.town.shiraoi.hokkaido.jp/bunya/tosyokan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.shiraoi.hokkaido.jp/common/images/apple-touch-icon.png + source_url: http://www.town.shiraoi.hokkaido.jp/bunya/tosyokan + css_selector: '[document] > html.history.no-touchevents > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T12:51:47.259345+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.shiraoi.hokkaido.jp/common/images/ogp.jpg + source_url: http://www.town.shiraoi.hokkaido.jp/bunya/tosyokan + css_selector: '[document] > html.history.no-touchevents > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T12:51:47.259345+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-01-SHI-L-SL.yaml b/data/custodian/JP-01-SHI-L-SL.yaml index 3ea9615849..7e3a9029e5 100644 --- a/data/custodian/JP-01-SHI-L-SL.yaml +++ b/data/custodian/JP-01-SHI-L-SL.yaml @@ -199,3 +199,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.shibetsu.lg.jp/www/contents/1134459220546/index.html wikidata_official_website: http://www.city.shibetsu.lg.jp/www/contents/1134459220546/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:51:58.102517+00:00' + source_url: http://www.city.shibetsu.lg.jp/www/contents/1134459220546/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.shibetsu.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.shibetsu.lg.jp/www/contents/1134459220546/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T12:51:58.102517+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 士別市 Shibetsu City + - claim_type: favicon_url + claim_value: http://www.city.shibetsu.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.shibetsu.lg.jp/www/contents/1134459220546/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:51:58.102517+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.shibetsu.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.shibetsu.lg.jp/www/contents/1134459220546/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:51:58.102517+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-01-SHI-L-SLA.yaml b/data/custodian/JP-01-SHI-L-SLA.yaml index 6c53ee0507..7bd92b7011 100644 --- a/data/custodian/JP-01-SHI-L-SLA.yaml +++ b/data/custodian/JP-01-SHI-L-SLA.yaml @@ -199,3 +199,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.shibetsu.lg.jp/www/contents/1245632240202/index.html wikidata_official_website: http://www.city.shibetsu.lg.jp/www/contents/1245632240202/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:52:08.245056+00:00' + source_url: http://www.city.shibetsu.lg.jp/www/contents/1245632240202/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.shibetsu.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.shibetsu.lg.jp/www/contents/1245632240202/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T12:52:08.245056+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 士別市 Shibetsu City + - claim_type: favicon_url + claim_value: http://www.city.shibetsu.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.shibetsu.lg.jp/www/contents/1245632240202/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:52:08.245056+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.shibetsu.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.shibetsu.lg.jp/www/contents/1245632240202/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:52:08.245056+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-01-SHI-L-STL.yaml b/data/custodian/JP-01-SHI-L-STL.yaml index 83df327619..b5aee2fa4c 100644 --- a/data/custodian/JP-01-SHI-L-STL.yaml +++ b/data/custodian/JP-01-SHI-L-STL.yaml @@ -202,3 +202,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.shibetsutown.jp/culture/toshokan/ wikidata_official_website: http://www.shibetsutown.jp/culture/toshokan/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:52:18.469668+00:00' + source_url: http://www.shibetsutown.jp/culture/toshokan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.shibetsutown.jp/image/favicon.ico + source_url: http://www.shibetsutown.jp/culture/toshokan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:52:18.469668+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.shibetsutown.jp/image/ogp.png + source_url: http://www.shibetsutown.jp/culture/toshokan + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T12:52:18.469668+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-01-SHI-M-SCM.yaml b/data/custodian/JP-01-SHI-M-SCM.yaml index dc9a22b88c..c20de0b325 100644 --- a/data/custodian/JP-01-SHI-M-SCM.yaml +++ b/data/custodian/JP-01-SHI-M-SCM.yaml @@ -225,3 +225,36 @@ location: postal_code: 095-0056 street_address: NISHISHIBETSUCHO, Shibetsu Shi, Hokkaido, 095-0056 normalization_timestamp: '2025-12-09T06:54:55.367243+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:52:30.123184+00:00' + source_url: https://www.city.shibetsu.lg.jp/gyoseisaito/kosodate_bunka_supotsu/shibetsushiritsuhakubutsukan/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.shibetsu.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.shibetsu.lg.jp/gyoseisaito/kosodate_bunka_supotsu/shibetsushiritsuhakubutsukan/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T12:52:30.123184+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 士別市 Shibetsu City + - claim_type: favicon_url + claim_value: https://www.city.shibetsu.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.shibetsu.lg.jp/gyoseisaito/kosodate_bunka_supotsu/shibetsushiritsuhakubutsukan/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T12:52:30.123184+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.shibetsu.lg.jp/material/images/group/1/e_large_museum_top.jpg + source_url: https://www.city.shibetsu.lg.jp/gyoseisaito/kosodate_bunka_supotsu/shibetsushiritsuhakubutsukan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T12:52:30.123184+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-01-SOR-L-KL.yaml b/data/custodian/JP-01-SOR-L-KL.yaml index 6abc0e467c..27be2a2388 100644 --- a/data/custodian/JP-01-SOR-L-KL.yaml +++ b/data/custodian/JP-01-SOR-L-KL.yaml @@ -200,3 +200,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.kamifurano.hokkaido.jp/index.php?id=256 wikidata_official_website: http://www.town.kamifurano.hokkaido.jp/index.php?id=256 +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:52:41.944878+00:00' + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=256 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.kamifurano.hokkaido.jp/images/mainlogo.jpg + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=256 + css_selector: '#logo > div:nth-of-type(2) > img' + retrieved_on: '2025-12-23T12:52:41.944878+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 北海道上富良野町公式（行政）ホームページ + - claim_type: favicon_url + claim_value: http://www.town.kamifurano.hokkaido.jp/icon.svg?t=2402230900 + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=256 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T12:52:41.944878+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.kamifurano.hokkaido.jp/images/kyosin/furendo/image001.jpg + source_url: http://www.town.kamifurano.hokkaido.jp/index.php?id=256 + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:52:41.944878+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-01-SOR-L-N.yaml b/data/custodian/JP-01-SOR-L-N.yaml index e83a9a66db..a1faeebd31 100644 --- a/data/custodian/JP-01-SOR-L-N.yaml +++ b/data/custodian/JP-01-SOR-L-N.yaml @@ -201,3 +201,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.nanporo.hokkaido.jp/cyousei/kakuka/sisetuannai/sisetu_003.jsp wikidata_official_website: http://www.town.nanporo.hokkaido.jp/cyousei/kakuka/sisetuannai/sisetu_003.jsp +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:52:56.817464+00:00' + source_url: http://www.town.nanporo.hokkaido.jp/cyousei/kakuka/sisetuannai/sisetu_003.jsp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.nanporo.hokkaido.jp/wp-content/themes/voteras_custom2/assets/img/common/logo.png + source_url: http://www.town.nanporo.hokkaido.jp/cyousei/kakuka/sisetuannai/sisetu_003.jsp + css_selector: '[document] > html > body > div.wrap:nth-of-type(2) > header > div.header-content-left + > div.site-name > a > img' + retrieved_on: '2025-12-23T12:52:56.817464+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 南幌町 + - claim_type: favicon_url + claim_value: https://www.town.nanporo.hokkaido.jp/wp-content/themes/voteras_custom2/favicon.ico + source_url: http://www.town.nanporo.hokkaido.jp/cyousei/kakuka/sisetuannai/sisetu_003.jsp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:52:56.817464+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-01-SOR-M-MSTW.yaml b/data/custodian/JP-01-SOR-M-MSTW.yaml index 3cb0621e69..b986109963 100644 --- a/data/custodian/JP-01-SOR-M-MSTW.yaml +++ b/data/custodian/JP-01-SOR-M-MSTW.yaml @@ -238,3 +238,22 @@ location: postal_code: 071-0502 street_address: NISHI2-SENKITA, Sorachi Gun Kamifurano Cho, Hokkaido, 071-0502 normalization_timestamp: '2025-12-09T06:54:55.536018+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:53:50.526745+00:00' + source_url: http://www.tsuchinoyakata.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.tsuchinoyakata.jp/web_clip_icon.png + source_url: http://www.tsuchinoyakata.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:53:50.526745+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-01-SOY-L-S.yaml b/data/custodian/JP-01-SOY-L-S.yaml index d7b37040d1..c7b23834e4 100644 --- a/data/custodian/JP-01-SOY-L-S.yaml +++ b/data/custodian/JP-01-SOY-L-S.yaml @@ -202,3 +202,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.vill.sarufutsu.hokkaido.jp/ wikidata_official_website: http://www.vill.sarufutsu.hokkaido.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:54:00.737666+00:00' + source_url: http://www.vill.sarufutsu.hokkaido.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.vill.sarufutsu.hokkaido.jp/favicon.ico + source_url: http://www.vill.sarufutsu.hokkaido.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:54:00.737666+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-01-SUN-L-SL.yaml b/data/custodian/JP-01-SUN-L-SL.yaml index d34bc80dcd..c1c58d5ad0 100644 --- a/data/custodian/JP-01-SUN-L-SL.yaml +++ b/data/custodian/JP-01-SUN-L-SL.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: https://www.city.sunagawa.hokkaido.jp/soshiki_shigoto/toshokan/ wikidata_official_website: https://www.city.sunagawa.hokkaido.jp/soshiki_shigoto/toshokan/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:54:10.350110+00:00' + source_url: https://www.city.sunagawa.hokkaido.jp/soshiki_shigoto/toshokan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sunagawa.hokkaido.jp/images/base/favicon.ico + source_url: https://www.city.sunagawa.hokkaido.jp/soshiki_shigoto/toshokan + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-23T12:54:10.350110+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-01-SUN-M-SCLMH.yaml b/data/custodian/JP-01-SUN-M-SCLMH.yaml index 3c5a981ae8..bea66cb03f 100644 --- a/data/custodian/JP-01-SUN-M-SCLMH.yaml +++ b/data/custodian/JP-01-SUN-M-SCLMH.yaml @@ -218,3 +218,22 @@ location: postal_code: 073-0168 street_address: NISHI8-JOKITA, Sunagawa Shi, Hokkaido, 073-0168 normalization_timestamp: '2025-12-09T06:54:55.614367+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:54:17.577552+00:00' + source_url: https://www.city.sunagawa.hokkaido.jp/soshiki_shigoto/kouminkan/kyoudoshiryoushitsu.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sunagawa.hokkaido.jp/images/base/favicon.ico + source_url: https://www.city.sunagawa.hokkaido.jp/soshiki_shigoto/kouminkan/kyoudoshiryoushitsu.html + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-23T12:54:17.577552+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-01-SUT-L-K.yaml b/data/custodian/JP-01-SUT-L-K.yaml index 1ddaf4f1f6..9035b13c14 100644 --- a/data/custodian/JP-01-SUT-L-K.yaml +++ b/data/custodian/JP-01-SUT-L-K.yaml @@ -202,3 +202,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.kuromatsunai-hkd.ed.jp/ wikidata_official_website: http://www.kuromatsunai-hkd.ed.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:54:27.771806+00:00' + source_url: http://www.kuromatsunai-hkd.ed.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.kuromatsunai-hkd.ed.jp/images/header_logo.png + source_url: http://www.kuromatsunai-hkd.ed.jp + css_selector: '#header_logo > h1 > a > img' + retrieved_on: '2025-12-23T12:54:27.771806+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 黒松内町 ふれあいの森情報館 マナヴェール + - claim_type: og_image_url + claim_value: http://www.kuromatsunai-hkd.ed.jp/images/og.png + source_url: http://www.kuromatsunai-hkd.ed.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:54:27.771806+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-01-SUT-L-S.yaml b/data/custodian/JP-01-SUT-L-S.yaml index b8dc6b16b8..afa5136cc4 100644 --- a/data/custodian/JP-01-SUT-L-S.yaml +++ b/data/custodian/JP-01-SUT-L-S.yaml @@ -202,3 +202,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.suttu.lg.jp/life/detail.php?id=67 wikidata_official_website: http://www.town.suttu.lg.jp/life/detail.php?id=67 +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:54:37.426313+00:00' + source_url: http://www.town.suttu.lg.jp/life/detail.php?id=67 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.suttu.lg.jp/favicon.ico + source_url: http://www.town.suttu.lg.jp/life/detail.php?id=67 + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T12:54:37.426313+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-01-TES-L-E.yaml b/data/custodian/JP-01-TES-L-E.yaml index dc352a2bab..0f92d8f11f 100644 --- a/data/custodian/JP-01-TES-L-E.yaml +++ b/data/custodian/JP-01-TES-L-E.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.embetsu.hokkaido.jp wikidata_official_website: http://www.town.embetsu.hokkaido.jp +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:55:32.300019+00:00' + source_url: http://www.town.embetsu.hokkaido.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.embetsu.hokkaido.jp/common/images/apple-touch-icon-180x180.png + source_url: http://www.town.embetsu.hokkaido.jp + css_selector: '[document] > html.history.no-touchevents > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T12:55:32.300019+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/JP-01-TES-L-T-toyotomichotoshoshitsu.yaml b/data/custodian/JP-01-TES-L-T-toyotomichotoshoshitsu.yaml index 69d940c351..51837d298b 100644 --- a/data/custodian/JP-01-TES-L-T-toyotomichotoshoshitsu.yaml +++ b/data/custodian/JP-01-TES-L-T-toyotomichotoshoshitsu.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.toyotomi.hokkaido.jp/section/kyouikuiinkai/a7cug600000002g7.html wikidata_official_website: http://www.town.toyotomi.hokkaido.jp/section/kyouikuiinkai/a7cug600000002g7.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:55:45.677919+00:00' + source_url: http://www.town.toyotomi.hokkaido.jp/section/kyouikuiinkai/a7cug600000002g7.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.toyotomi.hokkaido.jp/a7cug600000000lw-img/a7cug60000002t09.png + source_url: http://www.town.toyotomi.hokkaido.jp/section/kyouikuiinkai/a7cug600000002g7.html + css_selector: '[document] > html.js.history > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:55:45.677919+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.toyotomi.hokkaido.jp/section/kyouikuiinkai/a7cug600000002g7-img/ufvuj5000000ig4d.jpg + source_url: http://www.town.toyotomi.hokkaido.jp/section/kyouikuiinkai/a7cug600000002g7.html + css_selector: '[document] > html.js.history > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T12:55:45.677919+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-01-TES-L-T.yaml b/data/custodian/JP-01-TES-L-T.yaml index 1244939ad8..fd53d54a58 100644 --- a/data/custodian/JP-01-TES-L-T.yaml +++ b/data/custodian/JP-01-TES-L-T.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.teshiotown.hokkaido.jp/?page_id=616 wikidata_official_website: http://www.teshiotown.hokkaido.jp/?page_id=616 +logo_enrichment: + enrichment_timestamp: '2025-12-23T12:55:56.773245+00:00' + source_url: http://www.teshiotown.hokkaido.jp/?page_id=616 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.teshiotown.hokkaido.jp/wp-content/themes/teshio-town-2023-res/favicon.svg + source_url: http://www.teshiotown.hokkaido.jp/?page_id=616 + css_selector: '[document] > html.nivo-lightbox-notouch > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T12:55:56.773245+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.teshiotown.hokkaido.jp/wp-content/themes/teshio-town-2023-res/og_image.jpg + source_url: http://www.teshiotown.hokkaido.jp/?page_id=616 + css_selector: '[document] > html.nivo-lightbox-notouch > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T12:55:56.773245+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-01-TOK-L-KL.yaml b/data/custodian/JP-01-TOK-L-KL.yaml index 1fd86a714a..145d875192 100644 --- a/data/custodian/JP-01-TOK-L-KL.yaml +++ b/data/custodian/JP-01-TOK-L-KL.yaml @@ -202,3 +202,30 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.kunneppu.hokkaido.jp/library/ wikidata_official_website: http://www.town.kunneppu.hokkaido.jp/library/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:06:14.981082+00:00' + source_url: http://www.town.kunneppu.hokkaido.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.kunneppu.hokkaido.jp/images/logo-kunneppu.png + source_url: http://www.town.kunneppu.hokkaido.jp/library + css_selector: '#site-logo > a > img' + retrieved_on: '2025-12-23T13:06:14.981082+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 訓子府町 + - claim_type: favicon_url + claim_value: http://www.town.kunneppu.hokkaido.jp/apple-touch-icon-180x180.png + source_url: http://www.town.kunneppu.hokkaido.jp/library + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T13:06:14.981082+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: 3 diff --git a/data/custodian/JP-01-TOK-L-SL.yaml b/data/custodian/JP-01-TOK-L-SL.yaml index aaed6faf26..6ed5b2b51c 100644 --- a/data/custodian/JP-01-TOK-L-SL.yaml +++ b/data/custodian/JP-01-TOK-L-SL.yaml @@ -200,3 +200,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.saroma.hokkaido.jp/shisetsu/library/index.html wikidata_official_website: http://www.town.saroma.hokkaido.jp/shisetsu/library/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:06:33.525656+00:00' + source_url: http://www.town.saroma.hokkaido.jp/shisetsu/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.town.saroma.hokkaido.jp/ogp.jpg + source_url: http://www.town.saroma.hokkaido.jp/shisetsu/library/index.html + css_selector: '[document] > html.no-touchevents > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T13:06:33.525656+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-01-TOK-L-UL.yaml b/data/custodian/JP-01-TOK-L-UL.yaml index 7d18fbdf6c..425a3d12a3 100644 --- a/data/custodian/JP-01-TOK-L-UL.yaml +++ b/data/custodian/JP-01-TOK-L-UL.yaml @@ -200,3 +200,28 @@ wikidata_enrichment: wikidata_web: official_website: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/library/ wikidata_official_website: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/library/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:06:44.450249+00:00' + source_url: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.urahoro.jp/apple-touch-icon.png + source_url: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:06:44.450249+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.urahoro.jp/assets/images/og-image.jpg + source_url: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/library + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T13:06:44.450249+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-01-TOK-M-HMU.yaml b/data/custodian/JP-01-TOK-M-HMU.yaml index 2f7e40542f..51f27fb14a 100644 --- a/data/custodian/JP-01-TOK-M-HMU.yaml +++ b/data/custodian/JP-01-TOK-M-HMU.yaml @@ -241,3 +241,28 @@ location: postal_code: 089-5614 street_address: SAKURAMACHI, Tokachi Gun Urahoro Cho, Hokkaido, 089-5614 normalization_timestamp: '2025-12-09T06:54:55.994902+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:06:53.708829+00:00' + source_url: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.urahoro.jp/apple-touch-icon.png + source_url: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/museum + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:06:53.708829+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.urahoro.jp/assets/images/og-image.jpg + source_url: https://www.urahoro.jp/chosya_shisetsu/kokyoriyo/museum + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T13:06:53.708829+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-01-TOK-M-TCFM.yaml b/data/custodian/JP-01-TOK-M-TCFM.yaml index 3a9d4a74d4..75751d00d8 100644 --- a/data/custodian/JP-01-TOK-M-TCFM.yaml +++ b/data/custodian/JP-01-TOK-M-TCFM.yaml @@ -387,3 +387,22 @@ location: geonames_id: 1850185 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:23.446180+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:07:06.004607+00:00' + source_url: https://www.tokoname-tounomori.jp/aboutmuseum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tokoname-tounomori.jp/wp-content/uploads/2021/06/ahwx8-a9izm-001.png + source_url: https://www.tokoname-tounomori.jp/aboutmuseum + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-23T13:07:06.004607+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-01-TOM-L-H.yaml b/data/custodian/JP-01-TOM-L-H.yaml index 4ac563079e..1856d7c4d2 100644 --- a/data/custodian/JP-01-TOM-L-H.yaml +++ b/data/custodian/JP-01-TOM-L-H.yaml @@ -202,3 +202,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.haboro.lg.jp/shisetsu/culture/library.html wikidata_official_website: http://www.town.haboro.lg.jp/shisetsu/culture/library.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:07:15.139369+00:00' + source_url: http://www.town.haboro.lg.jp/shisetsu/culture/library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.haboro.lg.jp/images/base/favicon.ico + source_url: http://www.town.haboro.lg.jp/shisetsu/culture/library.html + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T13:07:15.139369+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-01-TOM-L-HUL.yaml b/data/custodian/JP-01-TOM-L-HUL.yaml index 86b81ad1c2..18511b7b6e 100644 --- a/data/custodian/JP-01-TOM-L-HUL.yaml +++ b/data/custodian/JP-01-TOM-L-HUL.yaml @@ -205,3 +205,30 @@ location: geonames_id: 2127733 geonames_name: Tomakomai feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:07:23.548027+00:00' + source_url: https://hokuyo.ac.jp/publics/index/35 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://hokuyo.ac.jp/cms/wp-content/themes/hokuyo/images/common/logo.png + source_url: https://hokuyo.ac.jp/publics/index/35 + css_selector: '#g-nav-list > div.center.mt60 > a > img.logowrap' + retrieved_on: '2025-12-23T13:07:23.548027+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 北洋大学 + - claim_type: favicon_url + claim_value: https://hokuyo.ac.jp/cms/wp-content/uploads/2023/06/cropped-favicon-180x180.png + source_url: https://hokuyo.ac.jp/publics/index/35 + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T13:07:23.548027+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-01-TOM-L-T.yaml b/data/custodian/JP-01-TOM-L-T.yaml index 7281aec7f7..845a8bef0a 100644 --- a/data/custodian/JP-01-TOM-L-T.yaml +++ b/data/custodian/JP-01-TOM-L-T.yaml @@ -202,3 +202,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib00000010lo.html wikidata_official_website: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib00000010lo.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:07:34.153500+00:00' + source_url: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib00000010lo.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.tomamae.lg.jp/lg6iib0000000hf7-img/oa5p850000000t3p.png + source_url: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib00000010lo.html + css_selector: '[document] > html.js.history > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:07:34.153500+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.tomamae.lg.jp/lg6iib0000000hf7-img/g6v5n20000000jay.jpg + source_url: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib00000010lo.html + css_selector: '[document] > html.js.history > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T13:07:34.153500+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-01-TOM-L-TCL.yaml b/data/custodian/JP-01-TOM-L-TCL.yaml index fc84247b83..1079be2099 100644 --- a/data/custodian/JP-01-TOM-L-TCL.yaml +++ b/data/custodian/JP-01-TOM-L-TCL.yaml @@ -213,3 +213,23 @@ wikidata_enrichment: wikidata_media: image: Tomakomai City Chuo Library.jpg wikidata_image: Tomakomai City Chuo Library.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:07:48.773629+00:00' + source_url: http://www.tomakomai-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tomakomai-lib.jp/wp-content/themes/tomakomai_lib/images/h_logo.png + source_url: http://www.tomakomai-lib.jp + css_selector: '[document] > html > body.drawer.drawer--right > header > div.h_1.cf + > h1 > a > img' + retrieved_on: '2025-12-23T13:07:48.773629+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-01-TOM-M-TK.yaml b/data/custodian/JP-01-TOM-M-TK.yaml index 06b7323481..2292944fca 100644 --- a/data/custodian/JP-01-TOM-M-TK.yaml +++ b/data/custodian/JP-01-TOM-M-TK.yaml @@ -227,3 +227,28 @@ location: postal_code: 078-3701 street_address: TOMAMAE, Tomamae Gun Tomamae Cho, Hokkaido, 078-3701 normalization_timestamp: '2025-12-09T06:54:56.197972+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:08:01.933637+00:00' + source_url: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib0000000lu6.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.tomamae.lg.jp/lg6iib0000000hf7-img/oa5p850000000t3p.png + source_url: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib0000000lu6.html + css_selector: '[document] > html.js.history > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:08:01.933637+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.tomamae.lg.jp/lg6iib0000000hf7-img/g6v5n20000000jay.jpg + source_url: http://www.town.tomamae.lg.jp/section/kyoiku/shakaikyoiku/lg6iib0000000lu6.html + css_selector: '[document] > html.js.history > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T13:08:01.933637+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-01-TOM-M-TSM.yaml b/data/custodian/JP-01-TOM-M-TSM.yaml index 4a222cc70c..eabb63c558 100644 --- a/data/custodian/JP-01-TOM-M-TSM.yaml +++ b/data/custodian/JP-01-TOM-M-TSM.yaml @@ -241,3 +241,22 @@ location: postal_code: 053-0018 street_address: ASAHIMACHI, Tomakomai Shi, Hokkaido, 053-0018 normalization_timestamp: '2025-12-09T06:54:56.219827+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:08:11.194814+00:00' + source_url: https://www.city.tomakomai.hokkaido.jp/kagaku + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.tomakomai.hokkaido.jp/kagaku/icon.png + source_url: https://www.city.tomakomai.hokkaido.jp/kagaku + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-23T13:08:11.194814+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-01-TOM-M-YMH.yaml b/data/custodian/JP-01-TOM-M-YMH.yaml index 1898347e07..ef19a4183a 100644 --- a/data/custodian/JP-01-TOM-M-YMH.yaml +++ b/data/custodian/JP-01-TOM-M-YMH.yaml @@ -218,3 +218,22 @@ location: postal_code: 059-1372 street_address: YUFUTSU, Tomakomai Shi, Hokkaido, 059-1372 normalization_timestamp: '2025-12-09T06:54:56.244279+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:08:19.365750+00:00' + source_url: http://www.city.tomakomai.hokkaido.jp/kyoiku/bunkashisetsu/yufutsushiryokan/siryokan.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.tomakomai.hokkaido.jp/icon.png + source_url: http://www.city.tomakomai.hokkaido.jp/kyoiku/bunkashisetsu/yufutsushiryokan/siryokan.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-23T13:08:19.365750+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-01-TOY-L-TL-toyokawashichuo_library.yaml b/data/custodian/JP-01-TOY-L-TL-toyokawashichuo_library.yaml index 31817edcda..0afcaef4e4 100644 --- a/data/custodian/JP-01-TOY-L-TL-toyokawashichuo_library.yaml +++ b/data/custodian/JP-01-TOY-L-TL-toyokawashichuo_library.yaml @@ -445,3 +445,20 @@ location: geonames_id: 1849845 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:23.488110+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:08:44.702159+00:00' + source_url: https://libweb.lib.city.toyokawa.aichi.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.lib.city.toyokawa.aichi.jp/contents/wp-content/uploads/TandS/OGP-img.jpg + source_url: https://libweb.lib.city.toyokawa.aichi.jp + css_selector: '[document] > html.translated-ltr > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T13:08:44.702159+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-01-URA-L-UL.yaml b/data/custodian/JP-01-URA-L-UL.yaml index 28c633b0dd..b5ede297a9 100644 --- a/data/custodian/JP-01-URA-L-UL.yaml +++ b/data/custodian/JP-01-URA-L-UL.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.urakawa.hokkaido.jp/sports-culture/library/index.html wikidata_official_website: http://www.town.urakawa.hokkaido.jp/sports-culture/library/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:08:55.496954+00:00' + source_url: http://www.town.urakawa.hokkaido.jp/sports-culture/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.urakawa.hokkaido.jp/apple-touch-icon.png + source_url: http://www.town.urakawa.hokkaido.jp/sports-culture/library/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:08:55.496954+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.town.urakawa.hokkaido.jp/assets/images/og-image.jpg + source_url: http://www.town.urakawa.hokkaido.jp/sports-culture/library/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T13:08:55.496954+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-01-URY-L-HL.yaml b/data/custodian/JP-01-URY-L-HL.yaml index bae8f856df..30e773e20b 100644 --- a/data/custodian/JP-01-URY-L-HL.yaml +++ b/data/custodian/JP-01-URY-L-HL.yaml @@ -201,3 +201,37 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.hokuryu.hokkaido.jp/ wikidata_official_website: http://www.town.hokuryu.hokkaido.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:09:32.821706+00:00' + source_url: http://www.town.hokuryu.hokkaido.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.hokuryu.hokkaido.jp/coupl/2022/08/akarui_yoko_tri2.jpg + source_url: http://www.town.hokuryu.hokkaido.jp + css_selector: '#header-in > div.logo.logo-header:nth-of-type(2) > a.site-name.site-name-text-link + > span.site-name-text > img.site-logo-image.header-site-logo-image' + retrieved_on: '2025-12-23T13:09:32.821706+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 北竜町 + - claim_type: favicon_url + claim_value: http://www.town.hokuryu.hokkaido.jp/coupl/2022/06/cropped-hr_favicon-180x180.png + source_url: http://www.town.hokuryu.hokkaido.jp + css_selector: '[document] > html > head > link:nth-of-type(52)' + retrieved_on: '2025-12-23T13:09:32.821706+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.hokuryu.hokkaido.jp/coupl/2024/02/sasaki-scaled.jpg + source_url: http://www.town.hokuryu.hokkaido.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T13:09:32.821706+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-01-URY-L-NL.yaml b/data/custodian/JP-01-URY-L-NL.yaml index 9ec389299a..bd6bd4a2b1 100644 --- a/data/custodian/JP-01-URY-L-NL.yaml +++ b/data/custodian/JP-01-URY-L-NL.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.numata.hokkaido.jp/section/library/ wikidata_official_website: http://www.town.numata.hokkaido.jp/section/library/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:09:59.693424+00:00' + source_url: http://www.town.numata.hokkaido.jp/section/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.numata.hokkaido.jp/h0opp20000000byl-img/logo.png + source_url: http://www.town.numata.hokkaido.jp/section/library + css_selector: '#headInfo > h1 > a > img' + retrieved_on: '2025-12-23T13:09:59.693424+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 北海道沼田町 + - claim_type: favicon_url + claim_value: http://www.town.numata.hokkaido.jp/h0opp20000000byl-att/favicon.ico + source_url: http://www.town.numata.hokkaido.jp/section/library + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:09:59.693424+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.numata.hokkaido.jp/section/library/ujj7s300000001n0-img/ujj7s300000001om.jpg + source_url: http://www.town.numata.hokkaido.jp/section/library + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T13:09:59.693424+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-01-UTA-L-UCL.yaml b/data/custodian/JP-01-UTA-L-UCL.yaml index fb81feae1c..ff78ee3844 100644 --- a/data/custodian/JP-01-UTA-L-UCL.yaml +++ b/data/custodian/JP-01-UTA-L-UCL.yaml @@ -204,3 +204,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.utashinai.hokkaido.jp/hotnews/detail/00001025.html wikidata_official_website: http://www.city.utashinai.hokkaido.jp/hotnews/detail/00001025.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:10:28.432888+00:00' + source_url: http://www.city.utashinai.hokkaido.jp/hotnews/detail/00001025.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.utashinai.hokkaido.jp/hotnews/detail/images/logo.png + source_url: http://www.city.utashinai.hokkaido.jp/hotnews/detail/00001025.html + css_selector: '#header_logo > h1 > a > img' + retrieved_on: '2025-12-23T13:10:28.432888+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 歌志内市 + - claim_type: favicon_url + claim_value: http://www.city.utashinai.hokkaido.jp/hotnews/detail/images/logo_mark_ios.png + source_url: http://www.city.utashinai.hokkaido.jp/hotnews/detail/00001025.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T13:10:28.432888+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.utashinai.hokkaido.jp/images/og.jpg + source_url: http://www.city.utashinai.hokkaido.jp/hotnews/detail/00001025.html + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T13:10:28.432888+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-01-WAK-L-HROFRDWFRI.yaml b/data/custodian/JP-01-WAK-L-HROFRDWFRI.yaml index 5f84413b8b..bb811e530c 100644 --- a/data/custodian/JP-01-WAK-L-HROFRDWFRI.yaml +++ b/data/custodian/JP-01-WAK-L-HROFRDWFRI.yaml @@ -275,3 +275,28 @@ location: postal_code: 097-0001 street_address: 4-5-15 SUEHIRO, Wakkanai Shi, Hokkaido, 097-0001 normalization_timestamp: '2025-12-09T08:40:40.943171+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:10:41.926307+00:00' + source_url: http://www.h-bungaku.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.h-bungaku.or.jp/images/favicon.ico + source_url: http://www.h-bungaku.or.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:10:41.926307+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/favicon.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.h-bungaku.or.jp/images/ogp_thumbnail.jpg + source_url: http://www.h-bungaku.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T13:10:41.926307+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-01-WAK-L-WCL.yaml b/data/custodian/JP-01-WAK-L-WCL.yaml index b82a583f09..f23a95b4e2 100644 --- a/data/custodian/JP-01-WAK-L-WCL.yaml +++ b/data/custodian/JP-01-WAK-L-WCL.yaml @@ -218,3 +218,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.wakkanai.hokkaido.jp/toshokan/ wikidata_official_website: http://www.city.wakkanai.hokkaido.jp/toshokan/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:10:55.505405+00:00' + source_url: http://www.city.wakkanai.hokkaido.jp/toshokan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.wakkanai.hokkaido.jp/images/toshokan_logo_mark_ios.png + source_url: http://www.city.wakkanai.hokkaido.jp/toshokan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T13:10:55.505405+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.wakkanai.hokkaido.jp/images/toshokan-og.jpg + source_url: http://www.city.wakkanai.hokkaido.jp/toshokan + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T13:10:55.505405+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-01-WAK-M-WKM.yaml b/data/custodian/JP-01-WAK-M-WKM.yaml index 9256ea3893..bb56fe187c 100644 --- a/data/custodian/JP-01-WAK-M-WKM.yaml +++ b/data/custodian/JP-01-WAK-M-WKM.yaml @@ -230,3 +230,38 @@ wikidata_enrichment: image: Wakkanai Fukukoichiba 18-06-02 2.jpg commons_category: Wakkanai Karafuto Museum wikidata_image: Wakkanai Fukukoichiba 18-06-02 2.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:11:06.436855+00:00' + source_url: http://www.wakkanai-fukukou.com/tenant/onsen/karahuto.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.wakkanai-fukukou.com/wp-content/uploads/2024/04/Wakkanai_logo.png + source_url: http://www.wakkanai-fukukou.com/tenant/onsen/karahuto.html + css_selector: '#zak-masthead > div.zak-main-header > div.zak-container > div.zak-row + > div.zak-header-col.zak-header-col--1 > div.site-branding > a.custom-logo-link + > img.custom-logo' + retrieved_on: '2025-12-23T13:11:06.436855+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Wakkanai Fukukou + - claim_type: favicon_url + claim_value: https://www.wakkanai-fukukou.com/wp-content/uploads/2024/04/Wakkanai_icon.png + source_url: http://www.wakkanai-fukukou.com/tenant/onsen/karahuto.html + css_selector: '[document] > html > head > link:nth-of-type(34)' + retrieved_on: '2025-12-23T13:11:06.436855+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://www.wakkanai-fukukou.com/wp-content/uploads/2024/04/Wakkanai_logo.png + source_url: http://www.wakkanai-fukukou.com/tenant/onsen/karahuto.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T13:11:06.436855+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-01-WAK-M-WMNMH.yaml b/data/custodian/JP-01-WAK-M-WMNMH.yaml index 703def8fe0..5970954917 100644 --- a/data/custodian/JP-01-WAK-M-WMNMH.yaml +++ b/data/custodian/JP-01-WAK-M-WMNMH.yaml @@ -278,3 +278,28 @@ location: postal_code: 097-0000 street_address: Wakkanai Shi, Hokkaido, 097-0000 normalization_timestamp: '2025-12-09T06:54:56.673564+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:11:19.448806+00:00' + source_url: http://w-shinko.co.jp/hoppo-kinenkan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://w-shinko.co.jp/wp-content/themes/w-shinko-temporary/icon/icon-152.png + source_url: http://w-shinko.co.jp/hoppo-kinenkan + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T13:11:19.448806+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://w-shinko.co.jp/wp-content/uploads/2015/08/P6180097.jpg + source_url: http://w-shinko.co.jp/hoppo-kinenkan + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T13:11:19.448806+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-01-WAK-M-WNA.yaml b/data/custodian/JP-01-WAK-M-WNA.yaml index 37a0bae66c..59d1460de1 100644 --- a/data/custodian/JP-01-WAK-M-WNA.yaml +++ b/data/custodian/JP-01-WAK-M-WNA.yaml @@ -254,3 +254,28 @@ location: postal_code: 097-0026 street_address: NOSHAPPU, Wakkanai Shi, Hokkaido, 097-0026 normalization_timestamp: '2025-12-09T06:54:56.697841+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:11:32.110503+00:00' + source_url: https://www.city.wakkanai.hokkaido.jp/suizokukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.wakkanai.hokkaido.jp/images/suizokukan_logo_mark_ios.png + source_url: https://www.city.wakkanai.hokkaido.jp/suizokukan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T13:11:32.110503+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.wakkanai.hokkaido.jp/images/suizokukan-og.jpg + source_url: https://www.city.wakkanai.hokkaido.jp/suizokukan + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T13:11:32.110503+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-01-YAM-L-OL.yaml b/data/custodian/JP-01-YAM-L-OL.yaml index 4bef1c1087..69d65234e3 100644 --- a/data/custodian/JP-01-YAM-L-OL.yaml +++ b/data/custodian/JP-01-YAM-L-OL.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.oshamambe.lg.jp wikidata_official_website: http://www.town.oshamambe.lg.jp +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:11:47.258199+00:00' + source_url: http://www.town.oshamambe.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.oshamambe.lg.jp/apple-touch-icon.png + source_url: http://www.town.oshamambe.lg.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T13:11:47.258199+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-01-YOI-L-N.yaml b/data/custodian/JP-01-YOI-L-N.yaml index dbd2525aef..9b8d9b2cd6 100644 --- a/data/custodian/JP-01-YOI-L-N.yaml +++ b/data/custodian/JP-01-YOI-L-N.yaml @@ -202,3 +202,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.niki.hokkaido.jp/section/kyoikuiinkai/irv9760000000m7l.html wikidata_official_website: http://www.town.niki.hokkaido.jp/section/kyoikuiinkai/irv9760000000m7l.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:12:09.444918+00:00' + source_url: http://www.town.niki.hokkaido.jp/section/kyoikuiinkai/irv9760000000m7l.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.niki.hokkaido.jp/irv97600000003lk-img/irv97600000003nr.png + source_url: http://www.town.niki.hokkaido.jp/section/kyoikuiinkai/irv9760000000m7l.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T13:12:09.444918+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.niki.hokkaido.jp/section/kyoikuiinkai/irv9760000000m7l-img/irv9760000000mc1.jpg + source_url: http://www.town.niki.hokkaido.jp/section/kyoikuiinkai/irv9760000000m7l.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T13:12:09.444918+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-01-YOI-L-YTL.yaml b/data/custodian/JP-01-YOI-L-YTL.yaml index 6d43d2d4e3..13539a675f 100644 --- a/data/custodian/JP-01-YOI-L-YTL.yaml +++ b/data/custodian/JP-01-YOI-L-YTL.yaml @@ -202,3 +202,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.yoichi-lib-unet.ocn.ne.jp wikidata_official_website: http://www.yoichi-lib-unet.ocn.ne.jp +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:42:15.904252+00:00' + source_url: http://www.yoichi-lib-unet.ocn.ne.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://localhost/TOSHOW/asp/shared/img/snsThumbnail.png + source_url: http://www.yoichi-lib-unet.ocn.ne.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-23T13:42:15.904252+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-01-YUB-L-KTL.yaml b/data/custodian/JP-01-YUB-L-KTL.yaml index af67294b4f..dbafd64dbc 100644 --- a/data/custodian/JP-01-YUB-L-KTL.yaml +++ b/data/custodian/JP-01-YUB-L-KTL.yaml @@ -201,3 +201,20 @@ wikidata_enrichment: wikidata_web: official_website: http://library.town.kuriyama.hokkaido.jp/ wikidata_official_website: http://library.town.kuriyama.hokkaido.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:42:37.499987+00:00' + source_url: http://library.town.kuriyama.hokkaido.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://library.town.kuriyama.hokkaido.jp/TOSHOW/asp/shared/img/snsThumbnail.png + source_url: http://library.town.kuriyama.hokkaido.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-23T13:42:37.499987+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-01-YUB-L-Y-yubarishitoshokona.yaml b/data/custodian/JP-01-YUB-L-Y-yubarishitoshokona.yaml index ea669c58ca..376d05f322 100644 --- a/data/custodian/JP-01-YUB-L-Y-yubarishitoshokona.yaml +++ b/data/custodian/JP-01-YUB-L-Y-yubarishitoshokona.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: wikidata_web: official_website: https://www.city.yubari.lg.jp/shisetsuannai/toshokan/tosho.html wikidata_official_website: https://www.city.yubari.lg.jp/shisetsuannai/toshokan/tosho.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:15:41.555423+00:00' + source_url: https://www.city.yubari.lg.jp/shisetsuannai/toshokan/tosho.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.yubari.lg.jp/apple-touch-icon.png + source_url: https://www.city.yubari.lg.jp/shisetsuannai/toshokan/tosho.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T13:15:41.555423+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-01-YUB-L-Y.yaml b/data/custodian/JP-01-YUB-L-Y.yaml index cd87014f4c..e1de7be026 100644 --- a/data/custodian/JP-01-YUB-L-Y.yaml +++ b/data/custodian/JP-01-YUB-L-Y.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.yuni.lg.jp/01020113kyoiku_syakai02_yumekku.html wikidata_official_website: http://www.town.yuni.lg.jp/01020113kyoiku_syakai02_yumekku.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:42:56.991879+00:00' + source_url: http://www.town.yuni.lg.jp/01020113kyoiku_syakai02_yumekku.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.yuni.lg.jp/wp-content/themes/yunitown-web/favicon.ico + source_url: http://www.town.yuni.lg.jp/01020113kyoiku_syakai02_yumekku.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T13:42:56.991879+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-01-YUF-L-A-abirachohayakitakominkantoshoshitsu.yaml b/data/custodian/JP-01-YUF-L-A-abirachohayakitakominkantoshoshitsu.yaml index 983e908050..ded71d6c46 100644 --- a/data/custodian/JP-01-YUF-L-A-abirachohayakitakominkantoshoshitsu.yaml +++ b/data/custodian/JP-01-YUF-L-A-abirachohayakitakominkantoshoshitsu.yaml @@ -202,3 +202,24 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/75 wikidata_official_website: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/75 +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:43:11.962377+00:00' + source_url: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/75 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.abira.lg.jp/common/forhp/images/common/logo2_rubi.png + source_url: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/75 + css_selector: '[document] > html > body > header.site-header.navbar > div.header-upside + > div.header-upside-inner > div.navbar-header > h1.header-logo.navbar-brand + > a > img' + retrieved_on: '2025-12-23T13:43:11.962377+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 安平町 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-01-YUF-L-A.yaml b/data/custodian/JP-01-YUF-L-A.yaml index d9915f1761..800a037f56 100644 --- a/data/custodian/JP-01-YUF-L-A.yaml +++ b/data/custodian/JP-01-YUF-L-A.yaml @@ -202,3 +202,24 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/76 wikidata_official_website: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/76 +logo_enrichment: + enrichment_timestamp: '2025-12-23T13:43:23.710114+00:00' + source_url: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/76 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.abira.lg.jp/common/forhp/images/common/logo2_rubi.png + source_url: http://www.town.abira.lg.jp/midokoro/shisetsu/kominkan/76 + css_selector: '[document] > html > body > header.site-header.navbar > div.header-upside + > div.header-upside-inner > div.navbar-header > h1.header-logo.navbar-brand + > a > img' + retrieved_on: '2025-12-23T13:43:23.710114+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 安平町 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-01-YUF-L-ML.yaml b/data/custodian/JP-01-YUF-L-ML.yaml index b1c33ff29c..bd596ca147 100644 --- a/data/custodian/JP-01-YUF-L-ML.yaml +++ b/data/custodian/JP-01-YUF-L-ML.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.mukawa.lg.jp/2031.htm wikidata_official_website: http://www.town.mukawa.lg.jp/2031.htm +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:01:13.788119+00:00' + source_url: http://www.town.mukawa.lg.jp/2031.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.mukawa.lg.jp/apple-touch-icon.png + source_url: http://www.town.mukawa.lg.jp/2031.htm + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-23T14:01:13.788119+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-01-YUF-L-S.yaml b/data/custodian/JP-01-YUF-L-S.yaml index 1bbba924b4..eb7d7eea35 100644 --- a/data/custodian/JP-01-YUF-L-S.yaml +++ b/data/custodian/JP-01-YUF-L-S.yaml @@ -202,3 +202,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.vill.shimukappu.lg.jp/shimukappu/section/kyouiku/nmudtq000000578f.html wikidata_official_website: http://www.vill.shimukappu.lg.jp/shimukappu/section/kyouiku/nmudtq000000578f.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:01:21.743392+00:00' + source_url: http://www.vill.shimukappu.lg.jp/shimukappu/section/kyouiku/nmudtq000000578f.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.vill.shimukappu.lg.jp/shimukappu/nmudtq00000001zb-img/fqprvo000000040o.png + source_url: http://www.vill.shimukappu.lg.jp/shimukappu/section/kyouiku/nmudtq000000578f.html + css_selector: '[document] > html.no-touchevents.history > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:01:21.743392+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.vill.shimukappu.lg.jp/shimukappu/section/kyouiku/nmudtq000000578f-img/nmudtq00000057d4.jpg + source_url: http://www.vill.shimukappu.lg.jp/shimukappu/section/kyouiku/nmudtq000000578f.html + css_selector: '[document] > html.no-touchevents.history > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T14:01:21.743392+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-01-YUF-M-HM.yaml b/data/custodian/JP-01-YUF-M-HM.yaml index c4c5c8f313..3fab5c07a1 100644 --- a/data/custodian/JP-01-YUF-M-HM.yaml +++ b/data/custodian/JP-01-YUF-M-HM.yaml @@ -262,3 +262,22 @@ location: postal_code: 054-0211 street_address: HOBETSU, Yufutsu Gun Mukawa Cho, Hokkaido, 054-0211 normalization_timestamp: '2025-12-09T06:54:57.124775+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:01:30.828930+00:00' + source_url: http://www.town.mukawa.lg.jp/1908.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.mukawa.lg.jp/apple-touch-icon.png + source_url: http://www.town.mukawa.lg.jp/1908.htm + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-23T14:01:30.828930+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-02-AKI-M-AKMKTM.yaml b/data/custodian/JP-02-AKI-M-AKMKTM.yaml index fa6b4b0c81..b55b1b1aca 100644 --- a/data/custodian/JP-02-AKI-M-AKMKTM.yaml +++ b/data/custodian/JP-02-AKI-M-AKMKTM.yaml @@ -411,3 +411,36 @@ location: geonames_id: 2113126 feature_code: PPLA normalization_timestamp: '2025-12-09T06:53:23.536595+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:01:43.732694+00:00' + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:01:43.732694+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秋田市公式サイト + - claim_type: favicon_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T14:01:43.732694+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T14:01:43.732694+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-02-AOM-L-A.yaml b/data/custodian/JP-02-AOM-L-A.yaml index 87b34d167d..5df22e50b3 100644 --- a/data/custodian/JP-02-AOM-L-A.yaml +++ b/data/custodian/JP-02-AOM-L-A.yaml @@ -204,3 +204,30 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.aomori.aomori.jp/view.rbz?nd=842&ik=1&pnp=160&pnp=476&pnp=740&pnp=842&cd=1946 wikidata_official_website: http://www.city.aomori.aomori.jp/view.rbz?nd=842&ik=1&pnp=160&pnp=476&pnp=740&pnp=842&cd=1946 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:02:06.755906+00:00' + source_url: http://www.city.aomori.aomori.jp/view.rbz?nd=842&ik=1&pnp=160&pnp=476&pnp=740&pnp=842&cd=1946 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.aomori.aomori.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.aomori.aomori.jp/view.rbz?nd=842&ik=1&pnp=160&pnp=476&pnp=740&pnp=842&cd=1946 + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:02:06.755906+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 青森市公式ホームページトップページ + - claim_type: favicon_url + claim_value: https://www.city.aomori.aomori.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: http://www.city.aomori.aomori.jp/view.rbz?nd=842&ik=1&pnp=160&pnp=476&pnp=740&pnp=842&cd=1946 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T14:02:06.755906+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-02-AOM-L-AAJCL.yaml b/data/custodian/JP-02-AOM-L-AAJCL.yaml index 2c1b6faa56..5b7fdd7de0 100644 --- a/data/custodian/JP-02-AOM-L-AAJCL.yaml +++ b/data/custodian/JP-02-AOM-L-AAJCL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:56.823614+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: AOM method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-AOM-L-AAJCL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-AOM-L-AAJCL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-AOM-L-AAJCL ghcid_numeric: 13856603565230820984 valid_from: '2025-12-06T23:38:56.823614+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: Aomori Akenohoshi Junior College Library @@ -189,7 +190,7 @@ wikidata_enrichment: location: city: Aomori Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 030-0961 street_address: 2-6-32 NAMIUCHI, Aomori Shi, Aomori Ken, 030-0961 @@ -204,3 +205,22 @@ location: geonames_id: 2130658 geonames_name: Aomori feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:02:26.511351+00:00' + source_url: http://www.aomori-akenohoshi.ac.jp/campus/library/library-index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.aomori-akenohoshi.ac.jp/wp-content/uploads/2022/04/logo2.png + source_url: http://www.aomori-akenohoshi.ac.jp/campus/library/library-index.html + css_selector: '[document] > html > body > link:nth-of-type(7)' + retrieved_on: '2025-12-23T14:02:26.511351+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-02-AOM-L-ACGUACJCLI.yaml b/data/custodian/JP-02-AOM-L-ACGUACJCLI.yaml index ec6e97c742..d327606eda 100644 --- a/data/custodian/JP-02-AOM-L-ACGUACJCLI.yaml +++ b/data/custodian/JP-02-AOM-L-ACGUACJCLI.yaml @@ -1,5 +1,6 @@ original_entry: - name: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and information center + name: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and information + center institution_type: LIBRARY source: CH-Annotator (japan_complete_ch_annotator.yaml) identifiers: @@ -32,25 +33,27 @@ ghcid: generation_timestamp: '2025-12-06T23:38:54.404637+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: AOM method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-AOM-L-ACGUACJCLI - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-AOM-L-ACGUACJCLI valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-AOM-L-ACGUACJCLI ghcid_numeric: 6950917505351160502 valid_from: '2025-12-06T23:38:54.404637+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and information center + claim_value: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and + information center source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -101,11 +104,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and information center + claim_value: Aomori Chuo Gakuin University・Aomori Chuo Junior College library + and information center property_uri: skos:prefLabel provenance: namespace: glam @@ -163,9 +167,11 @@ wikidata_enrichment: - P856 - P463 wikidata_labels: - en: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and information center + en: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and information + center ja: 青森中央学院大学･青森中央短期大学図書館情報センター - wikidata_label_en: Aomori Chuo Gakuin University・Aomori Chuo Junior College library and information center + wikidata_label_en: Aomori Chuo Gakuin University・Aomori Chuo Junior College library + and information center wikidata_label_ja: 青森中央学院大学･青森中央短期大学図書館情報センター wikidata_classification: instance_of: &id004 @@ -187,14 +193,15 @@ wikidata_enrichment: member_of: - 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.aomoricgu.ac.jp/library/ wikidata_official_website: http://www.aomoricgu.ac.jp/library/ location: city: Aomori Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 030-0132 street_address: 12 YOKOCHI KANDA, Aomori Shi, Aomori Ken, 030-0132 @@ -209,3 +216,28 @@ location: geonames_id: 2130658 geonames_name: Aomori feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:02:42.359394+00:00' + source_url: http://www.aomoricgu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.aomoricgu.ac.jp/application/files/9816/8255/8018/bookmark.png + source_url: http://www.aomoricgu.ac.jp/library + css_selector: '[document] > html.csspositionsticky.no-cssgridlegacy > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:02:42.359394+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.aomoricgu.ac.jp/application/files/5116/8255/7724/acgu_ogp.png + source_url: http://www.aomoricgu.ac.jp/library + css_selector: '[document] > html.csspositionsticky.no-cssgridlegacy > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T14:02:42.359394+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-02-AOM-L-ACL.yaml b/data/custodian/JP-02-AOM-L-ACL.yaml index a80758a08b..1bee6563aa 100644 --- a/data/custodian/JP-02-AOM-L-ACL.yaml +++ b/data/custodian/JP-02-AOM-L-ACL.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:41.390712+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: AOM method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-AOM-L-ACL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-AOM-L-ACL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-AOM-L-ACL ghcid_numeric: 11336555938013853268 valid_from: '2025-12-06T23:38:41.390712+00:00' @@ -238,8 +239,27 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Aomori Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: *id006 postal_code: 030-0801 street_address: 1-3-7 SHIMMACHI, Aomori Shi, Aomori Ken, 030-0801 normalization_timestamp: '2025-12-09T10:55:24.174435+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:02:50.603906+00:00' + source_url: https://www.library.city.aomori.aomori.jp/acl/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.city.aomori.aomori.jp/acl/favicon.png + source_url: https://www.library.city.aomori.aomori.jp/acl/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:02:50.603906+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-02-AOM-L-ALS.yaml b/data/custodian/JP-02-AOM-L-ALS.yaml index 8e46ce99f6..f657e6a557 100644 --- a/data/custodian/JP-02-AOM-L-ALS.yaml +++ b/data/custodian/JP-02-AOM-L-ALS.yaml @@ -205,3 +205,33 @@ location: geonames_id: 2130658 geonames_name: Aomori feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:03:16.154180+00:00' + source_url: https://www.aomori-u.ac.jp/%E4%BB%98%E5%B1%9E%E5%9B%B3%E6%9B%B8%E9%A4%A8 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.aomori-u.ac.jp/wp/wp-content/uploads/2022/07/logo_white2.png + source_url: https://www.aomori-u.ac.jp/%E4%BB%98%E5%B1%9E%E5%9B%B3%E6%9B%B8%E9%A4%A8 + css_selector: '#masthead > div.elementor.elementor-40679 > section.elementor-section.elementor-top-section + > div.elementor-container.elementor-column-gap-default:nth-of-type(2) > div.elementor-column.elementor-col-50 + > div.elementor-widget-wrap.elementor-element-populated > div.elementor-element.elementor-element-eac94ce + > div.elementor-widget-container > figure.wp-caption > a > img.attachment-full.size-full' + retrieved_on: '2025-12-23T14:03:16.154180+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://www.aomori-u.ac.jp/wp/wp-content/uploads/2019/03/cropped-512-180x180.png + source_url: https://www.aomori-u.ac.jp/%E4%BB%98%E5%B1%9E%E5%9B%B3%E6%9B%B8%E9%A4%A8 + css_selector: '[document] > html > head > link:nth-of-type(68)' + retrieved_on: '2025-12-23T14:03:16.154180+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-02-AOM-L-AUHWL.yaml b/data/custodian/JP-02-AOM-L-AUHWL.yaml index 88eb2fb23f..0cae7d93ce 100644 --- a/data/custodian/JP-02-AOM-L-AUHWL.yaml +++ b/data/custodian/JP-02-AOM-L-AUHWL.yaml @@ -211,3 +211,22 @@ location: geonames_id: 2130658 geonames_name: Aomori feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:03:48.104944+00:00' + source_url: http://www.auhw.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.auhw.ac.jp/favicon.ico + source_url: http://www.auhw.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:03:48.104944+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-02-AOM-M-ACACAPU.yaml b/data/custodian/JP-02-AOM-M-ACACAPU.yaml index 83e9ea22e5..ba8053b555 100644 --- a/data/custodian/JP-02-AOM-M-ACACAPU.yaml +++ b/data/custodian/JP-02-AOM-M-ACACAPU.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.403129+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: AOM method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-AOM-M-ACACAPU - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-AOM-M-ACACAPU valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-AOM-M-ACACAPU ghcid_numeric: 3349445038974451196 valid_from: '2025-12-06T23:38:30.403129+00:00' @@ -228,8 +229,33 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Aomori Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: *id006 postal_code: 030-0134 street_address: GOSHIZAWA, Aomori Shi, Aomori Ken, 030-0134 normalization_timestamp: '2025-12-09T10:55:24.340734+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:04:05.817675+00:00' + source_url: https://acac-aomori.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://acac-aomori.jp/prd/wp-content/uploads/2021/03/cropped-favicon-180x180.png + source_url: https://acac-aomori.jp + css_selector: '[document] > html.canvas.touchevents > head > link:nth-of-type(12)' + retrieved_on: '2025-12-23T14:04:05.817675+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://acac-aomori.jp/prd/wp-content/uploads/2021/04/ogp.png + source_url: https://acac-aomori.jp + css_selector: '[document] > html.canvas.touchevents > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:04:05.817675+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-02-AOM-M-APAA.yaml b/data/custodian/JP-02-AOM-M-APAA.yaml index 97f569d73b..4cfb694d7f 100644 --- a/data/custodian/JP-02-AOM-M-APAA.yaml +++ b/data/custodian/JP-02-AOM-M-APAA.yaml @@ -248,3 +248,36 @@ wikidata_enrichment: commons_category: Asamushi Aquarium image: Asamushi Aquarium Aomori Japan03n.jpg wikidata_image: Asamushi Aquarium Aomori Japan03n.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:04:35.449292+00:00' + source_url: http://www.asamushi-aqua.com + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://asamushi-aqua.com/wp-content/themes/asamushi-aqua/assets/img/common/logo.png + source_url: http://www.asamushi-aqua.com + css_selector: '#gHeader > h1 > a > img.pc' + retrieved_on: '2025-12-23T14:04:35.449292+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 浅虫水族館 AQUARIUM ASAMUSHI + - claim_type: favicon_url + claim_value: https://asamushi-aqua.com/wp-content/themes/asamushi-aqua/assets/img/favicons/favicon.ico + source_url: http://www.asamushi-aqua.com + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T14:04:35.449292+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://asamushi-aqua.com/wp-content/uploads/2022/05/og_image.jpg + source_url: http://www.asamushi-aqua.com + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T14:04:35.449292+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-02-AOM-M-MMAL.yaml b/data/custodian/JP-02-AOM-M-MMAL.yaml index 6eeb5b793e..f1d6ee709e 100644 --- a/data/custodian/JP-02-AOM-M-MMAL.yaml +++ b/data/custodian/JP-02-AOM-M-MMAL.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.408001+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: AOM method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-AOM-M-MMAL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-AOM-M-MMAL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-AOM-M-MMAL ghcid_numeric: 14345780850263089868 valid_from: '2025-12-06T23:38:30.408001+00:00' @@ -219,8 +220,33 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Aomori Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: *id005 postal_code: 030-0184 street_address: ARAKAWA, Aomori Shi, Aomori Ken, 030-0184 normalization_timestamp: '2025-12-09T10:55:24.552591+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:05:40.611309+00:00' + source_url: https://www.plib.pref.aomori.lg.jp/bungakukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.plib.pref.aomori.lg.jp/common/images/apple-touch-icon.png + source_url: https://www.plib.pref.aomori.lg.jp/bungakukan + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-23T14:05:40.611309+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.plib.pref.aomori.lg.jp/uploads/ogimage.png + source_url: https://www.plib.pref.aomori.lg.jp/bungakukan + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:05:40.611309+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-02-AOM-M-SMJCC.yaml b/data/custodian/JP-02-AOM-M-SMJCC.yaml index 6ed754aa70..9517e14174 100644 --- a/data/custodian/JP-02-AOM-M-SMJCC.yaml +++ b/data/custodian/JP-02-AOM-M-SMJCC.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.430435+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: AOM method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-AOM-M-SMJCC - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-AOM-M-SMJCC valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-AOM-M-SMJCC ghcid_numeric: 233506701080018567 valid_from: '2025-12-06T23:38:30.430435+00:00' @@ -230,8 +231,27 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Aomori Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: *id005 postal_code: 038-0031 street_address: SANNAI, Aomori Shi, Aomori Ken, 038-0031 normalization_timestamp: '2025-12-09T10:55:24.578823+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:05:58.359080+00:00' + source_url: https://sannaimaruyama.pref.aomori.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sannaimaruyama.pref.aomori.jp/wp-content/uploads/2021/07/sanmaru.png + source_url: https://sannaimaruyama.pref.aomori.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T14:05:58.359080+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-02-GOS-M-ODMHS.yaml b/data/custodian/JP-02-GOS-M-ODMHS.yaml index 2c8d34d95e..99b8e1cf1a 100644 --- a/data/custodian/JP-02-GOS-M-ODMHS.yaml +++ b/data/custodian/JP-02-GOS-M-ODMHS.yaml @@ -291,3 +291,22 @@ location: postal_code: 037-0202 street_address: KANAGICHO, Goshogawara Shi, Aomori Ken, 037-0202 normalization_timestamp: '2025-12-09T10:55:24.668006+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:06:23.591701+00:00' + source_url: http://www.kanagi-gc.net/dazai + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.kanagi-gc.net/favicon.ico + source_url: http://www.kanagi-gc.net/dazai + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:06:23.591701+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-02-GOS-M-SMHH.yaml b/data/custodian/JP-02-GOS-M-SMHH.yaml index bcb92d2add..7c75914399 100644 --- a/data/custodian/JP-02-GOS-M-SMHH.yaml +++ b/data/custodian/JP-02-GOS-M-SMHH.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.489544+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: GOS method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-GOS-M-SMHH - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-GOS-M-SMHH valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-GOS-M-SMHH ghcid_numeric: 3325714312194702670 valid_from: '2025-12-06T23:38:30.489544+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: SHIURA MATERIAL HALL OF HISTORY @@ -198,7 +199,7 @@ wikidata_enrichment: location: city: Goshogawara Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 037-0403 street_address: JUSAN, Goshogawara Shi, Aomori Ken, 037-0403 @@ -213,3 +214,22 @@ location: geonames_id: 2131612 geonames_name: Goshogawara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:06:32.662414+00:00' + source_url: https://www.city.goshogawara.lg.jp/kyouiku/bunka/shiurarekimin.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.goshogawara.lg.jp/favicon.ico + source_url: https://www.city.goshogawara.lg.jp/kyouiku/bunka/shiurarekimin.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:06:32.662414+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-02-HAC-M-HAM.yaml b/data/custodian/JP-02-HAC-M-HAM.yaml index e8cd748147..125d01ed84 100644 --- a/data/custodian/JP-02-HAC-M-HAM.yaml +++ b/data/custodian/JP-02-HAC-M-HAM.yaml @@ -927,3 +927,37 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/JLzSdJWger4/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:07:32.487450+00:00' + source_url: https://hachinohe-art-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://hachinohe-art-museum.jp/wp-content/themes/hachinohe-art-museum/lib/images/museam-logo.png + source_url: https://hachinohe-art-museum.jp + css_selector: '[document] > html > body.typesquare_option > header.header > div.header-main.flex + > div.top-header-logo > a > img' + retrieved_on: '2025-12-23T14:07:32.487450+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 八戸市美術館 + - claim_type: favicon_url + claim_value: https://hachinohe-art-museum.jp/wp-content/themes/hachinohe-art-museum/lib/images/apple-touch-icon.png + source_url: https://hachinohe-art-museum.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:07:32.487450+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://hachinohe-art-museum.jp/wp-content/uploads/2021/11/ogp.jpg + source_url: https://hachinohe-art-museum.jp + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T14:07:32.487450+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-02-HIG-L-HL.yaml b/data/custodian/JP-02-HIG-L-HL.yaml index 34b2a1718e..d949b5bc92 100644 --- a/data/custodian/JP-02-HIG-L-HL.yaml +++ b/data/custodian/JP-02-HIG-L-HL.yaml @@ -203,3 +203,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.hiranai.aomori.jp/index.cfm/8 wikidata_official_website: http://www.town.hiranai.aomori.jp/index.cfm/8 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:08:14.438756+00:00' + source_url: http://www.town.hiranai.aomori.jp/index.cfm/8 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.hiranai.aomori.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.hiranai.aomori.jp/index.cfm/8 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:08:14.438756+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.hiranai.aomori.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.hiranai.aomori.jp/index.cfm/8 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:08:14.438756+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-02-HIR-L-H.yaml b/data/custodian/JP-02-HIR-L-H.yaml index d166c10856..820beb56f7 100644 --- a/data/custodian/JP-02-HIR-L-H.yaml +++ b/data/custodian/JP-02-HIR-L-H.yaml @@ -204,3 +204,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hirakawa.lg.jp/docs/2010100500223/ wikidata_official_website: http://www.city.hirakawa.lg.jp/docs/2010100500223/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:08:49.031673+00:00' + source_url: http://www.city.hirakawa.lg.jp/docs/2010100500223 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.hirakawa.lg.jp/favicon.ico + source_url: http://www.city.hirakawa.lg.jp/docs/2010100500223 + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:08:49.031673+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.hirakawa.lg.jp/contents_images/logo.png + source_url: http://www.city.hirakawa.lg.jp/docs/2010100500223 + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:08:49.031673+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-02-HIR-L-HCPL.yaml b/data/custodian/JP-02-HIR-L-HCPL.yaml index e08b70eaf8..a1803e58aa 100644 --- a/data/custodian/JP-02-HIR-L-HCPL.yaml +++ b/data/custodian/JP-02-HIR-L-HCPL.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hirosaki.aomori.jp/tosho/ wikidata_official_website: http://www.city.hirosaki.aomori.jp/tosho/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:09:05.978429+00:00' + source_url: http://www.city.hirosaki.aomori.jp/tosho + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.hirosaki.aomori.jp/renew/content_images/ogimage.png + source_url: http://www.city.hirosaki.aomori.jp/tosho + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:09:05.978429+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-02-HIR-L-HL-hirakawashihiraka_library.yaml b/data/custodian/JP-02-HIR-L-HL-hirakawashihiraka_library.yaml index f06cb64d68..2ece15fc26 100644 --- a/data/custodian/JP-02-HIR-L-HL-hirakawashihiraka_library.yaml +++ b/data/custodian/JP-02-HIR-L-HL-hirakawashihiraka_library.yaml @@ -204,3 +204,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hirakawa.lg.jp/docs/2011111600025/ wikidata_official_website: http://www.city.hirakawa.lg.jp/docs/2011111600025/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:09:18.961840+00:00' + source_url: http://www.city.hirakawa.lg.jp/docs/2011111600025 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.hirakawa.lg.jp/favicon.ico + source_url: http://www.city.hirakawa.lg.jp/docs/2011111600025 + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:09:18.961840+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.hirakawa.lg.jp/contents_images/logo.png + source_url: http://www.city.hirakawa.lg.jp/docs/2011111600025 + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:09:18.961840+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-02-HIR-L-HL-hirakawashionoe_library.yaml b/data/custodian/JP-02-HIR-L-HL-hirakawashionoe_library.yaml index 2322aa040d..50351d71b1 100644 --- a/data/custodian/JP-02-HIR-L-HL-hirakawashionoe_library.yaml +++ b/data/custodian/JP-02-HIR-L-HL-hirakawashionoe_library.yaml @@ -204,3 +204,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hirakawa.lg.jp/docs/2011111600025/ wikidata_official_website: http://www.city.hirakawa.lg.jp/docs/2011111600025/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:09:26.197664+00:00' + source_url: http://www.city.hirakawa.lg.jp/docs/2011111600025 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.hirakawa.lg.jp/favicon.ico + source_url: http://www.city.hirakawa.lg.jp/docs/2011111600025 + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:09:26.197664+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.hirakawa.lg.jp/contents_images/logo.png + source_url: http://www.city.hirakawa.lg.jp/docs/2011111600025 + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:09:26.197664+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-02-HIR-L-HL.yaml b/data/custodian/JP-02-HIR-L-HL.yaml index 09863012a1..39791b5f1f 100644 --- a/data/custodian/JP-02-HIR-L-HL.yaml +++ b/data/custodian/JP-02-HIR-L-HL.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hirosaki.aomori.jp/tosho/ wikidata_official_website: http://www.city.hirosaki.aomori.jp/tosho/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:09:50.021206+00:00' + source_url: http://www.city.hirosaki.aomori.jp/tosho + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.hirosaki.aomori.jp/renew/content_images/ogimage.png + source_url: http://www.city.hirosaki.aomori.jp/tosho + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:09:50.021206+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-02-HIR-L-HLE.yaml b/data/custodian/JP-02-HIR-L-HLE.yaml index d20e1cd844..7fa8e7635e 100644 --- a/data/custodian/JP-02-HIR-L-HLE.yaml +++ b/data/custodian/JP-02-HIR-L-HLE.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1130-71.html wikidata_official_website: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1130-71.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:10:07.881859+00:00' + source_url: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1130-71.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.hirosaki.aomori.jp/renew/content_images/ogimage.png + source_url: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1130-71.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:10:07.881859+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-02-HIR-L-HLS.yaml b/data/custodian/JP-02-HIR-L-HLS.yaml index 602647d0da..1cfaab3695 100644 --- a/data/custodian/JP-02-HIR-L-HLS.yaml +++ b/data/custodian/JP-02-HIR-L-HLS.yaml @@ -204,3 +204,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1126-71.html wikidata_official_website: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1126-71.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:10:19.639662+00:00' + source_url: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1126-71.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.hirosaki.aomori.jp/renew/content_images/ogimage.png + source_url: http://www.city.hirosaki.aomori.jp/tosho/2014-1204-1126-71.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:10:19.639662+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-02-HIR-L-HUL.yaml b/data/custodian/JP-02-HIR-L-HUL.yaml index f3786cc56a..d5dc5413d1 100644 --- a/data/custodian/JP-02-HIR-L-HUL.yaml +++ b/data/custodian/JP-02-HIR-L-HUL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:53.132829+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: HIR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-HIR-L-HUL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-HIR-L-HUL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-HIR-L-HUL ghcid_numeric: 10628557314210762839 valid_from: '2025-12-06T23:38:53.132829+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: Hirosaki University Library @@ -187,14 +188,15 @@ wikidata_enrichment: member_of: - 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.ul.hirosaki-u.ac.jp wikidata_official_website: http://www.ul.hirosaki-u.ac.jp location: city: Hirosaki Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 036-8560 street_address: 1 BUNKYOCHO, Hirosaki Shi, Aomori Ken, 036-8560 @@ -209,3 +211,36 @@ location: geonames_id: 2130057 geonames_name: Hirosaki feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:10:30.645219+00:00' + source_url: http://www.ul.hirosaki-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://ul.hirosaki-u.ac.jp/wp-content/themes/ul.hirosaki-u/assets/img/logo.png + source_url: http://www.ul.hirosaki-u.ac.jp + css_selector: '#siteBranding > h1.siteTitle > img' + retrieved_on: '2025-12-23T14:10:30.645219+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 弘前大学附属図書館 + - claim_type: favicon_url + claim_value: https://ul.hirosaki-u.ac.jp/wp-content/uploads/2025/02/hirodai-300x300.png + source_url: http://www.ul.hirosaki-u.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-23T14:10:30.645219+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://ul.hirosaki-u.ac.jp/wp-content/themes/ul.hirosaki-u/assets/img/ogp.png + source_url: http://www.ul.hirosaki-u.ac.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:10:30.645219+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-02-HIR-L-SGUL.yaml b/data/custodian/JP-02-HIR-L-SGUL.yaml index 68f9e112a5..5369bf1145 100644 --- a/data/custodian/JP-02-HIR-L-SGUL.yaml +++ b/data/custodian/JP-02-HIR-L-SGUL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:54.393897+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: HIR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-HIR-L-SGUL - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-HIR-L-SGUL valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-HIR-L-SGUL ghcid_numeric: 6293518778637590936 valid_from: '2025-12-06T23:38:54.393897+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: Shibata Gakuen University Library @@ -190,14 +191,15 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: https://univ.shibata.ac.jp/campus-life/facilities/library/ wikidata_official_website: https://univ.shibata.ac.jp/campus-life/facilities/library/ location: city: Hirosaki Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 036-8530 street_address: 1-1-16 KIYOHARA, Hirosaki Shi, Aomori Ken, 036-8530 @@ -212,3 +214,36 @@ location: geonames_id: 2130057 geonames_name: Hirosaki feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:10:48.016709+00:00' + source_url: https://univ.shibata.ac.jp/campus-life/facilities/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://univ.shibata.ac.jp/wp-content/themes/shibatauniv/img/logo.png + source_url: https://univ.shibata.ac.jp/campus-life/facilities/library + css_selector: '#pages > header > div.head > a.logo > img' + retrieved_on: '2025-12-23T14:10:48.016709+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 柴田学園大学 + - claim_type: favicon_url + claim_value: https://univ.shibata.ac.jp/wp-content/themes/shibatauniv/img/icon.png + source_url: https://univ.shibata.ac.jp/campus-life/facilities/library + css_selector: '[document] > html.js.svg > head > link:nth-of-type(11)' + retrieved_on: '2025-12-23T14:10:48.016709+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://univ.shibata.ac.jp/wp-content/uploads/2021/03/library-head.jpg + source_url: https://univ.shibata.ac.jp/campus-life/facilities/library + css_selector: '[document] > html.js.svg > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-23T14:10:48.016709+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-02-HIR-M-HLLM.yaml b/data/custodian/JP-02-HIR-M-HLLM.yaml index 82ee9cf497..9da113249c 100644 --- a/data/custodian/JP-02-HIR-M-HLLM.yaml +++ b/data/custodian/JP-02-HIR-M-HLLM.yaml @@ -226,3 +226,20 @@ wikidata_enrichment: image: Hirosaki Municipal Library and Literature Museum.jpg commons_category: Hirosaki City Museum of Local Literature wikidata_image: Hirosaki Municipal Library and Literature Museum.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:12:19.128151+00:00' + source_url: http://www.city.hirosaki.aomori.jp/bungakukan + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.hirosaki.aomori.jp/renew/content_images/ogimage.png + source_url: http://www.city.hirosaki.aomori.jp/bungakukan + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:12:19.128151+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-02-HIR-M-HUM.yaml b/data/custodian/JP-02-HIR-M-HUM.yaml index b8d178d580..b06c9c7f03 100644 --- a/data/custodian/JP-02-HIR-M-HUM.yaml +++ b/data/custodian/JP-02-HIR-M-HUM.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.452236+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: HIR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-HIR-M-HUM - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-HIR-M-HUM valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-HIR-M-HUM ghcid_numeric: 253580022283103522 valid_from: '2025-12-06T23:38:30.452236+00:00' @@ -221,8 +222,35 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Hirosaki Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: *id005 postal_code: 036-8560 street_address: BUNKYOCHO, Hirosaki Shi, Aomori Ken, 036-8560 normalization_timestamp: '2025-12-09T10:55:25.527223+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:12:30.503374+00:00' + source_url: https://shiryokan.hirosaki-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://shiryokan.hirosaki-u.ac.jp/wp-content/themes/shiryokan/images/logo.png + source_url: https://shiryokan.hirosaki-u.ac.jp + css_selector: '#pageHeader > img.nodisplay' + retrieved_on: '2025-12-23T14:12:30.503374+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 弘前大学資料館 + - claim_type: favicon_url + claim_value: https://shiryokan.hirosaki-u.ac.jp/wp-content/uploads/2025/03/hirodai-220x220.png + source_url: https://shiryokan.hirosaki-u.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-23T14:12:30.503374+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-02-HIR-M-THMHC.yaml b/data/custodian/JP-02-HIR-M-THMHC.yaml index f4125385e2..8393bf14e4 100644 --- a/data/custodian/JP-02-HIR-M-THMHC.yaml +++ b/data/custodian/JP-02-HIR-M-THMHC.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.439408+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: HIR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-HIR-M-THMHC - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-HIR-M-THMHC valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-HIR-M-THMHC ghcid_numeric: 8443878028371177900 valid_from: '2025-12-06T23:38:30.439408+00:00' @@ -231,8 +232,25 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Hirosaki Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: *id005 postal_code: 036-1344 street_address: TAKAOKA, Hirosaki Shi, Aomori Ken, 036-1344 normalization_timestamp: '2025-12-09T10:55:25.551209+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:12:42.231147+00:00' + source_url: https://www.city.hirosaki.aomori.jp/takaoka-rekishikan + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.hirosaki.aomori.jp/renew/content_images/ogimage.png + source_url: https://www.city.hirosaki.aomori.jp/takaoka-rekishikan + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:12:42.231147+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-02-HIR-M-YI.yaml b/data/custodian/JP-02-HIR-M-YI.yaml index 168a473c4e..2cc9c09e2b 100644 --- a/data/custodian/JP-02-HIR-M-YI.yaml +++ b/data/custodian/JP-02-HIR-M-YI.yaml @@ -197,3 +197,28 @@ wikidata_enrichment: wikidata_official_website: http://www.hirosakipark.or.jp/yayoi/index.html wikidata_social_media: instagram_username: hirosakiyayoizoo +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:12:50.715368+00:00' + source_url: http://www.hirosakipark.or.jp/yayoi/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.hirosakipark.or.jp/images/favicon.ico + source_url: http://www.hirosakipark.or.jp/yayoi/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:12:50.715368+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.hirosakipark.or.jp/images/yayoi/animal/shima-hukurou.jpg + source_url: http://www.hirosakipark.or.jp/yayoi/index.html + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T14:12:50.715368+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-02-KAM-L-RL.yaml b/data/custodian/JP-02-KAM-L-RL.yaml index c1d4d7efac..5fc82917f3 100644 --- a/data/custodian/JP-02-KAM-L-RL.yaml +++ b/data/custodian/JP-02-KAM-L-RL.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.rokunohe.aomori.jp/kyoiku_tosyokan_riyoannai.html wikidata_official_website: http://www.town.rokunohe.aomori.jp/kyoiku_tosyokan_riyoannai.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:13:15.245926+00:00' + source_url: http://www.town.rokunohe.aomori.jp/kyoiku_tosyokan_riyoannai.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.rokunohe.aomori.jp/_files/00000086/header-logo.png + source_url: http://www.town.rokunohe.aomori.jp/kyoiku_tosyokan_riyoannai.html + css_selector: '#siteLogo > h1 > a > img' + retrieved_on: '2025-12-23T14:13:15.245926+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 六戸町 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-02-KAM-L-RVL.yaml b/data/custodian/JP-02-KAM-L-RVL.yaml index 2dd49f36e5..09d4a2caea 100644 --- a/data/custodian/JP-02-KAM-L-RVL.yaml +++ b/data/custodian/JP-02-KAM-L-RVL.yaml @@ -200,3 +200,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.rokkasho-tosho.jp/ wikidata_official_website: http://www.rokkasho-tosho.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:13:51.228475+00:00' + source_url: http://www.rokkasho-tosho.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rokkasho-tosho.jp/wp-content/uploads/2024/11/siteicon-300x300.png + source_url: http://www.rokkasho-tosho.jp + css_selector: '[document] > html > head > link:nth-of-type(33)' + retrieved_on: '2025-12-23T14:13:51.228475+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://www.rokkasho-tosho.jp/wp-content/uploads/2024/11/defphoto-4.png + source_url: http://www.rokkasho-tosho.jp + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T14:13:51.228475+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-02-KAM-L-S.yaml b/data/custodian/JP-02-KAM-L-S.yaml index df54425071..0567b2c69d 100644 --- a/data/custodian/JP-02-KAM-L-S.yaml +++ b/data/custodian/JP-02-KAM-L-S.yaml @@ -201,3 +201,37 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/chuoukouminkan.html wikidata_official_website: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/chuoukouminkan.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:14:00.324919+00:00' + source_url: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/chuoukouminkan.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/assets/img/logo.png + source_url: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/chuoukouminkan.html + css_selector: '[document] > html > body > header > div.l-dt-header > div.l-dt-header__wrap + > div.l-dt-header__up > h1.l-dt-header__logo > a > img' + retrieved_on: '2025-12-23T14:14:00.324919+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 青森県七戸町 + - claim_type: favicon_url + claim_value: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/icon.png + source_url: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/chuoukouminkan.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:14:00.324919+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.shichinohe.lg.jp/assets/img/ogp-img.png + source_url: http://www.town.shichinohe.lg.jp/gyosei/shisetsu/koukyou/chuoukouminkan.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:14:00.324919+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-02-KAM-L-TL.yaml b/data/custodian/JP-02-KAM-L-TL.yaml index 774a214adc..67f4cbf00b 100644 --- a/data/custodian/JP-02-KAM-L-TL.yaml +++ b/data/custodian/JP-02-KAM-L-TL.yaml @@ -201,3 +201,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.tohoku.lg.jp/community/study/study_tosho_01.html wikidata_official_website: http://www.town.tohoku.lg.jp/community/study/study_tosho_01.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:14:10.068475+00:00' + source_url: http://www.town.tohoku.lg.jp/community/study/study_tosho_01.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.tohoku.lg.jp/community/study/images/logo.png + source_url: http://www.town.tohoku.lg.jp/community/study/study_tosho_01.html + css_selector: '[document] > html > body > header > div.header-in > div.logo > + h1 > a > img' + retrieved_on: '2025-12-23T14:14:10.068475+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東北町ロゴ + - claim_type: favicon_url + claim_value: http://www.town.tohoku.lg.jp/images/apple-touch-icon.png + source_url: http://www.town.tohoku.lg.jp/community/study/study_tosho_01.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:14:10.068475+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: 3 diff --git a/data/custodian/JP-02-KAM-L-TLO.yaml b/data/custodian/JP-02-KAM-L-TLO.yaml index fef345b181..e20cd5cd7c 100644 --- a/data/custodian/JP-02-KAM-L-TLO.yaml +++ b/data/custodian/JP-02-KAM-L-TLO.yaml @@ -202,3 +202,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.tohoku.lg.jp/gyou_gui/info/info_shisetsu_13.html wikidata_official_website: http://www.town.tohoku.lg.jp/gyou_gui/info/info_shisetsu_13.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:14:17.061620+00:00' + source_url: http://www.town.tohoku.lg.jp/gyou_gui/info/info_shisetsu_13.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.tohoku.lg.jp/gyou_gui/info/images/logo.png + source_url: http://www.town.tohoku.lg.jp/gyou_gui/info/info_shisetsu_13.html + css_selector: '[document] > html > body > header > div.header-in > div.logo > + h1 > a > img' + retrieved_on: '2025-12-23T14:14:17.061620+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 東北町ロゴ + - claim_type: favicon_url + claim_value: http://www.town.tohoku.lg.jp/images/apple-touch-icon.png + source_url: http://www.town.tohoku.lg.jp/gyou_gui/info/info_shisetsu_13.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:14:17.061620+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: 3 diff --git a/data/custodian/JP-02-KAM-L-YL.yaml b/data/custodian/JP-02-KAM-L-YL.yaml index f12e0f0cb2..7cb6e73ab4 100644 --- a/data/custodian/JP-02-KAM-L-YL.yaml +++ b/data/custodian/JP-02-KAM-L-YL.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.yokohama.lg.jp/index.cfm/6 wikidata_official_website: http://www.town.yokohama.lg.jp/index.cfm/6 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:14:24.619210+00:00' + source_url: http://www.town.yokohama.lg.jp/index.cfm/6 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.yokohama.lg.jp/designs/default/favicon.ico + source_url: http://www.town.yokohama.lg.jp/index.cfm/6 + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T14:14:24.619210+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.yokohama.lg.jp/images/og_image.png + source_url: http://www.town.yokohama.lg.jp/index.cfm/6 + css_selector: '[document] > html > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-23T14:14:24.619210+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-02-KAM-M-UTMMA.yaml b/data/custodian/JP-02-KAM-M-UTMMA.yaml index 9ba5859a2c..463fb0d4ad 100644 --- a/data/custodian/JP-02-KAM-M-UTMMA.yaml +++ b/data/custodian/JP-02-KAM-M-UTMMA.yaml @@ -274,3 +274,36 @@ location: postal_code: 039-2501 street_address: ARAKUMANAI, Kamikita Gun Shichinohe Machi, Aomori Ken, 039-2501 normalization_timestamp: '2025-12-09T10:55:25.980920+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:14:56.929741+00:00' + source_url: http://www.takayamamuseum.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.takayamamuseum.jp/wp-content/themes/uichi00/assets/images/sp01_img_logo.svg + source_url: http://www.takayamamuseum.jp + css_selector: '#subhead > div.sp-header-main > h1.site-title > a > img' + retrieved_on: '2025-12-23T14:14:56.929741+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 七戸町立鷹山宇一記念美術館｜Takayama Uichi Memorial Museum of Art + - claim_type: favicon_url + claim_value: https://www.takayamamuseum.jp/wp-content/uploads/2023/05/cropped-favicon-2-180x180.png + source_url: http://www.takayamamuseum.jp + css_selector: '[document] > html.no-js > head > link:nth-of-type(13)' + retrieved_on: '2025-12-23T14:14:56.929741+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.takayamamuseum.jp/wp-content/uploads/2023/05/OGP.jpg + source_url: http://www.takayamamuseum.jp + css_selector: '[document] > html.no-js > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T14:14:56.929741+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-02-KAN-M-BGMMK.yaml b/data/custodian/JP-02-KAN-M-BGMMK.yaml index e810860a48..e04982878e 100644 --- a/data/custodian/JP-02-KAN-M-BGMMK.yaml +++ b/data/custodian/JP-02-KAN-M-BGMMK.yaml @@ -270,3 +270,28 @@ location: geonames_id: 2112364 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:23.618151+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:15:39.485380+00:00' + source_url: https://www.city.yokote.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.yokote.lg.jp + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T14:15:39.485380+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.yokote.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.yokote.lg.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T14:15:39.485380+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-02-KIT-L-ATIL.yaml b/data/custodian/JP-02-KIT-L-ATIL.yaml index a9e99f492b..2b9e4a7902 100644 --- a/data/custodian/JP-02-KIT-L-ATIL.yaml +++ b/data/custodian/JP-02-KIT-L-ATIL.yaml @@ -203,3 +203,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.itayanagi.aomori.jp/library/ wikidata_official_website: http://www.town.itayanagi.aomori.jp/library/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:15:47.732379+00:00' + source_url: http://www.town.itayanagi.aomori.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.itayanagi.aomori.jp/contents_images/favicon.png + source_url: http://www.town.itayanagi.aomori.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:15:47.732379+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-02-KIT-L-NL.yaml b/data/custodian/JP-02-KIT-L-NL.yaml index 31fce9a6b3..3831240109 100644 --- a/data/custodian/JP-02-KIT-L-NL.yaml +++ b/data/custodian/JP-02-KIT-L-NL.yaml @@ -203,3 +203,37 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.nakadomari.lg.jp/index.cfm/12 wikidata_official_website: http://www.town.nakadomari.lg.jp/index.cfm/12 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:15:57.570061+00:00' + source_url: http://www.town.nakadomari.lg.jp/index.cfm/12 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.nakadomari.lg.jp/theme/base/img_common/sub_logo.png + source_url: http://www.town.nakadomari.lg.jp/index.cfm/12 + css_selector: '#header > div.sub-header-wrap:nth-of-type(2) > div.sub-header-logo + > a > img' + retrieved_on: '2025-12-23T14:15:57.570061+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 中泊町 Nakadomari Town + - claim_type: favicon_url + claim_value: http://www.town.nakadomari.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.nakadomari.lg.jp/index.cfm/12 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:15:57.570061+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.nakadomari.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.town.nakadomari.lg.jp/index.cfm/12 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:15:57.570061+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-02-KIT-M-LMHIT.yaml b/data/custodian/JP-02-KIT-M-LMHIT.yaml index ad35b26906..68552f209a 100644 --- a/data/custodian/JP-02-KIT-M-LMHIT.yaml +++ b/data/custodian/JP-02-KIT-M-LMHIT.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.532190+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: KIT method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-KIT-M-LMHIT - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-KIT-M-LMHIT valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-KIT-M-LMHIT ghcid_numeric: 6919337991409181783 valid_from: '2025-12-06T23:38:30.532190+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: LOCAL MATERIALS HOUSE ITAYANAGI TOWN @@ -198,7 +199,7 @@ wikidata_enrichment: location: city: Kitatsugaru Gun Itayanagi Machi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 038-3672 street_address: HAINUMA, Kitatsugaru Gun Itayanagi Machi, Aomori Ken, 038-3672 @@ -215,3 +216,22 @@ location: geonames_id: 2129884 geonames_name: Itayanagi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:16:06.632380+00:00' + source_url: https://www.town.itayanagi.aomori.jp/tourism/kyoudo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.itayanagi.aomori.jp/contents_images/favicon.png + source_url: https://www.town.itayanagi.aomori.jp/tourism/kyoudo + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:16:06.632380+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-02-KUR-L-K.yaml b/data/custodian/JP-02-KUR-L-K.yaml index b5e0bc91a3..7802962957 100644 --- a/data/custodian/JP-02-KUR-L-K.yaml +++ b/data/custodian/JP-02-KUR-L-K.yaml @@ -199,3 +199,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_hor_00.html wikidata_official_website: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_hor_00.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:16:15.783030+00:00' + source_url: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_hor_00.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.city.kuroishi.aomori.jp/contents_images/common/logo.png + source_url: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_hor_00.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:16:15.783030+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-02-KUR-L-KCL.yaml b/data/custodian/JP-02-KUR-L-KCL.yaml index c03dbec835..1318b90a4e 100644 --- a/data/custodian/JP-02-KUR-L-KCL.yaml +++ b/data/custodian/JP-02-KUR-L-KCL.yaml @@ -199,3 +199,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_tos_00.html wikidata_official_website: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_tos_00.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:16:22.229915+00:00' + source_url: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_tos_00.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.city.kuroishi.aomori.jp/contents_images/common/logo.png + source_url: http://www.city.kuroishi.aomori.jp/Public_Address/Pub_tos_00.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:16:22.229915+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-02-KUR-M-TKH.yaml b/data/custodian/JP-02-KUR-M-TKH.yaml index 26960ae6be..7c56cb3467 100644 --- a/data/custodian/JP-02-KUR-M-TKH.yaml +++ b/data/custodian/JP-02-KUR-M-TKH.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.482066+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: KUR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-KUR-M-TKH - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-KUR-M-TKH valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-KUR-M-TKH ghcid_numeric: 12284930265107774217 valid_from: '2025-12-06T23:38:30.482066+00:00' @@ -246,8 +247,27 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Kuroishi Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: *id005 postal_code: 036-0412 street_address: FUKURO, Kuroishi Shi, Aomori Ken, 036-0412 normalization_timestamp: '2025-12-09T10:55:26.200445+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:16:35.992246+00:00' + source_url: http://tsugarukokeshi.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://tsugarukokeshi.com/wp-content/uploads/2018/07/fav_apple.png + source_url: http://tsugarukokeshi.com + css_selector: '[document] > html.js.svg > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T14:16:35.992246+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-02-MIN-L-FLT.yaml b/data/custodian/JP-02-MIN-L-FLT.yaml index 4ac80a96a5..440c823902 100644 --- a/data/custodian/JP-02-MIN-L-FLT.yaml +++ b/data/custodian/JP-02-MIN-L-FLT.yaml @@ -225,3 +225,20 @@ wikidata_enrichment: wikidata_media: image: Fujisaki Town Library 20191124.jpg wikidata_image: Fujisaki Town Library 20191124.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:16:43.969824+00:00' + source_url: http://www.town.fujisaki.lg.jp/index.cfm/10 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.town.fujisaki.lg.jp/images/og_image.png + source_url: http://www.town.fujisaki.lg.jp/index.cfm/10 + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-23T14:16:43.969824+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-02-MIN-L-T.yaml b/data/custodian/JP-02-MIN-L-T.yaml index 739ae9c1ec..7093329edd 100644 --- a/data/custodian/JP-02-MIN-L-T.yaml +++ b/data/custodian/JP-02-MIN-L-T.yaml @@ -203,3 +203,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.fujisaki.lg.jp/index.cfm/10 wikidata_official_website: http://www.town.fujisaki.lg.jp/index.cfm/10 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:16:55.925356+00:00' + source_url: http://www.town.fujisaki.lg.jp/index.cfm/10 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.town.fujisaki.lg.jp/images/og_image.png + source_url: http://www.town.fujisaki.lg.jp/index.cfm/10 + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-23T14:16:55.925356+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-02-MIS-M-MASMA.yaml b/data/custodian/JP-02-MIS-M-MASMA.yaml index faa3674748..420863341a 100644 --- a/data/custodian/JP-02-MIS-M-MASMA.yaml +++ b/data/custodian/JP-02-MIS-M-MASMA.yaml @@ -922,3 +922,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/MEdmbEyFtiw/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:17:14.840701+00:00' + source_url: http://www.kokukagaku.jp/01_museum/01_frame.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kokukagaku.jp/wp-content/themes/masm/img/favicon.ico + source_url: http://www.kokukagaku.jp/01_museum/01_frame.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:17:14.840701+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://kokukagaku.jp/wp-content/themes/masm/img/ogpimg.jpg + source_url: http://www.kokukagaku.jp/01_museum/01_frame.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T14:17:14.840701+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-02-MIS-M-MCMHFC.yaml b/data/custodian/JP-02-MIS-M-MCMHFC.yaml index 8c75053367..add7c6a7a4 100644 --- a/data/custodian/JP-02-MIS-M-MCMHFC.yaml +++ b/data/custodian/JP-02-MIS-M-MCMHFC.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.510018+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: MIS method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-MIS-M-MCMHFC - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-MIS-M-MCMHFC valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-MIS-M-MCMHFC ghcid_numeric: 8017823869250623213 valid_from: '2025-12-06T23:38:30.510018+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: MISAWA CITY MUSEUM OF HISTORY FOLK CUSTOMS @@ -215,7 +216,7 @@ wikidata_enrichment: location: city: Misawa Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 033-0022 street_address: MISAWA, Misawa Shi, Aomori Ken, 033-0022 @@ -230,3 +231,30 @@ location: geonames_id: 2129211 geonames_name: Misawa feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:17:28.407365+00:00' + source_url: http://kite-misawa.com/rekimin_misawa + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://kite-misawa.com/wp-content/themes/kite-misawa/images/titlelogo.svg + source_url: http://kite-misawa.com/rekimin_misawa + css_selector: '#branding > a.smt_head > img' + retrieved_on: '2025-12-23T14:17:28.407365+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 三沢市観光情報サイト　来て！みさわ + - claim_type: favicon_url + claim_value: https://kite-misawa.com/wp-content/uploads/2024/11/cropped-logo-180x180.jpg + source_url: http://kite-misawa.com/rekimin_misawa + css_selector: '[document] > html.wf-inactive.webkit > head > link:nth-of-type(22)' + retrieved_on: '2025-12-23T14:17:28.407365+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/JP-02-NIB-M-NFM.yaml b/data/custodian/JP-02-NIB-M-NFM.yaml index 2af22d302c..8c0e2391ca 100644 --- a/data/custodian/JP-02-NIB-M-NFM.yaml +++ b/data/custodian/JP-02-NIB-M-NFM.yaml @@ -330,3 +330,22 @@ location: geonames_id: 8321892 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:23.657173+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:18:14.249114+00:00' + source_url: https://www.rinya.maff.go.jp/tohoku/introduction/gaiyou_kyoku/nibetu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rinya.maff.go.jp/tohoku/shared_new/shared/images/rinya.ico + source_url: https://www.rinya.maff.go.jp/tohoku/introduction/gaiyou_kyoku/nibetu + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:18:14.249114+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-02-NIK-M-SAEMM.yaml b/data/custodian/JP-02-NIK-M-SAEMM.yaml index 243bdaaf43..10888a13fa 100644 --- a/data/custodian/JP-02-NIK-M-SAEMM.yaml +++ b/data/custodian/JP-02-NIK-M-SAEMM.yaml @@ -409,3 +409,30 @@ location: geonames_id: 6822198 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:23.703688+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:18:21.011424+00:00' + source_url: http://shirase-kinenkan.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://shirase-kinenkan.jp/images/banners/logo.png + source_url: http://shirase-kinenkan.jp + css_selector: '#header > div.inner:nth-of-type(2) > h2 > a > img' + retrieved_on: '2025-12-23T14:18:21.011424+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 白瀬南極探検隊記念館 + - claim_type: favicon_url + claim_value: http://shirase-kinenkan.jp/favicon.ico + source_url: http://shirase-kinenkan.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:18:21.011424+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-02-NIS-M-PMOM.yaml b/data/custodian/JP-02-NIS-M-PMOM.yaml index 61842839c4..d9086e5e6c 100644 --- a/data/custodian/JP-02-NIS-M-PMOM.yaml +++ b/data/custodian/JP-02-NIS-M-PMOM.yaml @@ -400,3 +400,22 @@ location: geonames_id: 9814841 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:23.745058+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:18:39.714094+00:00' + source_url: https://museum.vill.ogata.akita.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://museum.vill.ogata.akita.jp/t_cms/assets/themes/custom/apple-touch-icon.png + source_url: https://museum.vill.ogata.akita.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:18:39.714094+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-02-SAN-L-APL.yaml b/data/custodian/JP-02-SAN-L-APL.yaml index 598122ccfc..fa06de2f24 100644 --- a/data/custodian/JP-02-SAN-L-APL.yaml +++ b/data/custodian/JP-02-SAN-L-APL.yaml @@ -385,3 +385,28 @@ location: geonames_id: 8314067 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:23.785378+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:18:48.178550+00:00' + source_url: http://www.apl.pref.akita.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.apl.pref.akita.jp/assets/front/img/common/apple-touch-icon.png + source_url: http://www.apl.pref.akita.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:18:48.178550+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.apl.pref.akita.jp/uploads/common/og.png + source_url: http://www.apl.pref.akita.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T14:18:48.178550+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-02-SAN-L-HH.yaml b/data/custodian/JP-02-SAN-L-HH.yaml index 5c3d4d1007..926be74e16 100644 --- a/data/custodian/JP-02-SAN-L-HH.yaml +++ b/data/custodian/JP-02-SAN-L-HH.yaml @@ -201,3 +201,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.hashikami.lg.jp/index.cfm/10 wikidata_official_website: http://www.town.hashikami.lg.jp/index.cfm/10 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:19:01.709536+00:00' + source_url: http://www.town.hashikami.lg.jp/index.cfm/10 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.hashikami.lg.jp/designs/original/images/favicon.ico + source_url: http://www.town.hashikami.lg.jp/index.cfm/10 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:19:01.709536+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.hashikami.lg.jp/images/og_image.png + source_url: http://www.town.hashikami.lg.jp/index.cfm/10 + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-23T14:19:01.709536+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-02-SAN-L-N-nambuchoritsunagawachugakkotoshoshitsuikkai.yaml b/data/custodian/JP-02-SAN-L-N-nambuchoritsunagawachugakkotoshoshitsuikkai.yaml index 1b6a0a7e8d..d8d7dd3f20 100644 --- a/data/custodian/JP-02-SAN-L-N-nambuchoritsunagawachugakkotoshoshitsuikkai.yaml +++ b/data/custodian/JP-02-SAN-L-N-nambuchoritsunagawachugakkotoshoshitsuikkai.yaml @@ -201,3 +201,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 wikidata_official_website: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:19:10.158914+00:00' + source_url: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.aomori-nanbu.lg.jp/apple-touch-icon.png + source_url: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:19:10.158914+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-02-SAN-L-N.yaml b/data/custodian/JP-02-SAN-L-N.yaml index 40a3f85740..e53b31c4fe 100644 --- a/data/custodian/JP-02-SAN-L-N.yaml +++ b/data/custodian/JP-02-SAN-L-N.yaml @@ -202,3 +202,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 wikidata_official_website: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:19:16.059647+00:00' + source_url: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.aomori-nanbu.lg.jp/apple-touch-icon.png + source_url: http://www.town.aomori-nanbu.lg.jp/index.cfm/11 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:19:16.059647+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-02-SAN-L-SL.yaml b/data/custodian/JP-02-SAN-L-SL.yaml index 26f5e9e5d8..8321b725ac 100644 --- a/data/custodian/JP-02-SAN-L-SL.yaml +++ b/data/custodian/JP-02-SAN-L-SL.yaml @@ -225,3 +225,28 @@ wikidata_enrichment: wikidata_image: Sannohe Town Library.jpg wikidata_contact: phone_number: +81-179-22-1731 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:19:25.358395+00:00' + source_url: http://www.town.sannohe.aomori.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.sannohe.aomori.jp/smartphone.png + source_url: http://www.town.sannohe.aomori.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:19:25.358395+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.sannohe.aomori.jp/material/images/group/1/service01.png + source_url: http://www.town.sannohe.aomori.jp + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T14:19:25.358395+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-02-SAN-L-TL.yaml b/data/custodian/JP-02-SAN-L-TL.yaml index e5d93ff967..b27d204ec6 100644 --- a/data/custodian/JP-02-SAN-L-TL.yaml +++ b/data/custodian/JP-02-SAN-L-TL.yaml @@ -202,3 +202,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.takko.lg.jp/index.cfm/14 wikidata_official_website: http://www.town.takko.lg.jp/index.cfm/14 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:19:32.284772+00:00' + source_url: http://www.town.takko.lg.jp/index.cfm/14 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.town.takko.lg.jp/images/og_image.png + source_url: http://www.town.takko.lg.jp/index.cfm/14 + css_selector: '[document] > html > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-23T14:19:32.284772+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-02-SAN-M-SMLFHMH.yaml b/data/custodian/JP-02-SAN-M-SMLFHMH.yaml index e14c00e401..344b2aad95 100644 --- a/data/custodian/JP-02-SAN-M-SMLFHMH.yaml +++ b/data/custodian/JP-02-SAN-M-SMLFHMH.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.557248+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: SAN method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-SAN-M-SMLFHMH - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-SAN-M-SMLFHMH valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-SAN-M-SMLFHMH ghcid_numeric: 5115353803910708387 valid_from: '2025-12-06T23:38:30.557248+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: SANNOHE-MACHI LOCAL FOLK HISTORICAL MATERIAL HALL @@ -198,7 +199,7 @@ wikidata_enrichment: location: city: Sannohe Gun Sannohe Machi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 039-0112 street_address: UMENAI, Sannohe Gun Sannohe Machi, Aomori Ken, 039-0112 @@ -215,3 +216,28 @@ location: geonames_id: 2128303 geonames_name: Sannohe feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:19:38.495906+00:00' + source_url: https://www.town.sannohe.aomori.jp/soshiki/kyouikuiinkaijimukyoku/rekishi_bunka/4339.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.sannohe.aomori.jp/smartphone.png + source_url: https://www.town.sannohe.aomori.jp/soshiki/kyouikuiinkaijimukyoku/rekishi_bunka/4339.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:19:38.495906+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.sannohe.aomori.jp/material/images/group/12/shiryokangazou.JPG + source_url: https://www.town.sannohe.aomori.jp/soshiki/kyouikuiinkaijimukyoku/rekishi_bunka/4339.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T14:19:38.495906+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-02-SEN-M-SHM.yaml b/data/custodian/JP-02-SEN-M-SHM.yaml index ea10bbd8c6..298cce4500 100644 --- a/data/custodian/JP-02-SEN-M-SHM.yaml +++ b/data/custodian/JP-02-SEN-M-SHM.yaml @@ -424,3 +424,36 @@ location: geonames_id: 8315972 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:23.970927+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:20:04.220261+00:00' + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1002685/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1002685/index.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:20:04.220261+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秋田市公式サイト + - claim_type: favicon_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1002685/index.html + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T14:20:04.220261+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1002685/index.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:20:04.220261+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-02-SHI-M-KMK.yaml b/data/custodian/JP-02-SHI-M-KMK.yaml index f006479907..08c5cda97a 100644 --- a/data/custodian/JP-02-SHI-M-KMK.yaml +++ b/data/custodian/JP-02-SHI-M-KMK.yaml @@ -251,3 +251,36 @@ location: geonames_id: 8428667 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.000473+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:21:09.987816+00:00' + source_url: https://www.town.kosaka.akita.jp/machinososhiki/sonotashisetsu/sogouhakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.kosaka.akita.jp/theme/base/img_sub/header_logo_pc.png + source_url: https://www.town.kosaka.akita.jp/machinososhiki/sonotashisetsu/sogouhakubutsukan + css_selector: '#header > div.header-in > p.header-logo > a > img' + retrieved_on: '2025-12-23T14:21:09.987816+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秋田県小坂町 Kosaka Town Official Site ひとと自然と文化を未来につなぐ 魅力あふれるまち + - claim_type: favicon_url + claim_value: https://www.town.kosaka.akita.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.kosaka.akita.jp/machinososhiki/sonotashisetsu/sogouhakubutsukan + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:21:09.987816+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.kosaka.akita.jp/material/images/group/23/kyoudokangaikan.jpg + source_url: https://www.town.kosaka.akita.jp/machinososhiki/sonotashisetsu/sogouhakubutsukan + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T14:21:09.987816+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-02-TEN-M-OCM.yaml b/data/custodian/JP-02-TEN-M-OCM.yaml index d1f3806804..86c98ca68e 100644 --- a/data/custodian/JP-02-TEN-M-OCM.yaml +++ b/data/custodian/JP-02-TEN-M-OCM.yaml @@ -370,3 +370,22 @@ location: geonames_id: 8457028 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.039570+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:21:20.533714+00:00' + source_url: https://odate-city.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://odate-city.jp/wp-content/themes/keni70_wp_standard_prototype_201604232356/images/apple-touch-icon.png + source_url: https://odate-city.jp/museum + css_selector: '[document] > html.col2 > head > link:nth-of-type(13)' + retrieved_on: '2025-12-23T14:21:20.533714+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-02-TOG-M-OAG.yaml b/data/custodian/JP-02-TOG-M-OAG.yaml index 4dbd3cfd5c..1e238d2189 100644 --- a/data/custodian/JP-02-TOG-M-OAG.yaml +++ b/data/custodian/JP-02-TOG-M-OAG.yaml @@ -2149,3 +2149,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/KZVBAMdrDfU/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:21:31.247076+00:00' + source_url: https://www.gao-aqua.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.gao-aqua.jp/gao-cms/assets/themes/custom/favicon.png + source_url: https://www.gao-aqua.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:21:31.247076+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.gao-aqua.jp/gao-cms/assets/themes/custom/ogp.jpg + source_url: https://www.gao-aqua.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:21:31.247076+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-02-TOW-L-CLT.yaml b/data/custodian/JP-02-TOW-L-CLT.yaml index 479a15b82c..8e4e16333e 100644 --- a/data/custodian/JP-02-TOW-L-CLT.yaml +++ b/data/custodian/JP-02-TOW-L-CLT.yaml @@ -203,3 +203,31 @@ wikidata_enrichment: wikidata_web: official_website: http://www.towada-lib.jp/ wikidata_official_website: http://www.towada-lib.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:22:48.996218+00:00' + source_url: http://www.towada-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://chousanet.jp/wp-content/uploads/logo.jpg + source_url: http://www.towada-lib.jp + css_selector: '#header > div.l-header__inner.l-container > div.l-header__logo + > h1.c-headLogo.-img > a.c-headLogo__link > img.c-headLogo__img' + retrieved_on: '2025-12-23T14:22:48.996218+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: これ怪しい？ + - claim_type: favicon_url + claim_value: https://chousanet.jp/wp-content/uploads/cropped-favicon-180x180.png + source_url: http://www.towada-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-23T14:22:48.996218+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-02-TOW-M-NMM.yaml b/data/custodian/JP-02-TOW-M-NMM.yaml index d5f1612a47..288f4bae69 100644 --- a/data/custodian/JP-02-TOW-M-NMM.yaml +++ b/data/custodian/JP-02-TOW-M-NMM.yaml @@ -230,3 +230,28 @@ wikidata_enrichment: - id: Q11574760 label: Tsutomu Ikuta description: Japanese architect (1912-1980) +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:23:05.679829+00:00' + source_url: http://nitobe.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://nitobe.jp/assets/img/share/favi.png + source_url: http://nitobe.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:23:05.679829+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://nitobe.jp/assets/img/share/favicon.png + source_url: http://nitobe.jp + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T14:23:05.679829+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-02-TOW-M-TCFM.yaml b/data/custodian/JP-02-TOW-M-TCFM.yaml index 4e622a173c..c1c6caf689 100644 --- a/data/custodian/JP-02-TOW-M-TCFM.yaml +++ b/data/custodian/JP-02-TOW-M-TCFM.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.499438+00:00' location_resolution: country_code: JP - region_code: 02 + region_code: 2 city_code: TOW method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-02-TOW-M-TCFM - valid_from: "2025-12-10T09:43:29Z" + valid_from: '2025-12-10T09:43:29Z' valid_to: null - reason: "Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per ISO 3166-2:JP" + reason: Corrected region code from JP-AO (abbreviation) to JP-02 (Aomori) per + ISO 3166-2:JP - ghcid: JP-AO-TOW-M-TCFM valid_from: null - valid_to: "2025-12-10T09:43:29Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:29Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AO-TOW-M-TCFM ghcid_numeric: 17813339871031857714 valid_from: '2025-12-06T23:38:30.499438+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: TOWADA CITY FOLK MUSEUM @@ -189,7 +190,7 @@ wikidata_enrichment: location: city: Towada Shi region: Aomori Ken - region_code: 02 + region_code: 2 country: JP postal_code: 034-0301 street_address: OKUSE, Towada Shi, Aomori Ken, 034-0301 @@ -204,3 +205,20 @@ location: geonames_id: 6822207 geonames_name: Towada feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:23:18.206756+00:00' + source_url: https://www.city.towada.lg.jp/bunka/bunka/kyoudokan.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.towada.lg.jp/contents_images/logo.svg + source_url: https://www.city.towada.lg.jp/bunka/bunka/kyoudokan.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T14:23:18.206756+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-02-TSU-L-T-tsugarushimoritakominkantoshoshitsu.yaml b/data/custodian/JP-02-TSU-L-T-tsugarushimoritakominkantoshoshitsu.yaml index be9ca12bb6..ab421d4dd4 100644 --- a/data/custodian/JP-02-TSU-L-T-tsugarushimoritakominkantoshoshitsu.yaml +++ b/data/custodian/JP-02-TSU-L-T-tsugarushimoritakominkantoshoshitsu.yaml @@ -194,3 +194,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.tsugaru.aomori.jp/sisetu/00037.html wikidata_official_website: http://www.city.tsugaru.aomori.jp/sisetu/00037.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:23:29.891415+00:00' + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00037.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00037.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:23:29.891415+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00037.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:23:29.891415+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-02-TSU-L-T-tsugarushiushigatakominkantoshoshitsu.yaml b/data/custodian/JP-02-TSU-L-T-tsugarushiushigatakominkantoshoshitsu.yaml index 22481281fc..677e84a1f2 100644 --- a/data/custodian/JP-02-TSU-L-T-tsugarushiushigatakominkantoshoshitsu.yaml +++ b/data/custodian/JP-02-TSU-L-T-tsugarushiushigatakominkantoshoshitsu.yaml @@ -194,3 +194,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.tsugaru.aomori.jp/sisetu/00036.html wikidata_official_website: http://www.city.tsugaru.aomori.jp/sisetu/00036.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:23:39.193566+00:00' + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00036.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00036.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:23:39.193566+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00036.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:23:39.193566+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-02-TSU-L-T.yaml b/data/custodian/JP-02-TSU-L-T.yaml index 4ed585325d..73c5fc227e 100644 --- a/data/custodian/JP-02-TSU-L-T.yaml +++ b/data/custodian/JP-02-TSU-L-T.yaml @@ -199,3 +199,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.tsugaru.aomori.jp/sisetu/00001.html wikidata_official_website: http://www.city.tsugaru.aomori.jp/sisetu/00001.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:23:46.783020+00:00' + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00001.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00001.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:23:46.783020+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00001.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:23:46.783020+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-02-TSU-L-TIHC.yaml b/data/custodian/JP-02-TSU-L-TIHC.yaml index 05021082ac..4a8d30bd91 100644 --- a/data/custodian/JP-02-TSU-L-TIHC.yaml +++ b/data/custodian/JP-02-TSU-L-TIHC.yaml @@ -199,3 +199,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.tsugaru.aomori.jp/sisetu/00034.html wikidata_official_website: http://www.city.tsugaru.aomori.jp/sisetu/00034.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:24:02.705184+00:00' + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00034.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00034.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:24:02.705184+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.tsugaru.aomori.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.tsugaru.aomori.jp/sisetu/00034.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:24:02.705184+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-02-YAN-M-AMMA.yaml b/data/custodian/JP-02-YAN-M-AMMA.yaml index 9b18286df8..f3489dd615 100644 --- a/data/custodian/JP-02-YAN-M-AMMA.yaml +++ b/data/custodian/JP-02-YAN-M-AMMA.yaml @@ -417,3 +417,22 @@ location: geonames_id: 8579014 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.165397+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:24:12.102822+00:00' + source_url: https://akita-kinbi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://akita-kinbi.jp/wp-content/uploads/2024/04/cropped-forFavicon-1-180x180.png + source_url: https://akita-kinbi.jp + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-23T14:24:12.102822+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-03-DOT-M-HMCA.yaml b/data/custodian/JP-03-DOT-M-HMCA.yaml index e7f6a123c8..87a9efd68d 100644 --- a/data/custodian/JP-03-DOT-M-HMCA.yaml +++ b/data/custodian/JP-03-DOT-M-HMCA.yaml @@ -343,3 +343,36 @@ location: geonames_id: 8411801 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.211483+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:24:24.762596+00:00' + source_url: https://www.hirosaki-moca.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.hirosaki-moca.jp/wp-content/themes/hmca/assets/img/common/h-logo-bar.svg + source_url: https://www.hirosaki-moca.jp + css_selector: '#header > div.__inner > h1.logo > a > span.b > img' + retrieved_on: '2025-12-23T14:24:24.762596+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: H + - claim_type: favicon_url + claim_value: https://www.hirosaki-moca.jp/favicon.ico + source_url: https://www.hirosaki-moca.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:24:24.762596+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.hirosaki-moca.jp/wp-content/themes/hmca/assets/img/common/sns-enkired.png + source_url: https://www.hirosaki-moca.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-23T14:24:24.762596+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-03-FUK-M-ET.yaml b/data/custodian/JP-03-FUK-M-ET.yaml index baf1506c28..0a90c2abbf 100644 --- a/data/custodian/JP-03-FUK-M-ET.yaml +++ b/data/custodian/JP-03-FUK-M-ET.yaml @@ -265,3 +265,22 @@ location: geonames_id: 2038800 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.299705+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:24:36.925966+00:00' + source_url: https://www.engakuji.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.engakuji.jp/wp-content/uploads/2022/02/cropped-engakuji_favicon_brown-180x180.png + source_url: https://www.engakuji.jp + css_selector: '[document] > html.col2.layout-footer-show > head > link:nth-of-type(24)' + retrieved_on: '2025-12-23T14:24:36.925966+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-03-HAC-L-H-hachimantaishiritsuarayakomyuniteisentatoshoshitsu.yaml b/data/custodian/JP-03-HAC-L-H-hachimantaishiritsuarayakomyuniteisentatoshoshitsu.yaml index e8595ff249..45b501e819 100644 --- a/data/custodian/JP-03-HAC-L-H-hachimantaishiritsuarayakomyuniteisentatoshoshitsu.yaml +++ b/data/custodian/JP-03-HAC-L-H-hachimantaishiritsuarayakomyuniteisentatoshoshitsu.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://hachi-lib.jp/page-9/ wikidata_official_website: http://hachi-lib.jp/page-9/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:24:46.401877+00:00' + source_url: http://hachi-lib.jp/page-9 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://hachi-lib.jp/wp-content/themes/hd/images/favicon.ico + source_url: http://hachi-lib.jp/page-9 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:24:46.401877+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-03-HAC-L-H.yaml b/data/custodian/JP-03-HAC-L-H.yaml index 83eb742c25..6586cd77a0 100644 --- a/data/custodian/JP-03-HAC-L-H.yaml +++ b/data/custodian/JP-03-HAC-L-H.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://hachi-lib.jp/page-7/ wikidata_official_website: http://hachi-lib.jp/page-7/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:24:56.487980+00:00' + source_url: http://hachi-lib.jp/page-7 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://hachi-lib.jp/wp-content/themes/hd/images/favicon.ico + source_url: http://hachi-lib.jp/page-7 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:24:56.487980+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-03-HAC-L-HCL.yaml b/data/custodian/JP-03-HAC-L-HCL.yaml index b32ddc60de..84803c968c 100644 --- a/data/custodian/JP-03-HAC-L-HCL.yaml +++ b/data/custodian/JP-03-HAC-L-HCL.yaml @@ -207,3 +207,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.hachi-lib.jp/ wikidata_official_website: http://www.hachi-lib.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:25:06.679527+00:00' + source_url: http://www.hachi-lib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://hachi-lib.jp/wp-content/themes/hd/images/favicon.ico + source_url: http://www.hachi-lib.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:25:06.679527+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-03-HAC-M-HCM.yaml b/data/custodian/JP-03-HAC-M-HCM.yaml index a133fe73eb..d1a5e0af0d 100644 --- a/data/custodian/JP-03-HAC-M-HCM.yaml +++ b/data/custodian/JP-03-HAC-M-HCM.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.691193+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: HAC method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-HAC-M-HCM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-HAC-M-HCM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-HAC-M-HCM ghcid_numeric: 4500399539048902787 valid_from: '2025-12-06T23:38:30.691193+00:00' @@ -217,8 +218,27 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Hachimantai Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id005 postal_code: 028-7533 street_address: KAMASUDA, Hachimantai Shi, Iwate Ken, 028-7533 normalization_timestamp: '2025-12-09T10:56:40.379700+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:25:17.237717+00:00' + source_url: https://www.city.hachimantai.lg.jp/soshiki/hakubutsukan/1273.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.hachimantai.lg.jp/img/apple-touch-icon.png + source_url: https://www.city.hachimantai.lg.jp/soshiki/hakubutsukan/1273.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:25:17.237717+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-03-HAC-M-KK.yaml b/data/custodian/JP-03-HAC-M-KK.yaml index d0a64386d3..2614449e8f 100644 --- a/data/custodian/JP-03-HAC-M-KK.yaml +++ b/data/custodian/JP-03-HAC-M-KK.yaml @@ -259,3 +259,28 @@ location: geonames_id: 8563543 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.334077+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:25:27.950108+00:00' + source_url: https://www.kushihikihachimangu.com/treasure + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kushihikihachimangu.com/wp-content/themes/kushihiki/img/favicon.ico + source_url: https://www.kushihikihachimangu.com/treasure + css_selector: '[document] > html.enable-js > head > link' + retrieved_on: '2025-12-23T14:25:27.950108+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kushihikihachimangu.com/wp-content/uploads/2017/06/ic-treasure.jpg + source_url: https://www.kushihikihachimangu.com/treasure + css_selector: '[document] > html.enable-js > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T14:25:27.950108+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-03-HAN-L-FL.yaml b/data/custodian/JP-03-HAN-L-FL.yaml index 70f7f92d5b..3ca34a9aa5 100644 --- a/data/custodian/JP-03-HAN-L-FL.yaml +++ b/data/custodian/JP-03-HAN-L-FL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:54.418065+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: HAN method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-HAN-L-FL - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-HAN-L-FL valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-HAN-L-FL ghcid_numeric: 10616225085129563478 valid_from: '2025-12-06T23:38:54.418065+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: FUJIDAIGAKU Library @@ -200,7 +201,7 @@ wikidata_enrichment: location: city: Hanamaki Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 025-8501 street_address: 450-3 SHIMONEKO, Hanamaki Shi, Iwate Ken, 025-8501 @@ -215,3 +216,28 @@ location: geonames_id: 2112823 geonames_name: Hanamaki feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:25:40.283467+00:00' + source_url: http://www.fuji-u.ac.jp/campus/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://p1.ssl-cdn.jp/var/data/u/c4/fa8bec10387/img/webclip.jpg?cache=1438930744 + source_url: http://www.fuji-u.ac.jp/campus/lib + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T14:25:40.283467+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://p1.ssl-cdn.jp/var/data/u/c4/fa8bec10387/img/ogp.jpg?cache=1438930745 + source_url: http://www.fuji-u.ac.jp/campus/lib + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T14:25:40.283467+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-03-HAN-L-HIL.yaml b/data/custodian/JP-03-HAN-L-HIL.yaml index e9501b4796..06a0d42027 100644 --- a/data/custodian/JP-03-HAN-L-HIL.yaml +++ b/data/custodian/JP-03-HAN-L-HIL.yaml @@ -205,3 +205,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005430.html wikidata_official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005430.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:25:50.633075+00:00' + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005430.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005430.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:25:50.633075+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 花巻市トップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-HAN-L-HL-hanamakishiritsuohasama_library.yaml b/data/custodian/JP-03-HAN-L-HL-hanamakishiritsuohasama_library.yaml index f4079b847f..d49df19093 100644 --- a/data/custodian/JP-03-HAN-L-HL-hanamakishiritsuohasama_library.yaml +++ b/data/custodian/JP-03-HAN-L-HL-hanamakishiritsuohasama_library.yaml @@ -206,3 +206,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005434.html wikidata_official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005434.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:25:59.340548+00:00' + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005434.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005434.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:25:59.340548+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 花巻市トップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-HAN-L-HL.yaml b/data/custodian/JP-03-HAN-L-HL.yaml index 13ca0afe1c..fae83d0e06 100644 --- a/data/custodian/JP-03-HAN-L-HL.yaml +++ b/data/custodian/JP-03-HAN-L-HL.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005426.html wikidata_official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005426.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:26:07.729089+00:00' + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005426.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005426.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:26:07.729089+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 花巻市トップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-HAN-L-HTL.yaml b/data/custodian/JP-03-HAN-L-HTL.yaml index 02e2e12bfd..1b6980451f 100644 --- a/data/custodian/JP-03-HAN-L-HTL.yaml +++ b/data/custodian/JP-03-HAN-L-HTL.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005317.html wikidata_official_website: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005317.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:26:16.859370+00:00' + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005317.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.hanamaki.iwate.jp/shisetsu/853/864/p005317.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:26:16.859370+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 花巻市トップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-HAN-M-HCM.yaml b/data/custodian/JP-03-HAN-M-HCM.yaml index 936740169e..1a9711602d 100644 --- a/data/custodian/JP-03-HAN-M-HCM.yaml +++ b/data/custodian/JP-03-HAN-M-HCM.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.611969+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: HAN method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-HAN-M-HCM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-HAN-M-HCM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-HAN-M-HCM ghcid_numeric: 14415371129880242257 valid_from: '2025-12-06T23:38:30.611969+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: HANAMAKI CITY MUSEUM @@ -214,7 +215,7 @@ wikidata_enrichment: location: city: Hanamaki Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 025-0014 street_address: TAKAMATSU, Hanamaki Shi, Iwate Ken, 025-0014 @@ -229,3 +230,22 @@ location: geonames_id: 2112823 geonames_name: Hanamaki feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:26:27.300988+00:00' + source_url: https://www.city.hanamaki.iwate.jp/bunkasports/bunka/1008981 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.hanamaki.iwate.jp/bunkasports/bunka/1008981 + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:26:27.300988+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 花巻市トップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-HAN-M-HNM.yaml b/data/custodian/JP-03-HAN-M-HNM.yaml index 49f5b681db..421c3a605f 100644 --- a/data/custodian/JP-03-HAN-M-HNM.yaml +++ b/data/custodian/JP-03-HAN-M-HNM.yaml @@ -232,3 +232,22 @@ location: postal_code: 025-0014 street_address: TAKAMATSU, Hanamaki Shi, Iwate Ken, 025-0014 normalization_timestamp: '2025-12-09T10:56:40.579146+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:26:35.114736+00:00' + source_url: https://www.city.hanamaki.iwate.jp/bunkasports/bunka/nitobekinenkan/1001975.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.hanamaki.iwate.jp/bunkasports/bunka/nitobekinenkan/1001975.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:26:35.114736+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 花巻市トップページ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-HAN-M-MKM.yaml b/data/custodian/JP-03-HAN-M-MKM.yaml index bb31a1709f..6c3ca473de 100644 --- a/data/custodian/JP-03-HAN-M-MKM.yaml +++ b/data/custodian/JP-03-HAN-M-MKM.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.609233+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: HAN method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-HAN-M-MKM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-HAN-M-MKM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-HAN-M-MKM ghcid_numeric: 10219503375031035015 valid_from: '2025-12-06T23:38:30.609233+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: MIYAZAWA KENJI MUSEUM @@ -216,7 +217,7 @@ wikidata_enrichment: location: city: Hanamaki Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 025-0011 street_address: YASAWA, Hanamaki Shi, Iwate Ken, 025-0011 @@ -231,3 +232,28 @@ location: geonames_id: 2112823 geonames_name: Hanamaki feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:26:46.169445+00:00' + source_url: https://www.city.hanamaki.iwate.jp/miyazawakenji/kinenkan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.hanamaki.iwate.jp/miyazawakenji/kinenkan + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-23T14:26:46.169445+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.hanamaki.iwate.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.hanamaki.iwate.jp/miyazawakenji/kinenkan + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T14:26:46.169445+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-03-ICH-L-SJCL.yaml b/data/custodian/JP-03-ICH-L-SJCL.yaml index eafe3a6baf..e90083ee03 100644 --- a/data/custodian/JP-03-ICH-L-SJCL.yaml +++ b/data/custodian/JP-03-ICH-L-SJCL.yaml @@ -205,3 +205,20 @@ location: geonames_id: 2112656 geonames_name: Ichinoseki feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:27:55.061249+00:00' + source_url: http://www.shuko.ac.jp/index2.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://shuko.ac.jp/wp/wp-content/themes/cure_tcd082/img/common/no-image-510x320.gif + source_url: http://www.shuko.ac.jp/index2.html + css_selector: '[document] > html.pc > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:27:55.061249+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-03-IWA-L-ITL.yaml b/data/custodian/JP-03-IWA-L-ITL.yaml index 3a0728494c..d79e82a99a 100644 --- a/data/custodian/JP-03-IWA-L-ITL.yaml +++ b/data/custodian/JP-03-IWA-L-ITL.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: wikidata_web: official_website: http://library.town.iwate.iwate.jp/ wikidata_official_website: http://library.town.iwate.iwate.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:28:49.371959+00:00' + source_url: http://library.town.iwate.iwate.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.town.iwate.iwate.jp/favicon.ico?f=1766363337 + source_url: http://library.town.iwate.iwate.jp + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-23T14:28:49.371959+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-03-KIT-M-KCTKAM.yaml b/data/custodian/JP-03-KIT-M-KCTKAM.yaml index 0307f04463..f757996f4e 100644 --- a/data/custodian/JP-03-KIT-M-KCTKAM.yaml +++ b/data/custodian/JP-03-KIT-M-KCTKAM.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.631741+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: KIT method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-KIT-M-KCTKAM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-KIT-M-KCTKAM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-KIT-M-KCTKAM ghcid_numeric: 18101629860876990750 valid_from: '2025-12-06T23:38:30.631741+00:00' @@ -250,8 +251,33 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Kitakami Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id006 postal_code: 024-0043 street_address: TACHIBANA, Kitakami Shi, Iwate Ken, 024-0043 normalization_timestamp: '2025-12-09T10:56:41.407468+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:31:22.799740+00:00' + source_url: https://www.city.kitakami.iwate.jp/life/kurashi_tetsuduki/bunka_sports/bunkashisetsu/toneyama + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.kitakami.iwate.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.kitakami.iwate.jp/life/kurashi_tetsuduki/bunka_sports/bunkashisetsu/toneyama + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:31:22.799740+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.kitakami.iwate.jp/material/images/group/1/cms_kanren_02.jpg + source_url: https://www.city.kitakami.iwate.jp/life/kurashi_tetsuduki/bunka_sports/bunkashisetsu/toneyama + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T14:31:22.799740+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-03-KIT-M-KOM.yaml b/data/custodian/JP-03-KIT-M-KOM.yaml index c7e529a123..db3a28b4f4 100644 --- a/data/custodian/JP-03-KIT-M-KOM.yaml +++ b/data/custodian/JP-03-KIT-M-KOM.yaml @@ -223,3 +223,28 @@ wikidata_enrichment: image: Oninoyakata.jpg commons_category: Devils Museum in Kitakami wikidata_image: Oninoyakata.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:31:31.881982+00:00' + source_url: https://www.city.kitakami.iwate.jp/life/kurashi_tetsuduki/bunka_sports/bunkashisetsu/1 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.kitakami.iwate.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.kitakami.iwate.jp/life/kurashi_tetsuduki/bunka_sports/bunkashisetsu/1 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:31:31.881982+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.kitakami.iwate.jp/material/images/group/1/cms_kanren_02.jpg + source_url: https://www.city.kitakami.iwate.jp/life/kurashi_tetsuduki/bunka_sports/bunkashisetsu/1 + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T14:31:31.881982+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-03-KUJ-M-KAM.yaml b/data/custodian/JP-03-KUJ-M-KAM.yaml index 5f25f51cc9..d34b392009 100644 --- a/data/custodian/JP-03-KUJ-M-KAM.yaml +++ b/data/custodian/JP-03-KUJ-M-KAM.yaml @@ -231,3 +231,28 @@ wikidata_enrichment: image: Amber museumu, Kuji.jpg commons_category: Kuji Amber Museum wikidata_image: Amber museumu, Kuji.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:31:56.726243+00:00' + source_url: http://www.kuji.co.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://user-images.strikinglycdn.com/res/hrscywv4p/image/upload/c_limit,h_64,w_64/864235/%E3%83%9E%E3%83%BC%E3%82%AF_djrn5z.png + source_url: http://www.kuji.co.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T14:31:56.726243+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://user-images.strikinglycdn.com/res/hrscywv4p/image/upload/c_limit,h_630,w_1200/864235/P1170218_xq5lox.jpg + source_url: http://www.kuji.co.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T14:31:56.726243+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-03-KUJ-M-MJMG.yaml b/data/custodian/JP-03-KUJ-M-MJMG.yaml index 2b8960da6c..85fc5a41b7 100644 --- a/data/custodian/JP-03-KUJ-M-MJMG.yaml +++ b/data/custodian/JP-03-KUJ-M-MJMG.yaml @@ -238,3 +238,36 @@ location: postal_code: 028-0082 street_address: KAWANUKI, Kuji Shi, Iwate Ken, 028-0082 normalization_timestamp: '2025-12-09T10:56:41.512511+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:32:06.954741+00:00' + source_url: https://www.city.kuji.iwate.jp/kosodate/bunka/taikushisetsu/kinenkan.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.kuji.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.kuji.iwate.jp/kosodate/bunka/taikushisetsu/kinenkan.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:32:06.954741+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩手県久慈市 Kuji City + - claim_type: favicon_url + claim_value: https://www.city.kuji.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.kuji.iwate.jp/kosodate/bunka/taikushisetsu/kinenkan.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:32:06.954741+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.kuji.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.kuji.iwate.jp/kosodate/bunka/taikushisetsu/kinenkan.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:32:06.954741+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-03-KUN-L-NL.yaml b/data/custodian/JP-03-KUN-L-NL.yaml index a31def4a33..34133b9e6a 100644 --- a/data/custodian/JP-03-KUN-L-NL.yaml +++ b/data/custodian/JP-03-KUN-L-NL.yaml @@ -201,3 +201,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.vill.noda.iwate.jp/kyoikushogaigakusyu/302.html wikidata_official_website: http://www.vill.noda.iwate.jp/kyoikushogaigakusyu/302.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:33:38.973315+00:00' + source_url: http://www.vill.noda.iwate.jp/kyoikushogaigakusyu/302.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.vill.noda.iwate.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.vill.noda.iwate.jp/kyoikushogaigakusyu/302.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:33:38.973315+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩手県 野田村 Noda Village + - claim_type: favicon_url + claim_value: http://www.vill.noda.iwate.jp/theme/base/img_common/smartphone.png + source_url: http://www.vill.noda.iwate.jp/kyoikushogaigakusyu/302.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:33:38.973315+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.vill.noda.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.vill.noda.iwate.jp/kyoikushogaigakusyu/302.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:33:38.973315+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-03-KUN-M-KTMHF.yaml b/data/custodian/JP-03-KUN-M-KTMHF.yaml index b0d37cb720..6e2941867d 100644 --- a/data/custodian/JP-03-KUN-M-KTMHF.yaml +++ b/data/custodian/JP-03-KUN-M-KTMHF.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.764731+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: KUN method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-KUN-M-KTMHF - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-KUN-M-KTMHF valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-KUN-M-KTMHF ghcid_numeric: 17281720325830075473 valid_from: '2025-12-06T23:38:30.764731+00:00' @@ -200,8 +201,25 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Kunohe Gun Karumai Machi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id005 postal_code: 028-6302 street_address: KARUMAI, Kunohe Gun Karumai Machi, Iwate Ken, 028-6302 normalization_timestamp: '2025-12-09T10:56:41.656923+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:33:49.441284+00:00' + source_url: https://www.town.karumai.iwate.jp/article/kurashitetsuduki/facility/culture/entry-basename-4.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.town.karumai.iwate.jp/images/site-id_pc.png + source_url: https://www.town.karumai.iwate.jp/article/kurashitetsuduki/facility/culture/entry-basename-4.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:33:49.441284+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-03-MAT-M-ACSC.yaml b/data/custodian/JP-03-MAT-M-ACSC.yaml index 0d29bb1cf3..ca7ae02254 100644 --- a/data/custodian/JP-03-MAT-M-ACSC.yaml +++ b/data/custodian/JP-03-MAT-M-ACSC.yaml @@ -226,3 +226,30 @@ location: geonames_id: 8516154 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.409732+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:33:58.451598+00:00' + source_url: https://www.city.aomori.aomori.jp/chuo-center/kodomo-kyouiku/shimin-center/kouminkan/06.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.aomori.aomori.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.aomori.aomori.jp/chuo-center/kodomo-kyouiku/shimin-center/kouminkan/06.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:33:58.451598+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 青森市公式ホームページトップページ + - claim_type: favicon_url + claim_value: https://www.city.aomori.aomori.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.aomori.aomori.jp/chuo-center/kodomo-kyouiku/shimin-center/kouminkan/06.html + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T14:33:58.451598+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-03-MAT-M-MSMMA.yaml b/data/custodian/JP-03-MAT-M-MSMMA.yaml index a2d893eed9..4fbbbc9fb8 100644 --- a/data/custodian/JP-03-MAT-M-MSMMA.yaml +++ b/data/custodian/JP-03-MAT-M-MSMMA.yaml @@ -1165,3 +1165,31 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/axZAa95NMek/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:34:07.456755+00:00' + source_url: https://munakatashiko-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://munakatashiko-museum.jp/2024/wp-content/uploads/2024/10/tytle_bk.png + source_url: https://munakatashiko-museum.jp + css_selector: '#header > div.l-header__inner.l-container > div.l-header__logo + > h1.c-headLogo.-img > a.c-headLogo__link > img.c-headLogo__img' + retrieved_on: '2025-12-23T14:34:07.456755+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 一般財団法人 棟方志功記念館 + - claim_type: favicon_url + claim_value: https://munakatashiko-museum.jp/2024/wp-content/uploads/2024/10/cropped-name-180x180.png + source_url: https://munakatashiko-museum.jp + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-23T14:34:07.456755+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-03-MAY-M-HCM.yaml b/data/custodian/JP-03-MAY-M-HCM.yaml index 837ae909e9..32e02a2a5c 100644 --- a/data/custodian/JP-03-MAY-M-HCM.yaml +++ b/data/custodian/JP-03-MAY-M-HCM.yaml @@ -399,3 +399,20 @@ location: geonames_id: 8411771 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.478289+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:34:21.099811+00:00' + source_url: https://www.city.hirosaki.aomori.jp/hakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.hirosaki.aomori.jp/renew/content_images/ogimage.png + source_url: https://www.city.hirosaki.aomori.jp/hakubutsukan + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:34:21.099811+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-03-MIY-L-ML.yaml b/data/custodian/JP-03-MIY-L-ML.yaml index 6e9edc6d66..777bca3d2a 100644 --- a/data/custodian/JP-03-MIY-L-ML.yaml +++ b/data/custodian/JP-03-MIY-L-ML.yaml @@ -204,3 +204,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html wikidata_official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:34:37.781237+00:00' + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:34:37.781237+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩手県　宮古市 + - claim_type: favicon_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:34:37.781237+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:34:37.781237+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-03-MIY-L-MLK.yaml b/data/custodian/JP-03-MIY-L-MLK.yaml index 9eefcc7886..a0130c750d 100644 --- a/data/custodian/JP-03-MIY-L-MLK.yaml +++ b/data/custodian/JP-03-MIY-L-MLK.yaml @@ -204,3 +204,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html wikidata_official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:34:45.505315+00:00' + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:34:45.505315+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩手県　宮古市 + - claim_type: favicon_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:34:45.505315+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:34:45.505315+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-03-MIY-L-MLN.yaml b/data/custodian/JP-03-MIY-L-MLN.yaml index d72c7f1aa0..4720af5427 100644 --- a/data/custodian/JP-03-MIY-L-MLN.yaml +++ b/data/custodian/JP-03-MIY-L-MLN.yaml @@ -204,3 +204,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html wikidata_official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:34:53.435858+00:00' + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:34:53.435858+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩手県　宮古市 + - claim_type: favicon_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:34:53.435858+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:34:53.435858+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-03-MIY-L-MLT.yaml b/data/custodian/JP-03-MIY-L-MLT.yaml index 3f5965ff1b..a6248ce01d 100644 --- a/data/custodian/JP-03-MIY-L-MLT.yaml +++ b/data/custodian/JP-03-MIY-L-MLT.yaml @@ -204,3 +204,36 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html wikidata_official_website: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:35:00.662260+00:00' + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:35:00.662260+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩手県　宮古市 + - claim_type: favicon_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:35:00.662260+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.miyako.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.miyako.iwate.jp/shogai/tosyokan_top.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:35:00.662260+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-03-MIY-M-SSMJMAM.yaml b/data/custodian/JP-03-MIY-M-SSMJMAM.yaml index 7d848d7c33..aa175915a8 100644 --- a/data/custodian/JP-03-MIY-M-SSMJMAM.yaml +++ b/data/custodian/JP-03-MIY-M-SSMJMAM.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.601608+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: MIY method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-MIY-M-SSMJMAM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-MIY-M-SSMJMAM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-MIY-M-SSMJMAM ghcid_numeric: 10231794890271490398 valid_from: '2025-12-06T23:38:30.601608+00:00' @@ -240,8 +241,41 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Miyako Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id005 postal_code: 027-0097 street_address: SAKIYAMA, Miyako Shi, Iwate Ken, 027-0097 normalization_timestamp: '2025-12-09T10:56:41.845190+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:35:46.247923+00:00' + source_url: https://www.city.miyako.iwate.jp/bnka/sakiyamamuseum/sakiyama_museum1.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.miyako.iwate.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.miyako.iwate.jp/bnka/sakiyamamuseum/sakiyama_museum1.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:35:46.247923+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 岩手県　宮古市 + - claim_type: favicon_url + claim_value: https://www.city.miyako.iwate.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.miyako.iwate.jp/bnka/sakiyamamuseum/sakiyama_museum1.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:35:46.247923+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.miyako.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.miyako.iwate.jp/bnka/sakiyamamuseum/sakiyama_museum1.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:35:46.247923+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-03-MOR-L-A.yaml b/data/custodian/JP-03-MOR-L-A.yaml index 848f3df6bb..df1490468f 100644 --- a/data/custodian/JP-03-MOR-L-A.yaml +++ b/data/custodian/JP-03-MOR-L-A.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000847.html wikidata_official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000847.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:35:57.341621+00:00' + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000847.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000847.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:35:57.341621+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-L-M-moriokashichuokominkantoshoshitsu.yaml b/data/custodian/JP-03-MOR-L-M-moriokashichuokominkantoshoshitsu.yaml index 22752bdff4..bc19271d1d 100644 --- a/data/custodian/JP-03-MOR-L-M-moriokashichuokominkantoshoshitsu.yaml +++ b/data/custodian/JP-03-MOR-L-M-moriokashichuokominkantoshoshitsu.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/chuo/1000674.html wikidata_official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/chuo/1000674.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:36:35.723273+00:00' + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/chuo/1000674.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/chuo/1000674.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:36:35.723273+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-L-M-moriokashiuedakominkantoshoshitsu.yaml b/data/custodian/JP-03-MOR-L-M-moriokashiuedakominkantoshoshitsu.yaml index 426f38da98..40aa773a05 100644 --- a/data/custodian/JP-03-MOR-L-M-moriokashiuedakominkantoshoshitsu.yaml +++ b/data/custodian/JP-03-MOR-L-M-moriokashiuedakominkantoshoshitsu.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/ueda/1000697.html wikidata_official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/ueda/1000697.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:36:47.775900+00:00' + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/ueda/1000697.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kominkan/ueda/1000697.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:36:47.775900+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-L-M.yaml b/data/custodian/JP-03-MOR-L-M.yaml index de18dff427..9a2d050102 100644 --- a/data/custodian/JP-03-MOR-L-M.yaml +++ b/data/custodian/JP-03-MOR-L-M.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007326.html wikidata_official_website: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007326.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:36:58.455785+00:00' + source_url: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007326.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007326.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:36:58.455785+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-L-ML-moriokashishibutami_library.yaml b/data/custodian/JP-03-MOR-L-ML-moriokashishibutami_library.yaml index aa2c7d9705..da03325cee 100644 --- a/data/custodian/JP-03-MOR-L-ML-moriokashishibutami_library.yaml +++ b/data/custodian/JP-03-MOR-L-ML-moriokashishibutami_library.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000841.html wikidata_official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000841.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:37:10.486687+00:00' + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000841.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000841.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:37:10.486687+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-L-ML.yaml b/data/custodian/JP-03-MOR-L-ML.yaml index ad4ea89d54..6c76d862ce 100644 --- a/data/custodian/JP-03-MOR-L-ML.yaml +++ b/data/custodian/JP-03-MOR-L-ML.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000830.html wikidata_official_website: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000830.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:37:21.318131+00:00' + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000830.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/tosho/1000830.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:37:21.318131+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-L-O.yaml b/data/custodian/JP-03-MOR-L-O.yaml index 9db5e3eee6..bcca68b6a6 100644 --- a/data/custodian/JP-03-MOR-L-O.yaml +++ b/data/custodian/JP-03-MOR-L-O.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007330.html wikidata_official_website: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007330.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:37:30.996493+00:00' + source_url: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007330.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007330.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:37:30.996493+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-L-S.yaml b/data/custodian/JP-03-MOR-L-S.yaml index c4c27c67c3..51bcfc0caf 100644 --- a/data/custodian/JP-03-MOR-L-S.yaml +++ b/data/custodian/JP-03-MOR-L-S.yaml @@ -204,3 +204,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007324.html wikidata_official_website: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007324.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:37:39.433184+00:00' + source_url: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007324.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: http://www.city.morioka.iwate.jp/shisetsu/community/chiku/1007324.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T14:37:39.433184+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-03-MOR-M-HKMM.yaml b/data/custodian/JP-03-MOR-M-HKMM.yaml index 3bfa0dc94e..d14c5fdb3a 100644 --- a/data/custodian/JP-03-MOR-M-HKMM.yaml +++ b/data/custodian/JP-03-MOR-M-HKMM.yaml @@ -36,18 +36,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.575018+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: MOR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-MOR-M-HKMM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-MOR-M-HKMM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-MOR-M-HKMM ghcid_numeric: 5856659438378002992 valid_from: '2025-12-06T23:38:30.575018+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: HARA KEI MEMORIAL MUSEUM @@ -228,7 +229,7 @@ wikidata_enrichment: location: city: Morioka Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 020-0866 street_address: MOTOMIYA, Morioka Shi, Iwate Ken, 020-0866 @@ -243,3 +244,22 @@ location: geonames_id: 2111834 geonames_name: Morioka feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:37:49.676299+00:00' + source_url: https://www.mfca.jp/harakei + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mfca.jp/favicon.ico + source_url: https://www.mfca.jp/harakei + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:37:49.676299+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-03-MOR-M-HMAE.yaml b/data/custodian/JP-03-MOR-M-HMAE.yaml index 145788ead1..10a19fe35f 100644 --- a/data/custodian/JP-03-MOR-M-HMAE.yaml +++ b/data/custodian/JP-03-MOR-M-HMAE.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.589219+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: MOR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-MOR-M-HMAE - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-MOR-M-HMAE valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-MOR-M-HMAE ghcid_numeric: 14097427236991456662 valid_from: '2025-12-06T23:38:30.589219+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: Historical Museum for Agricultural Education @@ -168,8 +169,10 @@ wikidata_enrichment: - P791 wikidata_labels: ja: 岩手大学農学部附属農業教育資料館 - en: Historical Museum for Agricultural Education, Faculty of Agriculture, Iwate University - wikidata_label_en: Historical Museum for Agricultural Education, Faculty of Agriculture, Iwate University + en: Historical Museum for Agricultural Education, Faculty of Agriculture, Iwate + University + wikidata_label_en: Historical Museum for Agricultural Education, Faculty of Agriculture, + Iwate University wikidata_label_ja: 岩手大学農学部附属農業教育資料館 wikidata_descriptions: en: museum in Morioka, Iwate, Japan @@ -212,12 +215,14 @@ wikidata_enrichment: wikidata_official_website: *id007 wikidata_media: commons_category: Iwate University Historical Museum for Agricultural Education - image: 171103 Iwate University Historical Museum for Agricultural Education Morioka Iwate pref Japan02s3.jpg - wikidata_image: 171103 Iwate University Historical Museum for Agricultural Education Morioka Iwate pref Japan02s3.jpg + image: 171103 Iwate University Historical Museum for Agricultural Education Morioka + Iwate pref Japan02s3.jpg + wikidata_image: 171103 Iwate University Historical Museum for Agricultural Education + Morioka Iwate pref Japan02s3.jpg location: city: Morioka Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 020-8550 street_address: UEDA, Morioka Shi, Iwate Ken, 020-8550 @@ -232,3 +237,38 @@ location: geonames_id: 2111834 geonames_name: Morioka feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:37:59.492271+00:00' + source_url: https://www.iwate-u.ac.jp/academics/facility/hmae.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.iwate-u.ac.jp/academics/facility/assets/images/common/logo_page.svg + source_url: https://www.iwate-u.ac.jp/academics/facility/hmae.html + css_selector: '[document] > html > body.index.home > div.body__inner > header.header.header--page + > div.header__body:nth-of-type(2) > h1.header__logo.header__logo--page > a > + img' + retrieved_on: '2025-12-23T14:37:59.492271+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 国立大学法人岩手大学 IWATE UNIVERSITY + - claim_type: favicon_url + claim_value: https://www.iwate-u.ac.jp/academics/facility/favicon.ico + source_url: https://www.iwate-u.ac.jp/academics/facility/hmae.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:37:59.492271+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.iwate-u.ac.jp/assets/images/common/ogp.jpg + source_url: https://www.iwate-u.ac.jp/academics/facility/hmae.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:37:59.492271+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-03-MOR-M-IMA.yaml b/data/custodian/JP-03-MOR-M-IMA.yaml index 2d72449ab3..b0f1700779 100644 --- a/data/custodian/JP-03-MOR-M-IMA.yaml +++ b/data/custodian/JP-03-MOR-M-IMA.yaml @@ -264,3 +264,22 @@ wikidata_enrichment: image: Iwate Museum of Art.jpg commons_category: Iwate Museum of Art wikidata_image: Iwate Museum of Art.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:38:17.644193+00:00' + source_url: http://www.ima.or.jp/en/enhome.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ima.or.jp/en/global-image/site/favicon.ico + source_url: http://www.ima.or.jp/en/enhome.html + css_selector: '[document] > html.desktop.portrait > head > link' + retrieved_on: '2025-12-23T14:38:17.644193+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-03-MOR-M-ITMM.yaml b/data/custodian/JP-03-MOR-M-ITMM.yaml index 06deff4c49..882796f385 100644 --- a/data/custodian/JP-03-MOR-M-ITMM.yaml +++ b/data/custodian/JP-03-MOR-M-ITMM.yaml @@ -235,3 +235,22 @@ wikidata_enrichment: image: Ishikawa Takuboku Memorial Museum 20250516b.jpg commons_category: Ishikawa Takuboku Memorial Museum wikidata_image: Ishikawa Takuboku Memorial Museum 20250516b.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:38:35.422338+00:00' + source_url: https://www.mfca.jp/takuboku + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mfca.jp/favicon.ico + source_url: https://www.mfca.jp/takuboku + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:38:35.422338+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-03-MOR-M-IUM.yaml b/data/custodian/JP-03-MOR-M-IUM.yaml index 92660cbe3b..79afc6bf98 100644 --- a/data/custodian/JP-03-MOR-M-IUM.yaml +++ b/data/custodian/JP-03-MOR-M-IUM.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.591924+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: MOR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-MOR-M-IUM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-MOR-M-IUM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-MOR-M-IUM ghcid_numeric: 206059470407871373 valid_from: '2025-12-06T23:38:30.591924+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: IWATE UNIVERSITY MUSEUM @@ -204,7 +205,7 @@ wikidata_enrichment: location: city: Morioka Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 020-8550 street_address: 3-18-8 UEDA, Morioka Shi, Iwate Ken, 020-8550 @@ -219,3 +220,38 @@ location: geonames_id: 2111834 geonames_name: Morioka feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:38:48.248393+00:00' + source_url: https://www.iwate-u.ac.jp/academics/facility/museum.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.iwate-u.ac.jp/academics/facility/assets/images/common/logo_page.svg + source_url: https://www.iwate-u.ac.jp/academics/facility/museum.html + css_selector: '[document] > html > body.index.home > div.body__inner > header.header.header--page + > div.header__body:nth-of-type(2) > h1.header__logo.header__logo--page > a > + img' + retrieved_on: '2025-12-23T14:38:48.248393+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 国立大学法人岩手大学 IWATE UNIVERSITY + - claim_type: favicon_url + claim_value: https://www.iwate-u.ac.jp/academics/facility/favicon.ico + source_url: https://www.iwate-u.ac.jp/academics/facility/museum.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:38:48.248393+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.iwate-u.ac.jp/assets/images/common/ogp.jpg + source_url: https://www.iwate-u.ac.jp/academics/facility/museum.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:38:48.248393+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-03-MOR-M-KFFFM.yaml b/data/custodian/JP-03-MOR-M-KFFFM.yaml index c66f449b8d..f101e5ce7d 100644 --- a/data/custodian/JP-03-MOR-M-KFFFM.yaml +++ b/data/custodian/JP-03-MOR-M-KFFFM.yaml @@ -227,3 +227,20 @@ wikidata_enrichment: wikidata_web: official_website: http://www.nonohana.hs.plala.or.jp/ wikidata_official_website: http://www.nonohana.hs.plala.or.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:38:57.626732+00:00' + source_url: http://www.nonohana.hs.plala.or.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.nonohana.hs.plala.or.jp/wp-content/uploads/2017/10/top_slide01.jpg + source_url: http://www.nonohana.hs.plala.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:38:57.626732+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-03-MOR-M-MCSMS.yaml b/data/custodian/JP-03-MOR-M-MCSMS.yaml index e79c6246af..ad45b8179e 100644 --- a/data/custodian/JP-03-MOR-M-MCSMS.yaml +++ b/data/custodian/JP-03-MOR-M-MCSMS.yaml @@ -225,3 +225,30 @@ wikidata_enrichment: commons_category: Morioka Children Science Museum image: Morioka City Children's Science Museum 1.jpg wikidata_image: Morioka City Children's Science Museum 1.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:39:08.733435+00:00' + source_url: http://kodomokagakukan.com + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://kodomokagakukan.com/site/wp-content/themes/kagaku/images/common/logo_h.png + source_url: http://kodomokagakukan.com + css_selector: '[document] > html > body > header > h1 > a > img' + retrieved_on: '2025-12-23T14:39:08.733435+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市子ども科学館 + - claim_type: favicon_url + claim_value: https://kodomokagakukan.com/site/wp-content/themes/kagaku/favicon.ico + source_url: http://kodomokagakukan.com + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:39:08.733435+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-03-MOR-M-MHCM.yaml b/data/custodian/JP-03-MOR-M-MHCM.yaml index b3f31897a2..19d7aa2b15 100644 --- a/data/custodian/JP-03-MOR-M-MHCM.yaml +++ b/data/custodian/JP-03-MOR-M-MHCM.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.562100+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: MOR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-MOR-M-MHCM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-MOR-M-MHCM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-MOR-M-MHCM ghcid_numeric: 7673768982605010394 valid_from: '2025-12-06T23:38:30.562100+00:00' @@ -233,8 +234,25 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Morioka Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id006 postal_code: 020-8606 street_address: UCHIMARU, Morioka Shi, Iwate Ken, 020-0023 normalization_timestamp: '2025-12-09T10:56:42.489418+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:39:17.377113+00:00' + source_url: http://www.morireki.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://s0.wp.com/i/blank.jpg + source_url: http://www.morireki.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:39:17.377113+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-03-MOR-M-MSMAS.yaml b/data/custodian/JP-03-MOR-M-MSMAS.yaml index d442c9dcef..d2492a4d16 100644 --- a/data/custodian/JP-03-MOR-M-MSMAS.yaml +++ b/data/custodian/JP-03-MOR-M-MSMAS.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.577607+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: MOR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-MOR-M-MSMAS - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-MOR-M-MSMAS valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-MOR-M-MSMAS ghcid_numeric: 3848360075962537968 valid_from: '2025-12-06T23:38:30.577607+00:00' @@ -227,8 +228,35 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Morioka Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id006 postal_code: 020-0866 street_address: MOTOMIYA, Morioka Shi, Iwate Ken, 020-0866 normalization_timestamp: '2025-12-09T10:56:42.532745+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:39:32.963932+00:00' + source_url: https://www.city.morioka.iwate.jp/kankou/kankou/1037106/rekishi/1009437 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.morioka.iwate.jp/kankou/kankou/1037106/rekishi/_template_/_site_/_default_/_res/design/images/portal/logo.png + source_url: https://www.city.morioka.iwate.jp/kankou/kankou/1037106/rekishi/1009437 + css_selector: '#portalh1 > img' + retrieved_on: '2025-12-23T14:39:32.963932+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 盛岡市 + - claim_type: favicon_url + claim_value: https://www.city.morioka.iwate.jp/kankou/kankou/1037106/rekishi/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.morioka.iwate.jp/kankou/kankou/1037106/rekishi/1009437 + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T14:39:32.963932+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-03-MOR-M-MTHFM.yaml b/data/custodian/JP-03-MOR-M-MTHFM.yaml index 8d7632cb6a..c3d452bc44 100644 --- a/data/custodian/JP-03-MOR-M-MTHFM.yaml +++ b/data/custodian/JP-03-MOR-M-MTHFM.yaml @@ -212,3 +212,22 @@ location: geonames_id: 2111834 geonames_name: Morioka feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:39:50.573506+00:00' + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kinenkan/tonanrekishi/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kinenkan/tonanrekishi/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: http://www.city.morioka.iwate.jp/kurashi/kokyoshisetsu/kinenkan/tonanrekishi/index.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-23T14:39:50.573506+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-03-MOR-M-MZP.yaml b/data/custodian/JP-03-MOR-M-MZP.yaml index 87594d2509..ae8c2670b4 100644 --- a/data/custodian/JP-03-MOR-M-MZP.yaml +++ b/data/custodian/JP-03-MOR-M-MZP.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.567314+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: MOR method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-MOR-M-MZP - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-MOR-M-MZP valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-MOR-M-MZP ghcid_numeric: 1028096578132837740 valid_from: '2025-12-06T23:38:30.567314+00:00' @@ -242,8 +243,35 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Morioka Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id005 postal_code: 020-0803 street_address: SHINJO, Morioka Shi, Iwate Ken, 020-0803 normalization_timestamp: '2025-12-09T10:56:42.617924+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:39:56.620063+00:00' + source_url: http://moriokazoo.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://moriokazoo.org/asset/img/favicon.png + source_url: http://moriokazoo.org + css_selector: '[document] > html.i-amphtml-singledoc.i-amphtml-standalone > head + > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:39:56.620063+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://moriokazoo.org/asset/img/Result-HK.png + source_url: http://moriokazoo.org + css_selector: '[document] > html.i-amphtml-singledoc.i-amphtml-standalone > head + > meta:nth-of-type(11)' + retrieved_on: '2025-12-23T14:39:56.620063+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-03-MOT-M-HCBG.yaml b/data/custodian/JP-03-MOT-M-HCBG.yaml index 2e7741a594..2363edfb4b 100644 --- a/data/custodian/JP-03-MOT-M-HCBG.yaml +++ b/data/custodian/JP-03-MOT-M-HCBG.yaml @@ -248,3 +248,28 @@ location: geonames_id: 8411777 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.512908+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:40:03.788078+00:00' + source_url: http://www.hirosakipark.or.jp/plant/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.hirosakipark.or.jp/images/favicon.ico + source_url: http://www.hirosakipark.or.jp/plant/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:40:03.788078+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.hirosakipark.or.jp/images/plant/kitaannnaisho.jpg + source_url: http://www.hirosakipark.or.jp/plant/index.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:40:03.788078+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-03-NIS-L-HPL.yaml b/data/custodian/JP-03-NIS-L-HPL.yaml index cca44ef832..8d6093b551 100644 --- a/data/custodian/JP-03-NIS-L-HPL.yaml +++ b/data/custodian/JP-03-NIS-L-HPL.yaml @@ -203,3 +203,22 @@ wikidata_enrichment: wikidata_web: official_website: http://www.town.hiraizumi.iwate.jp/index.cfm/26 wikidata_official_website: http://www.town.hiraizumi.iwate.jp/index.cfm/26 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:40:44.508299+00:00' + source_url: http://www.town.hiraizumi.iwate.jp/index.cfm/26 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hi-hp-production.s3.ap-northeast-1.amazonaws.com/wp-content/uploads/2025/03/22163403/cropped-hiraizumi-1-180x180.png + source_url: http://www.town.hiraizumi.iwate.jp/index.cfm/26 + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-23T14:40:44.508299+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/JP-03-NIS-M-HCHC.yaml b/data/custodian/JP-03-NIS-M-HCHC.yaml index b3807031dd..01bc1ab1bd 100644 --- a/data/custodian/JP-03-NIS-M-HCHC.yaml +++ b/data/custodian/JP-03-NIS-M-HCHC.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.747482+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: NIS method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-NIS-M-HCHC - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-NIS-M-HCHC valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-NIS-M-HCHC ghcid_numeric: 2424491060517667333 valid_from: '2025-12-06T23:38:30.747482+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: HIRAIZUMI CULTURAL HERITAGE CENTER @@ -175,7 +176,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q18411786 label: visitor center - description: combination of tourist center and museum directly related to a point of interest or the local area + description: combination of tourist center and museum directly related to a + point of interest or the local area wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -203,7 +205,7 @@ wikidata_enrichment: location: city: Nishiiwai Gun Hiraizumi Cho region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 029-4102 street_address: HIRAIZUMI, Nishiiwai Gun Hiraizumi Cho, Iwate Ken, 029-4102 @@ -220,3 +222,22 @@ location: geonames_id: 11776759 geonames_name: Hiraizumi feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:40:55.491243+00:00' + source_url: https://www.town.hiraizumi.iwate.jp/index.cfm/26,1040,128,277,html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hi-hp-production.s3.ap-northeast-1.amazonaws.com/wp-content/uploads/2025/03/22163403/cropped-hiraizumi-1-180x180.png + source_url: https://www.town.hiraizumi.iwate.jp/index.cfm/26,1040,128,277,html + css_selector: '[document] > html > head > link:nth-of-type(24)' + retrieved_on: '2025-12-23T14:40:55.491243+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/JP-03-NIS-M-HWHIC.yaml b/data/custodian/JP-03-NIS-M-HWHIC.yaml index 995ee86201..c7693feb3a 100644 --- a/data/custodian/JP-03-NIS-M-HWHIC.yaml +++ b/data/custodian/JP-03-NIS-M-HWHIC.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.744884+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: NIS method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-NIS-M-HWHIC - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-NIS-M-HWHIC valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-NIS-M-HWHIC ghcid_numeric: 2706506571620490121 valid_from: '2025-12-06T23:38:30.744884+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: HIRAIZUMI WORLD HERITAGE INFORMATION CENTER @@ -177,10 +178,12 @@ wikidata_enrichment: instance_of: &id004 - id: Q18411786 label: visitor center - description: combination of tourist center and museum directly related to a point of interest or the local area + description: combination of tourist center and museum directly related to a + point of interest or the local area field_of_work: &id005 - id: Q2896261 - label: Hiraizumi – Temples, Gardens and Archaeological Sites Representing the Buddhist Pure Land + label: Hiraizumi – Temples, Gardens and Archaeological Sites Representing the + Buddhist Pure Land description: UNESCO World Heritage Site in Iwate Prefecture, Japan wikidata_instance_of: *id004 wikidata_field_of_work: *id005 @@ -205,7 +208,7 @@ wikidata_enrichment: location: city: Nishiiwai Gun Hiraizumi Cho region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 029-4102 street_address: HIRAIZUMI, Nishiiwai Gun Hiraizumi Cho, Iwate Ken, 029-4102 @@ -222,3 +225,28 @@ location: geonames_id: 11776759 geonames_name: Hiraizumi feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:41:09.124415+00:00' + source_url: https://www.sekaiisan.pref.iwate.jp/information + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.sekaiisan.pref.iwate.jp/assets/front/img/common/logo_page.svg + source_url: https://www.sekaiisan.pref.iwate.jp/information + css_selector: '#top > header.header > div.header-inner > p.header-logo > a > img' + retrieved_on: '2025-12-23T14:41:09.124415+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 平泉 + - claim_type: og_image_url + claim_value: https://www.sekaiisan.pref.iwate.jp/uploads/common/og.png + source_url: https://www.sekaiisan.pref.iwate.jp/information + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T14:41:09.124415+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-03-NIS-M-TAC.yaml b/data/custodian/JP-03-NIS-M-TAC.yaml index 7ef9d42f8d..a559c82983 100644 --- a/data/custodian/JP-03-NIS-M-TAC.yaml +++ b/data/custodian/JP-03-NIS-M-TAC.yaml @@ -2256,3 +2256,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/Lg_ue_giV50/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:41:25.238975+00:00' + source_url: https://towadaartcenter.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://towadaartcenter.com/wordpress/wp-content/uploads/2016/09/cropped-arts-towada-blue-300x300.png + source_url: https://towadaartcenter.com + css_selector: '#html-root > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T14:41:25.238975+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://towadaartcenter.com/wordpress/wp-content/themes/towadaartcenter/dist/assets/favicons/og.png + source_url: https://towadaartcenter.com + css_selector: '#html-root > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T14:41:25.238975+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-03-OFU-L-OL.yaml b/data/custodian/JP-03-OFU-L-OL.yaml index dbab141c4b..0099873c97 100644 --- a/data/custodian/JP-03-OFU-L-OL.yaml +++ b/data/custodian/JP-03-OFU-L-OL.yaml @@ -206,3 +206,37 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.ofunato.iwate.jp/www/contents/1226654674469/index.html wikidata_official_website: http://www.city.ofunato.iwate.jp/www/contents/1226654674469/index.html +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:41:33.466421+00:00' + source_url: http://www.city.ofunato.iwate.jp/www/contents/1226654674469/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ofunato.iwate.jp/assets/front/img/common/logo.svg + source_url: http://www.city.ofunato.iwate.jp/www/contents/1226654674469/index.html + css_selector: '[document] > html > body.page > div.site-container > header.header + > div.header-logo-utility > p.header-logo > a.header-logo__link > img.header-logo__image' + retrieved_on: '2025-12-23T14:41:33.466421+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大船渡市 + - claim_type: favicon_url + claim_value: https://www.city.ofunato.iwate.jp/assets/front/img/common/favicon.svg + source_url: http://www.city.ofunato.iwate.jp/www/contents/1226654674469/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:41:33.466421+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ofunato.iwate.jp/uploads/common/og.png + source_url: http://www.city.ofunato.iwate.jp/www/contents/1226654674469/index.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:41:33.466421+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-03-OFU-M-OCM.yaml b/data/custodian/JP-03-OFU-M-OCM.yaml index 41e6b26ad6..0fbc277752 100644 --- a/data/custodian/JP-03-OFU-M-OCM.yaml +++ b/data/custodian/JP-03-OFU-M-OCM.yaml @@ -36,18 +36,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.606596+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: OFU method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-OFU-M-OCM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-OFU-M-OCM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-OFU-M-OCM ghcid_numeric: 8216552419593819345 valid_from: '2025-12-06T23:38:30.606596+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: OFUNATO CITY MUSEUM @@ -229,7 +230,7 @@ wikidata_enrichment: location: city: Ofunato Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 022-0001 street_address: MASSAKICHO, Ofunato Shi, Iwate Ken, 022-0001 @@ -244,3 +245,37 @@ location: geonames_id: 2111530 geonames_name: Ōfunato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:41:40.734563+00:00' + source_url: https://www.city.ofunato.iwate.jp/site/hakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ofunato.iwate.jp/assets/front/img/common/logo.svg + source_url: https://www.city.ofunato.iwate.jp/site/hakubutsukan + css_selector: '[document] > html > body.page > div.site-container > header.header + > div.header-logo-utility > p.header-logo > a.header-logo__link > img.header-logo__image' + retrieved_on: '2025-12-23T14:41:40.734563+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大船渡市 + - claim_type: favicon_url + claim_value: https://www.city.ofunato.iwate.jp/assets/front/img/common/favicon.svg + source_url: https://www.city.ofunato.iwate.jp/site/hakubutsukan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:41:40.734563+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ofunato.iwate.jp/uploads/common/og.png + source_url: https://www.city.ofunato.iwate.jp/site/hakubutsukan + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T14:41:40.734563+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-03-OSH-L-K.yaml b/data/custodian/JP-03-OSH-L-K.yaml index 0a37a0c7e7..aaa63224ee 100644 --- a/data/custodian/JP-03-OSH-L-K.yaml +++ b/data/custodian/JP-03-OSH-L-K.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://library.city.oshu.iwate.jp/ wikidata_official_website: http://library.city.oshu.iwate.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:41:46.758573+00:00' + source_url: http://library.city.oshu.iwate.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.city.oshu.iwate.jp/favicon.ico + source_url: http://library.city.oshu.iwate.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:41:46.758573+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-03-OSH-L-OCEL.yaml b/data/custodian/JP-03-OSH-L-OCEL.yaml index 2344780048..40a567e50c 100644 --- a/data/custodian/JP-03-OSH-L-OCEL.yaml +++ b/data/custodian/JP-03-OSH-L-OCEL.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://library.city.oshu.iwate.jp/ wikidata_official_website: http://library.city.oshu.iwate.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:41:52.562657+00:00' + source_url: http://library.city.oshu.iwate.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.city.oshu.iwate.jp/favicon.ico + source_url: http://library.city.oshu.iwate.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:41:52.562657+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-03-OSH-L-OL-oshushiritsuisawa_library.yaml b/data/custodian/JP-03-OSH-L-OL-oshushiritsuisawa_library.yaml index 1323b249ac..baacadc9a4 100644 --- a/data/custodian/JP-03-OSH-L-OL-oshushiritsuisawa_library.yaml +++ b/data/custodian/JP-03-OSH-L-OL-oshushiritsuisawa_library.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://library.city.oshu.iwate.jp/ wikidata_official_website: http://library.city.oshu.iwate.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:41:58.402947+00:00' + source_url: http://library.city.oshu.iwate.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.city.oshu.iwate.jp/favicon.ico + source_url: http://library.city.oshu.iwate.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:41:58.402947+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-03-OSH-L-OL-oshushiritsumaesawa_library.yaml b/data/custodian/JP-03-OSH-L-OL-oshushiritsumaesawa_library.yaml index 7ac4455b12..922444c0f9 100644 --- a/data/custodian/JP-03-OSH-L-OL-oshushiritsumaesawa_library.yaml +++ b/data/custodian/JP-03-OSH-L-OL-oshushiritsumaesawa_library.yaml @@ -200,3 +200,22 @@ wikidata_enrichment: wikidata_web: official_website: http://library.city.oshu.iwate.jp/ wikidata_official_website: http://library.city.oshu.iwate.jp/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:42:04.275146+00:00' + source_url: http://library.city.oshu.iwate.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.city.oshu.iwate.jp/favicon.ico + source_url: http://library.city.oshu.iwate.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:42:04.275146+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-03-OSH-L-OL.yaml b/data/custodian/JP-03-OSH-L-OL.yaml index bb83250afb..c75a1e3d9e 100644 --- a/data/custodian/JP-03-OSH-L-OL.yaml +++ b/data/custodian/JP-03-OSH-L-OL.yaml @@ -199,3 +199,22 @@ wikidata_enrichment: wikidata_web: official_website: http://library.city.oshu.iwate.jp wikidata_official_website: http://library.city.oshu.iwate.jp +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:42:10.250938+00:00' + source_url: http://library.city.oshu.iwate.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.city.oshu.iwate.jp/favicon.ico + source_url: http://library.city.oshu.iwate.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:42:10.250938+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-03-OSH-M-CM.yaml b/data/custodian/JP-03-OSH-M-CM.yaml index 36bc38f6d1..73b0d32f6f 100644 --- a/data/custodian/JP-03-OSH-M-CM.yaml +++ b/data/custodian/JP-03-OSH-M-CM.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.712918+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: OSH method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-OSH-M-CM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-OSH-M-CM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-OSH-M-CM ghcid_numeric: 15659285398690493771 valid_from: '2025-12-06T23:38:30.712918+00:00' @@ -262,8 +263,41 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Oshu Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id006 postal_code: 029-4205 street_address: MAESAWAMINAMIJIMBA, Oshu Shi, Iwate Ken, 029-4205 normalization_timestamp: '2025-12-09T10:56:43.462671+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:42:19.388578+00:00' + source_url: https://www.city.oshu.iwate.jp/htm/ushi + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.oshu.iwate.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.oshu.iwate.jp/htm/ushi + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-23T14:42:19.388578+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 奥州市 Oshu City + - claim_type: favicon_url + claim_value: https://www.city.oshu.iwate.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.oshu.iwate.jp/htm/ushi + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:42:19.388578+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.oshu.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.oshu.iwate.jp/htm/ushi + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:42:19.388578+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-03-OSH-M-OCARC.yaml b/data/custodian/JP-03-OSH-M-OCARC.yaml index 05e260a872..e5b4bbef42 100644 --- a/data/custodian/JP-03-OSH-M-OCARC.yaml +++ b/data/custodian/JP-03-OSH-M-OCARC.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.693925+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: OSH method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-OSH-M-OCARC - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-OSH-M-OCARC valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-OSH-M-OCARC ghcid_numeric: 8816413776175411797 valid_from: '2025-12-06T23:38:30.693925+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: OSHU CITY ARCHAEOLOGICAL RESEARCH CENTER @@ -171,8 +172,8 @@ 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: country: &id005 @@ -196,7 +197,7 @@ wikidata_enrichment: location: city: Oshu Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: JP postal_code: 023-0003 street_address: MIZUSAWASAKURAKAWA, Oshu Shi, Iwate Ken, 023-0003 @@ -211,3 +212,28 @@ location: geonames_id: 6822184 geonames_name: Ōshū feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:42:39.713323+00:00' + source_url: http://www.oshu-bunka.or.jp/maibun + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.oshu-bunka.or.jp/maibun/files/favicon/favicon.ico?cache=1766500949 + source_url: http://www.oshu-bunka.or.jp/maibun + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:42:39.713323+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.oshu-bunka.or.jp/maibun/files/site_config/capture.jpg?1766500949 + source_url: http://www.oshu-bunka.or.jp/maibun + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-23T14:42:39.713323+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-03-RIK-L-N.yaml b/data/custodian/JP-03-RIK-L-N.yaml index a713f0bea1..9e960eb27b 100644 --- a/data/custodian/JP-03-RIK-L-N.yaml +++ b/data/custodian/JP-03-RIK-L-N.yaml @@ -205,3 +205,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#nijino wikidata_official_website: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#nijino +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:47:06.866636+00:00' + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#nijino + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.rikuzentakata.iwate.jp/smartphone.png + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#nijino + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:47:06.866636+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.rikuzentakata.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#nijino + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:47:06.866636+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-03-RIK-L-RCL.yaml b/data/custodian/JP-03-RIK-L-RCL.yaml index 88d3bf31ea..0465fad19c 100644 --- a/data/custodian/JP-03-RIK-L-RCL.yaml +++ b/data/custodian/JP-03-RIK-L-RCL.yaml @@ -205,3 +205,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#community wikidata_official_website: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#community +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:47:14.724805+00:00' + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#community + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.rikuzentakata.iwate.jp/smartphone.png + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#community + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:47:14.724805+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.rikuzentakata.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan/libinfo.html#community + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:47:14.724805+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-03-RIK-L-RLK.yaml b/data/custodian/JP-03-RIK-L-RLK.yaml index 9f03a7f518..7f97f3d2f0 100644 --- a/data/custodian/JP-03-RIK-L-RLK.yaml +++ b/data/custodian/JP-03-RIK-L-RLK.yaml @@ -205,3 +205,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.rikuzentakata.iwate.jp/tosyokan/ wikidata_official_website: http://www.city.rikuzentakata.iwate.jp/tosyokan/ +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:47:21.653711+00:00' + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.rikuzentakata.iwate.jp/smartphone.png + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:47:21.653711+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.rikuzentakata.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.rikuzentakata.iwate.jp/tosyokan + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:47:21.653711+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-03-RIK-M-ITMM.yaml b/data/custodian/JP-03-RIK-M-ITMM.yaml index 51d77314eb..264910a6e5 100644 --- a/data/custodian/JP-03-RIK-M-ITMM.yaml +++ b/data/custodian/JP-03-RIK-M-ITMM.yaml @@ -250,3 +250,22 @@ location: postal_code: 029-2204 street_address: KESENCHO, Rikuzentakata Shi, Iwate Ken, 029-2204 normalization_timestamp: '2025-12-09T10:56:43.722470+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:47:32.944520+00:00' + source_url: https://iwate-tsunami-memorial.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://iwate-tsunami-memorial.jp/wp/wp-content/uploads/2024/09/cropped-icon-180x180.png + source_url: https://iwate-tsunami-memorial.jp + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-23T14:47:32.944520+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-03-RIK-M-RTCM.yaml b/data/custodian/JP-03-RIK-M-RTCM.yaml index 62127f1f14..7ec7bd31fc 100644 --- a/data/custodian/JP-03-RIK-M-RTCM.yaml +++ b/data/custodian/JP-03-RIK-M-RTCM.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.674430+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: RIK method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-RIK-M-RTCM - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-RIK-M-RTCM valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-RIK-M-RTCM ghcid_numeric: 188631284639018200 valid_from: '2025-12-06T23:38:30.674430+00:00' @@ -251,8 +252,33 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Rikuzentakata Shi region: Iwate Ken - region_code: 03 + region_code: 3 country: *id006 postal_code: 029-2205 street_address: TAKATACHO, Rikuzentakata Shi, Iwate Ken, 029-2205 normalization_timestamp: '2025-12-09T10:56:43.770509+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:47:47.282233+00:00' + source_url: https://www.city.rikuzentakata.iwate.jp/soshiki/kanrika/hakubutsukan/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.rikuzentakata.iwate.jp/smartphone.png + source_url: https://www.city.rikuzentakata.iwate.jp/soshiki/kanrika/hakubutsukan/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:47:47.282233+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.rikuzentakata.iwate.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.rikuzentakata.iwate.jp/soshiki/kanrika/hakubutsukan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T14:47:47.282233+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-03-SAM-M-HMSH.yaml b/data/custodian/JP-03-SAM-M-HMSH.yaml index 91972eb486..db1932a198 100644 --- a/data/custodian/JP-03-SAM-M-HMSH.yaml +++ b/data/custodian/JP-03-SAM-M-HMSH.yaml @@ -365,3 +365,31 @@ location: geonames_id: 2128323 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.631988+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:48:18.485912+00:00' + source_url: http://www.marient.org + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.marient.org/image/logo.svg + source_url: http://www.marient.org + css_selector: '[document] > html > body > div.l-wrapper > header > div.l-hd > + h1.l-hd_logo > a > img' + retrieved_on: '2025-12-23T14:48:18.485912+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 八戸市水産科学館マリエント + - claim_type: favicon_url + claim_value: http://www.marient.org/favicons/favicon.png + source_url: http://www.marient.org + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:48:18.485912+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-03-SAN-M-AMA.yaml b/data/custodian/JP-03-SAN-M-AMA.yaml index 08ae3e3865..279b4df3d8 100644 --- a/data/custodian/JP-03-SAN-M-AMA.yaml +++ b/data/custodian/JP-03-SAN-M-AMA.yaml @@ -1499,3 +1499,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/3SYc1Biq4w8/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:48:31.388468+00:00' + source_url: http://www.aomori-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.aomori-museum.jp/assets/img/global/apple-touch-icon.png + source_url: http://www.aomori-museum.jp + css_selector: '[document] > html.desktop.landscape > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:48:31.388468+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.aomori-museum.jp/assets/img/global/ogimage.jpg + source_url: http://www.aomori-museum.jp + css_selector: '[document] > html.desktop.landscape > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T14:48:31.388468+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-03-SEK-M-MSM.yaml b/data/custodian/JP-03-SEK-M-MSM.yaml index c942826e87..3ab4bb1974 100644 --- a/data/custodian/JP-03-SEK-M-MSM.yaml +++ b/data/custodian/JP-03-SEK-M-MSM.yaml @@ -344,3 +344,30 @@ location: geonames_id: 2128244 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.705419+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:48:53.969192+00:00' + source_url: http://jmsfmml.or.jp/msm + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://jmsfmml.or.jp/common/images/logo.svg + source_url: http://jmsfmml.or.jp/msm + css_selector: '#logo > a > img' + retrieved_on: '2025-12-23T14:48:53.969192+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: むつ科学技術館 Mutsu Science Museum + - claim_type: favicon_url + claim_value: http://jmsfmml.or.jp/apple-touch-icon.png + source_url: http://jmsfmml.or.jp/msm + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T14:48:53.969192+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-03-SHI-M-ACFM.yaml b/data/custodian/JP-03-SHI-M-ACFM.yaml index b7e29bae7f..8900326b1c 100644 --- a/data/custodian/JP-03-SHI-M-ACFM.yaml +++ b/data/custodian/JP-03-SHI-M-ACFM.yaml @@ -364,3 +364,30 @@ location: geonames_id: 8506114 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.742450+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:50:40.455853+00:00' + source_url: https://www.aomori-shi.shinrinhakubutsukan.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.aomori-shi.shinrinhakubutsukan.jp/images/simages/shinpaku_logo004.png + source_url: https://www.aomori-shi.shinrinhakubutsukan.jp + css_selector: '#mod-custom166 > p > a > img' + retrieved_on: '2025-12-23T14:50:40.455853+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: shinpaku logo004 + - claim_type: favicon_url + claim_value: https://www.aomori-shi.shinrinhakubutsukan.jp/media/templates/site/cassiopeia_user_shinpaku/images/favicon.ico + source_url: https://www.aomori-shi.shinrinhakubutsukan.jp + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-23T14:50:40.455853+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-03-SHI-M-YCFHMH.yaml b/data/custodian/JP-03-SHI-M-YCFHMH.yaml index 1472a089d0..fde8aa6347 100644 --- a/data/custodian/JP-03-SHI-M-YCFHMH.yaml +++ b/data/custodian/JP-03-SHI-M-YCFHMH.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.727665+00:00' location_resolution: country_code: JP - region_code: 03 + region_code: 3 city_code: SHI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-03-SHI-M-YCFHMH - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-SHI-M-YCFHMH valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-IW-SHI-M-YCFHMH ghcid_numeric: 17765446989322748732 valid_from: '2025-12-06T23:38:30.727665+00:00' @@ -231,8 +232,35 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Shiwa Gun Yahaba Cho region: Iwate Ken - region_code: 03 + region_code: 3 country: *id005 postal_code: 028-3603 street_address: NISHITOKUTA, Shiwa Gun Yahaba Cho, Iwate Ken, 028-3603 normalization_timestamp: '2025-12-09T10:56:44.015944+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:51:03.405795+00:00' + source_url: https://www.town.yahaba.iwate.jp/soshiki/kyouiku/manabi/2019021500046 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://img.japandx.co.jp/yahabatown/master/home/yahaba-logo.png + source_url: https://www.town.yahaba.iwate.jp/soshiki/kyouiku/manabi/2019021500046 + css_selector: '#h_upper > div.h-u-logo > a > img' + retrieved_on: '2025-12-23T14:51:03.405795+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 矢巾町 + - claim_type: favicon_url + claim_value: https://img.japandx.co.jp/yahabatown/master/home/favicon.ico + source_url: https://www.town.yahaba.iwate.jp/soshiki/kyouiku/manabi/2019021500046 + css_selector: '[document] > html.s-font-size-normal > head > link' + retrieved_on: '2025-12-23T14:51:03.405795+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-03-SHI-M-YCSMWO.yaml b/data/custodian/JP-03-SHI-M-YCSMWO.yaml index 822c152a56..71722d9087 100644 --- a/data/custodian/JP-03-SHI-M-YCSMWO.yaml +++ b/data/custodian/JP-03-SHI-M-YCSMWO.yaml @@ -238,3 +238,28 @@ wikidata_enrichment: image: Museum of whale and sea.jpg commons_category: Science Museum of Whales and the Sea wikidata_image: Museum of whale and sea.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:51:15.015000+00:00' + source_url: https://yamada-kujirakan.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://yamada-kujirakan.jp/wp-content/uploads/2024/05/screenshot.png + source_url: https://yamada-kujirakan.jp + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-23T14:51:15.015000+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + - claim_type: og_image_url + claim_value: https://yamada-kujirakan.jp/wp-content/uploads/2018/06/mainbnr1.jpg + source_url: https://yamada-kujirakan.jp + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-23T14:51:15.015000+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-03-TAK-L-RL.yaml b/data/custodian/JP-03-TAK-L-RL.yaml index 97e3c1d5db..80de78fc85 100644 --- a/data/custodian/JP-03-TAK-L-RL.yaml +++ b/data/custodian/JP-03-TAK-L-RL.yaml @@ -33,7 +33,7 @@ ghcid: location_resolution: method: GOOGLE_PLACES_GEONAMES country_code: JP - region_code: 03 + region_code: 3 region_name: Iwate city_code: TAK city_name: Takada @@ -45,13 +45,14 @@ ghcid: resolution_date: '2025-12-07T12:05:18.535339+00:00' ghcid_history: - ghcid: JP-03-TAK-L-RL - valid_from: "2025-12-10T09:43:40Z" + valid_from: '2025-12-10T09:43:40Z' valid_to: null - reason: "Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO 3166-2:JP" + reason: Corrected region code from JP-IW (abbreviation) to JP-03 (Iwate) per ISO + 3166-2:JP - ghcid: JP-IW-TAK-L-RL valid_from: null - valid_to: "2025-12-10T09:43:40Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:40Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-XX-XXX-L-RL ghcid_numeric: 12075211796198909905 valid_from: '2025-12-06T23:38:41.526579+00:00' @@ -221,7 +222,26 @@ location: source_path: original_entry.locations[0] city: Takada region: Iwate - region_code: 03 + region_code: 3 country: *id005 street_address: Tatenooki-303-7 Takatachō, Rikuzentakata, Iwate 029-2205, Japan normalization_timestamp: '2025-12-09T10:56:44.131626+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T14:52:05.971676+00:00' + source_url: https://opac.libcloud.jp/rikutaka-library/advanced-search + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://opac.libcloud.jp/rikutaka-library/favicon.ico + source_url: https://opac.libcloud.jp/rikutaka-library/advanced-search + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T14:52:05.971676+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-03-TAK-L-TL.yaml b/data/custodian/JP-03-TAK-L-TL.yaml index 1775259cc2..1d1b9835ee 100644 --- a/data/custodian/JP-03-TAK-L-TL.yaml +++ b/data/custodian/JP-03-TAK-L-TL.yaml @@ -204,3 +204,28 @@ wikidata_enrichment: wikidata_web: official_website: http://www.city.takizawa.iwate.jp/kozan wikidata_official_website: http://www.city.takizawa.iwate.jp/kozan +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:04:05.746047+00:00' + source_url: http://www.city.takizawa.iwate.jp/kozan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.takizawa.iwate.jp/assets/front/img/common/favicon.svg + source_url: http://www.city.takizawa.iwate.jp/kozan + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T15:04:05.746047+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.takizawa.iwate.jp/uploads/common/og.png + source_url: http://www.city.takizawa.iwate.jp/kozan + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T15:04:05.746047+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-03-TON-M-TFV.yaml b/data/custodian/JP-03-TON-M-TFV.yaml index aaf9ed34a7..a6aa34e7a1 100644 --- a/data/custodian/JP-03-TON-M-TFV.yaml +++ b/data/custodian/JP-03-TON-M-TFV.yaml @@ -289,3 +289,30 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/9E_13oWjRB4/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:04:25.613926+00:00' + source_url: https://www.tono-furusato.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tono-furusato.jp/official/wp-content/themes/furusatomura/images/common/logo_h.png + source_url: https://www.tono-furusato.jp + css_selector: '[document] > html > body > header > h1.hlogo > a > img' + retrieved_on: '2025-12-23T15:04:25.613926+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 遠野ふるさと村 + - claim_type: favicon_url + claim_value: https://www.tono-furusato.jp/official/wp-content/themes/furusatomura/favicon.ico + source_url: https://www.tono-furusato.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T15:04:25.613926+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-03-WAG-M-HM.yaml b/data/custodian/JP-03-WAG-M-HM.yaml index 41b9799398..7a3a2edf8a 100644 --- a/data/custodian/JP-03-WAG-M-HM.yaml +++ b/data/custodian/JP-03-WAG-M-HM.yaml @@ -229,3 +229,23 @@ location: postal_code: 029-5614 street_address: SAWAUCHI OTA, Waga Gun Nishiwaga Machi, Iwate Ken, 029-5614 normalization_timestamp: '2025-12-09T10:56:44.291069+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:04:46.646150+00:00' + source_url: http://yamanoideyu.com/spot/article.php?p=74 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://yamanoideyu.com/common/images/header_sitelogo.gif + source_url: http://yamanoideyu.com/spot/article.php?p=74 + css_selector: '[document] > html.js.flexbox > body > header.header > div.header_top_box + > div.disp_c.div_flex > h1.header_title > a > img.h1_img_pc' + retrieved_on: '2025-12-23T15:04:46.646150+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 西和賀観光協会公式サイト + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-04-ABI-M-ACMB.yaml b/data/custodian/JP-04-ABI-M-ACMB.yaml index bbe2aa4bf0..7f0825e1a7 100644 --- a/data/custodian/JP-04-ABI-M-ACMB.yaml +++ b/data/custodian/JP-04-ABI-M-ACMB.yaml @@ -368,3 +368,20 @@ location: geonames_id: 2113164 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:24.777428+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:05:05.886193+00:00' + source_url: https://www.city.abiko.chiba.jp/bird-mus + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.abiko.chiba.jp/images/ogp_icon.jpg + source_url: https://www.city.abiko.chiba.jp/bird-mus + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-23T15:05:05.886193+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-04-CHI-M-CCMA.yaml b/data/custodian/JP-04-CHI-M-CCMA.yaml index 66cd8b9603..3e4cbff114 100644 --- a/data/custodian/JP-04-CHI-M-CCMA.yaml +++ b/data/custodian/JP-04-CHI-M-CCMA.yaml @@ -429,3 +429,28 @@ location: geonames_id: 2113015 feature_code: PPLA normalization_timestamp: '2025-12-09T06:53:24.824449+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:05:29.945069+00:00' + source_url: https://www.ccma-net.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ccma-net.jp/wp-content/themes/ccma/_img/favicon/apple-touch-icon-180x180.jpg + source_url: https://www.ccma-net.jp + css_selector: '#top > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T15:05:29.945069+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.ccma-net.jp/wp-content/themes/ccma/_img/home/home-architecture-1.jpg + source_url: https://www.ccma-net.jp + css_selector: '#top > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T15:05:29.945069+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-04-FUN-M-ILM.yaml b/data/custodian/JP-04-FUN-M-ILM.yaml index 1f855ad2d6..c03d9afb98 100644 --- a/data/custodian/JP-04-FUN-M-ILM.yaml +++ b/data/custodian/JP-04-FUN-M-ILM.yaml @@ -1522,3 +1522,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/NQSAXj5CgvU/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:06:03.920511+00:00' + source_url: https://lsm-ichihara.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lsm-ichihara.jp/_img/_icons/icon.png + source_url: https://lsm-ichihara.jp + css_selector: '[document] > html.js.backgroundsize > head > link' + retrieved_on: '2025-12-23T15:06:03.920511+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://lsm-ichihara.jp/_img/_icons/1000.jpg + source_url: https://lsm-ichihara.jp + css_selector: '[document] > html.js.backgroundsize > head > meta:nth-of-type(2)' + retrieved_on: '2025-12-23T15:06:03.920511+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-04-KAI-M-THSPM.yaml b/data/custodian/JP-04-KAI-M-THSPM.yaml index c41ea44602..efae3305e7 100644 --- a/data/custodian/JP-04-KAI-M-THSPM.yaml +++ b/data/custodian/JP-04-KAI-M-THSPM.yaml @@ -375,3 +375,36 @@ location: geonames_id: 10916348 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:24.921188+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:06:16.788525+00:00' + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0006/0001/p036786.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/logo.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0006/0001/p036786.html + css_selector: '#header > div.l-header__inner > div.l-header__logo > a > img' + retrieved_on: '2025-12-23T15:06:16.788525+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 船橋市 + - claim_type: favicon_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-apple-touch-icon.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0006/0001/p036786.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T15:06:16.788525+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.funabashi.lg.jp/share/imgs/main-ogimg.png + source_url: https://www.city.funabashi.lg.jp/shisetsu/bunka/0001/0006/0001/p036786.html + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T15:06:16.788525+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-04-NAG-M-NMM.yaml b/data/custodian/JP-04-NAG-M-NMM.yaml index 70bdeea6f2..7b833660e0 100644 --- a/data/custodian/JP-04-NAG-M-NMM.yaml +++ b/data/custodian/JP-04-NAG-M-NMM.yaml @@ -280,3 +280,20 @@ location: geonames_id: 1856184 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:24.991648+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:06:44.314488+00:00' + source_url: https://www.city.nagareyama.chiba.jp/life/1001780/1001785/index.html + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.city.nagareyama.chiba.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.nagareyama.chiba.jp/life/1001780/1001785/index.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-23T15:06:44.314488+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-04-NAR-L-NLB.yaml b/data/custodian/JP-04-NAR-L-NLB.yaml index 84a58e6c98..263e41d7a2 100644 --- a/data/custodian/JP-04-NAR-L-NLB.yaml +++ b/data/custodian/JP-04-NAR-L-NLB.yaml @@ -383,3 +383,28 @@ location: geonames_id: 2111684 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:25.025398+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:06:52.936054+00:00' + source_url: http://naritasanlib.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: data:image/png;base64,iVBORw0KGgo= + source_url: http://naritasanlib.jp + css_selector: '[document] > html.j-feature-js.j-feature-no-touch > head > link:nth-of-type(5)' + retrieved_on: '2025-12-23T15:06:52.936054+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://image.jimcdn.com/app/cms/image/transf/none/path/s0e240579dff14123/backgroundarea/i290d8eb8c57cdbcf/version/1526821757/image.jpg + source_url: http://naritasanlib.jp + css_selector: '[document] > html.j-feature-js.j-feature-no-touch > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-23T15:06:52.936054+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-04-OMA-M-ICZ.yaml b/data/custodian/JP-04-OMA-M-ICZ.yaml index ed7a855069..d9f4ed624a 100644 --- a/data/custodian/JP-04-OMA-M-ICZ.yaml +++ b/data/custodian/JP-04-OMA-M-ICZ.yaml @@ -276,3 +276,29 @@ location: geonames_id: 10936928 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:25.058878+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:07:05.623301+00:00' + source_url: https://www.city.ichikawa.lg.jp/zoo + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ichikawa.lg.jp/zoo/assets/images/common/logo_01.png + source_url: https://www.city.ichikawa.lg.jp/zoo + css_selector: '#header > div.container > div.header-lowerBox > div.header-logoBox + > a.header-logo > h1.header-logo-inner > img' + retrieved_on: '2025-12-23T15:07:05.623301+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 市川市動植物園 ICHIKAWA CITY ZOO + - claim_type: og_image_url + claim_value: https://www.city.ichikawa.lg.jp/common/img/common/ogp.png + source_url: https://www.city.ichikawa.lg.jp/zoo + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-23T15:07:05.623301+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-04-SAK-M-SCMA.yaml b/data/custodian/JP-04-SAK-M-SCMA.yaml index 4bb420f343..30db80bee4 100644 --- a/data/custodian/JP-04-SAK-M-SCMA.yaml +++ b/data/custodian/JP-04-SAK-M-SCMA.yaml @@ -398,3 +398,28 @@ location: geonames_id: 2111220 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:25.145395+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:07:18.576147+00:00' + source_url: https://www.city.sakura.lg.jp/sakura/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sakura.lg.jp/sakura/images/icon/icon180.png + source_url: https://www.city.sakura.lg.jp/sakura/museum + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T15:07:18.576147+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.city.sakura.lg.jp/sakura/image/ogp.jpg + source_url: https://www.city.sakura.lg.jp/sakura/museum + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T15:07:18.576147+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-04-SAW-M-ITM.yaml b/data/custodian/JP-04-SAW-M-ITM.yaml index 0432107e77..26e7f7c068 100644 --- a/data/custodian/JP-04-SAW-M-ITM.yaml +++ b/data/custodian/JP-04-SAW-M-ITM.yaml @@ -387,3 +387,28 @@ location: geonames_id: 2111173 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:25.218487+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:07:28.455176+00:00' + source_url: https://www.city.katori.lg.jp/sightseeing/museum/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.katori.lg.jp/images/apple-touch-icon.png + source_url: https://www.city.katori.lg.jp/sightseeing/museum/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T15:07:28.455176+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.katori.lg.jp/images/ogp.png + source_url: https://www.city.katori.lg.jp/sightseeing/museum/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T15:07:28.455176+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-04-SHI-M-SATHM.yaml b/data/custodian/JP-04-SHI-M-SATHM.yaml index db39ec153e..8ae0828789 100644 --- a/data/custodian/JP-04-SHI-M-SATHM.yaml +++ b/data/custodian/JP-04-SHI-M-SATHM.yaml @@ -412,3 +412,22 @@ location: geonames_id: 2111127 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:25.488863+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:07:36.405889+00:00' + source_url: https://www.haniwakan.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.haniwakan.com/apple-touch-icon-180x180.png + source_url: https://www.haniwakan.com + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-23T15:07:36.405889+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: 17 diff --git a/data/custodian/JP-04-USU-M-IMIHF.yaml b/data/custodian/JP-04-USU-M-IMIHF.yaml index 0151e121f9..dc41e8211a 100644 --- a/data/custodian/JP-04-USU-M-IMIHF.yaml +++ b/data/custodian/JP-04-USU-M-IMIHF.yaml @@ -360,3 +360,28 @@ location: geonames_id: 2110624 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:25.618068+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:07:45.606715+00:00' + source_url: https://www.city.inzai.lg.jp/soshiki/11-7-4-0-0_1.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.inzai.lg.jp/design_img/favicon.ico + source_url: https://www.city.inzai.lg.jp/soshiki/11-7-4-0-0_1.html + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T15:07:45.606715+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.inzai.lg.jp/design_img/og_image.jpg + source_url: https://www.city.inzai.lg.jp/soshiki/11-7-4-0-0_1.html + css_selector: '[document] > html > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-23T15:07:45.606715+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-04-YAM-M-AWR.yaml b/data/custodian/JP-04-YAM-M-AWR.yaml index b4902f4b8c..fa9ec35566 100644 --- a/data/custodian/JP-04-YAM-M-AWR.yaml +++ b/data/custodian/JP-04-YAM-M-AWR.yaml @@ -1411,3 +1411,30 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/gA43ItlESbY/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:08:28.601410+00:00' + source_url: https://zounokuni.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://zounokuni.com/wp/wp-content/themes/animal/images/favicon.ico + source_url: https://zounokuni.com + css_selector: '[document] > html.wf-apertura-n7-active.wf-apertura-condensed-n7-active + > head > link' + retrieved_on: '2025-12-23T15:08:28.601410+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://zounokuni.com/wp/wp-content/themes/animal/images/ogimage.png + source_url: https://zounokuni.com + css_selector: '[document] > html.wf-apertura-n7-active.wf-apertura-condensed-n7-active + > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-23T15:08:28.601410+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-04-YOT-M-CZP.yaml b/data/custodian/JP-04-YOT-M-CZP.yaml index dc348c426e..c4d9649070 100644 --- a/data/custodian/JP-04-YOT-M-CZP.yaml +++ b/data/custodian/JP-04-YOT-M-CZP.yaml @@ -1813,3 +1813,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/M0w9FrOd5f0/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:08:43.220717+00:00' + source_url: https://www.city.chiba.jp/zoo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.chiba.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.chiba.jp/zoo + css_selector: '[document] > html > head.notranslate > link:nth-of-type(16)' + retrieved_on: '2025-12-23T15:08:43.220717+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.chiba.jp/shared/images/sns/logo.png + source_url: https://www.city.chiba.jp/zoo + css_selector: '[document] > html > head.notranslate > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T15:08:43.220717+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-04-YOT-M-KSM.yaml b/data/custodian/JP-04-YOT-M-KSM.yaml index 913a2ae57c..3e2d511e2d 100644 --- a/data/custodian/JP-04-YOT-M-KSM.yaml +++ b/data/custodian/JP-04-YOT-M-KSM.yaml @@ -360,3 +360,28 @@ location: geonames_id: 2110480 feature_code: PPLA2 normalization_timestamp: '2025-12-09T06:53:25.837895+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:08:55.111074+00:00' + source_url: https://www.city.chiba.jp/kasori/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.chiba.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.chiba.jp/kasori/index.html + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-23T15:08:55.111074+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.chiba.jp/shared/images/sns/logo.png + source_url: https://www.city.chiba.jp/kasori/index.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T15:08:55.111074+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-05-AKI-A-APA.yaml b/data/custodian/JP-05-AKI-A-APA.yaml index c149ac2cbd..527efee0c7 100644 --- a/data/custodian/JP-05-AKI-A-APA.yaml +++ b/data/custodian/JP-05-AKI-A-APA.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:35:50.067749+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-A-APA - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-A-APA valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-A-APA ghcid_numeric: 5995486548408841283 valid_from: '2025-12-06T23:35:50.067749+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: AKITA PREFECTURAL ARCHIVES @@ -180,8 +181,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q166118 label: archive - description: agency or institution responsible for the preservation and communication of records selected for permanent - preservation + description: agency or institution responsible for the preservation and communication + of records selected for permanent preservation wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -207,7 +208,7 @@ wikidata_enrichment: location: city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: JP postal_code: 010-0952 street_address: SANNO SHIMMACHI, Akita Shi, Akita Ken, 010-0952 @@ -222,3 +223,28 @@ location: geonames_id: 2113126 geonames_name: Akita feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:09:13.489490+00:00' + source_url: http://www.pref.akita.lg.jp/kobunsyo + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.akita.lg.jp/uploads/common/apple-touch-icon.png + source_url: http://www.pref.akita.lg.jp/kobunsyo + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T15:09:13.489490+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.akita.lg.jp/uploads/public/genre_0000012451_00/⑥.jpg + source_url: http://www.pref.akita.lg.jp/kobunsyo + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-23T15:09:13.489490+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-05-AKI-L-AIUL.yaml b/data/custodian/JP-05-AKI-L-AIUL.yaml index feb58448b6..bf035d6c9e 100644 --- a/data/custodian/JP-05-AKI-L-AIUL.yaml +++ b/data/custodian/JP-05-AKI-L-AIUL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:53.919528+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-L-AIUL - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-L-AIUL valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-L-AIUL ghcid_numeric: 10446791882850445212 valid_from: '2025-12-06T23:38:53.919528+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: Akita International University Library @@ -189,7 +190,7 @@ wikidata_enrichment: location: city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: JP postal_code: 010-1292 street_address: 193-2 YUWA TSUBAKIGAWA OKUTSUBAKIDAI, Akita Shi, Akita Ken, 010-1292 @@ -204,3 +205,22 @@ location: geonames_id: 2113126 geonames_name: Akita feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:09:29.277149+00:00' + source_url: http://web.aiu.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://web.aiu.ac.jp/wp-content/themes/aiu/lib/common/img/favicon.ico + source_url: http://web.aiu.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(15)' + retrieved_on: '2025-12-23T15:09:29.277149+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-05-AKI-L-APUL.yaml b/data/custodian/JP-05-AKI-L-APUL.yaml index 755212bea9..4511ad1585 100644 --- a/data/custodian/JP-05-AKI-L-APUL.yaml +++ b/data/custodian/JP-05-AKI-L-APUL.yaml @@ -20,7 +20,8 @@ original_entry: city: Akita Shi region: Akita Ken postal_code: 010-0195 - street_address: 241-438 SHIMOSHINJO NAKANO KAIDOUBATA NISHI, Akita Shi, Akita Ken, 010-0195 + street_address: 241-438 SHIMOSHINJO NAKANO KAIDOUBATA NISHI, Akita Shi, Akita + Ken, 010-0195 processing_timestamp: '2025-12-06T23:38:53.908532+00:00' ghcid: ghcid_current: JP-05-AKI-L-APUL @@ -32,18 +33,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:53.908532+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-L-APUL - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-L-APUL valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-L-APUL ghcid_numeric: 18239345105737307760 valid_from: '2025-12-06T23:38:53.908532+00:00' @@ -101,8 +103,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Akita Prefectural University Library @@ -187,17 +189,19 @@ wikidata_enrichment: member_of: - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: https://libwww.akita-pu.ac.jp/drupal/ wikidata_official_website: https://libwww.akita-pu.ac.jp/drupal/ location: city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: JP postal_code: 010-0195 - street_address: 241-438 SHIMOSHINJO NAKANO KAIDOUBATA NISHI, Akita Shi, Akita Ken, 010-0195 + street_address: 241-438 SHIMOSHINJO NAKANO KAIDOUBATA NISHI, Akita Shi, Akita Ken, + 010-0195 normalization_timestamp: '2025-12-09T14:48:04.073397+00:00' latitude: 39.71667 longitude: 140.11667 @@ -209,3 +213,22 @@ location: geonames_id: 2113126 geonames_name: Akita feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:11:02.385495+00:00' + source_url: https://libwww.akita-pu.ac.jp/drupal + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://libwww.akita-pu.ac.jp/opac/images/cyan/favicon.ico + source_url: https://libwww.akita-pu.ac.jp/drupal + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-23T15:11:02.385495+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-05-AKI-L-AUL.yaml b/data/custodian/JP-05-AKI-L-AUL.yaml index 37ee6970bf..832c7f9f20 100644 --- a/data/custodian/JP-05-AKI-L-AUL.yaml +++ b/data/custodian/JP-05-AKI-L-AUL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:53.187763+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-L-AUL - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-L-AUL valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-L-AUL ghcid_numeric: 15842340777454129267 valid_from: '2025-12-06T23:38:53.187763+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: Akita University Library @@ -187,14 +188,15 @@ wikidata_enrichment: member_of: - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.lib.akita-u.ac.jp wikidata_official_website: http://www.lib.akita-u.ac.jp location: city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: JP postal_code: 010-8502 street_address: 1-1 TEGATA GAKUEMMACHI, Akita Shi, Akita Ken, 010-8502 @@ -209,3 +211,22 @@ location: geonames_id: 2113126 geonames_name: Akita feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:11:22.717634+00:00' + source_url: http://www.lib.akita-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.akita-u.ac.jp/top/sites/default/files/akita.png + source_url: http://www.lib.akita-u.ac.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T15:11:22.717634+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-05-AKI-L-AUMSL.yaml b/data/custodian/JP-05-AKI-L-AUMSL.yaml index 815f5ece47..bed0db8cf2 100644 --- a/data/custodian/JP-05-AKI-L-AUMSL.yaml +++ b/data/custodian/JP-05-AKI-L-AUMSL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:53.190283+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-L-AUMSL - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-L-AUMSL valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-L-AUMSL ghcid_numeric: 824083086115892761 valid_from: '2025-12-06T23:38:53.190283+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: Akita University Medical School Library @@ -189,7 +190,7 @@ wikidata_enrichment: location: city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: JP postal_code: 010-8543 street_address: 1-1-1 HONDO, Akita Shi, Akita Ken, 010-8543 @@ -204,3 +205,22 @@ location: geonames_id: 2113126 geonames_name: Akita feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:11:30.385917+00:00' + source_url: http://www.lib.akita-u.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.akita-u.ac.jp/top/sites/default/files/akita.png + source_url: http://www.lib.akita-u.ac.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-23T15:11:30.385917+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-05-AKI-L-NAUL.yaml b/data/custodian/JP-05-AKI-L-NAUL.yaml index 82db5c0062..1af46b306c 100644 --- a/data/custodian/JP-05-AKI-L-NAUL.yaml +++ b/data/custodian/JP-05-AKI-L-NAUL.yaml @@ -32,18 +32,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:54.483162+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-L-NAUL - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-L-NAUL valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-L-NAUL ghcid_numeric: 15019107386973043899 valid_from: '2025-12-06T23:38:54.483162+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: North Asia University Library @@ -194,7 +195,7 @@ wikidata_enrichment: location: city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: JP postal_code: 010-8515 street_address: 46-1 SHIMOKITATE SAKURA MAMORISAWA, Akita Shi, Akita Ken, 010-8515 @@ -209,3 +210,22 @@ location: geonames_id: 2113126 geonames_name: Akita feature_code: PPLA +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:11:54.759735+00:00' + source_url: http://www.nau.ac.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nau.ac.jp/assets/themes/custom/apple-touch-icon.png + source_url: http://www.nau.ac.jp/lib + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-23T15:11:54.759735+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-05-AKI-M-ACFPAHC.yaml b/data/custodian/JP-05-AKI-M-ACFPAHC.yaml index 30214a34f7..466e111471 100644 --- a/data/custodian/JP-05-AKI-M-ACFPAHC.yaml +++ b/data/custodian/JP-05-AKI-M-ACFPAHC.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:30.997053+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-M-ACFPAHC - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-M-ACFPAHC valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-M-ACFPAHC ghcid_numeric: 8888610542950353323 valid_from: '2025-12-06T23:38:30.997053+00:00' @@ -280,8 +281,41 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: *id006 postal_code: 010-0921 street_address: OMACHI, Akita Shi, Akita Ken, 010-0921 normalization_timestamp: '2025-12-09T10:55:21.372904+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:12:07.799589+00:00' + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T15:12:07.799589+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秋田市公式サイト + - claim_type: favicon_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T15:12:07.799589+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T15:12:07.799589+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-05-AKI-M-ACHMAFR.yaml b/data/custodian/JP-05-AKI-M-ACHMAFR.yaml index b3732277e0..eedfa9f25a 100644 --- a/data/custodian/JP-05-AKI-M-ACHMAFR.yaml +++ b/data/custodian/JP-05-AKI-M-ACHMAFR.yaml @@ -34,18 +34,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:31.017492+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-M-ACHMAFR - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-M-ACHMAFR valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-M-ACHMAFR ghcid_numeric: 14272761968911068585 valid_from: '2025-12-06T23:38:31.017492+00:00' @@ -231,8 +232,41 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: *id005 postal_code: 011-0907 street_address: TERAUCHI YAKEYAMA, Akita Shi, Akita Ken, 011-0907 normalization_timestamp: '2025-12-09T10:55:21.410263+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:12:16.549544+00:00' + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003616 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003616 + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T15:12:16.549544+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秋田市公式サイト + - claim_type: favicon_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003616 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T15:12:16.549544+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003616 + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-23T15:12:16.549544+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-05-AKI-M-APCH.yaml b/data/custodian/JP-05-AKI-M-APCH.yaml index f9f74db3a3..178f68bd3c 100644 --- a/data/custodian/JP-05-AKI-M-APCH.yaml +++ b/data/custodian/JP-05-AKI-M-APCH.yaml @@ -199,3 +199,23 @@ wikidata_enrichment: image: Akita Prefectural Children's Hall 20200328.jpg commons_category: Akita Prefectural Children's Hall wikidata_image: Akita Prefectural Children's Hall 20200328.jpg +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:17:21.759259+00:00' + source_url: http://akita-jidoukaikan.com + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://akita-jidoukaikan.com/wp-content/uploads/2024/09/d1929d7b0f624021a1ad802729eee8ee.png?1766502751 + source_url: http://akita-jidoukaikan.com + css_selector: '#js-header-sp > div.l-header__inner.u-flex > div.l-header__logo.u-flex-align-center + > h1.l-header__logo-image.u-flex-align-center > a.c-logo > img.c-logo__image' + retrieved_on: '2025-12-23T15:17:21.759259+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秋田県児童会館「みらいあ」 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-05-AKI-M-OKFH.yaml b/data/custodian/JP-05-AKI-M-OKFH.yaml index 5454a01279..dc90cb6501 100644 --- a/data/custodian/JP-05-AKI-M-OKFH.yaml +++ b/data/custodian/JP-05-AKI-M-OKFH.yaml @@ -38,18 +38,19 @@ ghcid: generation_timestamp: '2025-12-06T23:38:31.002390+00:00' location_resolution: country_code: JP - region_code: 05 + region_code: 5 city_code: AKI method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-05-AKI-M-OKFH - valid_from: "2025-12-10T09:43:28Z" + valid_from: '2025-12-10T09:43:28Z' valid_to: null - reason: "Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO 3166-2:JP" + reason: Corrected region code from JP-AK (abbreviation) to JP-05 (Akita) per ISO + 3166-2:JP - ghcid: JP-AK-AKI-M-OKFH valid_from: null - valid_to: "2025-12-10T09:43:28Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:43:28Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-AK-AKI-M-OKFH ghcid_numeric: 10991061981091810738 valid_from: '2025-12-06T23:38:31.002390+00:00' @@ -280,8 +281,41 @@ location: source_path: wikidata_enrichment.wikidata_coordinates city: Akita Shi region: Akita Ken - region_code: 05 + region_code: 5 country: *id006 postal_code: 010-0921 street_address: OMACHI, Akita Shi, Akita Ken, 010-0921 normalization_timestamp: '2025-12-09T10:55:21.542681+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-23T15:18:01.859894+00:00' + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-23T15:18:01.859894+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 秋田市公式サイト + - claim_type: favicon_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-23T15:18:01.859894+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.akita.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: https://www.city.akita.lg.jp/kanko/kanrenshisetsu/1003617 + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-23T15:18:01.859894+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/NL-DR-ASS-M-SDM.yaml b/data/custodian/NL-DR-ASS-M-SDM.yaml index 023d2f037f..f8949996fb 100644 --- a/data/custodian/NL-DR-ASS-M-SDM.yaml +++ b/data/custodian/NL-DR-ASS-M-SDM.yaml @@ -70,3 +70,11 @@ provenance: notes: - Created from unmatched LinkedIn company profile - 'Location resolution method: GEONAMES_LOOKUP' +wikidata_enrichment: + wikidata_id: Q137271106 + wikidata_url: https://www.wikidata.org/wiki/Q137271106 + label: Stichting Steunfonds Drents Museum + description: nonprofit organisation from the Netherlands + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Dutch label available, using institution name as label diff --git a/data/custodian/NL-DR-ASS-M-TM.yaml b/data/custodian/NL-DR-ASS-M-TM.yaml index 165259665d..aaee4cc13a 100644 --- a/data/custodian/NL-DR-ASS-M-TM.yaml +++ b/data/custodian/NL-DR-ASS-M-TM.yaml @@ -95,3 +95,10 @@ provenance: - 'Location resolved: Weiersstraat 1, 9401 JH Assen (Drenthe)' - Province corrected from OV to DR - Assen is capital of Drenthe - Museum dedicated to TT Circuit Assen motorcycle racing history +wikidata_enrichment: + wikidata_id: null + label: TT Museum + description: museum in Assen, Netherlands + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution diff --git a/data/custodian/NL-DR-ERI-M-ISM.yaml b/data/custodian/NL-DR-ERI-M-ISM.yaml index 087ec654c0..de957c7a0a 100644 --- a/data/custodian/NL-DR-ERI-M-ISM.yaml +++ b/data/custodian/NL-DR-ERI-M-ISM.yaml @@ -108,3 +108,10 @@ provenance: - Province corrected from Gelderland (GE) to Drenthe (DR) based on web search - Location resolved to Erica based on official smalspoorcentrum.nl website - Full name corrected to Industrieel Smalspoor Museum +wikidata_enrichment: + wikidata_id: Q1911968 + wikidata_url: https://www.wikidata.org/wiki/Q1911968 + label: Industrieel Smalspoor Museum + description: museum in Drenthe + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup diff --git a/data/custodian/NL-DR-MEP-M-MI.yaml b/data/custodian/NL-DR-MEP-M-MI.yaml index 6e62889a75..d272322ebf 100644 --- a/data/custodian/NL-DR-MEP-M-MI.yaml +++ b/data/custodian/NL-DR-MEP-M-MI.yaml @@ -73,3 +73,10 @@ provenance: notes: - Created from unmatched LinkedIn company profile - 'Location resolution method: GEONAMES_LOOKUP' +wikidata_enrichment: + wikidata_id: null + label: Museum Indruk + description: museum in Meppel, Netherlands + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution diff --git a/data/custodian/NL-DR-MEP-M-SMM.yaml b/data/custodian/NL-DR-MEP-M-SMM.yaml index c1d2747b3a..1205e79439 100644 --- a/data/custodian/NL-DR-MEP-M-SMM.yaml +++ b/data/custodian/NL-DR-MEP-M-SMM.yaml @@ -85,3 +85,11 @@ provenance: notes: - Created from unmatched LinkedIn company profile - 'Location resolution method: GEONAMES_LOOKUP' +wikidata_enrichment: + wikidata_id: Q111991796 + wikidata_url: https://www.wikidata.org/wiki/Q111991796 + label: Stedelijk Museum Meppel + description: museum in Meppel, Netherlands + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Dutch description available on Wikidata diff --git a/data/custodian/NL-DR-NIE-M-KMG.yaml b/data/custodian/NL-DR-NIE-M-KMG.yaml index cd79045bdc..1cd980583a 100644 --- a/data/custodian/NL-DR-NIE-M-KMG.yaml +++ b/data/custodian/NL-DR-NIE-M-KMG.yaml @@ -101,3 +101,11 @@ provenance: - Created from unmatched LinkedIn company profile - 'Location resolution method: WEB_RESEARCH' - City code updated from XXX to NIE (Nieuw-Buinen) on 2025-12-20 +wikidata_enrichment: + wikidata_id: Q106977687 + wikidata_url: https://www.wikidata.org/wiki/Q106977687 + label: Keramisch Museum Goedewaagen + description: museum in Nieuw-Buinen, Netherlands + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Dutch description available on Wikidata diff --git a/data/custodian/NL-DR-NIS-M-MJ-museum_janning.yaml b/data/custodian/NL-DR-NIS-M-MJ-museum_janning.yaml index 29fc470659..4878fc15de 100644 --- a/data/custodian/NL-DR-NIS-M-MJ-museum_janning.yaml +++ b/data/custodian/NL-DR-NIS-M-MJ-museum_janning.yaml @@ -87,3 +87,10 @@ provenance: - Reverted incorrect location enrichment on 2025-12-17 - LinkedIn HTML extraction was extracting wrong company's data - 'Location enriched on 2025-12-17 via Exa web search: Nieuw Schoonebeek, Drenthe' +wikidata_enrichment: + wikidata_id: null + label: Museum Janning + description: museum in Nieuw Schoonebeek, Netherlands + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup + notes: No Wikidata entry found for this institution (Q27032770 is a painting by Hein Janning, not the museum) diff --git a/data/custodian/NL-DR-ORV-M-JKM.yaml b/data/custodian/NL-DR-ORV-M-JKM.yaml index 0a6a4283c8..9116346f09 100644 --- a/data/custodian/NL-DR-ORV-M-JKM.yaml +++ b/data/custodian/NL-DR-ORV-M-JKM.yaml @@ -70,3 +70,10 @@ provenance: notes: - Created from unmatched LinkedIn company profile - 'Location resolution method: GEONAMES_LOOKUP' +wikidata_enrichment: + wikidata_id: Q66985422 + wikidata_url: https://www.wikidata.org/wiki/Q66985422 + label: Jan Kruis Museum + description: museum in Orvelte, Nederland + enrichment_timestamp: '2025-12-23T00:00:00Z' + enrichment_method: manual_wikidata_lookup diff --git a/frontend/public/schemas/20251121/linkml/manifest.json b/frontend/public/schemas/20251121/linkml/manifest.json index 782f49d588..b77f85a747 100644 --- a/frontend/public/schemas/20251121/linkml/manifest.json +++ b/frontend/public/schemas/20251121/linkml/manifest.json @@ -1,5 +1,5 @@ { - "generated": "2025-12-23T12:25:14.109Z", + "generated": "2025-12-23T14:47:28.725Z", "version": "1.0.0", "categories": [ { @@ -737,6 +737,11 @@ "path": "modules/classes/LiteraryArchive.yaml", "category": "classes" }, + { + "name": "LLMResponse", + "path": "modules/classes/LLMResponse.yaml", + "category": "classes" + }, { "name": "LocalGovernmentArchive", "path": "modules/classes/LocalGovernmentArchive.yaml", diff --git a/frontend/public/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml b/frontend/public/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml index 26e95c1a85..b373b4760b 100644 --- a/frontend/public/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml +++ b/frontend/public/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml @@ -17,6 +17,7 @@ prefixes: imports: - linkml:types - ../metadata + - ./LLMResponse default_range: string @@ -72,6 +73,7 @@ classes: - linkedin_url - cost_usd - request_id + - llm_response slot_usage: source_file: @@ -175,6 +177,48 @@ classes: examples: - value: "exa_12345678-abcd-efgh-ijkl-mnopqrstuv" description: "Exa API request ID" + + llm_response: + description: | + Full LLM response provenance including reasoning_content. + + Captures GLM 4.7 Thinking Modes (Interleaved, Preserved, Turn-level) + for extractions that use LLM processing. + + **PROV-O Alignment**: + - The LLMResponse IS a sub-activity (prov:qualifiedGeneration) + - Provides detailed audit trail of LLM inference for the extraction + + **Use Cases**: + - LinkedIn profile extraction with GLM 4.7 reasoning + - Web content extraction with chain-of-thought logging + - Staff list processing with schema conformity validation + + **When to Include**: + - extraction_method is exa_crawling_glm47 + - Any extraction involving LLM processing + - When reasoning_content provides valuable audit trail + slot_uri: prov:qualifiedGeneration + range: LLMResponse + required: false + inlined: true + examples: + - value: | + { + "content": "Extracted institution data...", + "reasoning_content": "Analyzing the input for LinkML schema conformity...", + "thinking_mode": "preserved", + "clear_thinking": false, + "model": "glm-4.7", + "provider": "zai", + "created": "2025-12-23T10:30:00Z", + "prompt_tokens": 150, + "completion_tokens": 450, + "total_tokens": 600, + "finish_reason": "stop", + "cost_usd": 0.0 + } + description: "GLM 4.7 response with Preserved Thinking for extraction" comments: - "Every person entity file MUST have extraction_metadata" @@ -255,3 +299,7 @@ slots: request_id: description: "Unique request ID from extraction service" range: string + + llm_response: + description: "Full LLM response with reasoning provenance (GLM 4.7 Thinking Modes)" + range: LLMResponse diff --git a/frontend/public/schemas/20251121/linkml/modules/classes/LLMResponse.yaml b/frontend/public/schemas/20251121/linkml/modules/classes/LLMResponse.yaml new file mode 100644 index 0000000000..b4eed2315e --- /dev/null +++ b/frontend/public/schemas/20251121/linkml/modules/classes/LLMResponse.yaml @@ -0,0 +1,529 @@ +# LLM Response Class +# Provenance for LLM API responses with GLM 4.7 Thinking Modes +# Captures reasoning_content for Interleaved, Preserved, and Turn-level Thinking + +id: https://nde.nl/ontology/hc/class/LLMResponse +name: llm_response_class +title: LLM Response Class +version: 1.0.0 + +prefixes: + linkml: https://w3id.org/linkml/ + hc: https://nde.nl/ontology/hc/ + schema: http://schema.org/ + prov: http://www.w3.org/ns/prov# + dct: http://purl.org/dc/terms/ + xsd: http://www.w3.org/2001/XMLSchema# + +imports: + - linkml:types + - ../metadata + +default_range: string + +classes: + + LLMResponse: + class_uri: prov:Activity + description: | + Provenance metadata for LLM API responses, including GLM 4.7 Thinking Modes. + + Captures complete response metadata from LLM providers (ZhipuAI GLM, Anthropic, + OpenAI, etc.) for traceability and analysis. The key innovation is capturing + `reasoning_content` - the chain-of-thought reasoning that GLM 4.7 exposes + through its three thinking modes. + + **GLM 4.7 Thinking Modes** (https://docs.z.ai/guides/capabilities/thinking-mode): + + 1. **Interleaved Thinking** (default, since GLM-4.5): + - Model thinks between tool calls and after receiving tool results + - Enables complex, step-by-step reasoning with tool chaining + - Returns `reasoning_content` alongside `content` in every response + + 2. **Preserved Thinking** (new in GLM-4.7): + - Retains reasoning_content from previous assistant turns in context + - Preserves reasoning continuity across multi-turn conversations + - Improves model performance and increases cache hit rates + - **Enabled by default on Coding Plan endpoint** + - Requires returning EXACT, UNMODIFIED reasoning_content back to API + - Set via: `"clear_thinking": false` (do NOT clear previous reasoning) + + 3. **Turn-level Thinking** (new in GLM-4.7): + - Control reasoning computation on a per-turn basis + - Enable/disable thinking independently for each request in a session + - Useful for balancing speed (simple queries) vs accuracy (complex tasks) + - Set via: `"thinking": {"type": "enabled"}` or `"thinking": {"type": "disabled"}` + + **Critical Implementation Note for Preserved Thinking**: + When using Preserved Thinking with tool calls, thinking blocks MUST be: + 1. Explicitly preserved in the messages array + 2. Returned together with tool results + 3. Kept in EXACT original sequence (no reordering/editing) + + **PROV-O Alignment**: + - LLMResponse IS a prov:Activity (the inference process) + - content IS prov:Entity (the generated output) + - model/provider IS prov:Agent (the AI system) + - reasoning_content documents the prov:Plan (how the agent reasoned) + - prompt (input) IS prov:used (input to the activity) + + **Use Cases**: + - DSPy RAG responses with reasoning traces + - Heritage institution extraction provenance + - LinkML schema conformity validation + - Ontology mapping decision logs + - Multi-turn agent conversations with preserved context + + **Example JSON Structure (GLM 4.7 with Preserved Thinking)**: + ```json + { + "llm_response": { + "content": "The Rijksmuseum is a museum in Amsterdam...", + "reasoning_content": "The user is asking about heritage institutions. Let me identify the key entities: 1) Rijksmuseum is the institution name, 2) It's a museum (institution_type: MUSEUM), 3) Located in Amsterdam (city)...", + "thinking_mode": "preserved", + "clear_thinking": false, + "model": "glm-4.7", + "provider": "zai", + "request_id": "req_abc123", + "created": "2025-12-23T10:30:00Z", + "prompt_tokens": 150, + "completion_tokens": 450, + "total_tokens": 600, + "cached_tokens": 50, + "finish_reason": "stop", + "latency_ms": 1250, + "cost_usd": 0.0 + } + } + ``` + + exact_mappings: + - prov:Activity + close_mappings: + - schema:Action + - schema:CreativeWork + + slots: + - content + - reasoning_content + - thinking_mode + - clear_thinking + - model + - provider + - request_id + - created + - prompt_tokens + - completion_tokens + - total_tokens + - cached_tokens + - finish_reason + - latency_ms + - cost_usd + + slot_usage: + content: + description: | + The final LLM response text (message.content from API response). + PROV-O: prov:generated - the entity produced by this activity. + + This is the primary output shown to users and used for downstream processing. + slot_uri: prov:generated + range: string + required: true + examples: + - value: "The Rijksmuseum is a national museum in Amsterdam dedicated to Dutch arts and history." + description: "Extracted heritage institution description" + + reasoning_content: + description: | + Interleaved Thinking - the model's chain-of-thought reasoning. + PROV-O: prov:hadPlan - documents HOW the agent reasoned. + + **GLM 4.7 Interleaved Thinking**: + GLM 4.7 returns `reasoning_content` in every response, exposing the + model's step-by-step reasoning process. This enables: + + 1. **Schema Validation**: Model reasons about LinkML constraints before generating output + 2. **Ontology Mapping**: Explicit reasoning about CIDOC-CRM, CPOV, TOOI class mappings + 3. **RDF Quality**: Chain-of-thought validates triple construction + 4. **Transparency**: Full audit trail of extraction decisions + + **DSPy Integration**: + When using DSPy, reasoning_content can be used to: + - Validate signature conformity + - Debug failed extractions + - Improve prompt engineering + - Train on successful reasoning patterns + + May be null for providers that don't expose reasoning (Claude, GPT-4). + slot_uri: prov:hadPlan + range: string + required: false + examples: + - value: "The user is asking about Dutch heritage institutions. I need to identify: 1) Institution name: Rijksmuseum, 2) Type: Museum (maps to InstitutionTypeEnum.MUSEUM), 3) Location: Amsterdam (city in Noord-Holland province)..." + description: "GLM 4.7 interleaved thinking showing explicit schema reasoning" + + model: + description: | + The LLM model identifier from the API response. + PROV-O: Part of prov:wasAssociatedWith - identifies the specific model version. + + Common values: + - glm-4.7: ZhipuAI GLM 4.7 (with Interleaved Thinking) + - glm-4.6: ZhipuAI GLM 4.6 + - claude-3-opus-20240229: Anthropic Claude Opus + - gpt-4-turbo: OpenAI GPT-4 Turbo + slot_uri: schema:softwareVersion + range: string + required: true + examples: + - value: "glm-4.7" + description: "ZhipuAI GLM 4.7 with Interleaved Thinking" + + provider: + description: | + The LLM provider/platform. + PROV-O: prov:wasAssociatedWith - the agent (organization) providing the model. + + Used by DSPy to route requests and track provider-specific behavior. + slot_uri: prov:wasAssociatedWith + range: LLMProviderEnum + required: true + examples: + - value: "zai" + description: "ZhipuAI (Z.AI) - GLM models" + + request_id: + description: | + Unique request ID from the LLM provider API (for tracing/debugging). + Enables correlation with provider logs for troubleshooting. + slot_uri: dct:identifier + range: string + required: false + examples: + - value: "req_8f3a2b1c4d5e6f7g" + description: "Provider-assigned request identifier" + + created: + description: | + Timestamp when the LLM response was generated (from API response). + PROV-O: prov:endedAtTime - when the inference activity completed. + slot_uri: prov:endedAtTime + range: datetime + required: true + examples: + - value: "2025-12-23T10:30:00Z" + description: "UTC timestamp of response generation" + + prompt_tokens: + description: | + Number of tokens in the input prompt. + From API response: usage.prompt_tokens + slot_uri: schema:value + range: integer + minimum_value: 0 + examples: + - value: 150 + description: "150 tokens in the input prompt" + + completion_tokens: + description: | + Number of tokens in the model's response (content + reasoning_content). + From API response: usage.completion_tokens + + Note: For GLM 4.7, this includes tokens from both content and reasoning_content. + slot_uri: schema:value + range: integer + minimum_value: 0 + examples: + - value: 450 + description: "450 tokens in the completion (content + reasoning)" + + total_tokens: + description: | + Total tokens used (prompt + completion). + From API response: usage.total_tokens + slot_uri: schema:value + range: integer + minimum_value: 0 + examples: + - value: 600 + description: "600 total tokens (150 prompt + 450 completion)" + + cached_tokens: + description: | + Number of prompt tokens served from cache (if provider supports caching). + From API response: usage.prompt_tokens_details.cached_tokens + + Cached tokens typically have reduced cost and latency. + slot_uri: schema:value + range: integer + minimum_value: 0 + required: false + examples: + - value: 50 + description: "50 tokens served from provider's prompt cache" + + finish_reason: + description: | + Why the model stopped generating (from API response). + + Common values: + - stop: Natural completion (hit stop token) + - length: Hit max_tokens limit + - tool_calls: Model invoked a tool (function calling) + - content_filter: Response filtered for safety + slot_uri: schema:status + range: FinishReasonEnum + required: false + examples: + - value: "stop" + description: "Model completed naturally" + + latency_ms: + description: | + Response latency in milliseconds (time from request to response). + Measured client-side (includes network time). + slot_uri: schema:duration + range: integer + minimum_value: 0 + required: false + examples: + - value: 1250 + description: "1.25 seconds total response time" + + cost_usd: + description: | + Estimated cost in USD for this LLM call. + + For Z.AI Coding Plan: $0.00 (free tier for GLM models) + For other providers: calculated from token counts and pricing + slot_uri: schema:price + range: float + minimum_value: 0.0 + required: false + examples: + - value: 0.0 + description: "Free (Z.AI Coding Plan)" + - value: 0.015 + description: "OpenAI GPT-4 Turbo cost estimate" + + thinking_mode: + description: | + The GLM 4.7 thinking mode used for this request. + + **Available Modes**: + - **enabled**: Thinking enabled (default) - model reasons before responding + - **disabled**: Thinking disabled - faster responses, no reasoning_content + - **interleaved**: Interleaved thinking - think between tool calls (default behavior) + - **preserved**: Preserved thinking - retain reasoning across turns (Coding Plan default) + + **Configuration**: + - Interleaved: Default behavior, no config needed + - Preserved: Set `"clear_thinking": false` + - Turn-level: Set `"thinking": {"type": "enabled"}` or `"thinking": {"type": "disabled"}` + slot_uri: schema:actionOption + range: ThinkingModeEnum + required: false + examples: + - value: "preserved" + description: "Preserved thinking for multi-turn agent conversations" + - value: "interleaved" + description: "Default interleaved thinking between tool calls" + - value: "disabled" + description: "Disabled for fast, simple queries" + + clear_thinking: + description: | + Whether to clear previous reasoning_content from context. + + **Preserved Thinking Control**: + - **false**: Preserved Thinking enabled (keep reasoning, better cache hits) + - **true**: Clear previous reasoning (default for standard API) + + **Z.AI Coding Plan**: Default is `false` (Preserved Thinking enabled) + + **Critical Implementation Note**: + When clear_thinking is false, you MUST return the EXACT, UNMODIFIED + reasoning_content back to the API in subsequent turns. Any modification + (reordering, editing, truncating) will degrade performance and cache hits. + slot_uri: schema:Boolean + range: boolean + required: false + examples: + - value: false + description: "Keep reasoning for Preserved Thinking (recommended)" + - value: true + description: "Clear previous reasoning (fresh context each turn)" + + comments: + - "reasoning_content is the key field for Interleaved Thinking (GLM 4.7)" + - "Store reasoning_content for debugging, auditing, and DSPy optimization" + - "Z.AI Coding Plan endpoint: https://api.z.ai/api/coding/paas/v4/chat/completions" + - "For DSPy: use LLMResponse to track all LLM calls in the pipeline" + - "See AGENTS.md Rule 11 for Z.AI API configuration" + + see_also: + - "https://www.w3.org/TR/prov-o/" + - "https://api.z.ai/docs" + - "https://dspy-docs.vercel.app/" + +enums: + LLMProviderEnum: + description: | + Enumeration of LLM providers/platforms supported by DSPy integration. + Used for routing, cost tracking, and provider-specific behavior. + permissible_values: + zai: + description: | + ZhipuAI (Z.AI) - Chinese AI provider offering GLM models. + Primary provider for this project via Z.AI Coding Plan. + Endpoint: https://api.z.ai/api/coding/paas/v4/chat/completions + Models: glm-4.5, glm-4.6, glm-4.7 (with Interleaved Thinking) + meaning: schema:Organization + anthropic: + description: | + Anthropic - Provider of Claude models. + Models: claude-3-opus, claude-3-sonnet, claude-3-haiku + meaning: schema:Organization + openai: + description: | + OpenAI - Provider of GPT models. + Models: gpt-4-turbo, gpt-4o, gpt-3.5-turbo + meaning: schema:Organization + huggingface: + description: | + HuggingFace - Open model hosting and inference. + Models: Various open-source models via Inference API + meaning: schema:Organization + groq: + description: | + Groq - High-speed inference provider. + Models: llama, mixtral, gemma via Groq hardware + meaning: schema:Organization + together: + description: | + Together AI - Open model inference platform. + Models: Various open-source models + meaning: schema:Organization + local: + description: | + Local inference (Ollama, llama.cpp, vLLM). + No external API calls, runs on local hardware. + meaning: schema:SoftwareApplication + + FinishReasonEnum: + description: | + Reasons why the LLM stopped generating output. + Standardized across providers. + permissible_values: + stop: + description: "Natural completion - model hit a stop token or finished" + length: + description: "Hit max_tokens limit - response was truncated" + tool_calls: + description: "Model invoked a tool/function (function calling)" + content_filter: + description: "Response was filtered for safety/content policy" + error: + description: "Generation failed due to an error" + + ThinkingModeEnum: + description: | + GLM 4.7 thinking mode configuration. + Controls how the model reasons during inference. + + **Reference**: https://docs.z.ai/guides/capabilities/thinking-mode + + GLM 4.7 introduces three distinct thinking modes that can be combined: + 1. Interleaved Thinking (between tool calls) + 2. Preserved Thinking (across conversation turns) + 3. Turn-level Thinking (enable/disable per request) + permissible_values: + enabled: + description: | + Thinking enabled (turn-level setting). + Model reasons before responding, returns reasoning_content. + Set via: `"thinking": {"type": "enabled"}` + meaning: schema:ActivateAction + disabled: + description: | + Thinking disabled (turn-level setting). + Faster responses, no reasoning_content returned. + Useful for simple queries where speed matters more than accuracy. + Set via: `"thinking": {"type": "disabled"}` + meaning: schema:DeactivateAction + interleaved: + description: | + Interleaved thinking mode (default since GLM-4.5). + Model thinks between tool calls and after receiving tool results. + Enables complex, step-by-step reasoning with tool chaining. + No special configuration needed - this is the default behavior. + meaning: schema:Action + preserved: + description: | + Preserved thinking mode (new in GLM-4.7). + Retains reasoning_content from previous assistant turns in context. + Improves model performance and increases cache hit rates. + **Enabled by default on Z.AI Coding Plan endpoint**. + Set via: `"clear_thinking": false` + + CRITICAL: Must return EXACT, UNMODIFIED reasoning_content back to API. + meaning: schema:Action + +slots: + content: + description: "The final LLM response text" + range: string + + reasoning_content: + description: "Interleaved Thinking - chain-of-thought reasoning from GLM 4.7" + range: string + + model: + description: "LLM model identifier" + range: string + + provider: + description: "LLM provider/platform" + range: LLMProviderEnum + + created: + description: "Timestamp when response was generated" + range: datetime + + prompt_tokens: + description: "Number of tokens in input prompt" + range: integer + + completion_tokens: + description: "Number of tokens in response" + range: integer + + total_tokens: + description: "Total tokens used" + range: integer + + cached_tokens: + description: "Number of tokens served from cache" + range: integer + + finish_reason: + description: "Why the model stopped generating" + range: FinishReasonEnum + + latency_ms: + description: "Response latency in milliseconds" + range: integer + + cost_usd: + description: "API cost in USD for this LLM call" + range: float + + thinking_mode: + description: "GLM 4.7 thinking mode configuration" + range: ThinkingModeEnum + + clear_thinking: + description: "Whether to clear previous reasoning from context (false = Preserved Thinking)" + range: boolean diff --git a/frontend/src/pages/LinkMLViewerPage.tsx b/frontend/src/pages/LinkMLViewerPage.tsx index 0828452211..5ce59f25df 100644 --- a/frontend/src/pages/LinkMLViewerPage.tsx +++ b/frontend/src/pages/LinkMLViewerPage.tsx @@ -37,6 +37,9 @@ import { getCustodianTypesForClass, getCustodianTypesForSlot, getCustodianTypesForEnum, + getCustodianTypesForClassAsync, + getCustodianTypesForSlotAsync, + getCustodianTypesForEnumAsync, isUniversalElement, } from '../lib/schema-custodian-mapping'; import './LinkMLViewerPage.css'; @@ -655,6 +658,13 @@ const LinkMLViewerPage: React.FC = () => { const [enumSearchFilters, setEnumSearchFilters] = useState>({}); const [enumShowAll, setEnumShowAll] = useState>({}); + // State for pre-loaded custodian types (loaded async from schema annotations) + // Maps element name -> custodian type codes + const [classCustodianTypes, setClassCustodianTypes] = useState>({}); + const [slotCustodianTypes, setSlotCustodianTypes] = useState>({}); + const [enumCustodianTypes, setEnumCustodianTypes] = useState>({}); + const [_custodianTypesLoaded, setCustodianTypesLoaded] = useState(false); + // State for sidebar search and category filters const [sidebarSearch, setSidebarSearch] = useState(''); const [categoryFilters, setCategoryFilters] = useState>({ @@ -854,6 +864,80 @@ const LinkMLViewerPage: React.FC = () => { loadSelectedSchema(); }, [selectedSchema]); + // Load custodian types from schema annotations when schema changes + // This pre-loads types asynchronously so they're available for rendering + useEffect(() => { + if (!schema) { + setCustodianTypesLoaded(false); + return; + } + + const loadCustodianTypes = async () => { + const classes = extractClasses(schema); + const slots = extractSlots(schema); + const enums = extractEnums(schema); + + // Load types for all classes in parallel + const classTypesPromises = classes.map(async (cls) => { + const types = await getCustodianTypesForClassAsync(cls.name); + return [cls.name, types] as const; + }); + + // Load types for all slots in parallel + const slotTypesPromises = slots.map(async (slot) => { + const types = await getCustodianTypesForSlotAsync(slot.name); + return [slot.name, types] as const; + }); + + // Load types for all enums in parallel + const enumTypesPromises = enums.map(async (enumDef) => { + const types = await getCustodianTypesForEnumAsync(enumDef.name); + return [enumDef.name, types] as const; + }); + + try { + const [classResults, slotResults, enumResults] = await Promise.all([ + Promise.all(classTypesPromises), + Promise.all(slotTypesPromises), + Promise.all(enumTypesPromises) + ]); + + // Convert to records + const classTypesMap: Record = {}; + for (const [name, types] of classResults) { + classTypesMap[name] = types; + } + + const slotTypesMap: Record = {}; + for (const [name, types] of slotResults) { + slotTypesMap[name] = types; + } + + const enumTypesMap: Record = {}; + for (const [name, types] of enumResults) { + enumTypesMap[name] = types; + } + + setClassCustodianTypes(classTypesMap); + setSlotCustodianTypes(slotTypesMap); + setEnumCustodianTypes(enumTypesMap); + setCustodianTypesLoaded(true); + + console.log('[LinkMLViewerPage] Loaded custodian types from schema annotations:', { + classes: Object.keys(classTypesMap).length, + slots: Object.keys(slotTypesMap).length, + enums: Object.keys(enumTypesMap).length + }); + } catch (error) { + console.error('[LinkMLViewerPage] Error loading custodian types:', error); + // Fall back to sync functions (will use defaults) + setCustodianTypesLoaded(true); + } + }; + + loadCustodianTypes(); + }, [schema]); + const toggleSection = (section: string) => { setExpandedSections(prev => { const next = new Set(prev); @@ -1021,7 +1105,8 @@ const LinkMLViewerPage: React.FC = () => { const renderClassDetails = (cls: LinkMLClass) => { const isHighlighted = highlightedClass === cls.name; - const custodianTypes = getCustodianTypesForClass(cls.name); + // Use pre-loaded types from schema annotations, fall back to sync function if not yet loaded + const custodianTypes = classCustodianTypes[cls.name] || getCustodianTypesForClass(cls.name); const isUniversal = isUniversalElement(custodianTypes); // Check if this class matches the current custodian type filter (multi-select) @@ -1107,7 +1192,8 @@ const LinkMLViewerPage: React.FC = () => { const rangeIsEnum = slot.range && isEnumRange(slot.range); const enumKey = slot.range ? `${slot.name}:${slot.range}` : ''; const isExpanded = expandedEnumRanges.has(enumKey); - const custodianTypes = getCustodianTypesForSlot(slot.name); + // Use pre-loaded types from schema annotations, fall back to sync function if not yet loaded + const custodianTypes = slotCustodianTypes[slot.name] || getCustodianTypesForSlot(slot.name); const isUniversal = isUniversalElement(custodianTypes); // Check if this slot matches the current custodian type filter (multi-select) @@ -1187,7 +1273,7 @@ const LinkMLViewerPage: React.FC = () => { const searchFilter = enumSearchFilters[enumName] || ''; const showAll = enumShowAll[enumName] || false; const displayCount = 20; - const custodianTypes = getCustodianTypesForEnum(enumDef.name); + const custodianTypes = enumCustodianTypes[enumDef.name] || getCustodianTypesForEnum(enumDef.name); const isUniversal = isUniversalElement(custodianTypes); // Filter values based on search @@ -1331,21 +1417,21 @@ const LinkMLViewerPage: React.FC = () => { // Count matching items when filter is active (for display purposes) const matchingClassCount = custodianTypeFilter.size > 0 ? classes.filter(cls => { - const types = getCustodianTypesForClass(cls.name); + const types = classCustodianTypes[cls.name] || getCustodianTypesForClass(cls.name); return types.some(t => custodianTypeFilter.has(t)); }).length : classes.length; const matchingSlotCount = custodianTypeFilter.size > 0 ? slots.filter(slot => { - const types = getCustodianTypesForSlot(slot.name); + const types = slotCustodianTypes[slot.name] || getCustodianTypesForSlot(slot.name); return types.some(t => custodianTypeFilter.has(t)); }).length : slots.length; const matchingEnumCount = custodianTypeFilter.size > 0 ? enums.filter(enumDef => { - const types = getCustodianTypesForEnum(enumDef.name); + const types = enumCustodianTypes[enumDef.name] || getCustodianTypesForEnum(enumDef.name); return types.some(t => custodianTypeFilter.has(t)); }).length : enums.length; diff --git a/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml b/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml index 26e95c1a85..b373b4760b 100644 --- a/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml +++ b/schemas/20251121/linkml/modules/classes/ExtractionMetadata.yaml @@ -17,6 +17,7 @@ prefixes: imports: - linkml:types - ../metadata + - ./LLMResponse default_range: string @@ -72,6 +73,7 @@ classes: - linkedin_url - cost_usd - request_id + - llm_response slot_usage: source_file: @@ -175,6 +177,48 @@ classes: examples: - value: "exa_12345678-abcd-efgh-ijkl-mnopqrstuv" description: "Exa API request ID" + + llm_response: + description: | + Full LLM response provenance including reasoning_content. + + Captures GLM 4.7 Thinking Modes (Interleaved, Preserved, Turn-level) + for extractions that use LLM processing. + + **PROV-O Alignment**: + - The LLMResponse IS a sub-activity (prov:qualifiedGeneration) + - Provides detailed audit trail of LLM inference for the extraction + + **Use Cases**: + - LinkedIn profile extraction with GLM 4.7 reasoning + - Web content extraction with chain-of-thought logging + - Staff list processing with schema conformity validation + + **When to Include**: + - extraction_method is exa_crawling_glm47 + - Any extraction involving LLM processing + - When reasoning_content provides valuable audit trail + slot_uri: prov:qualifiedGeneration + range: LLMResponse + required: false + inlined: true + examples: + - value: | + { + "content": "Extracted institution data...", + "reasoning_content": "Analyzing the input for LinkML schema conformity...", + "thinking_mode": "preserved", + "clear_thinking": false, + "model": "glm-4.7", + "provider": "zai", + "created": "2025-12-23T10:30:00Z", + "prompt_tokens": 150, + "completion_tokens": 450, + "total_tokens": 600, + "finish_reason": "stop", + "cost_usd": 0.0 + } + description: "GLM 4.7 response with Preserved Thinking for extraction" comments: - "Every person entity file MUST have extraction_metadata" @@ -255,3 +299,7 @@ slots: request_id: description: "Unique request ID from extraction service" range: string + + llm_response: + description: "Full LLM response with reasoning provenance (GLM 4.7 Thinking Modes)" + range: LLMResponse diff --git a/schemas/20251121/linkml/modules/classes/LLMResponse.yaml b/schemas/20251121/linkml/modules/classes/LLMResponse.yaml new file mode 100644 index 0000000000..b4eed2315e --- /dev/null +++ b/schemas/20251121/linkml/modules/classes/LLMResponse.yaml @@ -0,0 +1,529 @@ +# LLM Response Class +# Provenance for LLM API responses with GLM 4.7 Thinking Modes +# Captures reasoning_content for Interleaved, Preserved, and Turn-level Thinking + +id: https://nde.nl/ontology/hc/class/LLMResponse +name: llm_response_class +title: LLM Response Class +version: 1.0.0 + +prefixes: + linkml: https://w3id.org/linkml/ + hc: https://nde.nl/ontology/hc/ + schema: http://schema.org/ + prov: http://www.w3.org/ns/prov# + dct: http://purl.org/dc/terms/ + xsd: http://www.w3.org/2001/XMLSchema# + +imports: + - linkml:types + - ../metadata + +default_range: string + +classes: + + LLMResponse: + class_uri: prov:Activity + description: | + Provenance metadata for LLM API responses, including GLM 4.7 Thinking Modes. + + Captures complete response metadata from LLM providers (ZhipuAI GLM, Anthropic, + OpenAI, etc.) for traceability and analysis. The key innovation is capturing + `reasoning_content` - the chain-of-thought reasoning that GLM 4.7 exposes + through its three thinking modes. + + **GLM 4.7 Thinking Modes** (https://docs.z.ai/guides/capabilities/thinking-mode): + + 1. **Interleaved Thinking** (default, since GLM-4.5): + - Model thinks between tool calls and after receiving tool results + - Enables complex, step-by-step reasoning with tool chaining + - Returns `reasoning_content` alongside `content` in every response + + 2. **Preserved Thinking** (new in GLM-4.7): + - Retains reasoning_content from previous assistant turns in context + - Preserves reasoning continuity across multi-turn conversations + - Improves model performance and increases cache hit rates + - **Enabled by default on Coding Plan endpoint** + - Requires returning EXACT, UNMODIFIED reasoning_content back to API + - Set via: `"clear_thinking": false` (do NOT clear previous reasoning) + + 3. **Turn-level Thinking** (new in GLM-4.7): + - Control reasoning computation on a per-turn basis + - Enable/disable thinking independently for each request in a session + - Useful for balancing speed (simple queries) vs accuracy (complex tasks) + - Set via: `"thinking": {"type": "enabled"}` or `"thinking": {"type": "disabled"}` + + **Critical Implementation Note for Preserved Thinking**: + When using Preserved Thinking with tool calls, thinking blocks MUST be: + 1. Explicitly preserved in the messages array + 2. Returned together with tool results + 3. Kept in EXACT original sequence (no reordering/editing) + + **PROV-O Alignment**: + - LLMResponse IS a prov:Activity (the inference process) + - content IS prov:Entity (the generated output) + - model/provider IS prov:Agent (the AI system) + - reasoning_content documents the prov:Plan (how the agent reasoned) + - prompt (input) IS prov:used (input to the activity) + + **Use Cases**: + - DSPy RAG responses with reasoning traces + - Heritage institution extraction provenance + - LinkML schema conformity validation + - Ontology mapping decision logs + - Multi-turn agent conversations with preserved context + + **Example JSON Structure (GLM 4.7 with Preserved Thinking)**: + ```json + { + "llm_response": { + "content": "The Rijksmuseum is a museum in Amsterdam...", + "reasoning_content": "The user is asking about heritage institutions. Let me identify the key entities: 1) Rijksmuseum is the institution name, 2) It's a museum (institution_type: MUSEUM), 3) Located in Amsterdam (city)...", + "thinking_mode": "preserved", + "clear_thinking": false, + "model": "glm-4.7", + "provider": "zai", + "request_id": "req_abc123", + "created": "2025-12-23T10:30:00Z", + "prompt_tokens": 150, + "completion_tokens": 450, + "total_tokens": 600, + "cached_tokens": 50, + "finish_reason": "stop", + "latency_ms": 1250, + "cost_usd": 0.0 + } + } + ``` + + exact_mappings: + - prov:Activity + close_mappings: + - schema:Action + - schema:CreativeWork + + slots: + - content + - reasoning_content + - thinking_mode + - clear_thinking + - model + - provider + - request_id + - created + - prompt_tokens + - completion_tokens + - total_tokens + - cached_tokens + - finish_reason + - latency_ms + - cost_usd + + slot_usage: + content: + description: | + The final LLM response text (message.content from API response). + PROV-O: prov:generated - the entity produced by this activity. + + This is the primary output shown to users and used for downstream processing. + slot_uri: prov:generated + range: string + required: true + examples: + - value: "The Rijksmuseum is a national museum in Amsterdam dedicated to Dutch arts and history." + description: "Extracted heritage institution description" + + reasoning_content: + description: | + Interleaved Thinking - the model's chain-of-thought reasoning. + PROV-O: prov:hadPlan - documents HOW the agent reasoned. + + **GLM 4.7 Interleaved Thinking**: + GLM 4.7 returns `reasoning_content` in every response, exposing the + model's step-by-step reasoning process. This enables: + + 1. **Schema Validation**: Model reasons about LinkML constraints before generating output + 2. **Ontology Mapping**: Explicit reasoning about CIDOC-CRM, CPOV, TOOI class mappings + 3. **RDF Quality**: Chain-of-thought validates triple construction + 4. **Transparency**: Full audit trail of extraction decisions + + **DSPy Integration**: + When using DSPy, reasoning_content can be used to: + - Validate signature conformity + - Debug failed extractions + - Improve prompt engineering + - Train on successful reasoning patterns + + May be null for providers that don't expose reasoning (Claude, GPT-4). + slot_uri: prov:hadPlan + range: string + required: false + examples: + - value: "The user is asking about Dutch heritage institutions. I need to identify: 1) Institution name: Rijksmuseum, 2) Type: Museum (maps to InstitutionTypeEnum.MUSEUM), 3) Location: Amsterdam (city in Noord-Holland province)..." + description: "GLM 4.7 interleaved thinking showing explicit schema reasoning" + + model: + description: | + The LLM model identifier from the API response. + PROV-O: Part of prov:wasAssociatedWith - identifies the specific model version. + + Common values: + - glm-4.7: ZhipuAI GLM 4.7 (with Interleaved Thinking) + - glm-4.6: ZhipuAI GLM 4.6 + - claude-3-opus-20240229: Anthropic Claude Opus + - gpt-4-turbo: OpenAI GPT-4 Turbo + slot_uri: schema:softwareVersion + range: string + required: true + examples: + - value: "glm-4.7" + description: "ZhipuAI GLM 4.7 with Interleaved Thinking" + + provider: + description: | + The LLM provider/platform. + PROV-O: prov:wasAssociatedWith - the agent (organization) providing the model. + + Used by DSPy to route requests and track provider-specific behavior. + slot_uri: prov:wasAssociatedWith + range: LLMProviderEnum + required: true + examples: + - value: "zai" + description: "ZhipuAI (Z.AI) - GLM models" + + request_id: + description: | + Unique request ID from the LLM provider API (for tracing/debugging). + Enables correlation with provider logs for troubleshooting. + slot_uri: dct:identifier + range: string + required: false + examples: + - value: "req_8f3a2b1c4d5e6f7g" + description: "Provider-assigned request identifier" + + created: + description: | + Timestamp when the LLM response was generated (from API response). + PROV-O: prov:endedAtTime - when the inference activity completed. + slot_uri: prov:endedAtTime + range: datetime + required: true + examples: + - value: "2025-12-23T10:30:00Z" + description: "UTC timestamp of response generation" + + prompt_tokens: + description: | + Number of tokens in the input prompt. + From API response: usage.prompt_tokens + slot_uri: schema:value + range: integer + minimum_value: 0 + examples: + - value: 150 + description: "150 tokens in the input prompt" + + completion_tokens: + description: | + Number of tokens in the model's response (content + reasoning_content). + From API response: usage.completion_tokens + + Note: For GLM 4.7, this includes tokens from both content and reasoning_content. + slot_uri: schema:value + range: integer + minimum_value: 0 + examples: + - value: 450 + description: "450 tokens in the completion (content + reasoning)" + + total_tokens: + description: | + Total tokens used (prompt + completion). + From API response: usage.total_tokens + slot_uri: schema:value + range: integer + minimum_value: 0 + examples: + - value: 600 + description: "600 total tokens (150 prompt + 450 completion)" + + cached_tokens: + description: | + Number of prompt tokens served from cache (if provider supports caching). + From API response: usage.prompt_tokens_details.cached_tokens + + Cached tokens typically have reduced cost and latency. + slot_uri: schema:value + range: integer + minimum_value: 0 + required: false + examples: + - value: 50 + description: "50 tokens served from provider's prompt cache" + + finish_reason: + description: | + Why the model stopped generating (from API response). + + Common values: + - stop: Natural completion (hit stop token) + - length: Hit max_tokens limit + - tool_calls: Model invoked a tool (function calling) + - content_filter: Response filtered for safety + slot_uri: schema:status + range: FinishReasonEnum + required: false + examples: + - value: "stop" + description: "Model completed naturally" + + latency_ms: + description: | + Response latency in milliseconds (time from request to response). + Measured client-side (includes network time). + slot_uri: schema:duration + range: integer + minimum_value: 0 + required: false + examples: + - value: 1250 + description: "1.25 seconds total response time" + + cost_usd: + description: | + Estimated cost in USD for this LLM call. + + For Z.AI Coding Plan: $0.00 (free tier for GLM models) + For other providers: calculated from token counts and pricing + slot_uri: schema:price + range: float + minimum_value: 0.0 + required: false + examples: + - value: 0.0 + description: "Free (Z.AI Coding Plan)" + - value: 0.015 + description: "OpenAI GPT-4 Turbo cost estimate" + + thinking_mode: + description: | + The GLM 4.7 thinking mode used for this request. + + **Available Modes**: + - **enabled**: Thinking enabled (default) - model reasons before responding + - **disabled**: Thinking disabled - faster responses, no reasoning_content + - **interleaved**: Interleaved thinking - think between tool calls (default behavior) + - **preserved**: Preserved thinking - retain reasoning across turns (Coding Plan default) + + **Configuration**: + - Interleaved: Default behavior, no config needed + - Preserved: Set `"clear_thinking": false` + - Turn-level: Set `"thinking": {"type": "enabled"}` or `"thinking": {"type": "disabled"}` + slot_uri: schema:actionOption + range: ThinkingModeEnum + required: false + examples: + - value: "preserved" + description: "Preserved thinking for multi-turn agent conversations" + - value: "interleaved" + description: "Default interleaved thinking between tool calls" + - value: "disabled" + description: "Disabled for fast, simple queries" + + clear_thinking: + description: | + Whether to clear previous reasoning_content from context. + + **Preserved Thinking Control**: + - **false**: Preserved Thinking enabled (keep reasoning, better cache hits) + - **true**: Clear previous reasoning (default for standard API) + + **Z.AI Coding Plan**: Default is `false` (Preserved Thinking enabled) + + **Critical Implementation Note**: + When clear_thinking is false, you MUST return the EXACT, UNMODIFIED + reasoning_content back to the API in subsequent turns. Any modification + (reordering, editing, truncating) will degrade performance and cache hits. + slot_uri: schema:Boolean + range: boolean + required: false + examples: + - value: false + description: "Keep reasoning for Preserved Thinking (recommended)" + - value: true + description: "Clear previous reasoning (fresh context each turn)" + + comments: + - "reasoning_content is the key field for Interleaved Thinking (GLM 4.7)" + - "Store reasoning_content for debugging, auditing, and DSPy optimization" + - "Z.AI Coding Plan endpoint: https://api.z.ai/api/coding/paas/v4/chat/completions" + - "For DSPy: use LLMResponse to track all LLM calls in the pipeline" + - "See AGENTS.md Rule 11 for Z.AI API configuration" + + see_also: + - "https://www.w3.org/TR/prov-o/" + - "https://api.z.ai/docs" + - "https://dspy-docs.vercel.app/" + +enums: + LLMProviderEnum: + description: | + Enumeration of LLM providers/platforms supported by DSPy integration. + Used for routing, cost tracking, and provider-specific behavior. + permissible_values: + zai: + description: | + ZhipuAI (Z.AI) - Chinese AI provider offering GLM models. + Primary provider for this project via Z.AI Coding Plan. + Endpoint: https://api.z.ai/api/coding/paas/v4/chat/completions + Models: glm-4.5, glm-4.6, glm-4.7 (with Interleaved Thinking) + meaning: schema:Organization + anthropic: + description: | + Anthropic - Provider of Claude models. + Models: claude-3-opus, claude-3-sonnet, claude-3-haiku + meaning: schema:Organization + openai: + description: | + OpenAI - Provider of GPT models. + Models: gpt-4-turbo, gpt-4o, gpt-3.5-turbo + meaning: schema:Organization + huggingface: + description: | + HuggingFace - Open model hosting and inference. + Models: Various open-source models via Inference API + meaning: schema:Organization + groq: + description: | + Groq - High-speed inference provider. + Models: llama, mixtral, gemma via Groq hardware + meaning: schema:Organization + together: + description: | + Together AI - Open model inference platform. + Models: Various open-source models + meaning: schema:Organization + local: + description: | + Local inference (Ollama, llama.cpp, vLLM). + No external API calls, runs on local hardware. + meaning: schema:SoftwareApplication + + FinishReasonEnum: + description: | + Reasons why the LLM stopped generating output. + Standardized across providers. + permissible_values: + stop: + description: "Natural completion - model hit a stop token or finished" + length: + description: "Hit max_tokens limit - response was truncated" + tool_calls: + description: "Model invoked a tool/function (function calling)" + content_filter: + description: "Response was filtered for safety/content policy" + error: + description: "Generation failed due to an error" + + ThinkingModeEnum: + description: | + GLM 4.7 thinking mode configuration. + Controls how the model reasons during inference. + + **Reference**: https://docs.z.ai/guides/capabilities/thinking-mode + + GLM 4.7 introduces three distinct thinking modes that can be combined: + 1. Interleaved Thinking (between tool calls) + 2. Preserved Thinking (across conversation turns) + 3. Turn-level Thinking (enable/disable per request) + permissible_values: + enabled: + description: | + Thinking enabled (turn-level setting). + Model reasons before responding, returns reasoning_content. + Set via: `"thinking": {"type": "enabled"}` + meaning: schema:ActivateAction + disabled: + description: | + Thinking disabled (turn-level setting). + Faster responses, no reasoning_content returned. + Useful for simple queries where speed matters more than accuracy. + Set via: `"thinking": {"type": "disabled"}` + meaning: schema:DeactivateAction + interleaved: + description: | + Interleaved thinking mode (default since GLM-4.5). + Model thinks between tool calls and after receiving tool results. + Enables complex, step-by-step reasoning with tool chaining. + No special configuration needed - this is the default behavior. + meaning: schema:Action + preserved: + description: | + Preserved thinking mode (new in GLM-4.7). + Retains reasoning_content from previous assistant turns in context. + Improves model performance and increases cache hit rates. + **Enabled by default on Z.AI Coding Plan endpoint**. + Set via: `"clear_thinking": false` + + CRITICAL: Must return EXACT, UNMODIFIED reasoning_content back to API. + meaning: schema:Action + +slots: + content: + description: "The final LLM response text" + range: string + + reasoning_content: + description: "Interleaved Thinking - chain-of-thought reasoning from GLM 4.7" + range: string + + model: + description: "LLM model identifier" + range: string + + provider: + description: "LLM provider/platform" + range: LLMProviderEnum + + created: + description: "Timestamp when response was generated" + range: datetime + + prompt_tokens: + description: "Number of tokens in input prompt" + range: integer + + completion_tokens: + description: "Number of tokens in response" + range: integer + + total_tokens: + description: "Total tokens used" + range: integer + + cached_tokens: + description: "Number of tokens served from cache" + range: integer + + finish_reason: + description: "Why the model stopped generating" + range: FinishReasonEnum + + latency_ms: + description: "Response latency in milliseconds" + range: integer + + cost_usd: + description: "API cost in USD for this LLM call" + range: float + + thinking_mode: + description: "GLM 4.7 thinking mode configuration" + range: ThinkingModeEnum + + clear_thinking: + description: "Whether to clear previous reasoning from context (false = Preserved Thinking)" + range: boolean diff --git a/scripts/sync/oxigraph_person_sync.py b/scripts/sync/oxigraph_person_sync.py index e10ebaee84..efa638b611 100644 --- a/scripts/sync/oxigraph_person_sync.py +++ b/scripts/sync/oxigraph_person_sync.py @@ -233,12 +233,19 @@ class PersonRDFConverter: source_staff = data.get('source_staff_info', {}) profile_data = data.get('profile_data', {}) heritage_rel = data.get('heritage_relevance', {}) + person_data = data.get('person', {}) # Alternative schema variant + heritage_profile = data.get('heritage_profile', {}) # Alternative schema - # Get name (required) - handle both 'name' and 'full_name' variants + # Get name (required) - handle multiple schema variants: + # 1. profile_data.name / profile_data.full_name (standard schema) + # 2. source_staff_info.name (from staff list extraction) + # 3. person.full_name (alternative schema - exa_crawling_linkedin_profile) name = ( profile_data.get('name') or profile_data.get('full_name') or - source_staff.get('name') + source_staff.get('name') or + person_data.get('full_name') or + person_data.get('name') ) if not name: return None @@ -258,10 +265,11 @@ class PersonRDFConverter: self.graph.add((person_uri, RDFS.label, Literal(name))) self.graph.add((person_uri, SKOS.prefLabel, Literal(name))) - # LinkedIn URL as sameAs + # LinkedIn URL as sameAs - check multiple schema locations linkedin_url = ( extraction_meta.get('linkedin_url') or - profile_data.get('linkedin_url') + profile_data.get('linkedin_url') or + person_data.get('linkedin_url') ) if linkedin_url: try: @@ -270,14 +278,18 @@ class PersonRDFConverter: except Exception: pass - # Headline / job title - headline = profile_data.get('headline') or source_staff.get('headline') + # Headline / job title - check multiple schema locations + headline = ( + profile_data.get('headline') or + source_staff.get('headline') or + person_data.get('headline') + ) if headline: self.graph.add((person_uri, SCHEMA.jobTitle, Literal(headline))) self.graph.add((person_uri, SCHEMA.description, Literal(headline))) - # Location (handle both string and dict formats) - location_raw = profile_data.get('location') + # Location (handle both string and dict formats) - check multiple schema locations + location_raw = profile_data.get('location') or person_data.get('location') location = normalize_location(location_raw) if location: self.graph.add((person_uri, SCHEMA.workLocation, Literal(location))) @@ -286,13 +298,16 @@ class PersonRDFConverter: if country_code: self.graph.add((person_uri, HC.countryCode, Literal(country_code))) - # About / description - about = profile_data.get('about') + # About / description - check multiple schema locations + about = profile_data.get('about') or person_data.get('about') if about: self.graph.add((person_uri, SCHEMA.disambiguatingDescription, Literal(about))) - # Profile image - profile_image = profile_data.get('profile_image_url') + # Profile image - check multiple schema locations + profile_image = ( + profile_data.get('profile_image_url') or + person_data.get('photo_url') + ) if profile_image: try: self.graph.add((person_uri, SCHEMA.image, URIRef(profile_image))) @@ -300,12 +315,18 @@ class PersonRDFConverter: except Exception: pass - # Heritage relevance - is_heritage_relevant = heritage_rel.get('is_heritage_relevant', True) + # Heritage relevance - check multiple schema locations + is_heritage_relevant = ( + heritage_rel.get('is_heritage_relevant', True) or + heritage_profile.get('is_heritage_professional', True) + ) self.graph.add((person_uri, HC.heritageRelevant, Literal(is_heritage_relevant, datatype=XSD.boolean))) - heritage_types = heritage_rel.get('heritage_types', []) + heritage_types = ( + heritage_rel.get('heritage_types', []) or + heritage_profile.get('heritage_types', []) + ) if not heritage_types and source_staff.get('heritage_type'): heritage_types = [source_staff.get('heritage_type')]