From 63400392ffe04110cbc151f209b69cb0d02c44a7 Mon Sep 17 00:00:00 2001 From: kempersc Date: Thu, 25 Dec 2025 21:01:05 +0100 Subject: [PATCH] Fix CZ-52-PAB-L-IPVVZOVI logo: use primary_logo.png instead of favicon.ico - Primary logo (logo.png) identified via crawl4ai direct scraping - Favicon (favicon.ico) retained as secondary asset - Updated claims: primary_logo_url + favicon_url - Summary shows: has_primary_logo: true, total_claims: 2 --- .../.logo_enrichment_crawl4ai_checkpoint.json | 544 +++++++++++++++++- data/custodian/CZ-52-HRA-L-FNHKLK.yaml | 42 +- data/custodian/CZ-52-HRA-L-KMHK.yaml | 28 +- data/custodian/CZ-52-HRA-L-PPPSPCKKK.yaml | 37 +- data/custodian/CZ-52-HRA-L-TBSTK.yaml | 34 +- data/custodian/CZ-52-HRA-L-UKFFVHKSVK.yaml | 42 +- data/custodian/CZ-52-HRA-L-UKLFVHKLK.yaml | 42 +- data/custodian/CZ-52-HRA-M-KMVCVHK.yaml | 28 +- data/custodian/CZ-52-HRA-M-MVCVHKPOPK.yaml | 19 + data/custodian/CZ-52-HRA-O-KSVHKK.yaml | 19 + data/custodian/CZ-52-HRA-O-SOAVHKSOAH.yaml | 39 +- data/custodian/CZ-52-HRO-L-MKEH.yaml | 28 +- data/custodian/CZ-52-JAN-L-MKJL.yaml | 19 + data/custodian/CZ-52-JAN-L-SLLJLSPDLV.yaml | 36 +- data/custodian/CZ-52-JAR-L-OKVR.yaml | 28 +- data/custodian/CZ-52-JAR-L-OKVS.yaml | 19 + data/custodian/CZ-52-JAR-L-OKVV.yaml | 28 +- data/custodian/CZ-52-JAR-M-MMVJK.yaml | 28 +- data/custodian/CZ-52-JAS-L-OKJ.yaml | 28 +- data/custodian/CZ-52-JAV-L-MKJ.yaml | 28 +- ...-A-SOAJ-statni_okresni_archiv_jesenik.yaml | 19 + data/custodian/CZ-52-JIC-L-KVCVJ.yaml | 19 + data/custodian/CZ-52-JIC-L-MKM.yaml | 28 +- data/custodian/CZ-52-JIC-L-MKV.yaml | 28 +- data/custodian/CZ-52-JIC-L-MKVO.yaml | 28 +- data/custodian/CZ-52-JIC-L-OKVJ.yaml | 28 +- data/custodian/CZ-52-JIC-M-RMGJ.yaml | 19 + data/custodian/CZ-52-JIC-M-RMGVJK.yaml | 28 +- data/custodian/CZ-52-JIC-O-SOAVHKSOAJ.yaml | 39 +- data/custodian/CZ-52-JIL-L-MKVJ.yaml | 28 +- data/custodian/CZ-52-JIN-L-UCPKS.yaml | 19 + data/custodian/CZ-52-KAC-L-MKKL.yaml | 27 + data/custodian/CZ-52-KOC-L-OKK.yaml | 28 +- data/custodian/CZ-52-KOH-L-MKK.yaml | 28 +- data/custodian/CZ-52-KOP-L-KK.yaml | 19 + data/custodian/CZ-52-KOP-L-MKZ.yaml | 28 +- data/custodian/CZ-52-KOP-L-MLKVB.yaml | 28 +- data/custodian/CZ-52-KOS-L-MKB.yaml | 28 +- data/custodian/CZ-52-KOS-L-MKKH.yaml | 28 +- data/custodian/CZ-52-KOS-L-MKS.yaml | 28 +- data/custodian/CZ-52-KOS-L-OKK.yaml | 36 +- data/custodian/CZ-52-KOS-L-OKLUP.yaml | 28 +- data/custodian/CZ-52-KRA-L-MKVPK.yaml | 28 + data/custodian/CZ-52-KUK-L-OKK.yaml | 19 + data/custodian/CZ-52-KUK-M-CFMVK.yaml | 25 + data/custodian/CZ-52-KVA-L-MKVK.yaml | 19 + data/custodian/CZ-52-LAH-E-KMC.yaml | 19 + data/custodian/CZ-52-LAH-L-LKM.yaml | 20 + data/custodian/CZ-52-LAZ-L-MKC.yaml | 19 + data/custodian/CZ-52-LHO-L-MKVU.yaml | 28 +- data/custodian/CZ-52-LHO-L-OKLPL.yaml | 28 +- data/custodian/CZ-52-LHO-L-OKO.yaml | 28 +- data/custodian/CZ-52-LHO-L-OKR.yaml | 28 +- data/custodian/CZ-52-LHO-L-OKS.yaml | 28 +- data/custodian/CZ-52-LHO-L-OKT.yaml | 28 +- data/custodian/CZ-52-LIB-L-KABL.yaml | 28 +- ...-52-LIB-L-MKL-mistni_knihovna_librice.yaml | 28 +- ...-52-LIB-L-MKL-mistni_knihovna_libunec.yaml | 28 +- data/custodian/CZ-52-LIB-L-MKLPB.yaml | 28 +- data/custodian/CZ-52-LIB-L-MKLPH.yaml | 19 + data/custodian/CZ-52-LIB-L-OKVL.yaml | 28 +- data/custodian/CZ-52-LIC-L-MKL.yaml | 25 + data/custodian/CZ-52-LIP-L-MKLNO.yaml | 28 +- data/custodian/CZ-52-LIT-A-AS.yaml | 35 ++ data/custodian/CZ-52-LIT-L-AOPKCK.yaml | 29 + data/custodian/CZ-52-LIT-L-CMIUFMK.yaml | 19 + data/custodian/CZ-52-LIT-L-CRSZSSRCK.yaml | 19 + data/custodian/CZ-52-LIT-L-MUPPSOKJH.yaml | 19 + data/custodian/CZ-52-LIT-L-PDBSRDKN.yaml | 25 + data/custodian/CZ-52-LIT-O-AHMPK.yaml | 19 + data/custodian/CZ-52-LUZ-L-OKL.yaml | 25 + data/custodian/CZ-52-LYS-L-NTK.yaml | 17 + data/custodian/CZ-52-LYS-L-UEBACVVK.yaml | 19 + data/custodian/CZ-52-LYS-L-VSCTVPCIS.yaml | 17 + data/custodian/CZ-52-LYS-L-VSCTVPFCTU.yaml | 19 + data/custodian/CZ-52-MIL-L-KKJE.yaml | 36 +- data/custodian/CZ-52-MIL-L-LKT.yaml | 28 +- data/custodian/CZ-52-MIL-L-LKU.yaml | 28 +- data/custodian/CZ-52-MIL-L-VKSVM.yaml | 19 + data/custodian/CZ-52-MLA-L-LKM.yaml | 28 +- data/custodian/CZ-52-MLA-L-MKM.yaml | 28 +- data/custodian/CZ-52-NAC-L-MKNPS.yaml | 29 + data/custodian/CZ-52-NAC-L-OKVT.yaml | 38 +- data/custodian/CZ-52-NAC-L-ONNSOK.yaml | 28 +- data/custodian/CZ-52-NAC-M-KMN.yaml | 28 +- data/custodian/CZ-52-NAC-O-SOAVHKSOAN.yaml | 39 +- data/custodian/CZ-52-NAH-L-OKN.yaml | 28 +- data/custodian/CZ-52-NEC-L-MKNPSSVS.yaml | 32 +- data/custodian/CZ-52-NEC-L-OKH.yaml | 28 +- data/custodian/CZ-52-NEC-L-SMKN.yaml | 28 +- data/custodian/CZ-52-NEM-L-OKN.yaml | 28 +- data/custodian/CZ-52-NMN-M-MMNMNM.yaml | 34 +- data/custodian/CZ-52-NOV-E-GSOSVOSNBI.yaml | 28 +- data/custodian/CZ-52-NOV-E-SPSSOSSOUN.yaml | 19 + data/custodian/CZ-52-NOV-L-MKNMNM.yaml | 34 +- data/custodian/CZ-52-NOV-L-OKC.yaml | 28 +- data/custodian/CZ-52-NOV-L-OKH.yaml | 28 +- data/custodian/CZ-52-NOV-L-OKJ.yaml | 34 +- data/custodian/CZ-52-NOV-L-OKK.yaml | 19 + data/custodian/CZ-52-NOV-L-OKNP.yaml | 28 +- data/custodian/CZ-52-NOV-L-OKSNM.yaml | 28 +- data/custodian/CZ-52-NOV-L-OKSS.yaml | 28 +- data/custodian/CZ-52-NOV-L-OKVNH.yaml | 29 + data/custodian/CZ-52-NOV-L-OKVV.yaml | 28 +- data/custodian/CZ-52-OPO-L-MKO.yaml | 28 +- data/custodian/CZ-52-OSI-L-OKO.yaml | 26 +- data/custodian/CZ-52-OST-L-OKES.yaml | 27 + data/custodian/CZ-52-OTO-L-OKO.yaml | 38 +- data/custodian/CZ-52-PAB-L-IPVVZOVI.yaml | 34 +- data/custodian/CZ-52-PAB-L-MSRSIS.yaml | 17 + data/custodian/CZ-52-PAB-L-PMCPSDAK.yaml | 19 + ...52-PAB-L-PSK-pragoprojekt_as_knihovna.yaml | 25 + data/custodian/CZ-52-PAB-L-UZFGACVVSP.yaml | 19 + data/custodian/CZ-52-PEC-L-KKH.yaml | 29 + data/custodian/CZ-52-PEC-L-MLKVBUP.yaml | 28 +- ...rykova_ustavu_a_archivu_av_cr_v_v_i_k.yaml | 19 + data/custodian/CZ-52-PEL-L-KUJAKP.yaml | 19 + data/custodian/CZ-52-PEL-L-RFERL.yaml | 25 + data/custodian/CZ-52-PEL-L-SZUSVIK.yaml | 19 + data/custodian/CZ-52-PEL-L-UJFACVVDPO.yaml | 19 + data/custodian/CZ-52-PEL-O-NKUK.yaml | 19 + data/custodian/CZ-52-PIL-L-OKP.yaml | 19 + data/custodian/CZ-52-POD-L-MKP.yaml | 28 +- data/custodian/CZ-52-POL-O-AOPKCRRPVC.yaml | 38 +- data/custodian/CZ-52-POT-L-MKZ.yaml | 28 +- data/custodian/CZ-52-PRA-A-ABS.yaml | 29 + data/custodian/CZ-52-PRA-E-SPSEPJK.yaml | 25 + data/custodian/CZ-52-PRA-E-UK.yaml | 34 ++ data/custodian/CZ-52-PRA-H-KBOE.yaml | 19 + data/custodian/CZ-52-PRA-H-SPCPZSK.yaml | 19 + data/custodian/CZ-52-PRA-L-ADISRK.yaml | 28 + data/custodian/CZ-52-PRA-L-CAK.yaml | 25 + data/custodian/CZ-52-PRA-L-CNBOK.yaml | 19 + data/custodian/CZ-52-PRA-L-CPSUPPSK.yaml | 19 + data/custodian/CZ-52-PRA-L-CRROK.yaml | 25 + data/custodian/CZ-52-PRA-L-CSEK.yaml | 28 + data/custodian/CZ-52-PRA-L-CSPC.yaml | 19 + data/custodian/CZ-52-PRA-L-CSSPKCRK.yaml | 33 ++ data/custodian/CZ-52-PRA-L-CTSKAAPF.yaml | 25 + data/custodian/CZ-52-PRA-L-CVPUKCKAC.yaml | 19 + data/custodian/CZ-52-PRA-L-CVTPSK.yaml | 25 + ...-L-FIM-francouzsky_institut_mediateka.yaml | 25 + data/custodian/CZ-52-PRA-L-FIM.yaml | 25 + data/custodian/CZ-52-PRA-L-HLK.yaml | 19 + data/custodian/CZ-52-PRA-L-ICVPKCF.yaml | 19 + data/custodian/CZ-52-PRA-L-ITIK.yaml | 19 + data/custodian/CZ-52-PRA-L-KACVV.yaml | 29 + data/custodian/CZ-52-PRA-L-KAS.yaml | 19 + data/custodian/CZ-52-PRA-L-KLP.yaml | 32 ++ data/custodian/CZ-52-PRA-L-KVHNF.yaml | 25 + data/custodian/CZ-52-PRA-L-KVSPOSPS.yaml | 19 + data/custodian/CZ-52-PRA-L-MDA.yaml | 19 + data/custodian/CZ-52-PRA-L-MSCCCKNPKU.yaml | 33 ++ data/custodian/CZ-52-PRA-L-MVCVSOLKPM.yaml | 25 + data/custodian/CZ-52-PRA-L-NFAK.yaml | 25 + data/custodian/CZ-52-PRA-L-NKCR.yaml | 28 + ...vna_ceske_republiky_slovanska_knihovn.yaml | 34 ++ data/custodian/CZ-52-PRA-L-NKCRSKOS.yaml | 34 ++ data/custodian/CZ-52-PRA-L-NLK.yaml | 19 + data/custodian/CZ-52-PRA-L-NMKNMORST.yaml | 29 + data/custodian/CZ-52-PRA-L-NPUHKF.yaml | 25 + data/custodian/CZ-52-PRA-L-NPUK.yaml | 19 + data/custodian/CZ-52-PRA-L-OKVP.yaml | 19 + data/custodian/CZ-52-PRA-L-PUACVVPPK.yaml | 19 + data/custodian/CZ-52-PRA-L-SUACVVK.yaml | 19 + data/custodian/CZ-52-PRA-L-SUROVVK.yaml | 19 + data/custodian/CZ-52-PRA-L-TPSK.yaml | 19 + data/custodian/CZ-52-PRA-L-UDUACVVK.yaml | 19 + data/custodian/CZ-52-PRA-L-UKFFFUK.yaml | 28 + data/custodian/CZ-52-PRA-L-UKFFKE.yaml | 28 + data/custodian/CZ-52-PRA-L-UKFFKUE.yaml | 28 + data/custodian/CZ-52-PRA-L-UKFFUHSD.yaml | 19 + data/custodian/CZ-52-PRA-L-UKLFAU.yaml | 34 ++ data/custodian/CZ-52-PRA-L-UKLFFUK.yaml | 34 ++ data/custodian/CZ-52-PRA-L-UKLFSVI.yaml | 34 ++ data/custodian/CZ-52-PRA-L-UKLFUVI.yaml | 33 ++ data/custodian/CZ-52-PRA-L-UKLFVFNICK.yaml | 34 ++ ...rlova_1_lekarska_fakulta_a_vseobecna_.yaml | 28 + data/custodian/CZ-52-PRA-L-UKMFFKMOI.yaml | 19 + data/custodian/CZ-52-PRA-L-UKPFBK.yaml | 27 + ..._karlova_pedagogicka_fakulta_knihovna.yaml | 33 ++ data/custodian/CZ-52-PRA-L-UKPFKC.yaml | 27 + data/custodian/CZ-52-PRA-L-UKPFKKFDPV.yaml | 27 + data/custodian/CZ-52-PRA-L-UKUKLUVSU.yaml | 34 ++ data/custodian/JP-13-MIN-L-SL.yaml | 32 +- data/custodian/JP-13-MIN-L-TWSCL.yaml | 38 +- data/custodian/JP-13-MIN-M-AMT.yaml | 25 + data/custodian/JP-13-MIN-M-MAM.yaml | 30 +- ...-MIT-L-ML-mitakashiritsuseibu_library.yaml | 30 +- data/custodian/JP-13-MUS-L-SUL.yaml | 35 +- data/custodian/JP-13-MUS-M-KAM.yaml | 41 +- data/custodian/JP-13-MUS-M-MCM.yaml | 38 +- data/custodian/JP-13-MYO-L-K.yaml | 38 +- data/custodian/JP-13-MYO-L-SL.yaml | 19 + data/custodian/JP-13-MYO-L-TAFFTSC.yaml | 41 +- data/custodian/JP-13-NAK-L-FL.yaml | 37 +- ...jintokyozeimukyokaizeimukohoshiryoshi.yaml | 19 + data/custodian/JP-13-NAK-L-KL.yaml | 32 +- data/custodian/JP-13-NAK-L-MRISEH.yaml | 32 +- data/custodian/JP-13-NAK-L-NCCL.yaml | 19 + ...entral_library_mihatoshogakkobunshits.yaml | 32 +- data/custodian/JP-13-NAK-L-NCCLM.yaml | 32 +- data/custodian/JP-13-NAK-L-NCCLN.yaml | 32 +- data/custodian/JP-13-NAK-L-NCEL.yaml | 19 + data/custodian/JP-13-NAK-L-NCKL.yaml | 32 +- data/custodian/JP-13-NAK-L-NCML.yaml | 32 +- ...CNL-nakano_city_nakanohigashi_library.yaml | 19 + data/custodian/JP-13-NAK-L-NCNL.yaml | 32 +- data/custodian/JP-13-NAK-L-NCSL.yaml | 32 +- data/custodian/JP-13-NAK-L-NL.yaml | 33 ++ data/custodian/JP-13-NAK-L-TCSL.yaml | 25 + data/custodian/JP-13-NAK-L-TPUNL.yaml | 25 + data/custodian/JP-13-NAK-L-YECTL.yaml | 19 + data/custodian/JP-13-NAK-M-ASMA.yaml | 49 +- data/custodian/JP-13-NAK-M-KDNEM.yaml | 32 +- data/custodian/JP-13-NAK-M-NMFA.yaml | 19 + data/custodian/JP-13-NAK-M-NZP.yaml | 20 + data/custodian/JP-13-NAK-M-TMA.yaml | 33 +- data/custodian/JP-13-NAK-M-TMT.yaml | 42 +- data/custodian/JP-13-NAK-M-TTCAOTLM.yaml | 52 +- data/custodian/JP-13-NAK-M-YHCM.yaml | 36 +- data/custodian/JP-13-NAM-M-NCM.yaml | 53 +- data/custodian/JP-13-NAN-L-NCCML.yaml | 41 +- data/custodian/JP-13-NAN-L-NCFML.yaml | 28 + data/custodian/JP-13-NAN-L-NCIL.yaml | 41 +- data/custodian/JP-13-NAN-L-NCJML.yaml | 28 + ...toshi_futomiyama_kouryusenta_libarary.yaml | 38 +- data/custodian/JP-13-NAN-L-NL.yaml | 41 +- data/custodian/JP-13-NAN-L-NYKL.yaml | 38 +- data/custodian/JP-13-NAN-M-AFM.yaml | 32 +- data/custodian/JP-13-NAN-M-FAM.yaml | 35 +- data/custodian/JP-13-NAN-M-FCCH.yaml | 36 +- data/custodian/JP-13-NAN-M-JHFFM.yaml | 38 +- data/custodian/JP-13-NAN-M-NSE.yaml | 38 +- data/custodian/JP-13-NAN-M-NSGFMH.yaml | 19 + data/custodian/JP-13-NAR-L-NCL.yaml | 37 +- data/custodian/JP-13-NAR-M-NCKTM.yaml | 41 +- data/custodian/JP-13-NAR-M-NGH.yaml | 38 +- data/custodian/JP-13-NAR-M-OMA.yaml | 38 +- data/custodian/JP-13-NAS-L-NCL.yaml | 34 +- ...ukarasuyamashiritsuminaminasu_library.yaml | 34 +- ...NL-nasushiobarashinishinasuno_library.yaml | 32 +- ...-L-NL-nasushiobarashishiobara_library.yaml | 19 + data/custodian/JP-13-NAS-L-NL.yaml | 19 + data/custodian/JP-13-NAS-L-NLA.yaml | 32 +- data/custodian/JP-13-NAS-L-NLH.yaml | 32 +- data/custodian/JP-13-NAS-L-NLI.yaml | 32 +- data/custodian/JP-13-NAS-L-NLK.yaml | 32 +- ...hinishinasuno_library_mishimabunshits.yaml | 32 +- ...rashishiobara_library_momijibunshitsu.yaml | 19 + data/custodian/JP-13-NAS-L-NLM.yaml | 32 +- ...ashikuroiso_library_nabekakebunshitsu.yaml | 19 + data/custodian/JP-13-NAS-L-NLN.yaml | 19 + data/custodian/JP-13-NAS-L-NLO.yaml | 19 + ...hikuroiso_library_takabayashibunshits.yaml | 19 + ...arashikuroiso_library_toyorabunshitsu.yaml | 19 + data/custodian/JP-13-NAS-L-NLT.yaml | 32 +- data/custodian/JP-13-NAS-L-NTL.yaml | 32 +- data/custodian/JP-13-NAS-M-NH.yaml | 30 +- data/custodian/JP-13-NAS-M-NMBHMA.yaml | 32 +- data/custodian/JP-13-NAS-M-NOM.yaml | 32 +- data/custodian/JP-13-NAS-M-NPWM.yaml | 30 +- data/custodian/JP-13-NAS-M-SFM.yaml | 41 +- data/custodian/JP-13-NER-L-LRLJILPT.yaml | 38 +- data/custodian/JP-13-NER-L-MLE.yaml | 38 +- data/custodian/JP-13-NER-L-MUL.yaml | 38 +- ...R-L-NL-nerimakuritsukasugacho_library.yaml | 32 +- ...-NL-nerimakuritsuminamitanaka_library.yaml | 32 +- data/custodian/JP-13-NER-L-NLE.yaml | 38 +- data/custodian/JP-13-NER-M-AMNUCA.yaml | 19 + data/custodian/JP-13-NER-M-CAMT.yaml | 33 +- data/custodian/JP-13-NER-M-HMA.yaml | 38 +- data/custodian/JP-13-NER-M-KM.yaml | 30 +- data/custodian/JP-13-NER-M-MAMMMI.yaml | 25 + data/custodian/JP-13-NII-M-NMM.yaml | 28 +- data/custodian/JP-13-NIK-M-NBGGSSUT.yaml | 34 ++ data/custodian/JP-13-NIK-M-NCLMNSMM.yaml | 46 +- ...-13-NIS-L-HL-hinoharasonritsu_library.yaml | 34 +- data/custodian/JP-13-NIS-L-HL.yaml | 25 + data/custodian/JP-13-NIS-L-HLO.yaml | 38 +- data/custodian/JP-13-NIS-L-M.yaml | 25 + data/custodian/JP-13-NIS-L-ML.yaml | 38 +- data/custodian/JP-13-NIS-L-MUNRA.yaml | 38 +- data/custodian/JP-13-NIS-L-WUA.yaml | 38 +- data/custodian/JP-13-NIS-M-FMUT.yaml | 32 +- data/custodian/JP-13-NIS-M-KKMMLHM.yaml | 19 + data/custodian/JP-13-NIS-M-OVC.yaml | 43 +- data/custodian/JP-13-NIS-M-TSC.yaml | 19 + data/custodian/JP-13-OGA-M-OMC.yaml | 20 + ...for_maritime_sciences_kobe_university.yaml | 25 + .../JP-13-OME-L-OL-omeshibaigo_library.yaml | 32 +- .../JP-13-OME-L-OL-omeshidaimon_library.yaml | 32 +- .../JP-13-OME-L-OL-omeshiimai_library.yaml | 32 +- ...P-13-OME-L-OL-omeshinagabuchi_library.yaml | 32 +- .../JP-13-OME-L-OL-omeshinariki_library.yaml | 32 +- .../JP-13-OME-L-OL-omeshiome_library.yaml | 32 +- .../JP-13-OME-L-OL-omeshiosoki_library.yaml | 32 +- .../JP-13-OME-L-OL-omeshisawai_library.yaml | 32 +- ...P-13-OME-L-OL-omeshishimmachi_library.yaml | 32 +- data/custodian/JP-13-OME-L-OL.yaml | 32 +- data/custodian/JP-13-OME-M-OMMAKZMG.yaml | 32 +- data/custodian/JP-13-OME-M-OMMPH.yaml | 32 +- data/custodian/JP-13-OSH-M-OP.yaml | 25 + ...hinkamatafukushisentakoenotoshoshitsu.yaml | 47 +- ...-otakusangyopurazakankosangyojohokona.yaml | 41 +- ...13-OTA-L-OCHL-ota_city_haneda_library.yaml | 47 +- data/custodian/JP-13-OTA-L-OCHL.yaml | 47 +- ...3-OTA-L-OCIL-ota_city_iriarai_library.yaml | 47 +- data/custodian/JP-13-OTA-L-OCIL.yaml | 34 ++ ...-OTA-L-OCKL-ota_city_kugahara_library.yaml | 34 ++ data/custodian/JP-13-OTA-L-OCKL.yaml | 47 +- data/custodian/JP-13-OTA-L-OCML.yaml | 34 ++ ...TA-L-OCOL-ota_city_omorinishi_library.yaml | 47 +- data/custodian/JP-13-OTA-L-OCOL.yaml | 17 + data/custodian/JP-13-OTA-L-OCRL.yaml | 34 ++ ...TA-L-OCSL-ota_city_senzokuike_library.yaml | 34 ++ data/custodian/JP-13-OTA-L-OCSL.yaml | 47 +- data/custodian/JP-13-OTA-L-OCTL.yaml | 34 ++ ...A-L-OL-otakuritsukamataekimae_library.yaml | 47 +- ...A-L-OL-otakuritsuomorihigashi_library.yaml | 34 ++ ...TA-L-OL-otakuritsuomoriminami_library.yaml | 47 +- data/custodian/JP-13-OTA-L-T.yaml | 32 +- data/custodian/JP-13-OTA-L-TUMMC.yaml | 19 + data/custodian/JP-13-OTA-M-IR.yaml | 32 +- data/custodian/JP-13-OTA-M-KTEROCTP.yaml | 47 +- data/custodian/JP-13-OTA-M-OCFM.yaml | 47 +- data/custodian/JP-13-OTA-M-OCKKMM.yaml | 47 +- data/custodian/JP-13-OTA-M-ONM.yaml | 25 + data/custodian/JP-13-OTA-M-OSHFMH.yaml | 32 +- data/custodian/JP-13-OTA-M-OSNLMH.yaml | 19 + ...abeshiritsuarakawakominkantoshoshitsu.yaml | 32 +- ...oyabeshiritsuhanyukominkantoshoshitsu.yaml | 19 + ...iritsuhigashikandakominkantoshoshitsu.yaml | 19 + ...eshiritsukitakandakominkantoshoshitsu.yaml | 32 +- ...eshiritsumatsuzawakominkantoshoshitsu.yaml | 19 + ...beshiritsumiyajimakominkantoshoshitsu.yaml | 19 + ...abeshiritsushotokukominkantoshoshitsu.yaml | 32 +- ...-oyabeshiritsutobukominkantoshoshitsu.yaml | 32 +- ...abeshiritsutsuzawakominkantoshoshitsu.yaml | 32 +- ...hiritsuwakabayashikominkantoshoshitsu.yaml | 32 +- ...beshiritsuyabunamikominkantoshoshitsu.yaml | 19 + ...A-L-O-oyamashikinukominkantoshoshitsu.yaml | 32 +- ...A-L-O-oyamashinakakominkantoshoshitsu.yaml | 32 +- ...-L-O-oyamashinamaikominkantoshoshitsu.yaml | 32 +- ...-O-oyamashisangawakominkantoshoshitsu.yaml | 32 +- data/custodian/JP-13-OYA-L-O.yaml | 32 +- data/custodian/JP-13-OYA-L-OCCLKBL.yaml | 32 +- data/custodian/JP-13-OYA-L-OCCLOBL.yaml | 32 +- data/custodian/JP-13-OYA-L-OCL.yaml | 36 +- data/custodian/JP-13-OYA-L-OL.yaml | 32 +- data/custodian/JP-13-OYA-L-OLM.yaml | 19 + data/custodian/JP-13-OYA-L-OLO.yaml | 32 +- data/custodian/JP-13-OYA-L-ONCTL.yaml | 40 +- data/custodian/JP-13-OYA-M-MAFO.yaml | 27 + data/custodian/JP-13-OYA-M-OCM.yaml | 38 +- data/custodian/JP-13-OYA-M-THRM.yaml | 38 +- data/custodian/JP-13-SAI-L-DLD.yaml | 38 +- data/custodian/JP-13-SAI-L-DLN.yaml | 25 + data/custodian/JP-13-SAI-L-DML.yaml | 38 +- ...-hokichoritsunikkokominkantoshoshitsu.yaml | 32 +- data/custodian/JP-13-SAI-L-H.yaml | 32 +- ...-13-SAI-L-HL-hokichokishimoto_library.yaml | 32 +- data/custodian/JP-13-SAI-L-HL.yaml | 32 +- ...-SAI-L-NL-nambuchoritsutemman_library.yaml | 25 + data/custodian/JP-13-SAI-L-NL.yaml | 38 +- data/custodian/JP-13-SAI-M-SUMP.yaml | 38 +- data/custodian/JP-13-SAI-M-THDT.yaml | 38 +- data/custodian/JP-13-SAI-M-TPMHP.yaml | 19 + data/custodian/JP-13-SAI-M-TT.yaml | 25 + data/custodian/JP-13-SAK-L-SCL.yaml | 32 +- data/custodian/JP-13-SAK-M-MSM.yaml | 38 +- data/custodian/JP-13-SAK-M-SCMMKA.yaml | 32 +- ...-13-SAN-L-SL-sanotankidaigaku_library.yaml | 32 +- data/custodian/JP-13-SAN-M-AYSHMA.yaml | 32 +- data/custodian/JP-13-SAN-M-KTMCA.yaml | 38 +- data/custodian/JP-13-SAN-M-KUFMS.yaml | 25 + data/custodian/JP-13-SAN-M-SCM.yaml | 38 +- data/custodian/JP-13-SAN-M-STAM.yaml | 41 +- data/custodian/JP-13-SET-L-HRFL.yaml | 32 +- data/custodian/JP-13-SET-L-IESSU.yaml | 47 +- data/custodian/JP-13-SET-L-IFSSU.yaml | 47 +- data/custodian/JP-13-SET-L-KLJ.yaml | 38 +- data/custodian/JP-13-SET-L-KUL.yaml | 38 +- data/custodian/JP-13-SET-L-NL.yaml | 38 +- data/custodian/JP-13-SET-L-SAMAL.yaml | 38 +- data/custodian/JP-13-SET-L-SCDL.yaml | 17 + data/custodian/JP-13-SET-L-SCFL.yaml | 17 + data/custodian/JP-13-SET-L-SCKKL.yaml | 17 + ...T-L-SCKL-setagaya_city_kamata_library.yaml | 30 +- ...T-L-SCKL-setagaya_city_kasuya_library.yaml | 30 +- ...T-L-SCKL-setagaya_city_kinuta_library.yaml | 17 + ...ET-L-SCKL-setagaya_city_kyodo_library.yaml | 30 +- data/custodian/JP-13-SET-L-SCKL.yaml | 30 +- data/custodian/JP-13-SET-L-SCL.yaml | 30 +- ...L-SCOL-setagaya_city_oyamadai_library.yaml | 30 +- data/custodian/JP-13-SET-L-SCOL.yaml | 30 +- ...CSL-setagaya_city_sakuragaoka_library.yaml | 30 +- ...L-SCSL-setagaya_city_setagaya_library.yaml | 30 +- data/custodian/JP-13-SET-L-SCSL.yaml | 30 +- data/custodian/JP-13-SET-L-SCTL.yaml | 30 +- data/custodian/JP-13-SET-L-SCUL.yaml | 30 +- data/custodian/JP-13-SET-L-SFSBL.yaml | 46 +- data/custodian/JP-13-SET-L-SL.yaml | 25 + data/custodian/JP-13-SET-L-SUL.yaml | 41 +- ...ryohokendaigakufuzokusetagaya_library.yaml | 30 +- ...otoshidaigakutodorokikyampasu_library.yaml | 32 +- data/custodian/JP-13-SET-L-TL.yaml | 32 +- data/custodian/JP-13-SET-L-TMIMS.yaml | 32 +- data/custodian/JP-13-SET-M-FAMTUA.yaml | 32 +- data/custodian/JP-13-SET-M-GM.yaml | 41 +- data/custodian/JP-13-SET-M-HMAM.yaml | 33 +- data/custodian/JP-13-SET-M-JPSOFHG.yaml | 25 + data/custodian/JP-13-SET-M-KARC.yaml | 42 +- data/custodian/JP-13-SET-M-MZCHKU.yaml | 38 +- data/custodian/JP-13-SET-M-OPSOFHG.yaml | 25 + data/custodian/JP-13-SET-M-SAM.yaml | 38 +- data/custodian/JP-13-SET-M-SM.yaml | 19 + data/custodian/JP-13-SET-M-SMH.yaml | 38 +- data/custodian/JP-13-SHI-L-A.yaml | 32 +- data/custodian/JP-13-SHI-L-AGWSJCL.yaml | 32 +- data/custodian/JP-13-SHI-L-AL.yaml | 33 +- data/custodian/JP-13-SHI-L-APCCUAL.yaml | 33 +- data/custodian/JP-13-SHI-L-BGUL.yaml | 35 +- data/custodian/JP-13-SHI-L-BMFJINF.yaml | 38 +- data/custodian/JP-13-SHI-L-CIMOL.yaml | 32 +- data/custodian/JP-13-SHI-L-DHT.yaml | 38 +- 426 files changed, 11763 insertions(+), 1405 deletions(-) diff --git a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json index 8fe317cb56..04dca4b1e7 100644 --- a/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json +++ b/data/custodian/.logo_enrichment_crawl4ai_checkpoint.json @@ -11662,7 +11662,547 @@ "CZ-51-MIM-L-MKVK.yaml", "CZ-51-MIM-L-MKVNPR.yaml", "CZ-51-MIM-L-MKVPPR.yaml", - "CZ-51-MIM-L-MSK.yaml" + "CZ-51-MIM-L-MSK.yaml", + "CZ-51-MIM-L-OPMP.yaml", + "CZ-51-MIM-L-VAU.yaml", + "CZ-51-MNI-L-SMHS.yaml", + "CZ-51-MRI-L-MKVM.yaml", + "CZ-51-NMS-A-EHPNMPS.yaml", + "CZ-51-NOV-E-VOSSSSNBK.yaml", + "CZ-51-NOV-L-BS.yaml", + "CZ-51-NOV-L-CSTRK.yaml", + "CZ-51-NOV-L-MKNB.yaml", + "CZ-51-NOV-L-MKNO.yaml", + "JP-13-MEG-L-ML.yaml", + "JP-13-MEG-L-RCASTLUT.yaml", + "JP-13-MEG-L-THUHL.yaml", + "JP-13-MEG-L-UTGSMSL.yaml", + "JP-13-MEG-M-FGLC.yaml", + "JP-13-MEG-M-JFCM.yaml", + "JP-13-MEG-M-KMCASUT.yaml", + "JP-13-MEG-M-MCSACTOURC.yaml", + "JP-13-MEG-M-MHM.yaml", + "JP-13-MEG-M-MMAT.yaml", + "JP-13-MEG-M-SSM.yaml", + "JP-13-MEG-M-TPAM.yaml", + "JP-13-MIM-L-T.yaml", + "JP-13-MIM-M-MLHM.yaml", + "JP-13-MIM-M-ONFSH.yaml", + "JP-13-MIN-A-DAMFAJ-diplomatic_archives_of_the_ministry_of_foreign_aff.yaml", + "JP-13-MIN-A-DAMFAJ.yaml", + "JP-13-MIN-L-ACJ.yaml", + "JP-13-MIN-L-AICJUSM.yaml", + "JP-13-MIN-L-AIJL.yaml", + "JP-13-MIN-L-ALJAA.yaml", + "JP-13-MIN-L-ALNACT.yaml", + "JP-13-MIN-L-AMTL.yaml", + "JP-13-MIN-L-ARL.yaml", + "JP-13-MIN-L-BLERIJSPMI.yaml", + "JP-13-MIN-L-CEHNL.yaml", + "JP-13-MIN-L-CLFNPSPMAA.yaml", + "JP-13-MIN-L-FMCMJSKU.yaml", + "JP-13-MIN-L-GSU.yaml", + "JP-13-MIN-L-HGSBB.yaml", + "JP-13-MIN-L-HL.yaml", + "JP-13-MIN-L-HPGSIJ.yaml", + "JP-13-MIN-L-HRLCHRA.yaml", + "JP-13-MIN-L-IDDITPS.yaml", + "JP-13-MIN-L-IHJL.yaml", + "JP-13-MIN-L-IL.yaml", + "JP-13-MIN-L-IMSLUT.yaml", + "JP-13-MIN-L-IRCCS.yaml", + "JP-13-MIN-L-J.yaml", + "JP-13-MIN-L-JAICAF.yaml", + "JP-13-MIN-L-JBLT.yaml", + "JP-13-MIN-L-JCFRI.yaml", + "JP-13-MIN-L-JFTCI.yaml", + "JP-13-MIN-L-JMSI.yaml", + "JP-13-MIN-L-JOGMNCMRIC.yaml", + "JP-13-MIN-L-JREIL.yaml", + "JP-13-MIN-L-K-kabushikigaishadaikotokyoshiryoshitsu.yaml", + "JP-13-MIN-L-K-kabushikigaishafujitsusokenkeizaikenkyujo.yaml", + "JP-13-MIN-L-K-kabushikigaishaterepakkushiryoshitsu.yaml", + "JP-13-MIN-L-K.yaml", + "JP-13-MIN-L-KICLS.yaml", + "JP-13-MIN-L-KJG.yaml", + "JP-13-MIN-L-KK.yaml", + "JP-13-MIN-L-KNDID.yaml", + "JP-13-MIN-L-KUMCHO.yaml", + "JP-13-MIN-L-KUMMC.yaml", + "JP-13-MIN-L-KUSL.yaml", + "JP-13-MIN-L-LGSTEU.yaml", + "JP-13-MIN-L-LPFA.yaml", + "JP-13-MIN-L-LSCJBN.yaml", + "JP-13-MIN-L-LTCJTBF.yaml", + "JP-13-MIN-L-MCAL-minato_city_azabu_library.yaml", + "JP-13-MIN-L-MCAL.yaml", + "JP-13-MIN-L-MCKL.yaml", + "JP-13-MIN-L-MCML-minato_city_mita_library.yaml", + "JP-13-MIN-L-MCML.yaml", + "JP-13-MIN-L-MCPS.yaml", + "JP-13-MIN-L-MCTL.yaml", + "JP-13-MIN-L-MGULTKMAMJ.yaml", + "JP-13-MIN-L-MGUSCL.yaml", + "JP-13-MIN-L-MIL.yaml", + "JP-13-MIN-L-MLB.yaml", + "JP-13-MIN-L-N-nipponchuokeibakaikohobuhodoshitsutoshoshitsu.yaml", + "JP-13-MIN-L-N.yaml", + "JP-13-MIN-L-NAL.yaml", + "JP-13-MIN-L-NCACL.yaml", + "JP-13-MIN-L-NFHIS.yaml", + "JP-13-MIN-L-NGIPSL.yaml", + "JP-13-MIN-L-NRASR.yaml", + "JP-13-MIN-L-NSRASK.yaml", + "JP-13-MIN-L-NTNCETDCAL.yaml", + "JP-13-MIN-L-O.yaml", + "JP-13-MIN-L-RICE.yaml", + "JP-13-MIN-L-RL.yaml", + "JP-13-MIN-L-SBIOCKU.yaml", + "JP-13-MIN-L-SJCIC.yaml", + "JP-13-MIN-L-SL-shibaurakogyodaigakugakujutsujohosentashibaura_lib.yaml", + "JP-13-MIN-L-SL.yaml", + "JP-13-MIN-L-TL.yaml", + "JP-13-MIN-L-TMCL.yaml", + "JP-13-MIN-L-TMHRPL.yaml", + "JP-13-MIN-L-TUMSTL.yaml", + "JP-13-MIN-L-TUTL.yaml", + "JP-13-MIN-L-TVL.yaml", + "JP-13-MIN-L-TWSCL.yaml", + "JP-13-MIN-L-YGRI.yaml", + "JP-13-MIN-M-AMT.yaml", + "JP-13-MIN-M-HMMFA.yaml", + "JP-13-MIN-M-INSNMNS.yaml", + "JP-13-MIN-M-KUAC.yaml", + "JP-13-MIN-M-MAM.yaml", + "JP-13-MIN-M-MAPS.yaml", + "JP-13-MIN-M-MCLHM.yaml", + "JP-13-MIN-M-ML.yaml", + "JP-13-MIN-M-MMA.yaml", + "JP-13-MIN-M-MSM.yaml", + "JP-13-MIN-M-MT.yaml", + "JP-13-MIN-M-NACT.yaml", + "JP-13-MIN-M-NM.yaml", + "JP-13-MIN-M-NMB.yaml", + "JP-13-MIN-M-OMA.yaml", + "JP-13-MIN-M-PSMARG.yaml", + "JP-13-MIN-M-SMA.yaml", + "JP-13-MIN-M-SOHMT.yaml", + "JP-13-MIN-M-TA.yaml", + "JP-13-MIN-M-TATG.yaml", + "JP-13-MIN-M-TMTAM.yaml", + "JP-13-MIN-M-UH.yaml", + "JP-13-MIN-M-YMM.yaml", + "JP-13-MIT-L-AAL.yaml", + "JP-13-MIT-L-ICUL.yaml", + "JP-13-MIT-L-JLCL.yaml", + "JP-13-MIT-L-KUML.yaml", + "JP-13-MIT-L-ML-mitakashiritsumitakaekimae_library.yaml", + "JP-13-MIT-L-ML-mitakashiritsuseibu_library.yaml", + "JP-13-MIT-L-ML-mitakashiritsutobu_library.yaml", + "JP-13-MIT-L-ML.yaml", + "JP-13-MIT-L-MLM.yaml", + "JP-13-MIT-L-NAOJL.yaml", + "JP-13-MIT-L-TUTSL.yaml", + "JP-13-MIT-M-GMM.yaml", + "JP-13-MIT-M-ICUHYMM.yaml", + "JP-13-MIT-M-MMECCJ.yaml", + "JP-13-MIY-L-HL.yaml", + "JP-13-MIY-L-M.yaml", + "JP-13-MIY-L-ML-miyoshishiikawa_library.yaml", + "JP-13-MIY-L-ML.yaml", + "JP-13-MIY-M-AHTM.yaml", + "JP-13-MIY-M-HCFHMH.yaml", + "JP-13-MIY-M-HYMF.yaml", + "JP-13-MOK-L-M.yaml", + "JP-13-MOK-L-MCL.yaml", + "JP-13-MOK-L-ML.yaml", + "JP-13-MOK-M-KMTCECAEH.yaml", + "JP-13-MOK-M-SJSM.yaml", + "JP-13-MOR-M-ICCSMC.yaml", + "JP-13-MUS-A-MHM-musashino_histrical_museum.yaml", + "JP-13-MUS-A-MHM.yaml", + "JP-13-MUS-L-AUL.yaml", + "JP-13-MUS-L-CAPSSU.yaml", + "JP-13-MUS-L-LNIIDMB.yaml", + "JP-13-MUS-L-ML-musashimurayamashiritsumitsugichiku_library.yaml", + "JP-13-MUS-L-ML-musashimurayamashiritsunakakubo_library.yaml", + "JP-13-MUS-L-ML-musashimurayamashiritsunakatochiku_library.yaml", + "JP-13-MUS-L-ML-musashimurayamashiritsuominamichiku_library.yaml", + "JP-13-MUS-L-ML-musashimurayamashiritsuraizuka_library.yaml", + "JP-13-MUS-L-ML-musashimurayamashiritsuzamboriinadairachiku_librar.yaml", + "JP-13-MUS-L-ML-musashinoshiritsukichijoji_library.yaml", + "JP-13-MUS-L-ML.yaml", + "JP-13-MUS-L-MMJS.yaml", + "JP-13-MUS-L-NMRDCL.yaml", + "JP-13-MUS-L-NVLSUNMSMC.yaml", + "JP-13-MUS-L-SUL.yaml", + "JP-13-MUS-M-IPZ.yaml", + "JP-13-MUS-M-KAM.yaml", + "JP-13-MUS-M-MCM.yaml", + "JP-13-MYO-L-I.yaml", + "JP-13-MYO-L-K.yaml", + "JP-13-MYO-L-SL.yaml", + "JP-13-MYO-L-TAFFTSC.yaml", + "JP-13-NAK-L-CL.yaml", + "JP-13-NAK-L-CRICC.yaml", + "JP-13-NAK-L-FL.yaml", + "JP-13-NAK-L-JCAL.yaml", + "JP-13-NAK-L-K-koekizaidanhojintokyozeimukyokaizeimukohoshiryoshi.yaml", + "JP-13-NAK-L-K.yaml", + "JP-13-NAK-L-KL-kokusaitankidaigaku_library.yaml", + "JP-13-NAK-L-KL.yaml", + "JP-13-NAK-L-M.yaml", + "JP-13-NAK-L-MRISEH.yaml", + "JP-13-NAK-L-MUNL.yaml", + "JP-13-NAK-L-NCCL.yaml", + "JP-13-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits.yaml", + "JP-13-NAK-L-NCCLM.yaml", + "JP-13-NAK-L-NCCLN.yaml", + "JP-13-NAK-L-NCEL.yaml", + "JP-13-NAK-L-NCKL.yaml", + "JP-13-NAK-L-NCML.yaml", + "JP-13-NAK-L-NCNL-nakano_city_nakanohigashi_library.yaml", + "JP-13-NAK-L-NCNL.yaml", + "JP-13-NAK-L-NCSL.yaml", + "JP-13-NAK-L-NL-nitobebunkatankidaigaku_library.yaml", + "JP-13-NAK-L-NL.yaml", + "JP-13-NAK-L-S.yaml", + "JP-13-NAK-L-T-tateyamamachiashikurakominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-tateyamamachichigakikominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-tateyamamachiiwakurakominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-tateyamamachikamagafuchikominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-tateyamamachiniikawakominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-tateyamamachiritakominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-tateyamamachishinsetokominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-tateyamamachitaniguchikominkantoshoshitsu.yaml", + "JP-13-NAK-L-T-teikyoheiseidaigakunakanokyampasumedeiaraiburarise.yaml", + "JP-13-NAK-L-T.yaml", + "JP-13-NAK-L-TCSL.yaml", + "JP-13-NAK-L-TL.yaml", + "JP-13-NAK-L-TPUNL.yaml", + "JP-13-NAK-L-YECTL.yaml", + "JP-13-NAK-M-ACMH.yaml", + "JP-13-NAK-M-ASMA.yaml", + "JP-13-NAK-M-KDNEM.yaml", + "JP-13-NAK-M-KFHM.yaml", + "JP-13-NAK-M-NMFA.yaml", + "JP-13-NAK-M-NZP.yaml", + "JP-13-NAK-M-TCSM.yaml", + "JP-13-NAK-M-TMA.yaml", + "JP-13-NAK-M-TMT.yaml", + "JP-13-NAK-M-TNCC.yaml", + "JP-13-NAK-M-TTCAOTLM.yaml", + "JP-13-NAK-M-YHCM.yaml", + "JP-13-NAK-M-YMNHM.yaml", + "JP-13-NAM-L-N-namerikawashihayatsukikazumichikukominkantoshoshit.yaml", + "JP-13-NAM-L-N-namerikawashinakakazumichikukominkantoshoshitsu.yaml", + "JP-13-NAM-L-N.yaml", + "JP-13-NAM-L-NCL.yaml", + "JP-13-NAM-L-NL.yaml", + "JP-13-NAM-M-HM.yaml", + "JP-13-NAM-M-NCM.yaml", + "JP-13-NAN-L-N.yaml", + "JP-13-NAN-L-NCCML.yaml", + "JP-13-NAN-L-NCFML.yaml", + "JP-13-NAN-L-NCIL.yaml", + "JP-13-NAN-L-NCJML.yaml", + "JP-13-NAN-L-NFKL-nantoshi_fukunoseibu_kouryusenta_libarary.yaml", + "JP-13-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary.yaml", + "JP-13-NAN-L-NFKL.yaml", + "JP-13-NAN-L-NHKL.yaml", + "JP-13-NAN-L-NKKL.yaml", + "JP-13-NAN-L-NL.yaml", + "JP-13-NAN-L-NMKL.yaml", + "JP-13-NAN-L-NNKL.yaml", + "JP-13-NAN-L-NTKL-nantoshi_takasenishi_kouryusenta_libarary.yaml", + "JP-13-NAN-L-NTKL.yaml", + "JP-13-NAN-L-NYKL.yaml", + "JP-13-NAN-M-AFM.yaml", + "JP-13-NAN-M-FAM.yaml", + "JP-13-NAN-M-FCCH.yaml", + "JP-13-NAN-M-IWCCH.yaml", + "JP-13-NAN-M-JHFFM.yaml", + "JP-13-NAN-M-MFMR.yaml", + "JP-13-NAN-M-MSMM.yaml", + "JP-13-NAN-M-NSE.yaml", + "JP-13-NAN-M-NSGFMH.yaml", + "JP-13-NAR-L-NCL.yaml", + "JP-13-NAR-L-NUEL.yaml", + "JP-13-NAR-M-NCKTM.yaml", + "JP-13-NAR-M-NGH.yaml", + "JP-13-NAR-M-OMA.yaml", + "JP-13-NAS-L-N.yaml", + "JP-13-NAS-L-NCL.yaml", + "JP-13-NAS-L-NL-nakagawamachibato_library.yaml", + "JP-13-NAS-L-NL-nakagawamachiogawa_library.yaml", + "JP-13-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library.yaml", + "JP-13-NAS-L-NL-nasushiobarashinishinasuno_library.yaml", + "JP-13-NAS-L-NL-nasushiobarashishiobara_library.yaml", + "JP-13-NAS-L-NL.yaml", + "JP-13-NAS-L-NLA.yaml", + "JP-13-NAS-L-NLH.yaml", + "JP-13-NAS-L-NLI.yaml", + "JP-13-NAS-L-NLK.yaml", + "JP-13-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits.yaml", + "JP-13-NAS-L-NLM-nasushiobarashishiobara_library_momijibunshitsu.yaml", + "JP-13-NAS-L-NLM.yaml", + "JP-13-NAS-L-NLN-nasushiobarashikuroiso_library_nabekakebunshitsu.yaml", + "JP-13-NAS-L-NLN.yaml", + "JP-13-NAS-L-NLO.yaml", + "JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_takabayashibunshits.yaml", + "JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_toyorabunshitsu.yaml", + "JP-13-NAS-L-NLT.yaml", + "JP-13-NAS-L-NTL.yaml", + "JP-13-NAS-L-ULN.yaml", + "JP-13-NAS-M-KFM.yaml", + "JP-13-NAS-M-KIM.yaml", + "JP-13-NAS-M-NCNM.yaml", + "JP-13-NAS-M-NH.yaml", + "JP-13-NAS-M-NHM.yaml", + "JP-13-NAS-M-NMBFM.yaml", + "JP-13-NAS-M-NMBHMA.yaml", + "JP-13-NAS-M-NMNLMH.yaml", + "JP-13-NAS-M-NOM.yaml", + "JP-13-NAS-M-NPWM.yaml", + "JP-13-NAS-M-NSP.yaml", + "JP-13-NAS-M-SFM.yaml", + "JP-13-NER-L-LRLJILPT.yaml", + "JP-13-NER-L-MLE.yaml", + "JP-13-NER-L-MUL.yaml", + "JP-13-NER-L-NL-nerimakuritsuheiwadai_library.yaml", + "JP-13-NER-L-NL-nerimakuritsuhikarigaoka_library.yaml", + "JP-13-NER-L-NL-nerimakuritsuinariyama_library.yaml", + "JP-13-NER-L-NL-nerimakuritsukasugacho_library.yaml", + "JP-13-NER-L-NL-nerimakuritsukotake_library.yaml", + "JP-13-NER-L-NL-nerimakuritsuminamioizumi_library.yaml", + "JP-13-NER-L-NL-nerimakuritsuminamitanaka_library.yaml", + "JP-13-NER-L-NL-nerimakuritsunukui_library.yaml", + "JP-13-NER-L-NL-nerimakuritsuoizumi_library.yaml", + "JP-13-NER-L-NL-nerimakuritsusekimachi_library.yaml", + "JP-13-NER-L-NL.yaml", + "JP-13-NER-L-NLE.yaml", + "JP-13-NER-L-SUSCL.yaml", + "JP-13-NER-M-AMNUCA.yaml", + "JP-13-NER-M-CAMT.yaml", + "JP-13-NER-M-HMA.yaml", + "JP-13-NER-M-KM.yaml", + "JP-13-NER-M-MAMMMI.yaml", + "JP-13-NER-M-NAM.yaml", + "JP-13-NII-L-N.yaml", + "JP-13-NII-M-NMM.yaml", + "JP-13-NIK-L-NL-nikkoshiritsufujihara_library.yaml", + "JP-13-NIK-L-NL-nikkoshiritsuimaichi_library.yaml", + "JP-13-NIK-L-NL.yaml", + "JP-13-NIK-M-4ANTM.yaml", + "JP-13-NIK-M-KHMAN.yaml", + "JP-13-NIK-M-NBGGSSUT.yaml", + "JP-13-NIK-M-NCLMNSMM.yaml", + "JP-13-NIK-M-NFSM.yaml", + "JP-13-NIK-M-NNSM.yaml", + "JP-13-NIS-L-HL-hinoharasonritsu_library.yaml", + "JP-13-NIS-L-HL.yaml", + "JP-13-NIS-L-HLO.yaml", + "JP-13-NIS-L-M-motosayamafurusatomoidetoshoshitsu.yaml", + "JP-13-NIS-L-M.yaml", + "JP-13-NIS-L-ML.yaml", + "JP-13-NIS-L-MTL.yaml", + "JP-13-NIS-L-MUNRA.yaml", + "JP-13-NIS-L-N.yaml", + "JP-13-NIS-L-NL-nishitokyoshihibarigaoka_library.yaml", + "JP-13-NIS-L-NL-nishitokyoshihoyaekimae_library.yaml", + "JP-13-NIS-L-NL-nishitokyoshishibakubo_library.yaml", + "JP-13-NIS-L-NL-nishitokyoshiyagisawa_library.yaml", + "JP-13-NIS-L-NL-nishitokyoshiyato_library.yaml", + "JP-13-NIS-L-NL.yaml", + "JP-13-NIS-L-NLS.yaml", + "JP-13-NIS-L-OL-okutamachoritsukori_library.yaml", + "JP-13-NIS-L-OL.yaml", + "JP-13-NIS-L-T.yaml", + "JP-13-NIS-L-WUA.yaml", + "JP-13-NIS-M-FMUT.yaml", + "JP-13-NIS-M-KCMHF.yaml", + "JP-13-NIS-M-KKMMLHM.yaml", + "JP-13-NIS-M-KYMFMM.yaml", + "JP-13-NIS-M-OVC.yaml", + "JP-13-NIS-M-TSC.yaml", + "JP-13-OGA-L-H.yaml", + "JP-13-OGA-L-O.yaml", + "JP-13-OGA-M-OMC.yaml", + "JP-13-OGI-L-LMSKU-library_for_maritime_sciences_kobe_university.yaml", + "JP-13-OKU-M-EMCMA.yaml", + "JP-13-OME-L-OL-omeshibaigo_library.yaml", + "JP-13-OME-L-OL-omeshidaimon_library.yaml", + "JP-13-OME-L-OL-omeshiimai_library.yaml", + "JP-13-OME-L-OL-omeshinagabuchi_library.yaml", + "JP-13-OME-L-OL-omeshinariki_library.yaml", + "JP-13-OME-L-OL-omeshiome_library.yaml", + "JP-13-OME-L-OL-omeshiosoki_library.yaml", + "JP-13-OME-L-OL-omeshisawai_library.yaml", + "JP-13-OME-L-OL-omeshishimmachi_library.yaml", + "JP-13-OME-L-OL.yaml", + "JP-13-OME-M-GAM.yaml", + "JP-13-OME-M-MVC.yaml", + "JP-13-OME-M-OMMAKZMG.yaml", + "JP-13-OME-M-OMMPH.yaml", + "JP-13-OME-M-ORP.yaml", + "JP-13-OME-M-RMPSE.yaml", + "JP-13-OME-M-SMTJHO.yaml", + "JP-13-OSH-L-OL.yaml", + "JP-13-OSH-M-OP.yaml", + "JP-13-OSH-M-PM.yaml", + "JP-13-OTA-L-IUHWL.yaml", + "JP-13-OTA-L-MSRL.yaml", + "JP-13-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu.yaml", + "JP-13-OTA-L-O-otakusangyopurazakankosangyojohokona.yaml", + "JP-13-OTA-L-O.yaml", + "JP-13-OTA-L-OCHL-ota_city_haneda_library.yaml", + "JP-13-OTA-L-OCHL.yaml", + "JP-13-OTA-L-OCIL-ota_city_iriarai_library.yaml", + "JP-13-OTA-L-OCIL.yaml", + "JP-13-OTA-L-OCKL-ota_city_kugahara_library.yaml", + "JP-13-OTA-L-OCKL.yaml", + "JP-13-OTA-L-OCML.yaml", + "JP-13-OTA-L-OCOL-ota_city_omorinishi_library.yaml", + "JP-13-OTA-L-OCOL.yaml", + "JP-13-OTA-L-OCRL.yaml", + "JP-13-OTA-L-OCSL-ota_city_senzokuike_library.yaml", + "JP-13-OTA-L-OCSL.yaml", + "JP-13-OTA-L-OCTL.yaml", + "JP-13-OTA-L-OL-otakuritsukamataekimae_library.yaml", + "JP-13-OTA-L-OL-otakuritsuomorihigashi_library.yaml", + "JP-13-OTA-L-OL-otakuritsuomoriminami_library.yaml", + "JP-13-OTA-L-OL-otawarashiritsukurobane_library.yaml", + "JP-13-OTA-L-OL.yaml", + "JP-13-OTA-L-T.yaml", + "JP-13-OTA-L-TLML.yaml", + "JP-13-OTA-L-TUMMC.yaml", + "JP-13-OTA-M-IR.yaml", + "JP-13-OTA-M-KTEROCTP.yaml", + "JP-13-OTA-M-OCFM.yaml", + "JP-13-OTA-M-OCKKMM.yaml", + "JP-13-OTA-M-OFT.yaml", + "JP-13-OTA-M-ONM.yaml", + "JP-13-OTA-M-OSHFMH.yaml", + "JP-13-OTA-M-OSNLMH.yaml", + "JP-13-OYA-A-OCA-oyama_city_archives.yaml", + "JP-13-OYA-A-OCA.yaml", + "JP-13-OYA-L-HL.yaml", + "JP-13-OYA-L-HLB.yaml", + "JP-13-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsuhanyukominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsuhigashikandakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsumatsuzawakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsumiyajimakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyabeshiritsuyabunamikominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyamashikinukominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyamashinakakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyamashinamaikominkantoshoshitsu.yaml", + "JP-13-OYA-L-O-oyamashisangawakominkantoshoshitsu.yaml", + "JP-13-OYA-L-O.yaml", + "JP-13-OYA-L-OCCLKBL.yaml", + "JP-13-OYA-L-OCCLOBL.yaml", + "JP-13-OYA-L-OCL.yaml", + "JP-13-OYA-L-OL.yaml", + "JP-13-OYA-L-OLM.yaml", + "JP-13-OYA-L-OLO.yaml", + "JP-13-OYA-L-ONCTL.yaml", + "JP-13-OYA-M-MAFO.yaml", + "JP-13-OYA-M-OCM.yaml", + "JP-13-OYA-M-THRM.yaml", + "JP-13-SAI-L-DLD.yaml", + "JP-13-SAI-L-DLN.yaml", + "JP-13-SAI-L-DML.yaml", + "JP-13-SAI-L-H-hokichoritsunikkokominkantoshoshitsu.yaml", + "JP-13-SAI-L-H.yaml", + "JP-13-SAI-L-HL-hiezuson_library.yaml", + "JP-13-SAI-L-HL-hokichokishimoto_library.yaml", + "JP-13-SAI-L-HL.yaml", + "JP-13-SAI-L-NL-nambuchoritsutemman_library.yaml", + "JP-13-SAI-L-NL.yaml", + "JP-13-SAI-M-IYNM.yaml", + "JP-13-SAI-M-SUMP.yaml", + "JP-13-SAI-M-THDT.yaml", + "JP-13-SAI-M-TPMHP.yaml", + "JP-13-SAI-M-TT.yaml", + "JP-13-SAK-L-SCL.yaml", + "JP-13-SAK-L-SL-sakurashikitsuregawa_library.yaml", + "JP-13-SAK-L-SL.yaml", + "JP-13-SAK-M-MSM.yaml", + "JP-13-SAK-M-SCMMKA.yaml", + "JP-13-SAN-L-SL-sanoshiritsukuzu_library.yaml", + "JP-13-SAN-L-SL-sanoshiritsutanuma_library.yaml", + "JP-13-SAN-L-SL-sanotankidaigaku_library.yaml", + "JP-13-SAN-L-SL.yaml", + "JP-13-SAN-M-AYSHMA.yaml", + "JP-13-SAN-M-KTMCA.yaml", + "JP-13-SAN-M-KUFMS.yaml", + "JP-13-SAN-M-SCM.yaml", + "JP-13-SAN-M-STAM.yaml", + "JP-13-SET-L-DML.yaml", + "JP-13-SET-L-HRFL.yaml", + "JP-13-SET-L-IESSU.yaml", + "JP-13-SET-L-IFSSU.yaml", + "JP-13-SET-L-JRSL.yaml", + "JP-13-SET-L-JWSCPEL.yaml", + "JP-13-SET-L-KLJ.yaml", + "JP-13-SET-L-KUL.yaml", + "JP-13-SET-L-NIHSL.yaml", + "JP-13-SET-L-NL.yaml", + "JP-13-SET-L-NSSUL.yaml", + "JP-13-SET-L-NUCCL.yaml", + "JP-13-SET-L-OSL.yaml", + "JP-13-SET-L-SAMAL.yaml", + "JP-13-SET-L-SCDL.yaml", + "JP-13-SET-L-SCFL.yaml", + "JP-13-SET-L-SCKKL.yaml", + "JP-13-SET-L-SCKL-setagaya_city_kamata_library.yaml", + "JP-13-SET-L-SCKL-setagaya_city_kasuya_library.yaml", + "JP-13-SET-L-SCKL-setagaya_city_kinuta_library.yaml", + "JP-13-SET-L-SCKL-setagaya_city_kyodo_library.yaml", + "JP-13-SET-L-SCKL.yaml", + "JP-13-SET-L-SCL.yaml", + "JP-13-SET-L-SCOL-setagaya_city_oyamadai_library.yaml", + "JP-13-SET-L-SCOL.yaml", + "JP-13-SET-L-SCSL-setagaya_city_sakuragaoka_library.yaml", + "JP-13-SET-L-SCSL-setagaya_city_setagaya_library.yaml", + "JP-13-SET-L-SCSL.yaml", + "JP-13-SET-L-SCTL.yaml", + "JP-13-SET-L-SCUL.yaml", + "JP-13-SET-L-SFSBL.yaml", + "JP-13-SET-L-SL.yaml", + "JP-13-SET-L-SUL.yaml", + "JP-13-SET-L-SWSUL.yaml", + "JP-13-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library.yaml", + "JP-13-SET-L-TL-tokyotoshidaigakusetagayakyampasu_library.yaml", + "JP-13-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library.yaml", + "JP-13-SET-L-TL.yaml", + "JP-13-SET-L-TMIMS.yaml", + "JP-13-SET-L-TUAL.yaml", + "JP-13-SET-M-FAMTUA.yaml", + "JP-13-SET-M-GM.yaml", + "JP-13-SET-M-HMAM.yaml", + "JP-13-SET-M-JPSOFHG.yaml", + "JP-13-SET-M-KARC.yaml", + "JP-13-SET-M-MZCHKU.yaml", + "JP-13-SET-M-NUCHSM.yaml", + "JP-13-SET-M-OPSOFHG.yaml", + "JP-13-SET-M-SAM.yaml", + "JP-13-SET-M-SM.yaml", + "JP-13-SET-M-SMH.yaml", + "JP-13-SET-M-SWSUKM.yaml", + "JP-13-SHI-L-A-aoyamagakuindaigakuhokadaigakuinroraiburari.yaml", + "JP-13-SHI-L-A.yaml", + "JP-13-SHI-L-AGUL.yaml", + "JP-13-SHI-L-AGWSJCL.yaml", + "JP-13-SHI-L-AIITL.yaml", + "JP-13-SHI-L-AL.yaml", + "JP-13-SHI-L-APCCUAL.yaml", + "JP-13-SHI-L-BGUL.yaml" ], - "last_index": 259 + "last_index": 369 } \ No newline at end of file diff --git a/data/custodian/CZ-52-HRA-L-FNHKLK.yaml b/data/custodian/CZ-52-HRA-L-FNHKLK.yaml index e3ef6d70dd..3c12e72368 100644 --- a/data/custodian/CZ-52-HRA-L-FNHKLK.yaml +++ b/data/custodian/CZ-52-HRA-L-FNHKLK.yaml @@ -51,13 +51,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-L-FNHKLK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-L-FNHKLK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-L-FNHKLK ghcid_numeric: 6228454488770966403 valid_from: '2025-12-06T23:37:24.453955+00:00' @@ -221,3 +222,36 @@ location: postal_code: 500 03 street_address: Na Hradě 91 normalization_timestamp: '2025-12-09T10:53:00.603715+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:08.855819+00:00' + source_url: http://ukaz.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://ukaz.cuni.cz/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: http://ukaz.cuni.cz + css_selector: '#logoImage' + retrieved_on: '2025-12-25T18:44:08.855819+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo knihovny + - claim_type: favicon_url + claim_value: http://ukaz.cuni.cz/custom/420CKIS_INST-UKAZ/img/favicon.ico + source_url: http://ukaz.cuni.cz + css_selector: '#viewCustomerFavIcon' + retrieved_on: '2025-12-25T18:44:08.855819+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: http://ukaz.cuni.cz + css_selector: '#ogImage' + retrieved_on: '2025-12-25T18:44:08.855819+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-HRA-L-KMHK.yaml b/data/custodian/CZ-52-HRA-L-KMHK.yaml index e727eb61c3..737bb4f278 100644 --- a/data/custodian/CZ-52-HRA-L-KMHK.yaml +++ b/data/custodian/CZ-52-HRA-L-KMHK.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-L-KMHK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-L-KMHK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-L-KMHK ghcid_numeric: 12429576662135733715 valid_from: '2025-12-06T23:37:17.740391+00:00' @@ -280,3 +281,22 @@ location: postal_code: 500 02 street_address: Wonkova 1262/1a normalization_timestamp: '2025-12-09T10:53:00.727743+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:27.417437+00:00' + source_url: https://www.knihovnahk.cz/online-katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovnahk.cz/favicon.ico + source_url: https://www.knihovnahk.cz/online-katalog + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:44:27.417437+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HRA-L-PPPSPCKKK.yaml b/data/custodian/CZ-52-HRA-L-PPPSPCKKK.yaml index 40ac952942..dc671c4662 100644 --- a/data/custodian/CZ-52-HRA-L-PPPSPCKKK.yaml +++ b/data/custodian/CZ-52-HRA-L-PPPSPCKKK.yaml @@ -1,5 +1,6 @@ original_entry: - name: Pedagogicko–psychologická poradna a Speciálně pedagogické centrum Královéhradeckého kraje - knihovna + name: Pedagogicko–psychologická poradna a Speciálně pedagogické centrum Královéhradeckého + kraje - knihovna institution_type: LIBRARY source: CH-Annotator (czech_unified_ch_annotator.yaml) identifiers: @@ -37,20 +38,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-L-PPPSPCKKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-L-PPPSPCKKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-L-PPPSPCKKK ghcid_numeric: 18431100605699690624 valid_from: '2025-12-06T23:37:43.655506+00:00' reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Pedagogicko–psychologická poradna a Speciálně pedagogické centrum Královéhradeckého kraje - knihovna + claim_value: Pedagogicko–psychologická poradna a Speciálně pedagogické centrum Královéhradeckého + kraje - knihovna source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -106,7 +109,8 @@ ch_annotator: verified_by: null entity_claims: - claim_type: full_name - claim_value: Pedagogicko–psychologická poradna a Speciálně pedagogické centrum Královéhradeckého kraje - knihovna + claim_value: Pedagogicko–psychologická poradna a Speciálně pedagogické centrum + Královéhradeckého kraje - knihovna property_uri: skos:prefLabel provenance: namespace: glam @@ -162,3 +166,22 @@ location: postal_code: 500 02 street_address: Na Okrouhlíku 1371/30 normalization_timestamp: '2025-12-09T06:51:37.793039+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:39.330453+00:00' + source_url: https://www.poradenstvikhk.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.poradenstvikhk.cz/wp-content/uploads/2020/09/cropped-logo_web-180x180.jpg + source_url: https://www.poradenstvikhk.cz + css_selector: '[document] > html > head > link:nth-of-type(41)' + retrieved_on: '2025-12-25T18:44:39.330453+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-HRA-L-TBSTK.yaml b/data/custodian/CZ-52-HRA-L-TBSTK.yaml index 8251cac387..84ab1e2044 100644 --- a/data/custodian/CZ-52-HRA-L-TBSTK.yaml +++ b/data/custodian/CZ-52-HRA-L-TBSTK.yaml @@ -40,13 +40,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-L-TBSTK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-L-TBSTK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-L-TBSTK ghcid_numeric: 11841349388778017393 valid_from: '2025-12-06T23:37:17.707652+00:00' @@ -166,3 +167,28 @@ location: postal_code: 500 03 street_address: Akademika Bedrny 531/8a, Věkoše normalization_timestamp: '2025-12-09T06:51:37.854921+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:51.126779+00:00' + source_url: https://www.trelleborg.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.trelleborg.com/-/media/themes/trelleborg/global/trelleborgbasetheme/images/favicons/apple-touch-icon.png?rev=72f33296767f43778b0657d709f1f4d1 + source_url: https://www.trelleborg.com + css_selector: '[document] > html.js.no-applicationcache > body > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:44:51.126779+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.trelleborg.com/-/media/group/startpage/bridge-2024.jpg?rev=b0f0e6cacf70456ca724fa4e30144e69 + source_url: https://www.trelleborg.com + css_selector: '[document] > html.js.no-applicationcache > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-25T18:44:51.126779+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 7 diff --git a/data/custodian/CZ-52-HRA-L-UKFFVHKSVK.yaml b/data/custodian/CZ-52-HRA-L-UKFFVHKSVK.yaml index e6b08f65bd..9137e294fa 100644 --- a/data/custodian/CZ-52-HRA-L-UKFFVHKSVK.yaml +++ b/data/custodian/CZ-52-HRA-L-UKFFVHKSVK.yaml @@ -49,13 +49,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-L-UKFFVHKSVK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-L-UKFFVHKSVK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-L-UKFFVHKSVK ghcid_numeric: 992097322968623264 valid_from: '2025-12-06T23:37:17.690775+00:00' @@ -229,3 +230,36 @@ location: postal_code: 500 05 street_address: Heyrovského 1203 normalization_timestamp: '2025-12-09T10:53:00.939488+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:02.771118+00:00' + source_url: https://ukaz.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://ukaz.cuni.cz/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://ukaz.cuni.cz + css_selector: '#logoImage' + retrieved_on: '2025-12-25T18:45:02.771118+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo knihovny + - claim_type: favicon_url + claim_value: https://ukaz.cuni.cz/custom/420CKIS_INST-UKAZ/img/favicon.ico + source_url: https://ukaz.cuni.cz + css_selector: '#viewCustomerFavIcon' + retrieved_on: '2025-12-25T18:45:02.771118+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://ukaz.cuni.cz + css_selector: '#ogImage' + retrieved_on: '2025-12-25T18:45:02.771118+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-HRA-L-UKLFVHKLK.yaml b/data/custodian/CZ-52-HRA-L-UKLFVHKLK.yaml index 099273c24e..11f99c20e3 100644 --- a/data/custodian/CZ-52-HRA-L-UKLFVHKLK.yaml +++ b/data/custodian/CZ-52-HRA-L-UKLFVHKLK.yaml @@ -55,13 +55,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-L-UKLFVHKLK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-L-UKLFVHKLK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-L-UKLFVHKLK ghcid_numeric: 13578923285217669258 valid_from: '2025-12-06T23:37:17.680972+00:00' @@ -235,3 +236,36 @@ location: postal_code: 500 03 street_address: Na Hradě 91 normalization_timestamp: '2025-12-09T10:53:00.968452+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:08.456133+00:00' + source_url: http://ukaz.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://ukaz.cuni.cz/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: http://ukaz.cuni.cz + css_selector: '#logoImage' + retrieved_on: '2025-12-25T18:45:08.456133+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo knihovny + - claim_type: favicon_url + claim_value: http://ukaz.cuni.cz/custom/420CKIS_INST-UKAZ/img/favicon.ico + source_url: http://ukaz.cuni.cz + css_selector: '#viewCustomerFavIcon' + retrieved_on: '2025-12-25T18:45:08.456133+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: http://ukaz.cuni.cz + css_selector: '#ogImage' + retrieved_on: '2025-12-25T18:45:08.456133+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-HRA-M-KMVCVHK.yaml b/data/custodian/CZ-52-HRA-M-KMVCVHK.yaml index 8edbfa9a7c..c571d9ecff 100644 --- a/data/custodian/CZ-52-HRA-M-KMVCVHK.yaml +++ b/data/custodian/CZ-52-HRA-M-KMVCVHK.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-M-KMVCVHK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-M-KMVCVHK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-M-KMVCVHK ghcid_numeric: 61224068916721861 valid_from: '2025-12-08T11:21:26.431725+00:00' @@ -300,3 +301,22 @@ location: postal_code: 500 03 street_address: Opletalova 334 normalization_timestamp: '2025-12-09T10:53:01.064148+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:22.860055+00:00' + source_url: https://muzeumhk.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeumhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeumhk.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:45:22.860055+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-HRA-M-MVCVHKPOPK.yaml b/data/custodian/CZ-52-HRA-M-MVCVHKPOPK.yaml index d1cab7354a..e0a93d6339 100644 --- a/data/custodian/CZ-52-HRA-M-MVCVHKPOPK.yaml +++ b/data/custodian/CZ-52-HRA-M-MVCVHKPOPK.yaml @@ -222,3 +222,22 @@ location: postal_code: 500 01 street_address: Opletalova 334 normalization_timestamp: '2025-12-09T10:53:01.095307+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:33.522128+00:00' + source_url: https://muzeumhk.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeumhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeumhk.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:45:33.522128+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-HRA-O-KSVHKK.yaml b/data/custodian/CZ-52-HRA-O-KSVHKK.yaml index e39b197ed2..ab2b255476 100644 --- a/data/custodian/CZ-52-HRA-O-KSVHKK.yaml +++ b/data/custodian/CZ-52-HRA-O-KSVHKK.yaml @@ -207,3 +207,22 @@ location: postal_code: 502 08 street_address: Československé armády 218 normalization_timestamp: '2025-12-09T10:53:01.122438+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:39.707561+00:00' + source_url: https://www.justice.cz/web/krajsky-soud-v-hradci-kralove + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://msp.gov.cz/o/justicecz-js-theme/images/favicon.ico + source_url: https://www.justice.cz/web/krajsky-soud-v-hradci-kralove + css_selector: '[document] > html.ltr.yui3-js-enabled > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:45:39.707561+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-HRA-O-SOAVHKSOAH.yaml b/data/custodian/CZ-52-HRA-O-SOAVHKSOAH.yaml index 7cf620f326..39b5118ef8 100644 --- a/data/custodian/CZ-52-HRA-O-SOAVHKSOAH.yaml +++ b/data/custodian/CZ-52-HRA-O-SOAVHKSOAH.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRA-O-SOAVHKSOAH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRA-O-SOAVHKSOAH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRA-O-SOAVHKSOAH ghcid_numeric: 10962754927424344271 valid_from: '2025-12-06T23:37:24.521139+00:00' @@ -219,3 +220,33 @@ location: postal_code: 500 02 street_address: Škroupova 695 normalization_timestamp: '2025-12-09T10:53:01.151684+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:44.729220+00:00' + source_url: https://vychodoceskearchivy.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-1.png + source_url: https://vychodoceskearchivy.cz + css_selector: '#cb-row--header-main > div.header--row-inner.header-main-inner + > div.customify-container > div.customify-grid.cb-row--desktop > div.row-v2.row-v2-main + > div.col-v2.col-v2-left > div.item--inner.builder-item--logo > div.site-branding.logo-left + > a.logo-link > img.site-img-logo' + retrieved_on: '2025-12-25T18:45:44.729220+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Státní oblastní archiv v Hradci Králové + - claim_type: favicon_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-180x180.png + source_url: https://vychodoceskearchivy.cz + css_selector: '[document] > html > head > link:nth-of-type(31)' + retrieved_on: '2025-12-25T18:45:44.729220+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-HRO-L-MKEH.yaml b/data/custodian/CZ-52-HRO-L-MKEH.yaml index d0264fd4b7..76fbe6d7cc 100644 --- a/data/custodian/CZ-52-HRO-L-MKEH.yaml +++ b/data/custodian/CZ-52-HRO-L-MKEH.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-HRO-L-MKEH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-HRO-L-MKEH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-HRO-L-MKEH ghcid_numeric: 5787443853226947598 valid_from: '2025-12-06T23:37:18.813455+00:00' @@ -220,3 +221,22 @@ location: postal_code: 549 31 street_address: Komenského nám. 8 normalization_timestamp: '2025-12-09T10:53:01.201924+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:58.635442+00:00' + source_url: https://katalog.knihovnahronov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovnahronov.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovnahronov.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:45:58.635442+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-JAN-L-MKJL.yaml b/data/custodian/CZ-52-JAN-L-MKJL.yaml index 7181ae70e2..94369e8cd0 100644 --- a/data/custodian/CZ-52-JAN-L-MKJL.yaml +++ b/data/custodian/CZ-52-JAN-L-MKJL.yaml @@ -233,3 +233,22 @@ location: postal_code: 542 25 street_address: Černohorská 15 normalization_timestamp: '2025-12-09T10:53:01.231697+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:04.369675+00:00' + source_url: https://trutnov.tritius.cz/library/janskelazne + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/janskelazne + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:46:04.369675+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-JAN-L-SLLJLSPDLV.yaml b/data/custodian/CZ-52-JAN-L-SLLJLSPDLV.yaml index eeb43f226c..25c9f711aa 100644 --- a/data/custodian/CZ-52-JAN-L-SLLJLSPDLV.yaml +++ b/data/custodian/CZ-52-JAN-L-SLLJLSPDLV.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JAN-L-SLLJLSPDLV - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JAN-L-SLLJLSPDLV valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JAN-L-SLLJLSPDLV ghcid_numeric: 11798107467249176292 valid_from: '2025-12-06T23:37:20.324212+00:00' @@ -215,3 +216,30 @@ location: postal_code: 524 25 street_address: Horní promenáda 268 normalization_timestamp: '2025-12-09T10:53:01.260604+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:10.307086+00:00' + source_url: https://www.janskelazne.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.janskelazne.com/wp-content/uploads/2016/05/cropped-ikona-180x180.jpg + source_url: https://www.janskelazne.com + css_selector: '[document] > html.wf-titilliumweb-n4-active.wf-titilliumweb-n7-active + > head > link:nth-of-type(27)' + retrieved_on: '2025-12-25T18:46:10.307086+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.janskelazne.com/wp-content/uploads/2022/01/lazne.jpg + source_url: https://www.janskelazne.com + css_selector: '[document] > html.wf-titilliumweb-n4-active.wf-titilliumweb-n7-active + > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-25T18:46:10.307086+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-52-JAR-L-OKVR.yaml b/data/custodian/CZ-52-JAR-L-OKVR.yaml index b35559a2d0..e19973ba13 100644 --- a/data/custodian/CZ-52-JAR-L-OKVR.yaml +++ b/data/custodian/CZ-52-JAR-L-OKVR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JAR-L-OKVR - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JAR-L-OKVR valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JAR-L-OKVR ghcid_numeric: 3144920629976007133 valid_from: '2025-12-06T23:37:35.310829+00:00' @@ -210,3 +211,22 @@ location: postal_code: 551 01 street_address: Rožnov 72 normalization_timestamp: '2025-12-09T10:53:01.284631+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:15.148824+00:00' + source_url: https://knihovnaroznov.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaroznov.files.webk.cz/logov.png + source_url: https://knihovnaroznov.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:46:15.148824+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-JAR-L-OKVS.yaml b/data/custodian/CZ-52-JAR-L-OKVS.yaml index 1c42af7cf8..fd8f811599 100644 --- a/data/custodian/CZ-52-JAR-L-OKVS.yaml +++ b/data/custodian/CZ-52-JAR-L-OKVS.yaml @@ -216,3 +216,22 @@ location: postal_code: 551 01 street_address: Šestajovice 70 normalization_timestamp: '2025-12-09T10:53:01.312363+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:19.844809+00:00' + source_url: https://knihovnasestajovice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnasestajovice.files.webk.cz/logov.png + source_url: https://knihovnasestajovice.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:46:19.844809+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-JAR-L-OKVV.yaml b/data/custodian/CZ-52-JAR-L-OKVV.yaml index c9760aca01..8c6f8e3a5c 100644 --- a/data/custodian/CZ-52-JAR-L-OKVV.yaml +++ b/data/custodian/CZ-52-JAR-L-OKVV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JAR-L-OKVV - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JAR-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JAR-L-OKVV ghcid_numeric: 3757321022233295177 valid_from: '2025-12-06T23:37:35.307880+00:00' @@ -210,3 +211,22 @@ location: postal_code: 551 01 street_address: Vlkov 7 normalization_timestamp: '2025-12-09T10:53:01.336934+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:25.519721+00:00' + source_url: https://jaromer.tritius.cz/library/vlkov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jaromer.tritius.cz/apple-touch-icon-180x180.png + source_url: https://jaromer.tritius.cz/library/vlkov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:46:25.519721+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-JAR-M-MMVJK.yaml b/data/custodian/CZ-52-JAR-M-MMVJK.yaml index e70944a485..bb8faf4723 100644 --- a/data/custodian/CZ-52-JAR-M-MMVJK.yaml +++ b/data/custodian/CZ-52-JAR-M-MMVJK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JAR-M-MMVJK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JAR-M-MMVJK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JAR-M-MMVJK ghcid_numeric: 13435744350321151087 valid_from: '2025-12-06T23:37:27.161876+00:00' @@ -213,3 +214,22 @@ location: postal_code: 551 01 street_address: Husova 295 normalization_timestamp: '2025-12-09T10:53:01.362874+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:30.364066+00:00' + source_url: https://jaromer.tritius.cz/library/muzjaro + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://jaromer.tritius.cz/apple-touch-icon-180x180.png + source_url: https://jaromer.tritius.cz/library/muzjaro + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:46:30.364066+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-JAS-L-OKJ.yaml b/data/custodian/CZ-52-JAS-L-OKJ.yaml index 72defd479d..58dfa49044 100644 --- a/data/custodian/CZ-52-JAS-L-OKJ.yaml +++ b/data/custodian/CZ-52-JAS-L-OKJ.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JAS-L-OKJ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JAS-L-OKJ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JAS-L-OKJ ghcid_numeric: 10675189934227070375 valid_from: '2025-12-06T23:37:35.319281+00:00' @@ -210,3 +211,22 @@ location: postal_code: 552 22 street_address: Jasenná 68 normalization_timestamp: '2025-12-09T10:53:01.389651+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:37.555576+00:00' + source_url: https://merkur.tritius.cz/library/jasenna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://merkur.tritius.cz/apple-touch-icon-180x180.png + source_url: https://merkur.tritius.cz/library/jasenna + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:46:37.555576+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-JAV-L-MKJ.yaml b/data/custodian/CZ-52-JAV-L-MKJ.yaml index 3f10b8eb6c..e056211c9e 100644 --- a/data/custodian/CZ-52-JAV-L-MKJ.yaml +++ b/data/custodian/CZ-52-JAV-L-MKJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JAV-L-MKJ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JAV-L-MKJ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JAV-L-MKJ ghcid_numeric: 14458582073744292472 valid_from: '2025-12-06T23:37:35.493325+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 11 street_address: Javornice 3 normalization_timestamp: '2025-12-09T10:53:01.413687+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:43.124539+00:00' + source_url: https://rychnov.tritius.cz/library/javornice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rychnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://rychnov.tritius.cz/library/javornice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:46:43.124539+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-JES-A-SOAJ-statni_okresni_archiv_jesenik.yaml b/data/custodian/CZ-52-JES-A-SOAJ-statni_okresni_archiv_jesenik.yaml index 02c9293d4f..8094ead576 100644 --- a/data/custodian/CZ-52-JES-A-SOAJ-statni_okresni_archiv_jesenik.yaml +++ b/data/custodian/CZ-52-JES-A-SOAJ-statni_okresni_archiv_jesenik.yaml @@ -228,3 +228,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní okresní archiv Jeseník official youtube_search_timestamp: '2025-12-09T09:32:21.451807+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:50.509221+00:00' + source_url: http://www.archives.cz/web/soka/jesenik/o_archivu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.archives.cz/web/favicon/safari-pinned-tab.svg + source_url: http://www.archives.cz/web/soka/jesenik/o_archivu + css_selector: '[document] > html.js.no-touchevents > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:46:50.509221+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 12 diff --git a/data/custodian/CZ-52-JIC-L-KVCVJ.yaml b/data/custodian/CZ-52-JIC-L-KVCVJ.yaml index 4a333088c0..23f5706d96 100644 --- a/data/custodian/CZ-52-JIC-L-KVCVJ.yaml +++ b/data/custodian/CZ-52-JIC-L-KVCVJ.yaml @@ -580,3 +580,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/ps1Howc9Zdw/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:47:03.657915+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:47:03.657915+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-JIC-L-MKM.yaml b/data/custodian/CZ-52-JIC-L-MKM.yaml index e4bc4622f6..c79133ceba 100644 --- a/data/custodian/CZ-52-JIC-L-MKM.yaml +++ b/data/custodian/CZ-52-JIC-L-MKM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JIC-L-MKM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JIC-L-MKM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JIC-L-MKM ghcid_numeric: 16087549957052253609 valid_from: '2025-12-06T23:37:35.200069+00:00' @@ -210,3 +211,22 @@ location: postal_code: 506 01 street_address: Milíčeves 1 normalization_timestamp: '2025-12-09T10:53:01.559957+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:47:17.666465+00:00' + source_url: https://knihovnamiliceves.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnamiliceves.files.webk.cz/logov.png + source_url: https://knihovnamiliceves.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:47:17.666465+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-JIC-L-MKV.yaml b/data/custodian/CZ-52-JIC-L-MKV.yaml index fa20266389..a4a561b06f 100644 --- a/data/custodian/CZ-52-JIC-L-MKV.yaml +++ b/data/custodian/CZ-52-JIC-L-MKV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JIC-L-MKV - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JIC-L-MKV valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JIC-L-MKV ghcid_numeric: 17209594163432175618 valid_from: '2025-12-06T23:37:35.225656+00:00' @@ -210,3 +211,22 @@ location: postal_code: 506 01 street_address: Vitiněves 110 normalization_timestamp: '2025-12-09T10:53:01.636870+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:47:34.216738+00:00' + source_url: https://katalog.knihovna.jicin.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:47:34.216738+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-JIC-L-MKVO.yaml b/data/custodian/CZ-52-JIC-L-MKVO.yaml index f14e523b5b..6038bdcd3b 100644 --- a/data/custodian/CZ-52-JIC-L-MKVO.yaml +++ b/data/custodian/CZ-52-JIC-L-MKVO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JIC-L-MKVO - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JIC-L-MKVO valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JIC-L-MKVO ghcid_numeric: 15170314871997505093 valid_from: '2025-12-06T23:37:35.242293+00:00' @@ -210,3 +211,22 @@ location: postal_code: 506 01 street_address: Ostružno 5 normalization_timestamp: '2025-12-09T10:53:01.662918+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:47:39.124344+00:00' + source_url: https://knihovnaostruzno.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaostruzno.webk.cz/themes/cbdb-klasicky/letni/logo3.png + source_url: https://knihovnaostruzno.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:47:39.124344+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-JIC-L-OKVJ.yaml b/data/custodian/CZ-52-JIC-L-OKVJ.yaml index a51fccdf4a..2bb885d3a0 100644 --- a/data/custodian/CZ-52-JIC-L-OKVJ.yaml +++ b/data/custodian/CZ-52-JIC-L-OKVJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JIC-L-OKVJ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JIC-L-OKVJ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JIC-L-OKVJ ghcid_numeric: 5547736778974733790 valid_from: '2025-12-06T23:37:43.485595+00:00' @@ -205,3 +206,22 @@ location: postal_code: 507 31 street_address: Jičíněves 82 normalization_timestamp: '2025-12-09T10:53:01.688954+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:47:44.346875+00:00' + source_url: https://www.jicineves.cz/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jicineves.cz/image.php?nid=15630&oid=8354430&width=36 + source_url: https://www.jicineves.cz/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-25T18:47:44.346875+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-JIC-M-RMGJ.yaml b/data/custodian/CZ-52-JIC-M-RMGJ.yaml index e0bb3225b5..645961728c 100644 --- a/data/custodian/CZ-52-JIC-M-RMGJ.yaml +++ b/data/custodian/CZ-52-JIC-M-RMGJ.yaml @@ -273,3 +273,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Regionální muzeum a galerie Jičín official youtube_search_timestamp: '2025-12-09T09:32:22.782627+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:21.931712+00:00' + source_url: http://www.muzeumhry.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.muzeumhry.cz/templates/muzeumjicin/apple-touch-icon.png + source_url: http://www.muzeumhry.cz + css_selector: '[document] > html.eb-1-open.eb- > head > link:nth-of-type(12)' + retrieved_on: '2025-12-25T18:48:21.931712+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-52-JIC-M-RMGVJK.yaml b/data/custodian/CZ-52-JIC-M-RMGVJK.yaml index 6417c9d181..ad43f8c1eb 100644 --- a/data/custodian/CZ-52-JIC-M-RMGVJK.yaml +++ b/data/custodian/CZ-52-JIC-M-RMGVJK.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JIC-M-RMGVJK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JIC-M-RMGVJK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JIC-M-RMGVJK ghcid_numeric: 10453932008499387053 valid_from: '2025-12-06T23:37:17.839426+00:00' @@ -267,3 +268,22 @@ location: postal_code: 506 01 street_address: Valdštejnovo nám. 1 normalization_timestamp: '2025-12-09T10:53:01.739418+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:27.012808+00:00' + source_url: https://www.muzeumhry.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.muzeumhry.cz/templates/muzeumjicin/apple-touch-icon.png + source_url: https://www.muzeumhry.cz + css_selector: '[document] > html.eb-1-open.eb- > head > link:nth-of-type(12)' + retrieved_on: '2025-12-25T18:48:27.012808+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-52-JIC-O-SOAVHKSOAJ.yaml b/data/custodian/CZ-52-JIC-O-SOAVHKSOAJ.yaml index dd3cbdeb37..aa6be5b950 100644 --- a/data/custodian/CZ-52-JIC-O-SOAVHKSOAJ.yaml +++ b/data/custodian/CZ-52-JIC-O-SOAVHKSOAJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JIC-O-SOAVHKSOAJ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JIC-O-SOAVHKSOAJ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JIC-O-SOAVHKSOAJ ghcid_numeric: 7839031684782375922 valid_from: '2025-12-06T23:37:17.846006+00:00' @@ -219,3 +220,33 @@ location: postal_code: 506 01 street_address: Raisova 533 normalization_timestamp: '2025-12-09T10:53:01.771472+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:32.121923+00:00' + source_url: https://vychodoceskearchivy.cz/home/kontakty/statni-okresni-archiv-jicin + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-1.png + source_url: https://vychodoceskearchivy.cz/home/kontakty/statni-okresni-archiv-jicin + css_selector: '#cb-row--header-main > div.header--row-inner.header-main-inner + > div.customify-container > div.customify-grid.cb-row--desktop > div.row-v2.row-v2-main + > div.col-v2.col-v2-left > div.item--inner.builder-item--logo > div.site-branding.logo-left + > a.logo-link > img.site-img-logo' + retrieved_on: '2025-12-25T18:48:32.121923+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Státní oblastní archiv v Hradci Králové + - claim_type: favicon_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-180x180.png + source_url: https://vychodoceskearchivy.cz/home/kontakty/statni-okresni-archiv-jicin + css_selector: '[document] > html > head > link:nth-of-type(31)' + retrieved_on: '2025-12-25T18:48:32.121923+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-JIL-L-MKVJ.yaml b/data/custodian/CZ-52-JIL-L-MKVJ.yaml index 875acbf2a7..f67a66d530 100644 --- a/data/custodian/CZ-52-JIL-L-MKVJ.yaml +++ b/data/custodian/CZ-52-JIL-L-MKVJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-JIL-L-MKVJ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-JIL-L-MKVJ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-JIL-L-MKVJ ghcid_numeric: 2886104137699018747 valid_from: '2025-12-06T23:37:35.495954+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 72 street_address: Jílovice 103 normalization_timestamp: '2025-12-09T10:53:01.797371+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:39.561343+00:00' + source_url: https://kmhk.tritius.cz/library/jilovice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/jilovice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:48:39.561343+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-JIN-L-UCPKS.yaml b/data/custodian/CZ-52-JIN-L-UCPKS.yaml index e632132f7e..f2bc11aca9 100644 --- a/data/custodian/CZ-52-JIN-L-UCPKS.yaml +++ b/data/custodian/CZ-52-JIN-L-UCPKS.yaml @@ -190,3 +190,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1622062 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:52.316595+00:00' + source_url: https://ucp.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ucp.cz/files/responsive/152/0/1-34.png + source_url: https://ucp.cz + css_selector: '[document] > html.html.js > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:48:52.316595+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 152x152 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-KAC-L-MKKL.yaml b/data/custodian/CZ-52-KAC-L-MKKL.yaml index ba996819e5..9aa3fc1a2c 100644 --- a/data/custodian/CZ-52-KAC-L-MKKL.yaml +++ b/data/custodian/CZ-52-KAC-L-MKKL.yaml @@ -211,3 +211,30 @@ location: postal_code: 506 01 street_address: Kacákova Lhota 48 normalization_timestamp: '2025-12-09T10:53:01.819141+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:57.044583+00:00' + source_url: https://knihovnakacakovalhota.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnakacakovalhota.webk.cz/themes/new/orange/logo1.png + source_url: https://knihovnakacakovalhota.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-25T18:48:57.044583+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnakacakovalhota.webk.cz/themes/new/favicon.ico + source_url: https://knihovnakacakovalhota.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:48:57.044583+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KOC-L-OKK.yaml b/data/custodian/CZ-52-KOC-L-OKK.yaml index 8dd069a825..25d75c2a37 100644 --- a/data/custodian/CZ-52-KOC-L-OKK.yaml +++ b/data/custodian/CZ-52-KOC-L-OKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOC-L-OKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOC-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOC-L-OKK ghcid_numeric: 9283449121097156130 valid_from: '2025-12-06T23:37:35.652038+00:00' @@ -210,3 +211,22 @@ location: postal_code: 544 64 street_address: Kocbeře 53 normalization_timestamp: '2025-12-09T10:53:01.841796+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:09.373056+00:00' + source_url: https://trutnov.tritius.cz/library/kocbere + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/kocbere + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:49:09.373056+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-KOH-L-MKK.yaml b/data/custodian/CZ-52-KOH-L-MKK.yaml index 8d1b3a946b..9afc42afad 100644 --- a/data/custodian/CZ-52-KOH-L-MKK.yaml +++ b/data/custodian/CZ-52-KOH-L-MKK.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOH-L-MKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOH-L-MKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOH-L-MKK ghcid_numeric: 1554770346807155120 valid_from: '2025-12-06T23:37:35.654711+00:00' @@ -210,3 +211,22 @@ location: postal_code: 544 66 street_address: Kohoutov 65 normalization_timestamp: '2025-12-09T10:53:01.865458+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:15.044091+00:00' + source_url: https://trutnov.tritius.cz/library/kohoutov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/kohoutov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:49:15.044091+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-KOP-L-KK.yaml b/data/custodian/CZ-52-KOP-L-KK.yaml index f941b95fea..19310c8417 100644 --- a/data/custodian/CZ-52-KOP-L-KK.yaml +++ b/data/custodian/CZ-52-KOP-L-KK.yaml @@ -221,3 +221,22 @@ location: postal_code: 507 32 street_address: Hilmarova 86 normalization_timestamp: '2025-12-09T10:53:01.891574+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:24.857343+00:00' + source_url: https://kvc.kopidlno.cz/knihovna/d-1473/p1=1458 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kvc.kopidlno.cz/html/images/favicon.ico + source_url: https://kvc.kopidlno.cz/knihovna/d-1473/p1=1458 + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T18:49:24.857343+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KOP-L-MKZ.yaml b/data/custodian/CZ-52-KOP-L-MKZ.yaml index 8a08345d72..96b10889fe 100644 --- a/data/custodian/CZ-52-KOP-L-MKZ.yaml +++ b/data/custodian/CZ-52-KOP-L-MKZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOP-L-MKZ - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOP-L-MKZ valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOP-L-MKZ ghcid_numeric: 11747279985805929184 valid_from: '2025-12-08T11:21:25.294570+00:00' @@ -215,3 +216,22 @@ location: postal_code: 507 32 street_address: Židovice 7 normalization_timestamp: '2025-12-09T10:53:01.916144+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:29.484481+00:00' + source_url: https://knihovnazidovice.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnazidovice.webk.cz/themes/cbdb-klasicky/default/logo2.png + source_url: https://knihovnazidovice.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:49:29.484481+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-KOP-L-MLKVB.yaml b/data/custodian/CZ-52-KOP-L-MLKVB.yaml index 37ac623c15..44ada4b720 100644 --- a/data/custodian/CZ-52-KOP-L-MLKVB.yaml +++ b/data/custodian/CZ-52-KOP-L-MLKVB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOP-L-MLKVB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOP-L-MLKVB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOP-L-MLKVB ghcid_numeric: 11128966623772803571 valid_from: '2025-12-06T23:37:35.154338+00:00' @@ -210,3 +211,22 @@ location: postal_code: 507 32 street_address: Běchary 5 normalization_timestamp: '2025-12-09T10:53:01.937667+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:36.354239+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:49:36.354239+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KOS-L-MKB.yaml b/data/custodian/CZ-52-KOS-L-MKB.yaml index 9844a9ef0e..f4bc66dbfc 100644 --- a/data/custodian/CZ-52-KOS-L-MKB.yaml +++ b/data/custodian/CZ-52-KOS-L-MKB.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOS-L-MKB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOS-L-MKB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOS-L-MKB ghcid_numeric: 6964154266200985942 valid_from: '2025-12-06T23:37:35.556884+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 45 street_address: Borovnice 5 normalization_timestamp: '2025-12-09T10:53:01.962174+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:41.565954+00:00' + source_url: https://borovnice-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://borovnice-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://borovnice-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T18:49:41.565954+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KOS-L-MKKH.yaml b/data/custodian/CZ-52-KOS-L-MKKH.yaml index 8cd9a37b6b..86526790f1 100644 --- a/data/custodian/CZ-52-KOS-L-MKKH.yaml +++ b/data/custodian/CZ-52-KOS-L-MKKH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOS-L-MKKH - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOS-L-MKKH valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOS-L-MKKH ghcid_numeric: 9439104930487871239 valid_from: '2025-12-06T23:37:35.501565+00:00' @@ -207,3 +208,22 @@ location: postal_code: 517 41 street_address: Kostelecké Horky 58 normalization_timestamp: '2025-12-09T10:53:01.991600+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:47.175356+00:00' + source_url: https://kosteleckehorky-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kosteleckehorky-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://kosteleckehorky-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T18:49:47.175356+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KOS-L-MKS.yaml b/data/custodian/CZ-52-KOS-L-MKS.yaml index 5867dbd691..5ae20ce175 100644 --- a/data/custodian/CZ-52-KOS-L-MKS.yaml +++ b/data/custodian/CZ-52-KOS-L-MKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOS-L-MKS - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOS-L-MKS valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOS-L-MKS ghcid_numeric: 7961006423440510656 valid_from: '2025-12-06T23:37:35.582031+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 41 street_address: Svídnice 36 normalization_timestamp: '2025-12-09T10:53:02.017699+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:52.688771+00:00' + source_url: https://svidnice-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://svidnice-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://svidnice-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T18:49:52.688771+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KOS-L-OKK.yaml b/data/custodian/CZ-52-KOS-L-OKK.yaml index e16de92a12..da914c04ea 100644 --- a/data/custodian/CZ-52-KOS-L-OKK.yaml +++ b/data/custodian/CZ-52-KOS-L-OKK.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOS-L-OKK - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOS-L-OKK valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOS-L-OKK ghcid_numeric: 11715308265220798942 valid_from: '2025-12-06T23:37:34.970844+00:00' @@ -216,3 +217,30 @@ location: postal_code: 503 65 street_address: Kosičky 1 normalization_timestamp: '2025-12-09T10:53:02.066191+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:59.396834+00:00' + source_url: https://knihovnakosicky.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnakosicky.files.webk.cz/logov.png + source_url: https://knihovnakosicky.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-25T18:49:59.396834+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnakosicky.webk.cz/themes/new/favicon.ico + source_url: https://knihovnakosicky.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:49:59.396834+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KOS-L-OKLUP.yaml b/data/custodian/CZ-52-KOS-L-OKLUP.yaml index b7db2036ff..6e26f30e42 100644 --- a/data/custodian/CZ-52-KOS-L-OKLUP.yaml +++ b/data/custodian/CZ-52-KOS-L-OKLUP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-KOS-L-OKLUP - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-KOS-L-OKLUP valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-KOS-L-OKLUP ghcid_numeric: 12955209635091961915 valid_from: '2025-12-06T23:37:35.498878+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 41 street_address: Lhoty u Potštejna 34 normalization_timestamp: '2025-12-09T10:53:02.094759+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:04.295899+00:00' + source_url: https://www.obeclhoty.cz/?s=obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obeclhoty.cz/favicon.png + source_url: https://www.obeclhoty.cz/?s=obecni-knihovna + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:50:04.295899+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-KRA-L-MKVPK.yaml b/data/custodian/CZ-52-KRA-L-MKVPK.yaml index 0f97191a36..7c202acec1 100644 --- a/data/custodian/CZ-52-KRA-L-MKVPK.yaml +++ b/data/custodian/CZ-52-KRA-L-MKVPK.yaml @@ -246,3 +246,31 @@ location: youtube_status: NOT_FOUND youtube_search_query: Místní knihovna v Praze - Královicích official youtube_search_timestamp: '2025-12-09T09:32:26.755635+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:16.387831+00:00' + source_url: https://www.mckralovice.cz/mistni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.mckralovice.cz/img/ico-logo.png + source_url: https://www.mckralovice.cz/mistni-knihovna + css_selector: '#menu1 > a.navbar-brand.py-3 > div.d-flex.align-items-center > + div > img' + retrieved_on: '2025-12-25T18:50:16.387831+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Městská část Praha - Královice - Úřad městské části + - claim_type: favicon_url + claim_value: https://www.mckralovice.cz/img/apple-touch-icon-144-precomposed.png + source_url: https://www.mckralovice.cz/mistni-knihovna + css_selector: '[document] > html.no-js > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:50:16.387831+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 144x144 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-KUK-L-OKK.yaml b/data/custodian/CZ-52-KUK-L-OKK.yaml index 00a97de954..6c373941db 100644 --- a/data/custodian/CZ-52-KUK-L-OKK.yaml +++ b/data/custodian/CZ-52-KUK-L-OKK.yaml @@ -215,3 +215,22 @@ location: postal_code: 544 43 street_address: Kuks 12 normalization_timestamp: '2025-12-09T10:53:02.170557+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:22.034749+00:00' + source_url: https://trutnov.tritius.cz/library/kuks + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/kuks + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:50:22.034749+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-KUK-M-CFMVK.yaml b/data/custodian/CZ-52-KUK-M-CFMVK.yaml index faf80ca725..a05b521fb0 100644 --- a/data/custodian/CZ-52-KUK-M-CFMVK.yaml +++ b/data/custodian/CZ-52-KUK-M-CFMVK.yaml @@ -216,3 +216,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: České farmaceutické muzeum v Kuksu official youtube_search_timestamp: '2025-12-09T09:32:27.420691+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:27.034532+00:00' + source_url: https://www.ceska-apatyka.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ceska-apatyka.cz/ikony/apple-touch-icon-180x180.png + source_url: https://www.ceska-apatyka.cz + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T18:50:27.034532+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: http://www.ceska-apatyka.cz/images/profile_photo_1200x628.jpg + source_url: https://www.ceska-apatyka.cz + css_selector: '[document] > html > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-25T18:50:27.034532+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 11 diff --git a/data/custodian/CZ-52-KVA-L-MKVK.yaml b/data/custodian/CZ-52-KVA-L-MKVK.yaml index 41fae562be..2d04827c2e 100644 --- a/data/custodian/CZ-52-KVA-L-MKVK.yaml +++ b/data/custodian/CZ-52-KVA-L-MKVK.yaml @@ -221,3 +221,22 @@ location: postal_code: 517 02 street_address: Kvasiny 81 normalization_timestamp: '2025-12-09T10:53:02.227440+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:41.031105+00:00' + source_url: https://rychnov.tritius.cz/library/kvasiny + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rychnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://rychnov.tritius.cz/library/kvasiny + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:50:41.031105+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-LAH-E-KMC.yaml b/data/custodian/CZ-52-LAH-E-KMC.yaml index aa603baf17..5cfb355a22 100644 --- a/data/custodian/CZ-52-LAH-E-KMC.yaml +++ b/data/custodian/CZ-52-LAH-E-KMC.yaml @@ -225,3 +225,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Knihovna Montessori ČR official youtube_search_timestamp: '2025-12-09T09:32:28.089837+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:46.768230+00:00' + source_url: https://www.montessoricr.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.montessoricr.cz/templates/theme3092/favicon.ico + source_url: https://www.montessoricr.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:50:46.768230+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LAH-L-LKM.yaml b/data/custodian/CZ-52-LAH-L-LKM.yaml index 515a95d78a..dad4fc7822 100644 --- a/data/custodian/CZ-52-LAH-L-LKM.yaml +++ b/data/custodian/CZ-52-LAH-L-LKM.yaml @@ -222,3 +222,23 @@ location: youtube_status: NOT_FOUND youtube_search_query: Lékařská knihovna Medindex official youtube_search_timestamp: '2025-12-09T09:32:28.759779+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:52.566882+00:00' + source_url: https://www.medindex.cz/knihovna/knihy-novinky + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.medindex.cz/knihovna/images/favicon.ico + source_url: https://www.medindex.cz/knihovna/knihy-novinky + css_selector: '[document] > html.wf-sommetrounded-n4-active.wf-sommetrounded-n3-active + > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:50:52.566882+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LAZ-L-MKC.yaml b/data/custodian/CZ-52-LAZ-L-MKC.yaml index 087a04cd55..d11ff9b557 100644 --- a/data/custodian/CZ-52-LAZ-L-MKC.yaml +++ b/data/custodian/CZ-52-LAZ-L-MKC.yaml @@ -215,3 +215,22 @@ location: postal_code: 507 81 street_address: Choteč 129 normalization_timestamp: '2025-12-09T10:53:02.255705+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:59.717197+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:50:59.717197+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LHO-L-MKVU.yaml b/data/custodian/CZ-52-LHO-L-MKVU.yaml index ae24560a78..90af86bd66 100644 --- a/data/custodian/CZ-52-LHO-L-MKVU.yaml +++ b/data/custodian/CZ-52-LHO-L-MKVU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LHO-L-MKVU - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LHO-L-MKVU valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LHO-L-MKVU ghcid_numeric: 2083611789860285521 valid_from: '2025-12-06T23:37:24.483526+00:00' @@ -210,3 +211,22 @@ location: postal_code: 503 27 street_address: Urbanice 44 normalization_timestamp: '2025-12-09T10:53:02.292307+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:05.442536+00:00' + source_url: https://urbanice.cz/default/default/6345_knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://urbanice.cz/files/urbanice/logo/apple-touch-icon.png + source_url: https://urbanice.cz/default/default/6345_knihovna + css_selector: '[document] > html.fontSize--normal.show--consent > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T18:51:05.442536+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 4 diff --git a/data/custodian/CZ-52-LHO-L-OKLPL.yaml b/data/custodian/CZ-52-LHO-L-OKLPL.yaml index c818b20607..d06ce0376e 100644 --- a/data/custodian/CZ-52-LHO-L-OKLPL.yaml +++ b/data/custodian/CZ-52-LHO-L-OKLPL.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LHO-L-OKLPL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LHO-L-OKLPL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LHO-L-OKLPL ghcid_numeric: 14717452041070480329 valid_from: '2025-12-06T23:37:42.539296+00:00' @@ -212,3 +213,22 @@ location: postal_code: 503 27 street_address: Lhota pod Libčany 46 normalization_timestamp: '2025-12-09T10:53:02.320674+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:11.249707+00:00' + source_url: https://kmhk.tritius.cz/library/lhotaplib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/lhotaplib + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:51:11.249707+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-LHO-L-OKO.yaml b/data/custodian/CZ-52-LHO-L-OKO.yaml index d7fb1ec858..e371ca8c65 100644 --- a/data/custodian/CZ-52-LHO-L-OKO.yaml +++ b/data/custodian/CZ-52-LHO-L-OKO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LHO-L-OKO - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LHO-L-OKO valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LHO-L-OKO ghcid_numeric: 7374141814016532372 valid_from: '2025-12-06T23:37:35.047996+00:00' @@ -210,3 +211,22 @@ location: postal_code: 503 27 street_address: Osičky 19 normalization_timestamp: '2025-12-09T10:53:02.352460+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:16.256419+00:00' + source_url: https://www.osicky.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.osicky.cz/image.php?nid=7018&oid=8295376&width=32 + source_url: https://www.osicky.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-25T18:51:16.256419+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LHO-L-OKR.yaml b/data/custodian/CZ-52-LHO-L-OKR.yaml index e88d45fdd7..a3ab6dd9e6 100644 --- a/data/custodian/CZ-52-LHO-L-OKR.yaml +++ b/data/custodian/CZ-52-LHO-L-OKR.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LHO-L-OKR - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LHO-L-OKR valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LHO-L-OKR ghcid_numeric: 1330806854732375639 valid_from: '2025-12-06T23:37:34.982061+00:00' @@ -210,3 +211,22 @@ location: postal_code: 503 27 street_address: Roudnice 100 normalization_timestamp: '2025-12-09T10:53:02.380511+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:21.857128+00:00' + source_url: https://kmhk.tritius.cz/library/roudnice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/roudnice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:51:21.857128+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-LHO-L-OKS.yaml b/data/custodian/CZ-52-LHO-L-OKS.yaml index 01d36e3ffd..9e6cecfabc 100644 --- a/data/custodian/CZ-52-LHO-L-OKS.yaml +++ b/data/custodian/CZ-52-LHO-L-OKS.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LHO-L-OKS - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LHO-L-OKS valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LHO-L-OKS ghcid_numeric: 10799315689874061057 valid_from: '2025-12-06T23:37:35.084207+00:00' @@ -213,3 +214,22 @@ location: postal_code: 503 27 street_address: Syrovátka 69 normalization_timestamp: '2025-12-09T10:53:02.425903+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:27.479970+00:00' + source_url: https://kmhk.tritius.cz/library/syrovatka + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/syrovatka + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:51:27.479970+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-LHO-L-OKT.yaml b/data/custodian/CZ-52-LHO-L-OKT.yaml index 35c3df75ed..a2385f2ef0 100644 --- a/data/custodian/CZ-52-LHO-L-OKT.yaml +++ b/data/custodian/CZ-52-LHO-L-OKT.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LHO-L-OKT - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LHO-L-OKT valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LHO-L-OKT ghcid_numeric: 6918419242000055560 valid_from: '2025-12-06T23:37:34.979220+00:00' @@ -214,3 +215,22 @@ location: postal_code: 503 27 street_address: Těchlovice 18 normalization_timestamp: '2025-12-09T10:53:02.480619+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:32.661098+00:00' + source_url: https://www.obectechlovice.cz/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obectechlovice.cz/image.php?nid=18145&oid=7877829 + source_url: https://www.obectechlovice.cz/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(12)' + retrieved_on: '2025-12-25T18:51:32.661098+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIB-L-KABL.yaml b/data/custodian/CZ-52-LIB-L-KABL.yaml index fbe820496b..09642baf9e 100644 --- a/data/custodian/CZ-52-LIB-L-KABL.yaml +++ b/data/custodian/CZ-52-LIB-L-KABL.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LIB-L-KABL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LIB-L-KABL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LIB-L-KABL ghcid_numeric: 17529662578180080598 valid_from: '2025-12-06T23:37:27.012179+00:00' @@ -216,3 +217,22 @@ location: postal_code: 507 44 street_address: Libošovice č.p. 104 normalization_timestamp: '2025-12-09T10:53:02.554199+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:41.373601+00:00' + source_url: https://libosovice.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://libosovice.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://libosovice.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:51:41.373601+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_librice.yaml b/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_librice.yaml index 0b6f407c89..4d8afb8655 100644 --- a/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_librice.yaml +++ b/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_librice.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LIB-L-MKL-mistni_knihovna_librice - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LIB-L-MKL-mistni_knihovna_librice valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LIB-L-MKL-mistni_knihovna_librice ghcid_numeric: 14291630208813737325 valid_from: '2025-12-06T23:37:34.984797+00:00' @@ -212,3 +213,22 @@ location: postal_code: 503 44 street_address: Libřice 62 normalization_timestamp: '2025-12-09T10:53:02.607361+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:47.404259+00:00' + source_url: https://kmhk.tritius.cz/library/librice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/librice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:51:47.404259+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_libunec.yaml b/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_libunec.yaml index de28e48c7c..3c92fb190a 100644 --- a/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_libunec.yaml +++ b/data/custodian/CZ-52-LIB-L-MKL-mistni_knihovna_libunec.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LIB-L-MKL-mistni_knihovna_libunec - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LIB-L-MKL-mistni_knihovna_libunec valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LIB-L-MKL-mistni_knihovna_libunec ghcid_numeric: 9918847902818519370 valid_from: '2025-12-06T23:37:35.173358+00:00' @@ -210,3 +211,22 @@ location: postal_code: 507 15 street_address: Libunec 31 normalization_timestamp: '2025-12-09T10:53:02.668831+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:53.975246+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:51:53.975246+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIB-L-MKLPB.yaml b/data/custodian/CZ-52-LIB-L-MKLPB.yaml index 52686a08f8..c689b88402 100644 --- a/data/custodian/CZ-52-LIB-L-MKLPB.yaml +++ b/data/custodian/CZ-52-LIB-L-MKLPB.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LIB-L-MKLPB - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LIB-L-MKLPB valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LIB-L-MKLPB ghcid_numeric: 9279151113941883298 valid_from: '2025-12-06T23:37:35.518716+00:00' @@ -220,3 +221,22 @@ location: postal_code: 517 12 street_address: Bělá 1 normalization_timestamp: '2025-12-09T10:53:02.768747+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:00.871502+00:00' + source_url: https://www.obec-liberk.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-liberk.cz/skins/liberk_lego/favicons/safari-pinned-tab.svg + source_url: https://www.obec-liberk.cz/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:52:00.871502+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-LIB-L-MKLPH.yaml b/data/custodian/CZ-52-LIB-L-MKLPH.yaml index bf393bb2e2..3dec8db321 100644 --- a/data/custodian/CZ-52-LIB-L-MKLPH.yaml +++ b/data/custodian/CZ-52-LIB-L-MKLPH.yaml @@ -222,3 +222,22 @@ location: postal_code: 517 12 street_address: Hláska 61 normalization_timestamp: '2025-12-09T10:53:02.795449+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:07.740802+00:00' + source_url: https://www.obec-liberk.cz/obec/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.obec-liberk.cz/skins/liberk_lego/favicons/safari-pinned-tab.svg + source_url: https://www.obec-liberk.cz/obec/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:52:07.740802+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-LIB-L-OKVL.yaml b/data/custodian/CZ-52-LIB-L-OKVL.yaml index a2eb69496d..c30b2c7eda 100644 --- a/data/custodian/CZ-52-LIB-L-OKVL.yaml +++ b/data/custodian/CZ-52-LIB-L-OKVL.yaml @@ -40,13 +40,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LIB-L-OKVL - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LIB-L-OKVL valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LIB-L-OKVL ghcid_numeric: 14249681523085289578 valid_from: '2025-12-06T23:37:24.494666+00:00' @@ -208,3 +209,22 @@ location: country: *id006 postal_code: 503 22 normalization_timestamp: '2025-12-09T10:53:02.821224+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:13.487997+00:00' + source_url: https://kmhk.tritius.cz/library/libcany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kmhk.tritius.cz/apple-touch-icon-180x180.png + source_url: https://kmhk.tritius.cz/library/libcany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:52:13.487997+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-LIC-L-MKL.yaml b/data/custodian/CZ-52-LIC-L-MKL.yaml index cc0518addb..5a379164dc 100644 --- a/data/custodian/CZ-52-LIC-L-MKL.yaml +++ b/data/custodian/CZ-52-LIC-L-MKL.yaml @@ -212,3 +212,28 @@ location: postal_code: 517 35 street_address: Lično 43 normalization_timestamp: '2025-12-09T10:53:02.848834+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:20.996481+00:00' + source_url: http://www.licno.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.licno.cz/safari-pinned-tab.svg + source_url: http://www.licno.cz/knihovna + css_selector: '[document] > html.sizes.customelements > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:52:20.996481+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.licno.cz/www.licno.cz/images/logo_znak.png + source_url: http://www.licno.cz/knihovna + css_selector: '[document] > html.sizes.customelements > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T18:52:20.996481+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-52-LIP-L-MKLNO.yaml b/data/custodian/CZ-52-LIP-L-MKLNO.yaml index 9c84abf38e..228327bb5f 100644 --- a/data/custodian/CZ-52-LIP-L-MKLNO.yaml +++ b/data/custodian/CZ-52-LIP-L-MKLNO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-LIP-L-MKLNO - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-LIP-L-MKLNO valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-LIP-L-MKLNO ghcid_numeric: 1917327185512121965 valid_from: '2025-12-06T23:37:35.525083+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 21 street_address: Lípa nad Orlicí 23 normalization_timestamp: '2025-12-09T10:53:02.873960+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:25.842870+00:00' + source_url: https://lipa-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lipa-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://lipa-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T18:52:25.842870+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIT-A-AS.yaml b/data/custodian/CZ-52-LIT-A-AS.yaml index e1dd050313..2b7db01fff 100644 --- a/data/custodian/CZ-52-LIT-A-AS.yaml +++ b/data/custodian/CZ-52-LIT-A-AS.yaml @@ -227,3 +227,38 @@ location: youtube_status: NOT_FOUND youtube_search_query: Archiv Senátu official youtube_search_timestamp: '2025-12-09T09:32:29.420793+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:31.457206+00:00' + source_url: http://www.nacr.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.nacr.cz/wp-content/themes/narodni_archiv/img/logo_na_en.png + source_url: http://www.nacr.cz + css_selector: '#wrapper-navbar > header.header > div.header__main:nth-of-type(2) + > nav.navbar.navbar-expand-lg > div.navbar-mobile-top > div.navbar-brand > a + > img' + retrieved_on: '2025-12-25T18:52:31.457206+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: National Archives + - claim_type: favicon_url + claim_value: https://www.nacr.cz/wp-content/themes/narodni_archiv/img/favicon/apple-icon-180x180.png + source_url: http://www.nacr.cz + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:52:31.457206+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.nacr.cz/wp-content/uploads/2020/04/podatelna2_22-1.jpg + source_url: http://www.nacr.cz + css_selector: '[document] > html > head > meta:nth-of-type(17)' + retrieved_on: '2025-12-25T18:52:31.457206+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 13 diff --git a/data/custodian/CZ-52-LIT-L-AOPKCK.yaml b/data/custodian/CZ-52-LIT-L-AOPKCK.yaml index 4d769606fa..d708bb4e7a 100644 --- a/data/custodian/CZ-52-LIT-L-AOPKCK.yaml +++ b/data/custodian/CZ-52-LIT-L-AOPKCK.yaml @@ -231,3 +231,32 @@ location: youtube_status: NOT_FOUND youtube_search_query: Agentura ochrany přírody a krajiny ČR - knihovna official youtube_search_timestamp: '2025-12-09T09:32:30.082878+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:36.989528+00:00' + source_url: https://knihovna.nature.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovna.nature.cz/custom/design/logo_bila.png + source_url: https://knihovna.nature.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > div > img' + retrieved_on: '2025-12-25T18:52:36.989528+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://knihovna.nature.cz/favicon.png?v=2.3.0-32050 + source_url: https://knihovna.nature.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:52:36.989528+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIT-L-CMIUFMK.yaml b/data/custodian/CZ-52-LIT-L-CMIUFMK.yaml index 7006b1377f..a474093ede 100644 --- a/data/custodian/CZ-52-LIT-L-CMIUFMK.yaml +++ b/data/custodian/CZ-52-LIT-L-CMIUFMK.yaml @@ -236,3 +236,22 @@ youtube_status: NOT_FOUND youtube_search_query: Český metrologický institut - úsek fudamentální metrologie - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:30.755567+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:43.783293+00:00' + source_url: https://www.cmi.gov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://cmi.gov.cz/sites/all/files/public/logo_bez.png + source_url: https://www.cmi.gov.cz + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-25T18:52:43.783293+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIT-L-CRSZSSRCK.yaml b/data/custodian/CZ-52-LIT-L-CRSZSSRCK.yaml index c0bf1441ec..9817e575d1 100644 --- a/data/custodian/CZ-52-LIT-L-CRSZSSRCK.yaml +++ b/data/custodian/CZ-52-LIT-L-CRSZSSRCK.yaml @@ -232,3 +232,22 @@ youtube_status: NOT_FOUND youtube_search_query: Český rybářský svaz, z. s. - sekretariát Rady ČRS - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:31.422508+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:49.909481+00:00' + source_url: https://www.rybsvaz.cz/beta/index.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rybsvaz.cz/beta/templates/purity_iii/favicon.ico + source_url: https://www.rybsvaz.cz/beta/index.php + css_selector: '[document] > html.com_content.view-category > body > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:52:49.909481+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIT-L-MUPPSOKJH.yaml b/data/custodian/CZ-52-LIT-L-MUPPSOKJH.yaml index 90c1d5b770..24753b32b1 100644 --- a/data/custodian/CZ-52-LIT-L-MUPPSOKJH.yaml +++ b/data/custodian/CZ-52-LIT-L-MUPPSOKJH.yaml @@ -231,3 +231,22 @@ youtube_status: NOT_FOUND youtube_search_query: Metropolitní univerzita Praha, o.p.s. - Odborná knihovna Jiřího Hájka official youtube_search_timestamp: '2025-12-09T09:32:32.086085+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:55.020612+00:00' + source_url: https://tritius.mup.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.mup.cz/apple-touch-icon-180x180.png + source_url: https://tritius.mup.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:52:55.020612+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-LIT-L-PDBSRDKN.yaml b/data/custodian/CZ-52-LIT-L-PDBSRDKN.yaml index 8cb81214b0..aa612784ba 100644 --- a/data/custodian/CZ-52-LIT-L-PDBSRDKN.yaml +++ b/data/custodian/CZ-52-LIT-L-PDBSRDKN.yaml @@ -228,3 +228,28 @@ youtube_status: NOT_FOUND youtube_search_query: Pavel Dobrovský - BETA, s.r.o. - distribuce knih - nakladatelství official youtube_search_timestamp: '2025-12-09T09:32:32.746790+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:59.941650+00:00' + source_url: http://vo.dobrovsky.cz/exec/myaccount.aspx + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://vo.dobrovsky.cz/favicon.ico?v=1 + source_url: http://vo.dobrovsky.cz/exec/myaccount.aspx + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T18:52:59.941650+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://image200x200.jpg + source_url: http://vo.dobrovsky.cz/exec/myaccount.aspx + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(19)' + retrieved_on: '2025-12-25T18:52:59.941650+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-LIT-O-AHMPK.yaml b/data/custodian/CZ-52-LIT-O-AHMPK.yaml index 1ee42fa518..e5d9d2fb31 100644 --- a/data/custodian/CZ-52-LIT-O-AHMPK.yaml +++ b/data/custodian/CZ-52-LIT-O-AHMPK.yaml @@ -237,3 +237,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Archiv hlavního města Prahy - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:33.407643+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:05.534445+00:00' + source_url: https://ahmp.kpsys.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ahmp.kpsys.cz/favicon.png?v=2.3.0-32049 + source_url: https://ahmp.kpsys.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:53:05.534445+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LUZ-L-OKL.yaml b/data/custodian/CZ-52-LUZ-L-OKL.yaml index 15356e5d0d..98abc7d96d 100644 --- a/data/custodian/CZ-52-LUZ-L-OKL.yaml +++ b/data/custodian/CZ-52-LUZ-L-OKL.yaml @@ -211,3 +211,28 @@ location: postal_code: 503 05 street_address: Lužany 47 normalization_timestamp: '2025-12-09T10:53:02.922005+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:12.908620+00:00' + source_url: https://www.luzanynt.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.luzanynt.cz/www//cache/images-favicon-180-180.png + source_url: https://www.luzanynt.cz/obec/obecni-knihovna + css_selector: '[document] > html.wide.wow-animation > head > link' + retrieved_on: '2025-12-25T18:53:12.908620+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.luzanynt.cz/www//cache/images-logo-256-256.png + source_url: https://www.luzanynt.cz/obec/obecni-knihovna + css_selector: '[document] > html.wide.wow-animation > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-25T18:53:12.908620+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-52-LYS-L-NTK.yaml b/data/custodian/CZ-52-LYS-L-NTK.yaml index 8644afa6f2..db5d8f94c4 100644 --- a/data/custodian/CZ-52-LYS-L-NTK.yaml +++ b/data/custodian/CZ-52-LYS-L-NTK.yaml @@ -404,3 +404,20 @@ location: youtube_status: NOT_FOUND youtube_search_query: Národní technická knihovna official youtube_search_timestamp: '2025-12-09T09:32:35.388760+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:23.069896+00:00' + source_url: https://vufind.techlib.cz + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.techlib.cz/public/images/logos/logo-ntk4-square.jpg + source_url: https://vufind.techlib.cz + css_selector: '[document] > html.js.flexbox > body > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T18:53:23.069896+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/CZ-52-LYS-L-UEBACVVK.yaml b/data/custodian/CZ-52-LYS-L-UEBACVVK.yaml index 15374afd9f..9835c9b0f8 100644 --- a/data/custodian/CZ-52-LYS-L-UEBACVVK.yaml +++ b/data/custodian/CZ-52-LYS-L-UEBACVVK.yaml @@ -235,3 +235,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Ústav experimentální botaniky AV ČR, v. v. i. - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:36.719930+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:34.187843+00:00' + source_url: https://ueb.cas.cz/cs + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ueb.cas.cz/favicon.ico + source_url: https://ueb.cas.cz/cs + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:53:34.187843+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-LYS-L-VSCTVPCIS.yaml b/data/custodian/CZ-52-LYS-L-VSCTVPCIS.yaml index 8b265ea092..7f8e0a9e2c 100644 --- a/data/custodian/CZ-52-LYS-L-VSCTVPCIS.yaml +++ b/data/custodian/CZ-52-LYS-L-VSCTVPCIS.yaml @@ -277,3 +277,20 @@ youtube_status: NOT_FOUND youtube_search_query: Vysoká škola chemicko-technologická v Praze - Centrum informačních služeb official youtube_search_timestamp: '2025-12-09T09:32:38.050959+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:44.443695+00:00' + source_url: https://vufind.techlib.cz + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.techlib.cz/public/images/logos/logo-ntk4-square.jpg + source_url: https://vufind.techlib.cz + css_selector: '[document] > html.js.flexbox > body > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T18:53:44.443695+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/CZ-52-LYS-L-VSCTVPFCTU.yaml b/data/custodian/CZ-52-LYS-L-VSCTVPFCTU.yaml index 6c421b9066..16c01f279c 100644 --- a/data/custodian/CZ-52-LYS-L-VSCTVPFCTU.yaml +++ b/data/custodian/CZ-52-LYS-L-VSCTVPFCTU.yaml @@ -237,3 +237,22 @@ youtube_status: NOT_FOUND youtube_search_query: Vysoká škola chemicko-technologická v Praze - Fakulta chemické technologie - Ústav chemie pevných látek official youtube_search_timestamp: '2025-12-09T09:32:38.712171+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:49.832265+00:00' + source_url: https://fcht.vscht.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://fcht.vscht.cz/V12453/img/logo.png + source_url: https://fcht.vscht.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:53:49.832265+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-MIL-L-KKJE.yaml b/data/custodian/CZ-52-MIL-L-KKJE.yaml index 3e673d9431..8ee9556afe 100644 --- a/data/custodian/CZ-52-MIL-L-KKJE.yaml +++ b/data/custodian/CZ-52-MIL-L-KKJE.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-MIL-L-KKJE - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-MIL-L-KKJE valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-MIL-L-KKJE ghcid_numeric: 18065537308647243522 valid_from: '2025-12-06T23:37:17.893214+00:00' @@ -214,3 +215,30 @@ location: postal_code: 507 71 street_address: náměstí K.J. Erbena 5 normalization_timestamp: '2025-12-09T10:53:03.018594+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:06.435570+00:00' + source_url: https://knihovnamiletin.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnamiletin.webk.cz/themes/new/orange/logo1.png + source_url: https://knihovnamiletin.webk.cz + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-25T18:54:06.435570+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovnamiletin.webk.cz/themes/new/favicon.ico + source_url: https://knihovnamiletin.webk.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:54:06.435570+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-MIL-L-LKT.yaml b/data/custodian/CZ-52-MIL-L-LKT.yaml index 4ac096d63f..e2664a94fd 100644 --- a/data/custodian/CZ-52-MIL-L-LKT.yaml +++ b/data/custodian/CZ-52-MIL-L-LKT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-MIL-L-LKT - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-MIL-L-LKT valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-MIL-L-LKT ghcid_numeric: 4714081242644352300 valid_from: '2025-12-06T23:37:35.206045+00:00' @@ -210,3 +211,22 @@ location: postal_code: 507 71 street_address: Tetín 57 normalization_timestamp: '2025-12-09T10:53:03.043399+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:11.078273+00:00' + source_url: https://knihovnatetin.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnatetin.webk.cz/themes/cbdb-klasicky/letni/logo3.png + source_url: https://knihovnatetin.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:54:11.078273+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-MIL-L-LKU.yaml b/data/custodian/CZ-52-MIL-L-LKU.yaml index 5d18b87b8f..a0ec052714 100644 --- a/data/custodian/CZ-52-MIL-L-LKU.yaml +++ b/data/custodian/CZ-52-MIL-L-LKU.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-MIL-L-LKU - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-MIL-L-LKU valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-MIL-L-LKU ghcid_numeric: 2734878780572249474 valid_from: '2025-12-08T11:21:29.308840+00:00' @@ -215,3 +216,22 @@ location: postal_code: 507 71 street_address: Úhlejov 50 normalization_timestamp: '2025-12-09T10:53:03.063983+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:17.971547+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:54:17.971547+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-MIL-L-VKSVM.yaml b/data/custodian/CZ-52-MIL-L-VKSVM.yaml index 9a1a6c2a2d..9647e786ae 100644 --- a/data/custodian/CZ-52-MIL-L-VKSVM.yaml +++ b/data/custodian/CZ-52-MIL-L-VKSVM.yaml @@ -186,3 +186,22 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q385994 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:22.697837+00:00' + source_url: https://www.knihovnamartinamarcina.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.wix.com/favicon.ico + source_url: https://www.knihovnamartinamarcina.cz + css_selector: '[document] > html.ng-scope > head > link' + retrieved_on: '2025-12-25T18:54:22.697837+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-MLA-L-LKM.yaml b/data/custodian/CZ-52-MLA-L-LKM.yaml index e36a026508..877a39ca6b 100644 --- a/data/custodian/CZ-52-MLA-L-LKM.yaml +++ b/data/custodian/CZ-52-MLA-L-LKM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-MLA-L-LKM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-MLA-L-LKM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-MLA-L-LKM ghcid_numeric: 13908998193154147661 valid_from: '2025-12-06T23:37:35.185719+00:00' @@ -210,3 +211,22 @@ location: postal_code: 507 58 street_address: Náměstí 4 normalization_timestamp: '2025-12-09T10:53:03.083497+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:29.567375+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:54:29.567375+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-MLA-L-MKM.yaml b/data/custodian/CZ-52-MLA-L-MKM.yaml index d2ddd15dee..94607d7476 100644 --- a/data/custodian/CZ-52-MLA-L-MKM.yaml +++ b/data/custodian/CZ-52-MLA-L-MKM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-MLA-L-MKM - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-MLA-L-MKM valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-MLA-L-MKM ghcid_numeric: 13542787499439934494 valid_from: '2025-12-06T23:37:35.182950+00:00' @@ -216,3 +217,22 @@ location: postal_code: 507 45 street_address: Mladějov 22 normalization_timestamp: '2025-12-09T10:53:03.111036+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:36.497967+00:00' + source_url: https://katalog.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:54:36.497967+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NAC-L-MKNPS.yaml b/data/custodian/CZ-52-NAC-L-MKNPS.yaml index 72db500ca1..a90d15b125 100644 --- a/data/custodian/CZ-52-NAC-L-MKNPS.yaml +++ b/data/custodian/CZ-52-NAC-L-MKNPS.yaml @@ -245,3 +245,32 @@ location: postal_code: 547 01 street_address: Kamenice 105 normalization_timestamp: '2025-12-09T10:53:03.169498+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:46.330113+00:00' + source_url: https://katalog.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://katalog.mknachod.cz/custom/design/logo.png + source_url: https://katalog.mknachod.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > div > img' + retrieved_on: '2025-12-25T18:54:46.330113+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://katalog.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:54:46.330113+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NAC-L-OKVT.yaml b/data/custodian/CZ-52-NAC-L-OKVT.yaml index ad426f9d68..d0e226a782 100644 --- a/data/custodian/CZ-52-NAC-L-OKVT.yaml +++ b/data/custodian/CZ-52-NAC-L-OKVT.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NAC-L-OKVT - valid_from: "2025-12-10T09:47:03Z" + valid_from: '2025-12-10T09:47:03Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NAC-L-OKVT valid_from: null - valid_to: "2025-12-10T09:47:03Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:03Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NAC-L-OKVT ghcid_numeric: 17822907854352941452 valid_from: '2025-12-06T23:37:35.413407+00:00' @@ -210,3 +211,32 @@ location: postal_code: 547 01 street_address: Trubějov 13 normalization_timestamp: '2025-12-09T10:53:03.211415+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:51.889242+00:00' + source_url: https://trubejov.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://trubejov.mknachod.cz/custom/design/logo.png + source_url: https://trubejov.mknachod.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > div > img' + retrieved_on: '2025-12-25T18:54:51.889242+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://trubejov.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://trubejov.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:54:51.889242+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NAC-L-ONNSOK.yaml b/data/custodian/CZ-52-NAC-L-ONNSOK.yaml index bd70e74071..421b950715 100644 --- a/data/custodian/CZ-52-NAC-L-ONNSOK.yaml +++ b/data/custodian/CZ-52-NAC-L-ONNSOK.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NAC-L-ONNSOK - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NAC-L-ONNSOK valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NAC-L-ONNSOK ghcid_numeric: 14433238567876433140 valid_from: '2025-12-06T23:37:18.755565+00:00' @@ -214,3 +215,22 @@ location: postal_code: 547 69 street_address: Purkyňova 446 normalization_timestamp: '2025-12-09T10:53:03.258007+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:56.698866+00:00' + source_url: https://www.medvik.cz/bmc/?focus=NAE201 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.medvik.cz/bmc/img/favicon.ico + source_url: https://www.medvik.cz/bmc/?focus=NAE201 + css_selector: '[document] > html.show--consent > head > link' + retrieved_on: '2025-12-25T18:54:56.698866+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NAC-M-KMN.yaml b/data/custodian/CZ-52-NAC-M-KMN.yaml index d3f6f97158..d2286e7eed 100644 --- a/data/custodian/CZ-52-NAC-M-KMN.yaml +++ b/data/custodian/CZ-52-NAC-M-KMN.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NAC-M-KMN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NAC-M-KMN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NAC-M-KMN ghcid_numeric: 14397936816511824668 valid_from: '2025-12-06T23:37:26.660497+00:00' @@ -217,3 +218,22 @@ location: postal_code: 547 01 street_address: Masarykovo nám. 1 normalization_timestamp: '2025-12-09T10:53:03.320545+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:06.851669+00:00' + source_url: https://muzeum.tritius.cz/library/rmn + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://muzeum.tritius.cz/apple-touch-icon-180x180.png + source_url: https://muzeum.tritius.cz/library/rmn + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:55:06.851669+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-NAC-O-SOAVHKSOAN.yaml b/data/custodian/CZ-52-NAC-O-SOAVHKSOAN.yaml index 30c2ff3875..b03c0d0cb8 100644 --- a/data/custodian/CZ-52-NAC-O-SOAVHKSOAN.yaml +++ b/data/custodian/CZ-52-NAC-O-SOAVHKSOAN.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NAC-O-SOAVHKSOAN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NAC-O-SOAVHKSOAN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NAC-O-SOAVHKSOAN ghcid_numeric: 13863001141237732125 valid_from: '2025-12-06T23:37:21.564647+00:00' @@ -220,3 +221,33 @@ location: postal_code: 547 01 street_address: Dobenínská 96 normalization_timestamp: '2025-12-09T10:53:03.344254+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:18.970460+00:00' + source_url: https://vychodoceskearchivy.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-1.png + source_url: https://vychodoceskearchivy.cz + css_selector: '#cb-row--header-main > div.header--row-inner.header-main-inner + > div.customify-container > div.customify-grid.cb-row--desktop > div.row-v2.row-v2-main + > div.col-v2.col-v2-left > div.item--inner.builder-item--logo > div.site-branding.logo-left + > a.logo-link > img.site-img-logo' + retrieved_on: '2025-12-25T18:55:18.970460+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Státní oblastní archiv v Hradci Králové + - claim_type: favicon_url + claim_value: https://vychodoceskearchivy.cz/wp-content/uploads/2019/10/cropped-logo_SOA_acko_modra_nova_web-180x180.png + source_url: https://vychodoceskearchivy.cz + css_selector: '[document] > html > head > link:nth-of-type(31)' + retrieved_on: '2025-12-25T18:55:18.970460+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-NAH-L-OKN.yaml b/data/custodian/CZ-52-NAH-L-OKN.yaml index 94e37bc19a..08cbc944d5 100644 --- a/data/custodian/CZ-52-NAH-L-OKN.yaml +++ b/data/custodian/CZ-52-NAH-L-OKN.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NAH-L-OKN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NAH-L-OKN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NAH-L-OKN ghcid_numeric: 11598602745438746005 valid_from: '2025-12-06T23:37:35.332793+00:00' @@ -210,3 +211,22 @@ location: postal_code: 549 07 street_address: Nahořany 76 normalization_timestamp: '2025-12-09T10:53:03.396260+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:26.388517+00:00' + source_url: https://tritius.knihovnanm.cz/library/nahorany + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovnanm.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovnanm.cz/library/nahorany + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:55:26.388517+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-NEC-L-MKNPSSVS.yaml b/data/custodian/CZ-52-NEC-L-MKNPSSVS.yaml index f9f9932956..a079e950c1 100644 --- a/data/custodian/CZ-52-NEC-L-MKNPSSVS.yaml +++ b/data/custodian/CZ-52-NEC-L-MKNPSSVS.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NEC-L-MKNPSSVS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NEC-L-MKNPSSVS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NEC-L-MKNPSSVS ghcid_numeric: 9134546135975135025 valid_from: '2025-12-06T23:37:42.542239+00:00' @@ -104,8 +105,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.95 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Městská knihovna Nechanice, pobočka se sídlem v Suché @@ -210,3 +211,22 @@ location: geonames_id: 3069980 geonames_name: Nechanice feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:35.761133+00:00' + source_url: https://knihovnanechanice.webk.cz/pages/regon.-funkce.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnanechanice.files.webk.cz/logov.png + source_url: https://knihovnanechanice.webk.cz/pages/regon.-funkce.html + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:55:35.761133+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-NEC-L-OKH.yaml b/data/custodian/CZ-52-NEC-L-OKH.yaml index 85d36f4594..dc09ae5626 100644 --- a/data/custodian/CZ-52-NEC-L-OKH.yaml +++ b/data/custodian/CZ-52-NEC-L-OKH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NEC-L-OKH - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NEC-L-OKH valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NEC-L-OKH ghcid_numeric: 2701450257332969114 valid_from: '2025-12-06T23:37:35.008934+00:00' @@ -216,3 +217,22 @@ location: postal_code: 503 15 street_address: Hněvčeves 42 normalization_timestamp: '2025-12-09T10:53:03.468350+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:40.740648+00:00' + source_url: https://www.hnevceves.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hnevceves.cz/images/favicon-114px.png + source_url: https://www.hnevceves.cz/obec/obecni-knihovna + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:55:40.740648+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 114x114 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-NEC-L-SMKN.yaml b/data/custodian/CZ-52-NEC-L-SMKN.yaml index b86f4934c1..05d52b5994 100644 --- a/data/custodian/CZ-52-NEC-L-SMKN.yaml +++ b/data/custodian/CZ-52-NEC-L-SMKN.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NEC-L-SMKN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NEC-L-SMKN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NEC-L-SMKN ghcid_numeric: 5647947503768434863 valid_from: '2025-12-08T11:21:25.000591+00:00' @@ -225,3 +226,22 @@ location: postal_code: 503 15 street_address: Raabova 110 normalization_timestamp: '2025-12-09T10:53:03.551343+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:49.859495+00:00' + source_url: https://katalog.knihovna-nechanice.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.knihovna-nechanice.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.knihovna-nechanice.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T18:55:49.859495+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NEM-L-OKN.yaml b/data/custodian/CZ-52-NEM-L-OKN.yaml index 971d51c40a..92247a5b20 100644 --- a/data/custodian/CZ-52-NEM-L-OKN.yaml +++ b/data/custodian/CZ-52-NEM-L-OKN.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NEM-L-OKN - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NEM-L-OKN valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NEM-L-OKN ghcid_numeric: 5033298890059590191 valid_from: '2025-12-06T23:37:35.671367+00:00' @@ -211,3 +212,22 @@ location: postal_code: 544 61 street_address: Nemojov 13 normalization_timestamp: '2025-12-09T10:53:03.577888+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:57.009479+00:00' + source_url: https://trutnov.tritius.cz/library/nemojov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/nemojov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:55:57.009479+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-NMN-M-MMNMNM.yaml b/data/custodian/CZ-52-NMN-M-MMNMNM.yaml index 84c22ac44c..ba994e9157 100644 --- a/data/custodian/CZ-52-NMN-M-MMNMNM.yaml +++ b/data/custodian/CZ-52-NMN-M-MMNMNM.yaml @@ -51,7 +51,8 @@ ghcid: reason: 'Region resolved via Wikidata P131: XX->52 (CZ-52)' - ghcid: CZ-52-NMN-M-MMNMNM valid_from: '2025-12-07T00:37:20.210007+00:00' - reason: 'City resolved via Wikidata Q85838530 coordinates: XXX->NMN (Nove Mesto nad Metuji)' + reason: 'City resolved via Wikidata Q85838530 coordinates: XXX->NMN (Nove Mesto + nad Metuji)' custodian_name: claim_type: custodian_name claim_value: Městské muzeum Nové Město nad Metují @@ -80,8 +81,8 @@ provenance: notes: - 'Country resolved 2025-12-06T23:54:39Z: XX→CZ via Wikidata P17' - 'Region resolved 2025-12-07T00:00:08Z: XX->52 via Wikidata P131 (CZ-52)' - - 'City resolved 2025-12-07T00:37:20Z: XXX->NMN via Wikidata Q85838530 coords (50.3446,16.1515) -> Nove Mesto nad Metuji - (GeoNames:3069466)' + - 'City resolved 2025-12-07T00:37:20Z: XXX->NMN via Wikidata Q85838530 coords (50.3446,16.1515) + -> Nove Mesto nad Metuji (GeoNames:3069466)' - Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:15Z - Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:39Z - 'YouTube/Google Maps enrichment 2025-12-09T09:32:40Z: YouTube: not found' @@ -112,8 +113,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.85 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Městské muzeum Nové Město nad Metují @@ -184,8 +185,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance wikidata_instance_of: *id005 wikidata_location: headquarters_location: @@ -227,3 +228,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Městské muzeum Nové Město nad Metují official youtube_search_timestamp: '2025-12-09T09:32:40.696572+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:10.180357+00:00' + source_url: http://www.muzeum-nmnm.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.muzeum-nmnm.cz/templates/jsn_epic_pro/favicon.ico + source_url: http://www.muzeum-nmnm.cz + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:56:10.180357+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NOV-E-GSOSVOSNBI.yaml b/data/custodian/CZ-52-NOV-E-GSOSVOSNBI.yaml index 30fa554605..60ae67b3c7 100644 --- a/data/custodian/CZ-52-NOV-E-GSOSVOSNBI.yaml +++ b/data/custodian/CZ-52-NOV-E-GSOSVOSNBI.yaml @@ -49,13 +49,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-E-GSOSVOSNBI - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-E-GSOSVOSNBI valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-E-GSOSVOSNBI ghcid_numeric: 6397617684988907262 valid_from: '2025-12-08T11:21:37.629641+00:00' @@ -229,3 +230,22 @@ location: postal_code: 504 01 street_address: Jana Maláta 1869 normalization_timestamp: '2025-12-09T10:53:03.641889+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:21.262603+00:00' + source_url: https://www.gnb.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.gnb.cz/html/images/favicon.ico + source_url: https://www.gnb.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:56:21.262603+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NOV-E-SPSSOSSOUN.yaml b/data/custodian/CZ-52-NOV-E-SPSSOSSOUN.yaml index 3634e9dd4d..4de383dc1e 100644 --- a/data/custodian/CZ-52-NOV-E-SPSSOSSOUN.yaml +++ b/data/custodian/CZ-52-NOV-E-SPSSOSSOUN.yaml @@ -236,3 +236,22 @@ location: postal_code: 549 01 street_address: ČSA 376 normalization_timestamp: '2025-12-09T10:53:03.680154+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:28.622221+00:00' + source_url: https://sps.skolynome.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sps.skolynome.cz/wp-content/uploads/2020/09/cropped-Obrazek1-1-300x300.png + source_url: https://sps.skolynome.cz + css_selector: '[document] > html > head > link:nth-of-type(35)' + retrieved_on: '2025-12-25T18:56:28.622221+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-52-NOV-L-MKNMNM.yaml b/data/custodian/CZ-52-NOV-L-MKNMNM.yaml index f4069980a6..6d8d5f3c99 100644 --- a/data/custodian/CZ-52-NOV-L-MKNMNM.yaml +++ b/data/custodian/CZ-52-NOV-L-MKNMNM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-MKNMNM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-MKNMNM valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-MKNMNM ghcid_numeric: 12966900689065044154 valid_from: '2025-12-06T23:37:18.806620+00:00' @@ -225,3 +226,28 @@ location: postal_code: 549 01 street_address: Komenského 30 normalization_timestamp: '2025-12-09T10:53:03.755508+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:36.220281+00:00' + source_url: https://www.knihovnanm.cz/katalog + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.knihovnanm.cz/Themes/Default/Images/favicon/apple-icon-180x180.png + source_url: https://www.knihovnanm.cz/katalog + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:56:36.220281+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.knihovnanm.cz/Themes/Default/Images/logos/og-image.png + source_url: https://www.knihovnanm.cz/katalog + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T18:56:36.220281+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 12 diff --git a/data/custodian/CZ-52-NOV-L-OKC.yaml b/data/custodian/CZ-52-NOV-L-OKC.yaml index 067c3224b4..10f0ef2d3d 100644 --- a/data/custodian/CZ-52-NOV-L-OKC.yaml +++ b/data/custodian/CZ-52-NOV-L-OKC.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-OKC - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-OKC valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-OKC ghcid_numeric: 17272654556280296152 valid_from: '2025-12-08T11:21:30.568771+00:00' @@ -215,3 +216,22 @@ location: postal_code: 549 01 street_address: Černčice 68 normalization_timestamp: '2025-12-09T10:53:03.870842+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:48.214462+00:00' + source_url: https://tritius.knihovnanm.cz/library/cerncice + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovnanm.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovnanm.cz/library/cerncice + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:56:48.214462+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-NOV-L-OKH.yaml b/data/custodian/CZ-52-NOV-L-OKH.yaml index 9acc744a05..4f5a67fa27 100644 --- a/data/custodian/CZ-52-NOV-L-OKH.yaml +++ b/data/custodian/CZ-52-NOV-L-OKH.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-OKH - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-OKH valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-OKH ghcid_numeric: 16907904859616095075 valid_from: '2025-12-06T23:37:35.030812+00:00' @@ -210,3 +211,22 @@ location: postal_code: 504 01 street_address: Humburky 41 normalization_timestamp: '2025-12-09T10:53:03.923802+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:54.942707+00:00' + source_url: https://www.humburky.cz/obecni%2Dknihovna/os-1009/p1=1024 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.humburky.cz/html/images/favicon.ico + source_url: https://www.humburky.cz/obecni%2Dknihovna/os-1009/p1=1024 + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:56:54.942707+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NOV-L-OKJ.yaml b/data/custodian/CZ-52-NOV-L-OKJ.yaml index 9afd9b3d23..02592c704a 100644 --- a/data/custodian/CZ-52-NOV-L-OKJ.yaml +++ b/data/custodian/CZ-52-NOV-L-OKJ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-OKJ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-OKJ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-OKJ ghcid_numeric: 14553747040908636005 valid_from: '2025-12-06T23:37:35.344077+00:00' @@ -207,3 +208,28 @@ location: postal_code: 549 01 street_address: Jestřebí 60 normalization_timestamp: '2025-12-09T10:53:03.991099+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:00.813471+00:00' + source_url: https://www.jestrebinadmetuji.cz/obec/obecni-knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jestrebinadmetuji.cz/www//cache/images-favicon-180-180.png + source_url: https://www.jestrebinadmetuji.cz/obec/obecni-knihovna + css_selector: '[document] > html.wide.wow-animation > head > link' + retrieved_on: '2025-12-25T18:57:00.813471+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.jestrebinadmetuji.cz/www//cache/images-logo-256-256.png + source_url: https://www.jestrebinadmetuji.cz/obec/obecni-knihovna + css_selector: '[document] > html.wide.wow-animation > head > meta:nth-of-type(16)' + retrieved_on: '2025-12-25T18:57:00.813471+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-52-NOV-L-OKK.yaml b/data/custodian/CZ-52-NOV-L-OKK.yaml index 692db93a59..eb0aab41f7 100644 --- a/data/custodian/CZ-52-NOV-L-OKK.yaml +++ b/data/custodian/CZ-52-NOV-L-OKK.yaml @@ -211,3 +211,22 @@ location: postal_code: 504 01 street_address: Králíky 29 normalization_timestamp: '2025-12-09T10:53:04.024390+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:06.217739+00:00' + source_url: https://ou.kraliky.info/view.php?cisloclanku=2008050001 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://admin-storage.munipolis.com/kraliky-u-hk/logo.png?v=1740413967 + source_url: https://ou.kraliky.info/view.php?cisloclanku=2008050001 + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-25T18:57:06.217739+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NOV-L-OKNP.yaml b/data/custodian/CZ-52-NOV-L-OKNP.yaml index b907af3ebf..cb26c607af 100644 --- a/data/custodian/CZ-52-NOV-L-OKNP.yaml +++ b/data/custodian/CZ-52-NOV-L-OKNP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-OKNP - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-OKNP valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-OKNP ghcid_numeric: 3486041637364214273 valid_from: '2025-12-06T23:37:35.313539+00:00' @@ -210,3 +211,22 @@ location: postal_code: 551 01 street_address: Nový Ples 28 normalization_timestamp: '2025-12-09T10:53:04.083816+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:13.212767+00:00' + source_url: https://knihovnanovyples.webk.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnanovyples.files.webk.cz/logov.png + source_url: https://knihovnanovyples.webk.cz + css_selector: '#header_in > a > h1 > img.mobile_display_none' + retrieved_on: '2025-12-25T18:57:13.212767+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-NOV-L-OKSNM.yaml b/data/custodian/CZ-52-NOV-L-OKSNM.yaml index 696a3d626c..5cf7c51040 100644 --- a/data/custodian/CZ-52-NOV-L-OKSNM.yaml +++ b/data/custodian/CZ-52-NOV-L-OKSNM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-OKSNM - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-OKSNM valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-OKSNM ghcid_numeric: 9843814147949845492 valid_from: '2025-12-06T23:37:35.346887+00:00' @@ -210,3 +211,22 @@ location: postal_code: 549 01 street_address: Slavětín nad Metují 83 normalization_timestamp: '2025-12-09T10:53:04.106169+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:18.351096+00:00' + source_url: https://tritius.knihovnanm.cz/library/slavetin + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://tritius.knihovnanm.cz/apple-touch-icon-180x180.png + source_url: https://tritius.knihovnanm.cz/library/slavetin + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:57:18.351096+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-NOV-L-OKSS.yaml b/data/custodian/CZ-52-NOV-L-OKSS.yaml index ef4bffc56e..fbc5487685 100644 --- a/data/custodian/CZ-52-NOV-L-OKSS.yaml +++ b/data/custodian/CZ-52-NOV-L-OKSS.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-OKSS - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-OKSS valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-OKSS ghcid_numeric: 1734163508175113669 valid_from: '2025-12-06T23:37:35.037034+00:00' @@ -205,3 +206,22 @@ location: postal_code: 504 01 street_address: Stará Skřeněř 62 normalization_timestamp: '2025-12-09T10:53:04.129402+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:24.440097+00:00' + source_url: http://www.novybydzov.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://res.cloudinary.com/dcejiykxi/image/upload/v1713281695/tmp-5-1713281694910.png + source_url: http://www.novybydzov.cz + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:57:24.440097+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-52-NOV-L-OKVNH.yaml b/data/custodian/CZ-52-NOV-L-OKVNH.yaml index 382ef0d997..dd9ed8f2a2 100644 --- a/data/custodian/CZ-52-NOV-L-OKVNH.yaml +++ b/data/custodian/CZ-52-NOV-L-OKVNH.yaml @@ -217,3 +217,32 @@ location: postal_code: 549 22 street_address: Hradní 102 normalization_timestamp: '2025-12-09T10:53:04.187130+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:32.463492+00:00' + source_url: https://novyhradek.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://novyhradek.mknachod.cz/custom/design/logo.png + source_url: https://novyhradek.mknachod.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > div > img' + retrieved_on: '2025-12-25T18:57:32.463492+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://novyhradek.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://novyhradek.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:57:32.463492+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-NOV-L-OKVV.yaml b/data/custodian/CZ-52-NOV-L-OKVV.yaml index 33329ba78b..78644c12ad 100644 --- a/data/custodian/CZ-52-NOV-L-OKVV.yaml +++ b/data/custodian/CZ-52-NOV-L-OKVV.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-NOV-L-OKVV - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-NOV-L-OKVV valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-NOV-L-OKVV ghcid_numeric: 1185872281560856172 valid_from: '2025-12-06T23:37:35.341344+00:00' @@ -210,3 +211,22 @@ location: postal_code: 549 01 street_address: Vršovka 56 normalization_timestamp: '2025-12-09T10:53:04.213518+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:37.648304+00:00' + source_url: https://www.vrsovka.cz/obecni-knihovna-vrsovka + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vrsovka.cz/www/obecvrsovka/fs/design/favicon-32x32.png + source_url: https://www.vrsovka.cz/obecni-knihovna-vrsovka + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:57:37.648304+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-OPO-L-MKO.yaml b/data/custodian/CZ-52-OPO-L-MKO.yaml index 61fbe5d37d..fee6048c74 100644 --- a/data/custodian/CZ-52-OPO-L-MKO.yaml +++ b/data/custodian/CZ-52-OPO-L-MKO.yaml @@ -48,13 +48,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-OPO-L-MKO - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-OPO-L-MKO valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-OPO-L-MKO ghcid_numeric: 11386285934988977902 valid_from: '2025-12-06T23:37:21.256345+00:00' @@ -229,3 +230,22 @@ location: postal_code: 517 73 street_address: Kupkovo nám. 142 normalization_timestamp: '2025-12-09T10:53:04.302882+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:55.335830+00:00' + source_url: https://rychnov.tritius.cz/library/opocno + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://rychnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://rychnov.tritius.cz/library/opocno + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T18:57:55.335830+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-OSI-L-OKO.yaml b/data/custodian/CZ-52-OSI-L-OKO.yaml index 2d969dcaf7..3f818c252c 100644 --- a/data/custodian/CZ-52-OSI-L-OKO.yaml +++ b/data/custodian/CZ-52-OSI-L-OKO.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-OSI-L-OKO - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-OSI-L-OKO valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-OSI-L-OKO ghcid_numeric: 5780800586070920041 valid_from: '2025-12-06T23:37:35.042491+00:00' @@ -207,3 +208,20 @@ location: postal_code: 503 26 street_address: Osice normalization_timestamp: '2025-12-09T10:53:04.354707+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:02.485682+00:00' + source_url: https://www.osice.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.osice.cz/img/og-img.png + source_url: https://www.osice.cz/knihovna + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T18:58:02.485682+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/CZ-52-OST-L-OKES.yaml b/data/custodian/CZ-52-OST-L-OKES.yaml index e1e748b674..1566bc72b8 100644 --- a/data/custodian/CZ-52-OST-L-OKES.yaml +++ b/data/custodian/CZ-52-OST-L-OKES.yaml @@ -220,3 +220,30 @@ location: country: *id006 postal_code: 507 52 normalization_timestamp: '2025-12-09T10:53:04.378727+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:17.400238+00:00' + source_url: https://knihovna.ostromer.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovnaostromer.files.webk.cz/logov.png + source_url: https://knihovna.ostromer.cz/#! + css_selector: '#outpage > header.tmava > a > img.mobile_display_none' + retrieved_on: '2025-12-25T18:58:17.400238+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Na úvodní stranu + - claim_type: favicon_url + claim_value: https://knihovna.ostromer.cz/themes/new/favicon.ico + source_url: https://knihovna.ostromer.cz/#! + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:58:17.400238+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-OTO-L-OKO.yaml b/data/custodian/CZ-52-OTO-L-OKO.yaml index 3a8b3036a5..811cbea085 100644 --- a/data/custodian/CZ-52-OTO-L-OKO.yaml +++ b/data/custodian/CZ-52-OTO-L-OKO.yaml @@ -38,13 +38,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-OTO-L-OKO - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-OTO-L-OKO valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-OTO-L-OKO ghcid_numeric: 4044047270289660776 valid_from: '2025-12-06T23:37:35.352677+00:00' @@ -207,3 +208,32 @@ location: postal_code: 549 72 street_address: Otovice 196 normalization_timestamp: '2025-12-09T10:53:04.406132+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:23.416731+00:00' + source_url: https://otovice.mknachod.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://otovice.mknachod.cz/custom/design/logo.png + source_url: https://otovice.mknachod.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > div > img' + retrieved_on: '2025-12-25T18:58:23.416731+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://otovice.mknachod.cz/favicon.png?v=2.3.0-32050 + source_url: https://otovice.mknachod.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:58:23.416731+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PAB-L-IPVVZOVI.yaml b/data/custodian/CZ-52-PAB-L-IPVVZOVI.yaml index 0aa3dbf3d4..318e93b811 100644 --- a/data/custodian/CZ-52-PAB-L-IPVVZOVI.yaml +++ b/data/custodian/CZ-52-PAB-L-IPVVZOVI.yaml @@ -229,7 +229,33 @@ location: geonames_id: 3068655 feature_code: PPL normalization_timestamp: '2025-12-09T06:49:39.207083+00:00' -youtube_status: NOT_FOUND -youtube_search_query: Institut postgraduálního vzdělávání ve zdravotnictví - Oddělení - vědeckých informací official -youtube_search_timestamp: '2025-12-09T09:32:43.338715+00:00' + youtube_status: NOT_FOUND + youtube_search_query: Institut postgraduálního vzdělávání ve zdravotnictví - Oddělení + vědeckých informací official + youtube_search_timestamp: '2025-12-09T09:32:43.338715+00:00' + logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:00.000000+00:00' + source_url: https://www.medvik.cz/bmc/?focus=ABE202 + extraction_method: crawl4ai + claims: + - claim_type: primary_logo_url + claim_value: https://www.medvik.cz/bmc/img/logo.png + source_url: https://www.medvik.cz/bmc/ + retrieved_on: '2025-12-25T19:00:00.000000+00:00' + extraction_method: crawl4ai_img_detection + logo_type: image/png + - claim_type: favicon_url + claim_value: https://www.medvik.cz/bmc/img/favicon.ico + source_url: https://www.medvik.cz/bmc/ + retrieved_on: '2025-12-25T19:00:00.000000+00:00' + extraction_method: crawl4ai_link_rel + css_selector: '[document] > html.show--consent > head > link' + 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 + primary_logo_detection_note: Primary logo (logo.png) identified via crawl4ai direct scraping, not via favicon link selector diff --git a/data/custodian/CZ-52-PAB-L-MSRSIS.yaml b/data/custodian/CZ-52-PAB-L-MSRSIS.yaml index 9956212ee4..3d6a81029f 100644 --- a/data/custodian/CZ-52-PAB-L-MSRSIS.yaml +++ b/data/custodian/CZ-52-PAB-L-MSRSIS.yaml @@ -226,3 +226,20 @@ location: youtube_status: NOT_FOUND youtube_search_query: MEDISTYL, s.r.o. - Středoevropské informační středisko official youtube_search_timestamp: '2025-12-09T09:32:43.995824+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:42.215652+00:00' + source_url: https://www.medistyl.cz + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.medistyl.cz/wp-content/uploads/medistyl_logo.png + source_url: https://www.medistyl.cz + css_selector: '[document] > html.no-js > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-25T18:58:42.215652+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/CZ-52-PAB-L-PMCPSDAK.yaml b/data/custodian/CZ-52-PAB-L-PMCPSDAK.yaml index edd9810135..f2e8bc3c00 100644 --- a/data/custodian/CZ-52-PAB-L-PMCPSDAK.yaml +++ b/data/custodian/CZ-52-PAB-L-PMCPSDAK.yaml @@ -223,3 +223,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: PRO.MED.CS Praha, a.s. - Documentation ADM - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:44.663232+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:47.493143+00:00' + source_url: https://www.promed.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.promed.cz/themes/custom/basic/dist/img/favicon/apple-touch-icon.png?v=24082023 + source_url: https://www.promed.cz + css_selector: '[document] > html.js > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:58:47.493143+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: 6 diff --git a/data/custodian/CZ-52-PAB-L-PSK-pragoprojekt_as_knihovna.yaml b/data/custodian/CZ-52-PAB-L-PSK-pragoprojekt_as_knihovna.yaml index 9f9b973dc7..547e119992 100644 --- a/data/custodian/CZ-52-PAB-L-PSK-pragoprojekt_as_knihovna.yaml +++ b/data/custodian/CZ-52-PAB-L-PSK-pragoprojekt_as_knihovna.yaml @@ -227,3 +227,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: PRAGOPROJEKT, a.s. - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:45.330823+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:53.107605+00:00' + source_url: https://www.pragoprojekt.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pragoprojekt.cz/media/favicon/safari-pinned-tab.svg + source_url: https://www.pragoprojekt.cz + css_selector: '[document] > html.nivo-lightbox-notouch.js > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:58:53.107605+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://pragoprojekt.cz/admin/upload/data/fb-nahled.jpg + source_url: https://www.pragoprojekt.cz + css_selector: '[document] > html.nivo-lightbox-notouch.js > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:58:53.107605+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-52-PAB-L-UZFGACVVSP.yaml b/data/custodian/CZ-52-PAB-L-UZFGACVVSP.yaml index aa4e6ae011..e34abd6d90 100644 --- a/data/custodian/CZ-52-PAB-L-UZFGACVVSP.yaml +++ b/data/custodian/CZ-52-PAB-L-UZFGACVVSP.yaml @@ -238,3 +238,22 @@ youtube_status: NOT_FOUND youtube_search_query: Ústav živočišné fyziologie a genetiky AV ČR, v. v. i. - Sekce Praha - Středisko vědeckých informací - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:46.645439+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:01.129621+00:00' + source_url: https://www.iapg.cas.cz/cs + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.iapg.cas.cz/favicon.ico?v=2 + source_url: https://www.iapg.cas.cz/cs + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T18:59:01.129621+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PEC-L-KKH.yaml b/data/custodian/CZ-52-PEC-L-KKH.yaml index af2cd43123..6b7a7b569d 100644 --- a/data/custodian/CZ-52-PEC-L-KKH.yaml +++ b/data/custodian/CZ-52-PEC-L-KKH.yaml @@ -230,3 +230,32 @@ location: postal_code: 507 82 street_address: Pecka 2 normalization_timestamp: '2025-12-09T10:53:04.429779+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:28.135527+00:00' + source_url: https://pecka.kpsys.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://pecka.kpsys.cz/custom/design/logopecka.png + source_url: https://pecka.kpsys.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > div > img' + retrieved_on: '2025-12-25T18:59:28.135527+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://pecka.kpsys.cz/favicon.png?v=2.3.0-32050 + source_url: https://pecka.kpsys.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:59:28.135527+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PEC-L-MLKVBUP.yaml b/data/custodian/CZ-52-PEC-L-MLKVBUP.yaml index 26cf72fb6f..b5c1cd624b 100644 --- a/data/custodian/CZ-52-PEC-L-MLKVBUP.yaml +++ b/data/custodian/CZ-52-PEC-L-MLKVBUP.yaml @@ -44,13 +44,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-PEC-L-MLKVBUP - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-PEC-L-MLKVBUP valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-PEC-L-MLKVBUP ghcid_numeric: 17798790741876205018 valid_from: '2025-12-06T23:37:42.530449+00:00' @@ -212,3 +213,22 @@ location: postal_code: 507 82 street_address: Bělá u Pecky 11 normalization_timestamp: '2025-12-09T10:53:04.456588+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:35.251395+00:00' + source_url: https://bela.knihovna.jicin.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bela.knihovna.jicin.cz/favicon.png?v=2.3.0-32050 + source_url: https://bela.knihovna.jicin.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:59:35.251395+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PEL-L-KMUAACVVKV-knihovna_masarykova_ustavu_a_archivu_av_cr_v_v_i_k.yaml b/data/custodian/CZ-52-PEL-L-KMUAACVVKV-knihovna_masarykova_ustavu_a_archivu_av_cr_v_v_i_k.yaml index 78ab0c7b22..895a3d6ea8 100644 --- a/data/custodian/CZ-52-PEL-L-KMUAACVVKV-knihovna_masarykova_ustavu_a_archivu_av_cr_v_v_i_k.yaml +++ b/data/custodian/CZ-52-PEL-L-KMUAACVVKV-knihovna_masarykova_ustavu_a_archivu_av_cr_v_v_i_k.yaml @@ -241,3 +241,22 @@ youtube_status: NOT_FOUND youtube_search_query: Knihovna Masarykova ústavu a Archivu AV ČR, v. v. i. - Knihovna vědeckého útvaru Masarykův ústav AV ČR official youtube_search_timestamp: '2025-12-09T09:32:47.961823+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:44.290801+00:00' + source_url: https://katalog.lib.cas.cz/MUA + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/MUA/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/MUA + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:44.290801+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PEL-L-KUJAKP.yaml b/data/custodian/CZ-52-PEL-L-KUJAKP.yaml index 71c2b8d435..2ce0ccc5f1 100644 --- a/data/custodian/CZ-52-PEL-L-KUJAKP.yaml +++ b/data/custodian/CZ-52-PEL-L-KUJAKP.yaml @@ -223,3 +223,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Knihovna Univerzity Jana Amose Komenského Praha official youtube_search_timestamp: '2025-12-09T09:32:49.289275+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:54.791072+00:00' + source_url: https://www.ujak.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.ujak.cz/files/responsive/152/0/logo-web-1.png + source_url: https://www.ujak.cz + css_selector: '[document] > html.html.js > head > link:nth-of-type(15)' + retrieved_on: '2025-12-25T18:59:54.791072+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 152x152 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-PEL-L-RFERL.yaml b/data/custodian/CZ-52-PEL-L-RFERL.yaml index f7de60dfed..7b1809a874 100644 --- a/data/custodian/CZ-52-PEL-L-RFERL.yaml +++ b/data/custodian/CZ-52-PEL-L-RFERL.yaml @@ -186,3 +186,28 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q385994 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:59.486361+00:00' + source_url: https://www.rferl.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.rferl.org/Content/responsive/RFE/img/webApp/favicon.svg + source_url: https://www.rferl.org + css_selector: '[document] > html.js > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:59:59.486361+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.rferl.org/Content/responsive/RFE/en-US/img/top_logo_news.png + source_url: https://www.rferl.org + css_selector: '[document] > html.js > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-25T18:59:59.486361+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 10 diff --git a/data/custodian/CZ-52-PEL-L-SZUSVIK.yaml b/data/custodian/CZ-52-PEL-L-SZUSVIK.yaml index 7f4f7eebf6..2b8b313095 100644 --- a/data/custodian/CZ-52-PEL-L-SZUSVIK.yaml +++ b/data/custodian/CZ-52-PEL-L-SZUSVIK.yaml @@ -235,3 +235,22 @@ youtube_status: NOT_FOUND youtube_search_query: Státní zdravotní ústav - Středisko vědeckých informací - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:50.607856+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:05.533236+00:00' + source_url: https://katalog.szu.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.szu.cz/favicon.png?v=2.3.0-32050 + source_url: https://katalog.szu.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T19:00:05.533236+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PEL-L-UJFACVVDPO.yaml b/data/custodian/CZ-52-PEL-L-UJFACVVDPO.yaml index a804f0b3a9..7842909768 100644 --- a/data/custodian/CZ-52-PEL-L-UJFACVVDPO.yaml +++ b/data/custodian/CZ-52-PEL-L-UJFACVVDPO.yaml @@ -237,3 +237,22 @@ youtube_status: NOT_FOUND youtube_search_query: Ústav jaderné fyziky AV ČR, v. v. i. - detašované pracoviště - Oddělení dozimetrie záření - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:51.282765+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:16.118643+00:00' + source_url: http://www.ujf.cas.cz/cs + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.ujf.cas.cz/favicon.ico + source_url: http://www.ujf.cas.cz/cs + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T19:00:16.118643+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PEL-O-NKUK.yaml b/data/custodian/CZ-52-PEL-O-NKUK.yaml index 59848ff391..2941708641 100644 --- a/data/custodian/CZ-52-PEL-O-NKUK.yaml +++ b/data/custodian/CZ-52-PEL-O-NKUK.yaml @@ -230,3 +230,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Nejvyšší kontrolní úřad - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:51.941938+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:21.073300+00:00' + source_url: https://www.nku.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nku.cz/favicon.ico + source_url: https://www.nku.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:00:21.073300+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PIL-L-OKP.yaml b/data/custodian/CZ-52-PIL-L-OKP.yaml index f7d1b8b091..be44ae1666 100644 --- a/data/custodian/CZ-52-PIL-L-OKP.yaml +++ b/data/custodian/CZ-52-PIL-L-OKP.yaml @@ -211,3 +211,22 @@ location: postal_code: 542 42 street_address: Ke hřišti 100 normalization_timestamp: '2025-12-09T10:53:04.511684+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:27.167926+00:00' + source_url: https://trutnov.tritius.cz/library/pilnikov + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://trutnov.tritius.cz/apple-touch-icon-180x180.png + source_url: https://trutnov.tritius.cz/library/pilnikov + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T19:00:27.167926+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-POD-L-MKP.yaml b/data/custodian/CZ-52-POD-L-MKP.yaml index be5230fa3a..cb589c23d4 100644 --- a/data/custodian/CZ-52-POD-L-MKP.yaml +++ b/data/custodian/CZ-52-POD-L-MKP.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-POD-L-MKP - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-POD-L-MKP valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-POD-L-MKP ghcid_numeric: 10801230500255168035 valid_from: '2025-12-06T23:37:35.545725+00:00' @@ -210,3 +211,22 @@ location: postal_code: 518 03 street_address: Podbřezí 16 normalization_timestamp: '2025-12-09T10:53:04.539410+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:32.311357+00:00' + source_url: https://knihovna-podbrezi.webnode.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knihovna-podbrezi.webnode.cz/favicon.svg + source_url: https://knihovna-podbrezi.webnode.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:00:32.311357+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: any + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-POL-O-AOPKCRRPVC.yaml b/data/custodian/CZ-52-POL-O-AOPKCRRPVC.yaml index cd45a67e35..ab77ef53ba 100644 --- a/data/custodian/CZ-52-POL-O-AOPKCRRPVC.yaml +++ b/data/custodian/CZ-52-POL-O-AOPKCRRPVC.yaml @@ -42,13 +42,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-POL-O-AOPKCRRPVC - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-POL-O-AOPKCRRPVC valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-POL-O-AOPKCRRPVC ghcid_numeric: 14294348116513187770 valid_from: '2025-12-08T11:21:33.587756+00:00' @@ -222,3 +223,32 @@ location: postal_code: 549 54 street_address: Ledhujská 59 normalization_timestamp: '2025-12-09T10:53:04.588867+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:42.246937+00:00' + source_url: https://knihovna.nature.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://knihovna.nature.cz/custom/design/logo_bila.png + source_url: https://knihovna.nature.cz/#! + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > div > img' + retrieved_on: '2025-12-25T19:00:42.246937+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://knihovna.nature.cz/favicon.png?v=2.3.0-32050 + source_url: https://knihovna.nature.cz/#! + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T19:00:42.246937+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-POT-L-MKZ.yaml b/data/custodian/CZ-52-POT-L-MKZ.yaml index 37b4d3db70..5f90e54062 100644 --- a/data/custodian/CZ-52-POT-L-MKZ.yaml +++ b/data/custodian/CZ-52-POT-L-MKZ.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: CZ-52-POT-L-MKZ - valid_from: "2025-12-10T09:47:04Z" + valid_from: '2025-12-10T09:47:04Z' valid_to: null - reason: "Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) per ISO 3166-2:CZ" + reason: Corrected region code from CZ-KR to CZ-52 (Hradec Králové (Královéhradecký)) + per ISO 3166-2:CZ - ghcid: CZ-KR-POT-L-MKZ valid_from: null - valid_to: "2025-12-10T09:47:04Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:47:04Z' + reason: Previous GHCID with incorrect region code - ghcid: CZ-KR-POT-L-MKZ ghcid_numeric: 18265739301015004292 valid_from: '2025-12-06T23:37:35.548394+00:00' @@ -210,3 +211,22 @@ location: postal_code: 517 43 street_address: Záměl 158 normalization_timestamp: '2025-12-09T10:53:04.617519+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:49.086280+00:00' + source_url: https://zamel-katalog.biblio.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://zamel-katalog.biblio.cz/themes/root/images/vufind-favicon.ico + source_url: https://zamel-katalog.biblio.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:00:49.086280+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-A-ABS.yaml b/data/custodian/CZ-52-PRA-A-ABS.yaml index eac4f73c6f..76e1bcd564 100644 --- a/data/custodian/CZ-52-PRA-A-ABS.yaml +++ b/data/custodian/CZ-52-PRA-A-ABS.yaml @@ -268,3 +268,32 @@ location: youtube_status: NOT_FOUND youtube_search_query: Archiv bezpečnostních složek official youtube_search_timestamp: '2025-12-09T09:32:53.286588+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:54.740417+00:00' + source_url: https://www.abscr.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.abscr.cz/wp-content/themes/ustrcr/img/logo.png + source_url: https://www.abscr.cz + css_selector: '[document] > html.no-js > body.home.wp-singular > div.container:nth-of-type(2) + > header.header.cf > div.header__between.cf:nth-of-type(2) > p.header__logo + > a > img' + retrieved_on: '2025-12-25T19:00:54.740417+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Archiv bezpečnostních složek + - claim_type: favicon_url + claim_value: https://www.abscr.cz/wp-content/themes/ustrcr/img/favicon.ico + source_url: https://www.abscr.cz + css_selector: '[document] > html.no-js > head > link' + retrieved_on: '2025-12-25T19:00:54.740417+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-E-SPSEPJK.yaml b/data/custodian/CZ-52-PRA-E-SPSEPJK.yaml index e0673bdbad..91cd3589f4 100644 --- a/data/custodian/CZ-52-PRA-E-SPSEPJK.yaml +++ b/data/custodian/CZ-52-PRA-E-SPSEPJK.yaml @@ -192,3 +192,28 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1076099 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:00.159439+00:00' + source_url: https://www.spsejecna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.spsejecna.cz/icfaviconon.svg + source_url: https://www.spsejecna.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:01:00.159439+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.spsejecna.cz/ci/logo-310x310.png + source_url: https://www.spsejecna.cz + css_selector: '[document] > html > head > meta:nth-of-type(17)' + retrieved_on: '2025-12-25T19:01:00.159439+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-52-PRA-E-UK.yaml b/data/custodian/CZ-52-PRA-E-UK.yaml index 3364a1e7e7..8f947859df 100644 --- a/data/custodian/CZ-52-PRA-E-UK.yaml +++ b/data/custodian/CZ-52-PRA-E-UK.yaml @@ -773,3 +773,37 @@ wikidata_enrichment: logo: Univerzita Karlova horizontal logo 2023.svg wikidata_image: Praha, Univerzita Karlova - Karolinum.jpg wikidata_logo: Univerzita Karlova horizontal logo 2023.svg +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:08.614182+00:00' + source_url: https://cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://cuni.cz/UK-1-version1-afoto.jpg + source_url: https://cuni.cz + css_selector: '[document] > html > body > div.container-fluid.headerHolder > div.container.headerSubHolder + > div.row > header > div.col-md-7 > div.logo > a > img.logoSize.mobileLogoSize' + retrieved_on: '2025-12-25T19:01:08.614182+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Homepage - Univerzita Karlova + - claim_type: favicon_url + claim_value: https://cuni.cz/newlayout/UK-favicon-32x32px.png + source_url: https://cuni.cz + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:01:08.614182+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.cz/newlayout/images/logosoc.png + source_url: https://cuni.cz + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T19:01:08.614182+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-H-KBOE.yaml b/data/custodian/CZ-52-PRA-H-KBOE.yaml index 544d2da4a4..1d98b6c845 100644 --- a/data/custodian/CZ-52-PRA-H-KBOE.yaml +++ b/data/custodian/CZ-52-PRA-H-KBOE.yaml @@ -176,3 +176,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Knihovna Benediktinského opatství Emauzy official youtube_search_timestamp: '2025-12-09T09:32:55.920373+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:28.945801+00:00' + source_url: https://opatstvi-emauzy.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://opatstvi-emauzy.cz/wp-content/uploads/2019/11/EMAUZY-ZNAK-outline-300x300.png + source_url: https://opatstvi-emauzy.cz + css_selector: '[document] > html > head > link:nth-of-type(42)' + retrieved_on: '2025-12-25T19:01:28.945801+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/CZ-52-PRA-H-SPCPZSK.yaml b/data/custodian/CZ-52-PRA-H-SPCPZSK.yaml index e8f5b232d1..b451b1693f 100644 --- a/data/custodian/CZ-52-PRA-H-SPCPZSK.yaml +++ b/data/custodian/CZ-52-PRA-H-SPCPZSK.yaml @@ -222,3 +222,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Společnost pro církevní právo, z. s. - knihovna official youtube_search_timestamp: '2025-12-09T09:32:56.576954+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:34.369154+00:00' + source_url: https://spcp.prf.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://spcp.prf.cuni.cz/favicon.ico + source_url: https://spcp.prf.cuni.cz + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T19:01:34.369154+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-ADISRK.yaml b/data/custodian/CZ-52-PRA-L-ADISRK.yaml index 0071704d7f..16037c95de 100644 --- a/data/custodian/CZ-52-PRA-L-ADISRK.yaml +++ b/data/custodian/CZ-52-PRA-L-ADISRK.yaml @@ -226,3 +226,31 @@ location: youtube_status: NOT_FOUND youtube_search_query: ART & DESIGN INSTITUT, s.r.o. - Knihovna official youtube_search_timestamp: '2025-12-09T09:32:57.242725+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:39.750926+00:00' + source_url: http://www.adi.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.adi.cz/data/original/adi-logo.png + source_url: http://www.adi.cz + css_selector: '[document] > html > body.default.core-menu-lang > section.site-wrapper + > header.header > div.main-menu > div.logo > a > img' + retrieved_on: '2025-12-25T19:01:39.750926+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: http://www.adi.cz/data/192x192/adi-favicon.png + source_url: http://www.adi.cz + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-25T19:01:39.750926+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 192x192 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/CZ-52-PRA-L-CAK.yaml b/data/custodian/CZ-52-PRA-L-CAK.yaml index 8ae0279a52..f6c4b0e2ba 100644 --- a/data/custodian/CZ-52-PRA-L-CAK.yaml +++ b/data/custodian/CZ-52-PRA-L-CAK.yaml @@ -195,3 +195,28 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q385994 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:49.652062+00:00' + source_url: https://www.cak.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.cak.cz/build/images/favicon.png + source_url: https://www.cak.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:01:49.652062+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.cak.cz/storage/images/settings/6/8/3/6835924b7b5a7522494085.png + source_url: https://www.cak.cz + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-25T19:01:49.652062+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-CNBOK.yaml b/data/custodian/CZ-52-PRA-L-CNBOK.yaml index 5b4b7c0aeb..9fce780db3 100644 --- a/data/custodian/CZ-52-PRA-L-CNBOK.yaml +++ b/data/custodian/CZ-52-PRA-L-CNBOK.yaml @@ -232,3 +232,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Česká národní banka - odborná knihovna official youtube_search_timestamp: '2025-12-09T09:33:00.109157+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:00.590459+00:00' + source_url: https://katalog.cnb.cz/#! + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.cnb.cz/export/system/modules/org.opencms.apollo/resources/img/favicon_120.png + source_url: https://katalog.cnb.cz/#! + css_selector: '[document] > html.show--consent.show--settings > head > link' + retrieved_on: '2025-12-25T19:02:00.590459+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-CPSUPPSK.yaml b/data/custodian/CZ-52-PRA-L-CPSUPPSK.yaml index 00a270b4bf..a3b0198992 100644 --- a/data/custodian/CZ-52-PRA-L-CPSUPPSK.yaml +++ b/data/custodian/CZ-52-PRA-L-CPSUPPSK.yaml @@ -224,3 +224,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Centrum pro současné umění Praha, o.p.s. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:00.768154+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:05.182743+00:00' + source_url: https://csupraha.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://csupraha.cz/favicon.ico + source_url: https://csupraha.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T19:02:05.182743+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-CRROK.yaml b/data/custodian/CZ-52-PRA-L-CRROK.yaml index 154e7e0a86..28e01f3629 100644 --- a/data/custodian/CZ-52-PRA-L-CRROK.yaml +++ b/data/custodian/CZ-52-PRA-L-CRROK.yaml @@ -239,3 +239,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Český rozhlas - Rešeršní oddělení a knihovna official youtube_search_timestamp: '2025-12-09T09:33:01.427211+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:11.002904+00:00' + source_url: https://portal.rozhlas.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://portal.rozhlas.cz/themes/mr_frontend/img/favicons/safari-pinned-tab.svg + source_url: https://portal.rozhlas.cz + css_selector: '[document] > html.no-touchevents.supports > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T19:02:11.002904+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.mujrozhlas.cz/sites/default/files/2019-12/logo_mR_OG_1200x628.png + source_url: https://portal.rozhlas.cz + css_selector: '[document] > html.no-touchevents.supports > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-25T19:02:11.002904+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-52-PRA-L-CSEK.yaml b/data/custodian/CZ-52-PRA-L-CSEK.yaml index 302b60dfe2..5dc67d2f0a 100644 --- a/data/custodian/CZ-52-PRA-L-CSEK.yaml +++ b/data/custodian/CZ-52-PRA-L-CSEK.yaml @@ -232,3 +232,31 @@ location: youtube_status: NOT_FOUND youtube_search_query: Česká společnost entomologická - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:02.085923+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:16.868635+00:00' + source_url: https://www.entospol.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.entospol.cz/wp-content/uploads/2021/04/cropped-banner-logo-maly-01-1-1.png + source_url: https://www.entospol.cz + css_selector: '#masthead > div.tg-site-header-bottom:nth-of-type(2) > div.tg-header-container.tg-container + > div.tg-block.tg-block--one > div.site-branding > a.custom-logo-link > img.custom-logo' + retrieved_on: '2025-12-25T19:02:16.868635+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Česká společnost entomologická + - claim_type: favicon_url + claim_value: https://www.entospol.cz/wp-content/uploads/2021/04/cropped-logo-cse-01-2-180x180.png + source_url: https://www.entospol.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T19:02:16.868635+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-PRA-L-CSPC.yaml b/data/custodian/CZ-52-PRA-L-CSPC.yaml index 27a91cacb4..13cb23a5d8 100644 --- a/data/custodian/CZ-52-PRA-L-CSPC.yaml +++ b/data/custodian/CZ-52-PRA-L-CSPC.yaml @@ -246,3 +246,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Česká společnost průmyslové chemie official youtube_search_timestamp: '2025-12-09T09:33:02.745904+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:22.061465+00:00' + source_url: http://www.cspch.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.cspch.cz/wp-content/uploads/2025/10/cspch-logo.png + source_url: http://www.cspch.cz + css_selector: '#site-logo-inner > a.custom-logo-link > img.custom-logo' + retrieved_on: '2025-12-25T19:02:22.061465+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Česká společnost průmyslové chemie + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/CZ-52-PRA-L-CSSPKCRK.yaml b/data/custodian/CZ-52-PRA-L-CSSPKCRK.yaml index a31d5f0edc..35d46942cd 100644 --- a/data/custodian/CZ-52-PRA-L-CSSPKCRK.yaml +++ b/data/custodian/CZ-52-PRA-L-CSSPKCRK.yaml @@ -227,3 +227,36 @@ youtube_status: NOT_FOUND youtube_search_query: Centrum sociálních služeb Praha - Krizové centrum RIAPS - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:03.408537+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:26.973725+00:00' + source_url: https://www.csspraha.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://static.wixstatic.com/media/4834da_1e5421aa0a3343e09ef4c86b6734d5b0~mv2.png/v1/fill/w_136,h_60,al_c,q_85,usm_0.66_1.00_0.01,enc_avif,quality_auto/CSSP_new_logo.png + source_url: https://www.csspraha.cz + css_selector: '#img_comp-ko324hyr' + retrieved_on: '2025-12-25T19:02:26.973725+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: CSSP_new_logo.png + - claim_type: favicon_url + claim_value: https://static.wixstatic.com/media/4834da_ffd8919570224b47a1b86e9882dea54b%7Emv2.png/v1/fill/w_180%2Ch_180%2Clg_1%2Cusm_0.66_1.00_0.01/4834da_ffd8919570224b47a1b86e9882dea54b%7Emv2.png + source_url: https://www.csspraha.cz + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:02:26.973725+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://static.wixstatic.com/media/4834da_ffd8919570224b47a1b86e9882dea54b%7Emv2.png/v1/fit/w_2500,h_1330,al_c/4834da_ffd8919570224b47a1b86e9882dea54b%7Emv2.png + source_url: https://www.csspraha.cz + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-25T19:02:26.973725+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-52-PRA-L-CTSKAAPF.yaml b/data/custodian/CZ-52-PRA-L-CTSKAAPF.yaml index b424a1fd83..f73efbb464 100644 --- a/data/custodian/CZ-52-PRA-L-CTSKAAPF.yaml +++ b/data/custodian/CZ-52-PRA-L-CTSKAAPF.yaml @@ -233,3 +233,28 @@ youtube_status: NOT_FOUND youtube_search_query: Česká televize - Studijní knihovna - APF (Archiv a programové fondy) official youtube_search_timestamp: '2025-12-09T09:33:04.072613+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:32.185134+00:00' + source_url: https://www.ceskatelevize.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://ctfs.ceskatelevize.cz/static/assets/favicon/favicon.svg + source_url: https://www.ceskatelevize.cz + css_selector: '[document] > html.js.canvas > head > link:nth-of-type(12)' + retrieved_on: '2025-12-25T19:02:32.185134+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://imgct.ceskatelevize.cz/global/images/og-image.png?_ts=1366977078 + source_url: https://www.ceskatelevize.cz + css_selector: '[document] > html.js.canvas > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T19:02:32.185134+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/CZ-52-PRA-L-CVPUKCKAC.yaml b/data/custodian/CZ-52-PRA-L-CVPUKCKAC.yaml index 500a5c0e89..b2e3b21da2 100644 --- a/data/custodian/CZ-52-PRA-L-CVPUKCKAC.yaml +++ b/data/custodian/CZ-52-PRA-L-CVPUKCKAC.yaml @@ -237,3 +237,22 @@ youtube_status: NOT_FOUND youtube_search_query: ČVUT v Praze - Ústřední knihovna ČVUT - Knihovna Archivu ČVUT official youtube_search_timestamp: '2025-12-09T09:33:04.736584+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:37.562921+00:00' + source_url: https://www.cvut.cz/archiv/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.cvut.cz/sites/default/files/favicon.ico + source_url: https://www.cvut.cz/archiv/knihovna + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-25T19:02:37.562921+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-CVTPSK.yaml b/data/custodian/CZ-52-PRA-L-CVTPSK.yaml index 457d8d57cf..610f5dac04 100644 --- a/data/custodian/CZ-52-PRA-L-CVTPSK.yaml +++ b/data/custodian/CZ-52-PRA-L-CVTPSK.yaml @@ -231,3 +231,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Člověk v tísni o. p. s. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:06.053005+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:48.315410+00:00' + source_url: https://www.clovekvtisni.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.clovekvtisni.cz/images/android-chrome-512x512.png + source_url: https://www.clovekvtisni.cz + css_selector: '[document] > html.no-cssgridlegacy.cssgrid > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:02:48.315410+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 512x512 + - claim_type: og_image_url + claim_value: https://www.clovekvtisni.cz/image-cache/www/media/metatags/23218/image/kramatorsk-zapo-104.jpg_1203x630-crop-cp_0x206-cs_3000x1570.webp?ts=1765801226 + source_url: https://www.clovekvtisni.cz + css_selector: '[document] > html.no-cssgridlegacy.cssgrid > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T19:02:48.315410+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 11 diff --git a/data/custodian/CZ-52-PRA-L-FIM-francouzsky_institut_mediateka.yaml b/data/custodian/CZ-52-PRA-L-FIM-francouzsky_institut_mediateka.yaml index b0855db2d0..7cfec0eac4 100644 --- a/data/custodian/CZ-52-PRA-L-FIM-francouzsky_institut_mediateka.yaml +++ b/data/custodian/CZ-52-PRA-L-FIM-francouzsky_institut_mediateka.yaml @@ -186,3 +186,28 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q385994 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:55.283060+00:00' + source_url: https://prague.bibenligne.fr/?action=Accueil + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prague.bibenligne.fr/resources/images/favicon.png + source_url: https://prague.bibenligne.fr/?action=Accueil + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:02:55.283060+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://prague.bibenligne.fr/data/prague.bibenligne.fr/application/layout/logo.png + source_url: https://prague.bibenligne.fr/?action=Accueil + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T19:02:55.283060+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-FIM.yaml b/data/custodian/CZ-52-PRA-L-FIM.yaml index 068f09e568..b99ef5e8af 100644 --- a/data/custodian/CZ-52-PRA-L-FIM.yaml +++ b/data/custodian/CZ-52-PRA-L-FIM.yaml @@ -186,3 +186,28 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q385994 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:02.189936+00:00' + source_url: https://prague.bibenligne.fr/?action=Accueil + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://prague.bibenligne.fr/resources/images/favicon.png + source_url: https://prague.bibenligne.fr/?action=Accueil + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:03:02.189936+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://prague.bibenligne.fr/data/prague.bibenligne.fr/application/layout/logo.png + source_url: https://prague.bibenligne.fr/?action=Accueil + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T19:03:02.189936+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-HLK.yaml b/data/custodian/CZ-52-PRA-L-HLK.yaml index 1cabc07055..3b31c369de 100644 --- a/data/custodian/CZ-52-PRA-L-HLK.yaml +++ b/data/custodian/CZ-52-PRA-L-HLK.yaml @@ -184,3 +184,22 @@ wikidata_enrichment: instance_of: - Q7075 located_in: Q1085 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:11.988090+00:00' + source_url: https://katalog.hornikovaknihovna.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.hornikovaknihovna.cz/themes/root/images/vufind-favicon.ico + source_url: https://katalog.hornikovaknihovna.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T19:03:11.988090+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-ICVPKCF.yaml b/data/custodian/CZ-52-PRA-L-ICVPKCF.yaml index d5fb3e2bb1..896f943645 100644 --- a/data/custodian/CZ-52-PRA-L-ICVPKCF.yaml +++ b/data/custodian/CZ-52-PRA-L-ICVPKCF.yaml @@ -198,3 +198,22 @@ wikidata_enrichment: - Q12317349 inception: +2006-01-01T00:00:00Z located_in: Q1085 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:21.872286+00:00' + source_url: https://catalogo-bibliotecas.cervantes.es + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://catalogo-bibliotecas.cervantes.es/general/imag/icons/logo_36x36.png + source_url: https://catalogo-bibliotecas.cervantes.es + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:03:21.872286+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: 6 diff --git a/data/custodian/CZ-52-PRA-L-ITIK.yaml b/data/custodian/CZ-52-PRA-L-ITIK.yaml index 6bdec8d072..4900b55ca4 100644 --- a/data/custodian/CZ-52-PRA-L-ITIK.yaml +++ b/data/custodian/CZ-52-PRA-L-ITIK.yaml @@ -224,3 +224,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Institut Terezínské iniciativy - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:11.326423+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:36.495990+00:00' + source_url: http://www.terezinstudies.cz/cs/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.terezinstudies.cz/favicon.ico + source_url: http://www.terezinstudies.cz/cs/knihovna + css_selector: '[document] > html.layout-homepage.js > head > link' + retrieved_on: '2025-12-25T19:03:36.495990+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-KACVV.yaml b/data/custodian/CZ-52-PRA-L-KACVV.yaml index 7693aa2c8d..b6a5c9b25d 100644 --- a/data/custodian/CZ-52-PRA-L-KACVV.yaml +++ b/data/custodian/CZ-52-PRA-L-KACVV.yaml @@ -204,3 +204,32 @@ wikidata_enrichment: - Q108935461 inception: +1952-01-01T00:00:00Z located_in: Q748211 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:41.418987+00:00' + source_url: https://katalog.lib.cas.cz/KNAV + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://katalog.lib.cas.cz/themes/knav_katalog/images/svg/bank-id-logo.svg + source_url: https://katalog.lib.cas.cz/KNAV + css_selector: '[document] > html > body.template-dir-.template-name- > header.hidden-print + > div.container-head.navbar > div.library_closed:nth-of-type(3) > span > a:nth-of-type(2) + > img' + retrieved_on: '2025-12-25T19:03:41.418987+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Bank iD button + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/KNAV/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/KNAV + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:03:41.418987+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-KAS.yaml b/data/custodian/CZ-52-PRA-L-KAS.yaml index 115b6ae1e1..739e38e1e7 100644 --- a/data/custodian/CZ-52-PRA-L-KAS.yaml +++ b/data/custodian/CZ-52-PRA-L-KAS.yaml @@ -270,3 +270,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Knihovna Antonína Švehly official youtube_search_timestamp: '2025-12-09T09:33:13.310763+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:52.333497+00:00' + source_url: https://aleph.uzei.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://aleph.uzei.cz/exlibris/aleph/u23_1/alephe/www_f_cze/icon/favicon.ico + source_url: https://aleph.uzei.cz + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:03:52.333497+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-KLP.yaml b/data/custodian/CZ-52-PRA-L-KLP.yaml index 2354e77ee1..d07b55e73e 100644 --- a/data/custodian/CZ-52-PRA-L-KLP.yaml +++ b/data/custodian/CZ-52-PRA-L-KLP.yaml @@ -189,3 +189,35 @@ wikidata_enrichment: instance_of: - Q7075 inception: +1990-10-22T00:00:00Z +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:58.051571+00:00' + source_url: http://www.libpro.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://cdn.libpro.cz/content/uploads/2019/06/logo.png + source_url: http://www.libpro.cz + css_selector: '#masthead > div.elementor.elementor-2793 > section.elementor-section.elementor-top-section + > div.elementor-container.elementor-column-gap-no > div.elementor-column.elementor-col-100 + > div.elementor-widget-wrap.elementor-element-populated > section.elementor-section.elementor-inner-section:nth-of-type(2) + > div.elementor-container.elementor-column-gap-no > div.elementor-column.elementor-col-50 + > div.elementor-widget-wrap.elementor-element-populated > div.elementor-element.elementor-element-bb2711e + > div.elementor-widget-container > a > noscript > img.attachment-large.size-large' + retrieved_on: '2025-12-25T19:03:58.051571+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: '' + - claim_type: favicon_url + claim_value: https://cdn.libpro.cz/content/uploads/2019/06/favicon.ico + source_url: http://www.libpro.cz + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T19:03:58.051571+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-KVHNF.yaml b/data/custodian/CZ-52-PRA-L-KVHNF.yaml index 0bab4bb471..8c3530bf42 100644 --- a/data/custodian/CZ-52-PRA-L-KVHNF.yaml +++ b/data/custodian/CZ-52-PRA-L-KVHNF.yaml @@ -196,3 +196,28 @@ wikidata_enrichment: - Q11812394 - Q2085381 inception: +2004-07-26T00:00:00Z +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:05.772395+00:00' + source_url: https://www.vaclavhavel.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vaclavhavel.cz/favicon.ico + source_url: https://www.vaclavhavel.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:04:05.772395+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.vaclavhavel.cz/img/kvh-logo2.png + source_url: https://www.vaclavhavel.cz + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T19:04:05.772395+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-KVSPOSPS.yaml b/data/custodian/CZ-52-PRA-L-KVSPOSPS.yaml index 744bf40047..e74d913e7e 100644 --- a/data/custodian/CZ-52-PRA-L-KVSPOSPS.yaml +++ b/data/custodian/CZ-52-PRA-L-KVSPOSPS.yaml @@ -191,3 +191,22 @@ wikidata_enrichment: instance_of: - Q7075 inception: +2003-03-20T00:00:00Z +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:11.881293+00:00' + source_url: https://knv.tritius.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://knv.tritius.cz/apple-touch-icon-180x180.png + source_url: https://knv.tritius.cz + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T19:04:11.881293+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-PRA-L-MDA.yaml b/data/custodian/CZ-52-PRA-L-MDA.yaml index 97aa73ed9a..e454665d67 100644 --- a/data/custodian/CZ-52-PRA-L-MDA.yaml +++ b/data/custodian/CZ-52-PRA-L-MDA.yaml @@ -227,3 +227,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Masarykova demokratická akademie official youtube_search_timestamp: '2025-12-09T09:33:16.593460+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:20.297015+00:00' + source_url: https://masarykovaakademie.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://masarykovaakademie.cz/wp-content/uploads/2_05_vertikal_Mda-favico.png + source_url: https://masarykovaakademie.cz/knihovna + css_selector: '[document] > html.csstransforms.csstransforms3d > head > link:nth-of-type(34)' + retrieved_on: '2025-12-25T19:04:20.297015+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-MSCCCKNPKU.yaml b/data/custodian/CZ-52-PRA-L-MSCCCKNPKU.yaml index 3cc031616f..980bd9008f 100644 --- a/data/custodian/CZ-52-PRA-L-MSCCCKNPKU.yaml +++ b/data/custodian/CZ-52-PRA-L-MSCCCKNPKU.yaml @@ -241,3 +241,36 @@ youtube_status: NOT_FOUND youtube_search_query: Mezinárodní sinologické centrum Chiang Ching-Kuovy nadace při Karlově univerzitě - knihovna official youtube_search_timestamp: '2025-12-09T09:33:17.255952+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:25.581229+00:00' + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#logoImage' + retrieved_on: '2025-12-25T19:04:25.581229+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo knihovny + - claim_type: favicon_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/favicon.ico + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#viewCustomerFavIcon' + retrieved_on: '2025-12-25T19:04:25.581229+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#ogImage' + retrieved_on: '2025-12-25T19:04:25.581229+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-MVCVSOLKPM.yaml b/data/custodian/CZ-52-PRA-L-MVCVSOLKPM.yaml index ddb9e11057..942df64b2b 100644 --- a/data/custodian/CZ-52-PRA-L-MVCVSOLKPM.yaml +++ b/data/custodian/CZ-52-PRA-L-MVCVSOLKPM.yaml @@ -237,3 +237,28 @@ youtube_status: NOT_FOUND youtube_search_query: Ministrstvo vnitra ČR - Veřejná správa - Odbor legislativy a koordinace předpisů MV ČR - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:17.924607+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:31.337475+00:00' + source_url: https://www.mvcr.cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mvcr.cz/favicon.ico + source_url: https://www.mvcr.cz + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:04:31.337475+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/ico + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mv.gov.cz/design/img/logo-sn.jpg + source_url: https://www.mvcr.cz + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:04:31.337475+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-NFAK.yaml b/data/custodian/CZ-52-PRA-L-NFAK.yaml index 9757c7f027..113e973b45 100644 --- a/data/custodian/CZ-52-PRA-L-NFAK.yaml +++ b/data/custodian/CZ-52-PRA-L-NFAK.yaml @@ -244,3 +244,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Národní filmový archiv - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:18.590406+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:36.663409+00:00' + source_url: https://arl.nfa.cz/arl-nfa/cs/index + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://arl.nfa.cz/safari-pinned-tab.svg + source_url: https://arl.nfa.cz/arl-nfa/cs/index + css_selector: '[document] > html.no-js.show--consent > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:04:36.663409+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://nfa.cz/dokumenty/74703/image-thumb__74703__OGImage/zastupny-obrazek-open-graph.jpg + source_url: https://arl.nfa.cz/arl-nfa/cs/index + css_selector: '[document] > html.no-js.show--consent > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:04:36.663409+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 5 diff --git a/data/custodian/CZ-52-PRA-L-NKCR.yaml b/data/custodian/CZ-52-PRA-L-NKCR.yaml index d4e0a1f6b2..cba8dff0a2 100644 --- a/data/custodian/CZ-52-PRA-L-NKCR.yaml +++ b/data/custodian/CZ-52-PRA-L-NKCR.yaml @@ -537,3 +537,31 @@ wikidata_enrichment: label: Jikji Memory of the World Prize description: UNESCO award to promote the objectives of the Memory of the World Programme +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:42.186893+00:00' + source_url: https://www.nkp.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.nkp.cz/img/nk-logo.svg + source_url: https://www.nkp.cz + css_selector: '#page > header > div.section.section--header > div.header > div.header__l + > div.logo > h1 > a > img.logo__img' + retrieved_on: '2025-12-25T19:04:42.186893+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Národní knihovna České republiky + - claim_type: favicon_url + claim_value: https://www.nkp.cz/file/ae52310515fab0ec98da775993a73b07/6647/favicon/nkcr_web_favicon.png + source_url: https://www.nkp.cz + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T19:04:42.186893+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-NKCRSKOS-narodni_knihovna_ceske_republiky_slovanska_knihovn.yaml b/data/custodian/CZ-52-PRA-L-NKCRSKOS-narodni_knihovna_ceske_republiky_slovanska_knihovn.yaml index 3c791c949b..c7dfbc20ce 100644 --- a/data/custodian/CZ-52-PRA-L-NKCRSKOS-narodni_knihovna_ceske_republiky_slovanska_knihovn.yaml +++ b/data/custodian/CZ-52-PRA-L-NKCRSKOS-narodni_knihovna_ceske_republiky_slovanska_knihovn.yaml @@ -193,3 +193,37 @@ wikidata_enrichment: instance_of: - Q7075 inception: +1924-00-00T00:00:00Z +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:52.564566+00:00' + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.nkp.cz/img/nk-logo.svg + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + css_selector: '#page > header > div.section.section--header > div.header > div.header__l + > div.logo > a > img.logo__img' + retrieved_on: '2025-12-25T19:04:52.564566+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Národní knihovna České republiky + - claim_type: favicon_url + claim_value: https://www.nkp.cz/file/ae52310515fab0ec98da775993a73b07/6647/favicon/nkcr_web_favicon.png + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:04:52.564566+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.nkp.cz/file/677eb0433e3c03c235e277d22c20bbd2/869/nkcr_studovnaslovanskeknihovny_26_3_2024_web%282%29.jpg + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:04:52.564566+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-NKCRSKOS.yaml b/data/custodian/CZ-52-PRA-L-NKCRSKOS.yaml index 6a0721ff1c..6f9cdffe77 100644 --- a/data/custodian/CZ-52-PRA-L-NKCRSKOS.yaml +++ b/data/custodian/CZ-52-PRA-L-NKCRSKOS.yaml @@ -193,3 +193,37 @@ wikidata_enrichment: instance_of: - Q7075 inception: +1924-00-00T00:00:00Z +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:57.850064+00:00' + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.nkp.cz/img/nk-logo.svg + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + css_selector: '#page > header > div.section.section--header > div.header > div.header__l + > div.logo > a > img.logo__img' + retrieved_on: '2025-12-25T19:04:57.850064+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Národní knihovna České republiky + - claim_type: favicon_url + claim_value: https://www.nkp.cz/file/ae52310515fab0ec98da775993a73b07/6647/favicon/nkcr_web_favicon.png + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:04:57.850064+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.nkp.cz/file/677eb0433e3c03c235e277d22c20bbd2/869/nkcr_studovnaslovanskeknihovny_26_3_2024_web%282%29.jpg + source_url: https://www.nkp.cz/studovny-a-prostory/pujcovna-a-studovna-slovanske-knihovny + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:04:57.850064+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-NLK.yaml b/data/custodian/CZ-52-PRA-L-NLK.yaml index 14581db625..29800f3698 100644 --- a/data/custodian/CZ-52-PRA-L-NLK.yaml +++ b/data/custodian/CZ-52-PRA-L-NLK.yaml @@ -310,3 +310,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Národní lékařská knihovna official youtube_search_timestamp: '2025-12-09T09:33:21.882507+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:02.591599+00:00' + source_url: https://www.medvik.cz/bmc/index.do?focus=ABA008 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.medvik.cz/bmc/img/favicon.ico + source_url: https://www.medvik.cz/bmc/index.do?focus=ABA008 + css_selector: '[document] > html.show--consent > head > link' + retrieved_on: '2025-12-25T19:05:02.591599+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-NMKNMORST.yaml b/data/custodian/CZ-52-PRA-L-NMKNMORST.yaml index c44c98b162..25c2e3ae98 100644 --- a/data/custodian/CZ-52-PRA-L-NMKNMORST.yaml +++ b/data/custodian/CZ-52-PRA-L-NMKNMORST.yaml @@ -228,3 +228,32 @@ youtube_status: NOT_FOUND youtube_search_query: Národní muzeum - Knihovna Národního muzea - Oddělení rukopisů a starých tisků official youtube_search_timestamp: '2025-12-09T09:33:22.550437+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:08.029804+00:00' + source_url: https://stt.opac.nm.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://stt.opac.nm.cz/custom/design/AJ_logo_200_cerna.png + source_url: https://stt.opac.nm.cz + css_selector: '#portaro-classic-layout > kp-svelte-component-wrapper.kp-header-component-wrapper.ng-isolate-scope + > header.kp-header.logo-stripe > div.logo-content-container.container > div.logo-search-row.row + > div.customLogoArea.custom-logo-area > a > img' + retrieved_on: '2025-12-25T19:05:08.029804+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Národní muzeum + - claim_type: favicon_url + claim_value: https://stt.opac.nm.cz/favicon.png?v=2.3.0-32049 + source_url: https://stt.opac.nm.cz + css_selector: '#ng-app > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T19:05:08.029804+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 256x256 + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-NPUHKF.yaml b/data/custodian/CZ-52-PRA-L-NPUHKF.yaml index f3f2b4fa9c..66455faba6 100644 --- a/data/custodian/CZ-52-PRA-L-NPUHKF.yaml +++ b/data/custodian/CZ-52-PRA-L-NPUHKF.yaml @@ -235,3 +235,28 @@ location: youtube_status: NOT_FOUND youtube_search_query: Národní památkový ústav - Historické knihovní fondy official youtube_search_timestamp: '2025-12-09T09:33:23.210348+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:13.270567+00:00' + source_url: https://www.npu.cz/cs + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.npu.cz/safari-pinned-tab.svg + source_url: https://www.npu.cz/cs + css_selector: '[document] > html.show--consent > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T19:05:13.270567+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.npu.cz/portal/001-hp/ilustracni-fotky/zastupny-obrazek_web.jpg + source_url: https://www.npu.cz/cs + css_selector: '[document] > html.show--consent > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T19:05:13.270567+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/CZ-52-PRA-L-NPUK.yaml b/data/custodian/CZ-52-PRA-L-NPUK.yaml index 472af9fae6..9140c61818 100644 --- a/data/custodian/CZ-52-PRA-L-NPUK.yaml +++ b/data/custodian/CZ-52-PRA-L-NPUK.yaml @@ -238,3 +238,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Národní památkový ústav - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:23.876571+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:20.044132+00:00' + source_url: https://iispp.npu.cz/carmen/library/gnr + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://iispp.npu.cz/carmen/apple-touch-icon-180x180.png + source_url: https://iispp.npu.cz/carmen/library/gnr + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T19:05:20.044132+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-PRA-L-OKVP.yaml b/data/custodian/CZ-52-PRA-L-OKVP.yaml index 91a3b738ad..ca8a433d0c 100644 --- a/data/custodian/CZ-52-PRA-L-OKVP.yaml +++ b/data/custodian/CZ-52-PRA-L-OKVP.yaml @@ -211,3 +211,22 @@ location: postal_code: 504 01 street_address: Prasek 229 normalization_timestamp: '2025-12-09T10:53:04.646260+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:27.602085+00:00' + source_url: https://merkur.tritius.cz/library/prasek + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://merkur.tritius.cz/apple-touch-icon-180x180.png + source_url: https://merkur.tritius.cz/library/prasek + css_selector: '[document] > html > head > link:nth-of-type(14)' + retrieved_on: '2025-12-25T19:05:27.602085+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 14 diff --git a/data/custodian/CZ-52-PRA-L-PUACVVPPK.yaml b/data/custodian/CZ-52-PRA-L-PUACVVPPK.yaml index 7062a8b738..9823d1e29e 100644 --- a/data/custodian/CZ-52-PRA-L-PUACVVPPK.yaml +++ b/data/custodian/CZ-52-PRA-L-PUACVVPPK.yaml @@ -234,3 +234,22 @@ youtube_status: NOT_FOUND youtube_search_query: Psychologický ústav AV ČR, v. v. i. - pobočka Praha - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:24.545316+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:32.566803+00:00' + source_url: https://katalog.lib.cas.cz/PSUA + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/PSUA/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/PSUA + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:05:32.566803+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-SUACVVK.yaml b/data/custodian/CZ-52-PRA-L-SUACVVK.yaml index 5c6980c03e..2a07e434a4 100644 --- a/data/custodian/CZ-52-PRA-L-SUACVVK.yaml +++ b/data/custodian/CZ-52-PRA-L-SUACVVK.yaml @@ -232,3 +232,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Slovanský ústav AV ČR, v. v. i. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:26.520835+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:14.115172+00:00' + source_url: https://katalog.lib.cas.cz/SLUA + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/SLUA/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/SLUA + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:06:14.115172+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-SUROVVK.yaml b/data/custodian/CZ-52-PRA-L-SUROVVK.yaml index 2f721f0c21..b7b3e6c19a 100644 --- a/data/custodian/CZ-52-PRA-L-SUROVVK.yaml +++ b/data/custodian/CZ-52-PRA-L-SUROVVK.yaml @@ -231,3 +231,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Státní ústav radiační ochrany, v. v. i. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:27.191298+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:19.428262+00:00' + source_url: https://www.suro.cz/cz + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.suro.cz/files/favicon_0.ico + source_url: https://www.suro.cz/cz + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-25T19:06:19.428262+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-TPSK.yaml b/data/custodian/CZ-52-PRA-L-TPSK.yaml index 0556283091..4e069951e4 100644 --- a/data/custodian/CZ-52-PRA-L-TPSK.yaml +++ b/data/custodian/CZ-52-PRA-L-TPSK.yaml @@ -224,3 +224,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Tyfloservis, o.p.s. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:27.850149+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:25.149179+00:00' + source_url: https://www.tyfloservis.cz/organizacni-a-metodicke-centrum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tyfloservis.cz/wp-content/uploads/2020/12/cropped-favicaArtboard-1-8-180x180.png + source_url: https://www.tyfloservis.cz/organizacni-a-metodicke-centrum + css_selector: '[document] > html.js > head > link:nth-of-type(20)' + retrieved_on: '2025-12-25T19:06:25.149179+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/CZ-52-PRA-L-UDUACVVK.yaml b/data/custodian/CZ-52-PRA-L-UDUACVVK.yaml index 80802905da..8d9e9fb57c 100644 --- a/data/custodian/CZ-52-PRA-L-UDUACVVK.yaml +++ b/data/custodian/CZ-52-PRA-L-UDUACVVK.yaml @@ -236,3 +236,22 @@ location: youtube_status: NOT_FOUND youtube_search_query: Ústav dějin umění AV ČR, v. v. i. - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:28.513406+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:29.983334+00:00' + source_url: https://katalog.lib.cas.cz/UDU + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://katalog.lib.cas.cz/UDU/themes/knav_katalog/images/vufind-favicon.ico?_=1636405137 + source_url: https://katalog.lib.cas.cz/UDU + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:06:29.983334+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-UKFFFUK.yaml b/data/custodian/CZ-52-PRA-L-UKFFFUK.yaml index 008bb7dcbb..15fab6b8f2 100644 --- a/data/custodian/CZ-52-PRA-L-UKFFFUK.yaml +++ b/data/custodian/CZ-52-PRA-L-UKFFFUK.yaml @@ -238,3 +238,31 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Filozofická fakulta - Fonetický ústav - knihovna official youtube_search_timestamp: '2025-12-09T09:33:29.181918+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:36.937810+00:00' + source_url: https://fonetika.ff.cuni.cz/knihovna + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sites.ff.cuni.cz/fonetika/wp-content/uploads/sites/104/2020/11/Foneticky_ustav.svg + source_url: https://fonetika.ff.cuni.cz/knihovna + css_selector: '[document] > html > body.topmenu > header.faheader > div.row.clearfix + > div.columns.large-10 > h1 > a > img.faheader-logo' + retrieved_on: '2025-12-25T19:06:36.937810+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Fonetický ústav + - claim_type: favicon_url + claim_value: https://sites.ff.cuni.cz/fonetika/wp-content/uploads/sites/104/2017/11/cropped-logo-fu-180x180.png + source_url: https://fonetika.ff.cuni.cz/knihovna + css_selector: '[document] > html > head > link:nth-of-type(20)' + retrieved_on: '2025-12-25T19:06:36.937810+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/CZ-52-PRA-L-UKFFKE.yaml b/data/custodian/CZ-52-PRA-L-UKFFKE.yaml index daeb9c30dd..92b3663d4e 100644 --- a/data/custodian/CZ-52-PRA-L-UKFFKE.yaml +++ b/data/custodian/CZ-52-PRA-L-UKFFKE.yaml @@ -197,3 +197,31 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1622062 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:15.781032+00:00' + source_url: https://kest.ff.cuni.cz/index.php?s=kontakt + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sites.ff.cuni.cz/estetika/wp-content/uploads/sites/167/2020/11/Katedra_estetiky.svg + source_url: https://kest.ff.cuni.cz/index.php?s=kontakt + css_selector: '[document] > html > body.topmenu > header.faheader > div.row.clearfix + > div.columns.large-10 > h1 > a > img.faheader-logo' + retrieved_on: '2025-12-25T19:07:15.781032+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: KATEDRA ESTETIKY + - claim_type: favicon_url + claim_value: https://sites.ff.cuni.cz/estetika/wp-content/uploads/sites/167/2020/11/cropped-logo_uk_cerne-180x180.png + source_url: https://kest.ff.cuni.cz/index.php?s=kontakt + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T19:07:15.781032+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/CZ-52-PRA-L-UKFFKUE.yaml b/data/custodian/CZ-52-PRA-L-UKFFKUE.yaml index 291654e095..3d3a3bbf95 100644 --- a/data/custodian/CZ-52-PRA-L-UKFFKUE.yaml +++ b/data/custodian/CZ-52-PRA-L-UKFFKUE.yaml @@ -239,3 +239,31 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Filozofická fakulta - Knihovna Ústavu etnologie official youtube_search_timestamp: '2025-12-09T09:33:31.171638+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:21.666858+00:00' + source_url: https://uesebs.ff.cuni.cz/cs + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sites.ff.cuni.cz/uesebs/wp-content/uploads/sites/178/2023/10/Ustav_etnologie_a_stredoevropskych_a_balkanskych_-studii.svg + source_url: https://uesebs.ff.cuni.cz/cs + css_selector: '[document] > html > body.topmenu > header.faheader > div.row.clearfix + > div.columns.large-10 > h1 > a > img.faheader-logo' + retrieved_on: '2025-12-25T19:07:21.666858+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Ústav etnologie a středoevropských a balkánských studií + - claim_type: favicon_url + claim_value: https://uesebs.ff.cuni.cz/wp-content/themes/ffuk/favicon.ico + source_url: https://uesebs.ff.cuni.cz/cs + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:07:21.666858+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-UKFFUHSD.yaml b/data/custodian/CZ-52-PRA-L-UKFFUHSD.yaml index 026c4ab84c..444462848e 100644 --- a/data/custodian/CZ-52-PRA-L-UKFFUHSD.yaml +++ b/data/custodian/CZ-52-PRA-L-UKFFUHSD.yaml @@ -190,3 +190,22 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Filozofická fakulta - Ústav hospodářských a sociálních dějin official youtube_search_timestamp: '2025-12-09T09:33:31.839648+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:28.512041+00:00' + source_url: https://uhsd.ff.cuni.cz/?q=node/18 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sites.ff.cuni.cz/uhsd/wp-content/uploads/sites/165/2015/10/cropped-logo_uk_cerne-180x180.png + source_url: https://uhsd.ff.cuni.cz/?q=node/18 + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T19:07:28.512041+00:00' + extraction_method: 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/CZ-52-PRA-L-UKLFAU.yaml b/data/custodian/CZ-52-PRA-L-UKLFAU.yaml index 21075e0ed9..41c83177de 100644 --- a/data/custodian/CZ-52-PRA-L-UKLFAU.yaml +++ b/data/custodian/CZ-52-PRA-L-UKLFAU.yaml @@ -235,3 +235,37 @@ location: youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - 1.lékařská fakulta - Anatomický ústav official youtube_search_timestamp: '2025-12-09T09:33:32.502189+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:33.469940+00:00' + source_url: https://www.lf1.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lf1.cuni.cz/content/img/logo-cz.svg + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > body > header > div.logocz > a.lf1.logocz + > img' + retrieved_on: '2025-12-25T19:07:33.469940+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 1. lékařská fakulta Univerzity Karlovy + - claim_type: favicon_url + claim_value: https://www.lf1.cuni.cz/content/img/apple-icon.png + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:07:33.469940+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lf1.cuni.cz + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T19:07:33.469940+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/CZ-52-PRA-L-UKLFFUK.yaml b/data/custodian/CZ-52-PRA-L-UKLFFUK.yaml index 24ba255483..971ad7154e 100644 --- a/data/custodian/CZ-52-PRA-L-UKLFFUK.yaml +++ b/data/custodian/CZ-52-PRA-L-UKLFFUK.yaml @@ -237,3 +237,37 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - 1.lékařská fakulta - Fyziologický ústav - knihovna official youtube_search_timestamp: '2025-12-09T09:33:33.168351+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:38.235227+00:00' + source_url: https://www.lf1.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lf1.cuni.cz/content/img/logo-cz.svg + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > body > header > div.logocz > a.lf1.logocz + > img' + retrieved_on: '2025-12-25T19:07:38.235227+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 1. lékařská fakulta Univerzity Karlovy + - claim_type: favicon_url + claim_value: https://www.lf1.cuni.cz/content/img/apple-icon.png + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:07:38.235227+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lf1.cuni.cz + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T19:07:38.235227+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/CZ-52-PRA-L-UKLFSVI.yaml b/data/custodian/CZ-52-PRA-L-UKLFSVI.yaml index 758ba157dc..eee85c8cd3 100644 --- a/data/custodian/CZ-52-PRA-L-UKLFSVI.yaml +++ b/data/custodian/CZ-52-PRA-L-UKLFSVI.yaml @@ -243,3 +243,37 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - 3. lékařská fakulta - Středisko vědeckých informací official youtube_search_timestamp: '2025-12-09T09:33:33.830858+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:43.341948+00:00' + source_url: https://www.lf3.cuni.cz/3LFSVI-1.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lf3.cuni.cz/3LFSVI-1-version1-afoto.jpg + source_url: https://www.lf3.cuni.cz/3LFSVI-1.html + css_selector: '[document] > html > body > div.container-fluid.headerHolder > div.container.headerSubHolder + > div.row > header > div.col-md-7 > div.logo > a > img.logoSize.mobileLogoSize' + retrieved_on: '2025-12-25T19:07:43.341948+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Homepage - Středisko vědeckých informací, 3. lékařská fakulta + - claim_type: favicon_url + claim_value: https://www.lf3.cuni.cz/3LFSVI-1-version1-favicon.ico + source_url: https://www.lf3.cuni.cz/3LFSVI-1.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:07:43.341948+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lf3.cuni.cz/newlayout/images/logosoc.png + source_url: https://www.lf3.cuni.cz/3LFSVI-1.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T19:07:43.341948+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-UKLFUVI.yaml b/data/custodian/CZ-52-PRA-L-UKLFUVI.yaml index 11464141a6..505ef3f27a 100644 --- a/data/custodian/CZ-52-PRA-L-UKLFUVI.yaml +++ b/data/custodian/CZ-52-PRA-L-UKLFUVI.yaml @@ -243,3 +243,36 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - 1. lékařská fakulta - Ústav vědeckých informací official youtube_search_timestamp: '2025-12-09T09:33:34.498034+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:49.030175+00:00' + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#logoImage' + retrieved_on: '2025-12-25T19:07:49.030175+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo knihovny + - claim_type: favicon_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/favicon.ico + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#viewCustomerFavIcon' + retrieved_on: '2025-12-25T19:07:49.030175+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#ogImage' + retrieved_on: '2025-12-25T19:07:49.030175+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-UKLFVFNICK.yaml b/data/custodian/CZ-52-PRA-L-UKLFVFNICK.yaml index 1b38d5b0f3..73d12f7366 100644 --- a/data/custodian/CZ-52-PRA-L-UKLFVFNICK.yaml +++ b/data/custodian/CZ-52-PRA-L-UKLFVFNICK.yaml @@ -238,3 +238,37 @@ youtube_search_query: Univerzita Karlova - 1. lékařská fakulta a Všeobecná nemocnice - II.chirurgická klinika kardiovaskulární chirurgie - Lékařská knihovna official youtube_search_timestamp: '2025-12-09T09:33:35.169815+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:53.784720+00:00' + source_url: https://www.lf1.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lf1.cuni.cz/content/img/logo-cz.svg + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > body > header > div.logocz > a.lf1.logocz + > img' + retrieved_on: '2025-12-25T19:07:53.784720+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 1. lékařská fakulta Univerzity Karlovy + - claim_type: favicon_url + claim_value: https://www.lf1.cuni.cz/content/img/apple-icon.png + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:07:53.784720+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lf1.cuni.cz + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T19:07:53.784720+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/CZ-52-PRA-L-UKLFVFNIIK-univerzita_karlova_1_lekarska_fakulta_a_vseobecna_.yaml b/data/custodian/CZ-52-PRA-L-UKLFVFNIIK-univerzita_karlova_1_lekarska_fakulta_a_vseobecna_.yaml index cbaeb03947..5351827b87 100644 --- a/data/custodian/CZ-52-PRA-L-UKLFVFNIIK-univerzita_karlova_1_lekarska_fakulta_a_vseobecna_.yaml +++ b/data/custodian/CZ-52-PRA-L-UKLFVFNIIK-univerzita_karlova_1_lekarska_fakulta_a_vseobecna_.yaml @@ -238,3 +238,31 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - 1. lékařská fakulta a Všeobecná fakultní nemocnice - IV. interní klinika - Klinika gastroenterologie a hepatologie official youtube_search_timestamp: '2025-12-09T09:33:35.834847+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:58.813637+00:00' + source_url: https://int4.lf1.cuni.cz/knihovna-6161 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://int4.lf1.cuni.cz/content/img/logo-cz.svg + source_url: https://int4.lf1.cuni.cz/knihovna-6161 + css_selector: '[document] > html.lang-cs.js > body.b0 > header > div.in.defaulthtml + > img.logo' + retrieved_on: '2025-12-25T19:07:58.813637+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 1. lékařská fakulta Univerzita Karlova + - claim_type: favicon_url + claim_value: https://int4.lf1.cuni.cz/favicon.ico + source_url: https://int4.lf1.cuni.cz/knihovna-6161 + css_selector: '[document] > html.lang-cs.js > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T19:07:58.813637+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-UKMFFKMOI.yaml b/data/custodian/CZ-52-PRA-L-UKMFFKMOI.yaml index 59a1cd017f..b2f9ef21a9 100644 --- a/data/custodian/CZ-52-PRA-L-UKMFFKMOI.yaml +++ b/data/custodian/CZ-52-PRA-L-UKMFFKMOI.yaml @@ -241,3 +241,22 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Matematicko-fyzikální fakulta - Knihovna MFF - odd. informatické official youtube_search_timestamp: '2025-12-09T09:33:36.498407+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:08:04.160159+00:00' + source_url: https://www.mff.cuni.cz/cs/knihovna/kontakty-a-oddeleni/informaticke-oddeleni + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.mff.cuni.cz/modules/MatFyzWeb/img/favicon.ico + source_url: https://www.mff.cuni.cz/cs/knihovna/kontakty-a-oddeleni/informaticke-oddeleni + css_selector: '[document] > html.show--consent > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T19:08:04.160159+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-UKPFBK.yaml b/data/custodian/CZ-52-PRA-L-UKPFBK.yaml index b94c9894f5..07ab3847a7 100644 --- a/data/custodian/CZ-52-PRA-L-UKPFBK.yaml +++ b/data/custodian/CZ-52-PRA-L-UKPFBK.yaml @@ -228,3 +228,30 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Přírodovědecká fakulta - Biologická knihovna official youtube_search_timestamp: '2025-12-09T09:33:37.174797+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:08:09.593036+00:00' + source_url: https://natur.cuni.cz/biologie/katedry-a-pracoviste/knihovna-biologie + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://natur.cuni.cz/modules/NaturWeb/templates/base/main/img/mobil/m_logo_PrFUK_var5.png?w=406 + source_url: https://natur.cuni.cz/biologie/katedry-a-pracoviste/knihovna-biologie + css_selector: '#header-logo-mobile > a > picture > source > img.nolazy.d-lg-none' + retrieved_on: '2025-12-25T19:08:09.593036+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Přírodovědecká fakulta - Univerzita Karlova + - claim_type: favicon_url + claim_value: https://natur.cuni.cz/modules/NaturWeb/templates/base/main/img/cuni_fav_180.png + source_url: https://natur.cuni.cz/biologie/katedry-a-pracoviste/knihovna-biologie + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T19:08:09.593036+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: 7 diff --git a/data/custodian/CZ-52-PRA-L-UKPFK-univerzita_karlova_pedagogicka_fakulta_knihovna.yaml b/data/custodian/CZ-52-PRA-L-UKPFK-univerzita_karlova_pedagogicka_fakulta_knihovna.yaml index fa672139a5..9cd4c188e3 100644 --- a/data/custodian/CZ-52-PRA-L-UKPFK-univerzita_karlova_pedagogicka_fakulta_knihovna.yaml +++ b/data/custodian/CZ-52-PRA-L-UKPFK-univerzita_karlova_pedagogicka_fakulta_knihovna.yaml @@ -240,3 +240,36 @@ location: youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Pedagogická fakulta - Knihovna official youtube_search_timestamp: '2025-12-09T09:33:37.836274+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:08:16.341482+00:00' + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#logoImage' + retrieved_on: '2025-12-25T19:08:16.341482+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Logo knihovny + - claim_type: favicon_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/favicon.ico + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#viewCustomerFavIcon' + retrieved_on: '2025-12-25T19:08:16.341482+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cuni.primo.exlibrisgroup.com/discovery/custom/420CKIS_INST-UKAZ/img/library-logo.png + source_url: https://cuni.primo.exlibrisgroup.com/discovery/search?vid=420CKIS_INST:UKAZ&lang=cs + css_selector: '#ogImage' + retrieved_on: '2025-12-25T19:08:16.341482+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/CZ-52-PRA-L-UKPFKC.yaml b/data/custodian/CZ-52-PRA-L-UKPFKC.yaml index 2b4d936d67..38f63102e0 100644 --- a/data/custodian/CZ-52-PRA-L-UKPFKC.yaml +++ b/data/custodian/CZ-52-PRA-L-UKPFKC.yaml @@ -252,3 +252,30 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Přírodovědecká fakulta - Knihovna chemie official youtube_search_timestamp: '2025-12-09T09:33:38.504036+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:23:19.450547+00:00' + source_url: https://natur.cuni.cz/chemie/katedry-a-pracoviste/knihovna-chemie + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://natur.cuni.cz/modules/NaturWeb/templates/base/main/img/mobil/m_logo_PrFUK_var5.png?w=406 + source_url: https://natur.cuni.cz/chemie/katedry-a-pracoviste/knihovna-chemie + css_selector: '#header-logo-mobile > a > picture > source > img.nolazy.d-lg-none' + retrieved_on: '2025-12-25T19:23:19.450547+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Přírodovědecká fakulta - Univerzita Karlova + - claim_type: favicon_url + claim_value: https://natur.cuni.cz/modules/NaturWeb/templates/base/main/img/cuni_fav_180.png + source_url: https://natur.cuni.cz/chemie/katedry-a-pracoviste/knihovna-chemie + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T19:23:19.450547+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: 7 diff --git a/data/custodian/CZ-52-PRA-L-UKPFKKFDPV.yaml b/data/custodian/CZ-52-PRA-L-UKPFKKFDPV.yaml index 9f6bb51a80..2b5d9f37e9 100644 --- a/data/custodian/CZ-52-PRA-L-UKPFKKFDPV.yaml +++ b/data/custodian/CZ-52-PRA-L-UKPFKKFDPV.yaml @@ -232,3 +232,30 @@ youtube_status: NOT_FOUND youtube_search_query: Univerzita Karlova - Přírodovědecká fakulta - Knihovna katedry filosofie a dějin přírodních věd official youtube_search_timestamp: '2025-12-09T09:33:39.173252+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:23:53.668319+00:00' + source_url: https://natur.cuni.cz/biologie/katedry-a-pracoviste/knihovna-biologie/knihovna-filosofie + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://natur.cuni.cz/modules/NaturWeb/templates/base/main/img/mobil/m_logo_PrFUK_var5.png?w=406 + source_url: https://natur.cuni.cz/biologie/katedry-a-pracoviste/knihovna-biologie/knihovna-filosofie + css_selector: '#header-logo-mobile > a > picture > source > img.nolazy.d-lg-none' + retrieved_on: '2025-12-25T19:23:53.668319+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: Přírodovědecká fakulta - Univerzita Karlova + - claim_type: favicon_url + claim_value: https://natur.cuni.cz/modules/NaturWeb/templates/base/main/img/cuni_fav_180.png + source_url: https://natur.cuni.cz/biologie/katedry-a-pracoviste/knihovna-biologie/knihovna-filosofie + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T19:23:53.668319+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: 7 diff --git a/data/custodian/CZ-52-PRA-L-UKUKLUVSU.yaml b/data/custodian/CZ-52-PRA-L-UKUKLUVSU.yaml index dd491cfab6..0b2dc6b436 100644 --- a/data/custodian/CZ-52-PRA-L-UKUKLUVSU.yaml +++ b/data/custodian/CZ-52-PRA-L-UKUKLUVSU.yaml @@ -199,3 +199,37 @@ wikidata_enrichment: enrichment_version: 2.1.0 instance_of: - Q1622062 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:23:27.871958+00:00' + source_url: https://www.lf1.cuni.cz + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.lf1.cuni.cz/content/img/logo-cz.svg + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > body > header > div.logocz > a.lf1.logocz + > img' + retrieved_on: '2025-12-25T19:23:27.871958+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 1. lékařská fakulta Univerzity Karlovy + - claim_type: favicon_url + claim_value: https://www.lf1.cuni.cz/content/img/apple-icon.png + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:23:27.871958+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lf1.cuni.cz + source_url: https://www.lf1.cuni.cz + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(13)' + retrieved_on: '2025-12-25T19:23:27.871958+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-MIN-L-SL.yaml b/data/custodian/JP-13-MIN-L-SL.yaml index da74487ec9..48d69cbd1b 100644 --- a/data/custodian/JP-13-MIN-L-SL.yaml +++ b/data/custodian/JP-13-MIN-L-SL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MIN-L-SL - valid_from: "2025-12-10T09:44:07Z" + valid_from: '2025-12-10T09:44:07Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MIN-L-SL valid_from: null - valid_to: "2025-12-10T09:44:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:07Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MIN-L-SL ghcid_numeric: 4238670493658317621 valid_from: '2025-12-06T23:38:43.996192+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SANKO LIBRARY @@ -151,3 +152,22 @@ location: geonames_id: 1852383 geonames_name: Minato feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:35:30.079623+00:00' + source_url: https://sanko-bunka-kenkyujo.or.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://sanko-bunka-kenkyujo.or.jp/asset/00032/common/logo.png + source_url: https://sanko-bunka-kenkyujo.or.jp + css_selector: '#site-title > a.image > img' + retrieved_on: '2025-12-25T18:35:30.079623+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 三康文化研究所/三康図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-MIN-L-TWSCL.yaml b/data/custodian/JP-13-MIN-L-TWSCL.yaml index e676b28e08..b336cece26 100644 --- a/data/custodian/JP-13-MIN-L-TWSCL.yaml +++ b/data/custodian/JP-13-MIN-L-TWSCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MIN-L-TWSCL - valid_from: "2025-12-10T09:44:07Z" + valid_from: '2025-12-10T09:44:07Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MIN-L-TWSCL valid_from: null - valid_to: "2025-12-10T09:44:07Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:07Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MIN-L-TWSCL ghcid_numeric: 481973486564589191 valid_from: '2025-12-06T23:38:57.054921+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: Toita Women's College Library @@ -204,3 +205,28 @@ location: geonames_id: 1852383 geonames_name: Minato feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:00.130647+00:00' + source_url: http://www.toita.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://toita.opac.jp/common/images/op4-favicon.ico + source_url: http://www.toita.ac.jp/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:36:00.130647+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://toita.opac.jp/common/images/ogp-image.jpg + source_url: http://www.toita.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T18:36:00.130647+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-MIN-M-AMT.yaml b/data/custodian/JP-13-MIN-M-AMT.yaml index 800ca68fe1..ad0e06ab16 100644 --- a/data/custodian/JP-13-MIN-M-AMT.yaml +++ b/data/custodian/JP-13-MIN-M-AMT.yaml @@ -1476,3 +1476,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/Kt49wfHGn4Q/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:10.107552+00:00' + source_url: https://www.admt.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.admt.jp/favicon.ico + source_url: https://www.admt.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:36:10.107552+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.admt.jp/images/common/og.jpg + source_url: https://www.admt.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T18:36:10.107552+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-MIN-M-MAM.yaml b/data/custodian/JP-13-MIN-M-MAM.yaml index 5bef4c2f28..d1743666b9 100644 --- a/data/custodian/JP-13-MIN-M-MAM.yaml +++ b/data/custodian/JP-13-MIN-M-MAM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MIN-M-MAM - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MIN-M-MAM valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MIN-M-MAM ghcid_numeric: 4331178836799637759 valid_from: '2025-12-06T23:38:33.020552+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MORI ART MUSEUM @@ -151,3 +152,20 @@ location: geonames_id: 1852383 geonames_name: Minato feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:29.718053+00:00' + source_url: https://www.mori.art.museum + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.mori.art.museum/common/img/share.png + source_url: https://www.mori.art.museum + css_selector: '[document] > html.device-lang-jp.device-js-on > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T18:36:29.718053+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-MIT-L-ML-mitakashiritsuseibu_library.yaml b/data/custodian/JP-13-MIT-L-ML-mitakashiritsuseibu_library.yaml index 41219839cf..3a36a6569f 100644 --- a/data/custodian/JP-13-MIT-L-ML-mitakashiritsuseibu_library.yaml +++ b/data/custodian/JP-13-MIT-L-ML-mitakashiritsuseibu_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MIT-L-ML-mitakashiritsuseibu_library - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MIT-L-ML-mitakashiritsuseibu_library valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MIT-L-ML-mitakashiritsuseibu_library ghcid_numeric: 15080760680754041715 valid_from: '2025-12-06T23:38:43.656672+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MITAKASHIRITSUSEIBU Library @@ -151,3 +152,20 @@ location: geonames_id: 11790343 geonames_name: Mitaka feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:38:18.372130+00:00' + source_url: https://www.library.mitaka.tokyo.jp/contents?15&pid=192 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.library.mitaka.tokyo.jp/images/ogimage.png + source_url: https://www.library.mitaka.tokyo.jp/contents?15&pid=192 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:38:18.372130+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-MUS-L-SUL.yaml b/data/custodian/JP-13-MUS-L-SUL.yaml index 9d5bade1b7..e167ff289c 100644 --- a/data/custodian/JP-13-MUS-L-SUL.yaml +++ b/data/custodian/JP-13-MUS-L-SUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MUS-L-SUL - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MUS-L-SUL valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MUS-L-SUL ghcid_numeric: 266123591396862168 valid_from: '2025-12-06T23:38:54.906943+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: Seikei University Library @@ -190,7 +191,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.seikei.ac.jp/university/library wikidata_official_website: http://www.seikei.ac.jp/university/library @@ -212,3 +214,22 @@ location: geonames_id: 1856367 geonames_name: Musashino feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:25:19.357762+00:00' + source_url: http://www.seikei.ac.jp/university/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.seikei.ac.jp/university/favicon.ico + source_url: http://www.seikei.ac.jp/university/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:25:19.357762+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-MUS-M-KAM.yaml b/data/custodian/JP-13-MUS-M-KAM.yaml index 8fa8b901bd..e85b0e07f7 100644 --- a/data/custodian/JP-13-MUS-M-KAM.yaml +++ b/data/custodian/JP-13-MUS-M-KAM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MUS-M-KAM - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MUS-M-KAM valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MUS-M-KAM ghcid_numeric: 989245429120867031 valid_from: '2025-12-06T23:38:33.582524+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: Kichijoji Art Museum @@ -190,7 +191,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) wikidata_instance_of: *id005 wikidata_location: country: &id006 @@ -229,3 +231,28 @@ location: geonames_id: 1856367 geonames_name: Musashino feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:25:45.610136+00:00' + source_url: http://www.musashino.or.jp/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.musashino.or.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: http://www.musashino.or.jp/museum + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T18:25:45.610136+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.musashino.or.jp/_template_/_site_/_default_/_res/images/sns/ogimage.png + source_url: http://www.musashino.or.jp/museum + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T18:25:45.610136+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-MUS-M-MCM.yaml b/data/custodian/JP-13-MUS-M-MCM.yaml index e0da1870c3..6fc7edc159 100644 --- a/data/custodian/JP-13-MUS-M-MCM.yaml +++ b/data/custodian/JP-13-MUS-M-MCM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MUS-M-MCM - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MUS-M-MCM valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MUS-M-MCM ghcid_numeric: 11527810931404177181 valid_from: '2025-12-06T23:38:33.716487+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: MUSASHIMURAYAMA CITY MUSEUM @@ -151,3 +152,28 @@ location: geonames_id: 6822130 geonames_name: Musashimurayama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:25:55.963624+00:00' + source_url: https://www.city.musashimurayama.lg.jp/kankou/spots/rekishiminzoku/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.musashimurayama.lg.jp/_template_/_site_/_default_/_res/images/apple-touch-icon-precomposed.png + source_url: https://www.city.musashimurayama.lg.jp/kankou/spots/rekishiminzoku/index.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T18:25:55.963624+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.musashimurayama.lg.jp/_template_/_site_/_default_/_res/images/sns/ogimage.gif + source_url: https://www.city.musashimurayama.lg.jp/kankou/spots/rekishiminzoku/index.html + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-25T18:25:55.963624+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-MYO-L-K.yaml b/data/custodian/JP-13-MYO-L-K.yaml index 1a6997ea11..28a9b24438 100644 --- a/data/custodian/JP-13-MYO-L-K.yaml +++ b/data/custodian/JP-13-MYO-L-K.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MYO-L-K - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MYO-L-K valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MYO-L-K ghcid_numeric: 18009030993275839416 valid_from: '2025-12-06T23:38:50.519819+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KAMIYAMACHOKYOIKUIINKAI @@ -153,3 +154,28 @@ location: geonames_id: 1860382 geonames_name: Kamiyama feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:26:20.604983+00:00' + source_url: http://www.town.kamiyama.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.kamiyama.lg.jp/img/tit_index_logo-w_pc.png + source_url: http://www.town.kamiyama.lg.jp + css_selector: '#homeHeader > div.spBar > div.inner > h1 > a > img.pc.white' + retrieved_on: '2025-12-25T18:26:20.604983+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 神山町 kamiyama-cho + - claim_type: og_image_url + claim_value: http://www.town.kamiyama.lg.jp/common/img/ogp_image.jpg + source_url: http://www.town.kamiyama.lg.jp + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-25T18:26:20.604983+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-MYO-L-SL.yaml b/data/custodian/JP-13-MYO-L-SL.yaml index 65a0b1d9e8..92011c8818 100644 --- a/data/custodian/JP-13-MYO-L-SL.yaml +++ b/data/custodian/JP-13-MYO-L-SL.yaml @@ -155,3 +155,22 @@ location: geonames_id: 13156714 geonames_name: Sanagōchi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:26:27.988076+00:00' + source_url: https://www.vill.sanagochi.lg.jp/mainpage-library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vill.sanagochi.lg.jp/_themes/vill/img/favicon/safari-pinned-tab.svg + source_url: https://www.vill.sanagochi.lg.jp/mainpage-library.html + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T18:26:27.988076+00:00' + extraction_method: 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-13-MYO-L-TAFFTSC.yaml b/data/custodian/JP-13-MYO-L-TAFFTSC.yaml index b84b78cf76..d47ea408ff 100644 --- a/data/custodian/JP-13-MYO-L-TAFFTSC.yaml +++ b/data/custodian/JP-13-MYO-L-TAFFTSC.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-MYO-L-TAFFTSC - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-MYO-L-TAFFTSC valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-MYO-L-TAFFTSC ghcid_numeric: 4018406270062629137 valid_from: '2025-12-06T23:38:59.411910+00:00' @@ -96,11 +97,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Tokushima Agriculture, Forestry and Fisheries Technology Support Center + claim_value: Tokushima Agriculture, Forestry and Fisheries Technology Support + Center property_uri: skos:prefLabel provenance: namespace: glam @@ -153,3 +155,28 @@ location: geonames_id: 1861400 geonames_name: Ishii feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:26:36.509864+00:00' + source_url: https://www.pref.tokushima.lg.jp/tafftsc + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.tokushima.lg.jp/favicon.ico + source_url: https://www.pref.tokushima.lg.jp/tafftsc + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:26:36.509864+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.tokushima.lg.jp/file/cooperation/banner_white.png + source_url: https://www.pref.tokushima.lg.jp/tafftsc + css_selector: '[document] > html > head > meta:nth-of-type(4)' + retrieved_on: '2025-12-25T18:26:36.509864+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-FL.yaml b/data/custodian/JP-13-NAK-L-FL.yaml index 22ec1cc0f8..e8f370d6e8 100644 --- a/data/custodian/JP-13-NAK-L-FL.yaml +++ b/data/custodian/JP-13-NAK-L-FL.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-FL - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-FL valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-FL ghcid_numeric: 8962324176693897620 valid_from: '2025-12-06T23:38:44.467140+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: FUNAHASHISONRITSU Library @@ -193,8 +194,9 @@ wikidata_enrichment: instance_of: &id004 - id: Q7075 label: library - description: institution charged with the care of a collection of literary, musical, artistic, or reference materials, - such as books, manuscripts, recordings, or films + description: institution charged with the care of a collection of literary, + musical, artistic, or reference materials, such as books, manuscripts, recordings, + or films wikidata_instance_of: *id004 wikidata_location: coordinates: &id007 @@ -232,3 +234,22 @@ location: postal_code: 930-0289 street_address: 602 TAKENOCHI, Nakaniikawa Gun Funahashi Mura, Toyama Ken, 930-0289 normalization_timestamp: '2025-12-09T12:22:00.432680+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:27:00.445222+00:00' + source_url: https://www.vill.funahashi.toyama.jp/facility_new/library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vill.funahashi.toyama.jp/favicon.ico + source_url: https://www.vill.funahashi.toyama.jp/facility_new/library.html + css_selector: '[document] > html.is-small > head > link' + retrieved_on: '2025-12-25T18:27:00.445222+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-K-koekizaidanhojintokyozeimukyokaizeimukohoshiryoshi.yaml b/data/custodian/JP-13-NAK-L-K-koekizaidanhojintokyozeimukyokaizeimukohoshiryoshi.yaml index 5fdc40fc9c..012eb790f5 100644 --- a/data/custodian/JP-13-NAK-L-K-koekizaidanhojintokyozeimukyokaizeimukohoshiryoshi.yaml +++ b/data/custodian/JP-13-NAK-L-K-koekizaidanhojintokyozeimukyokaizeimukohoshiryoshi.yaml @@ -152,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:27:15.129246+00:00' + source_url: http://www.zeikyo.or.jp/02_library/library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.zeikyo.or.jp/favicon.ico?1736236369 + source_url: http://www.zeikyo.or.jp/02_library/library.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:27:15.129246+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-KL.yaml b/data/custodian/JP-13-NAK-L-KL.yaml index ed2ee7121c..49382c0cd4 100644 --- a/data/custodian/JP-13-NAK-L-KL.yaml +++ b/data/custodian/JP-13-NAK-L-KL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-KL - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-KL valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-KL ghcid_numeric: 9186288080853554970 valid_from: '2025-12-06T23:38:55.465190+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: KODOMOKYOIKUHOSENDAIGAKU Library @@ -215,3 +216,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:27:36.440962+00:00' + source_url: http://hosen.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://hosen.ac.jp/contents/wp-content/uploads/fbrfg/safari-pinned-tab.svg + source_url: http://hosen.ac.jp + css_selector: '[document] > html.js > body > link:nth-of-type(23)' + retrieved_on: '2025-12-25T18:27:36.440962+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-13-NAK-L-MRISEH.yaml b/data/custodian/JP-13-NAK-L-MRISEH.yaml index 3d3f18bf80..12bdb1e70a 100644 --- a/data/custodian/JP-13-NAK-L-MRISEH.yaml +++ b/data/custodian/JP-13-NAK-L-MRISEH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-MRISEH - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-MRISEH valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-MRISEH ghcid_numeric: 14557945537117493162 valid_from: '2025-12-06T23:38:58.969551+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Mitsui Research Institute for Social and Economic History @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:27:47.246613+00:00' + source_url: http://www.mitsui-bunko.or.jp/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mitsui-bunko.or.jp/images/favicon.ico + source_url: http://www.mitsui-bunko.or.jp/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:27:47.246613+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCCL.yaml b/data/custodian/JP-13-NAK-L-NCCL.yaml index 622ecfe25b..bb9865ed0e 100644 --- a/data/custodian/JP-13-NAK-L-NCCL.yaml +++ b/data/custodian/JP-13-NAK-L-NCCL.yaml @@ -238,3 +238,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:28:02.237379+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:28:02.237379+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits.yaml b/data/custodian/JP-13-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits.yaml index de51eb9b2f..d38ec824b5 100644 --- a/data/custodian/JP-13-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits.yaml +++ b/data/custodian/JP-13-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-NCCLM-nakano_city_central_library_mihatoshogakkobunshits ghcid_numeric: 8073388028519509983 valid_from: '2025-12-06T23:38:52.941330+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakano City Central Library MIHATOSHOGAKKOBUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:28:10.142018+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp/facility/bunshitu.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp/facility/bunshitu.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:28:10.142018+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCCLM.yaml b/data/custodian/JP-13-NAK-L-NCCLM.yaml index eb75bd647c..fbd7e2b714 100644 --- a/data/custodian/JP-13-NAK-L-NCCLM.yaml +++ b/data/custodian/JP-13-NAK-L-NCCLM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-NCCLM - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-NCCLM valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-NCCLM ghcid_numeric: 13681742302412927808 valid_from: '2025-12-06T23:38:52.939026+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakano City Central Library MINAMINOSHOGAKKOBUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:28:21.360466+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp/facility/bunshitu.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp/facility/bunshitu.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:28:21.360466+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCCLN.yaml b/data/custodian/JP-13-NAK-L-NCCLN.yaml index 62f136df69..36790ad507 100644 --- a/data/custodian/JP-13-NAK-L-NCCLN.yaml +++ b/data/custodian/JP-13-NAK-L-NCCLN.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-NCCLN - valid_from: "2025-12-10T09:44:08Z" + valid_from: '2025-12-10T09:44:08Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-NCCLN valid_from: null - valid_to: "2025-12-10T09:44:08Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:08Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-NCCLN ghcid_numeric: 16160426697458445107 valid_from: '2025-12-06T23:38:52.936706+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakano City Central Library NAKANODAIICHISHOGAKKOBUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:28:30.488679+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp/facility/bunshitu.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp/facility/bunshitu.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:28:30.488679+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCEL.yaml b/data/custodian/JP-13-NAK-L-NCEL.yaml index 4d1e98374a..30e1fd86c2 100644 --- a/data/custodian/JP-13-NAK-L-NCEL.yaml +++ b/data/custodian/JP-13-NAK-L-NCEL.yaml @@ -152,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:28:39.454423+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:28:39.454423+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCKL.yaml b/data/custodian/JP-13-NAK-L-NCKL.yaml index aa43b6f53b..98ef72e345 100644 --- a/data/custodian/JP-13-NAK-L-NCKL.yaml +++ b/data/custodian/JP-13-NAK-L-NCKL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-NCKL - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-NCKL valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-NCKL ghcid_numeric: 5582536926061526568 valid_from: '2025-12-06T23:38:43.376643+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakano City Kamitakada Library @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:28:48.488738+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:28:48.488738+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCML.yaml b/data/custodian/JP-13-NAK-L-NCML.yaml index 3ddc3989a1..01edfcbd83 100644 --- a/data/custodian/JP-13-NAK-L-NCML.yaml +++ b/data/custodian/JP-13-NAK-L-NCML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-NCML - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-NCML valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-NCML ghcid_numeric: 13607573677569020775 valid_from: '2025-12-06T23:38:43.372210+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakano City Minamidai Library @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:28:57.785541+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:28:57.785541+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCNL-nakano_city_nakanohigashi_library.yaml b/data/custodian/JP-13-NAK-L-NCNL-nakano_city_nakanohigashi_library.yaml index 93f8aa0991..514f3f742b 100644 --- a/data/custodian/JP-13-NAK-L-NCNL-nakano_city_nakanohigashi_library.yaml +++ b/data/custodian/JP-13-NAK-L-NCNL-nakano_city_nakanohigashi_library.yaml @@ -152,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:29:06.827464+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp/facility/nakanohigashi.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp/facility/nakanohigashi.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:29:06.827464+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCNL.yaml b/data/custodian/JP-13-NAK-L-NCNL.yaml index 01ccc4d377..6011909b91 100644 --- a/data/custodian/JP-13-NAK-L-NCNL.yaml +++ b/data/custodian/JP-13-NAK-L-NCNL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-NCNL - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-NCNL valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-NCNL ghcid_numeric: 5168405970368320511 valid_from: '2025-12-06T23:38:43.370036+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakano City Nogata Library @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:29:15.902354+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:29:15.902354+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NCSL.yaml b/data/custodian/JP-13-NAK-L-NCSL.yaml index 19b1a7457d..48178a2a45 100644 --- a/data/custodian/JP-13-NAK-L-NCSL.yaml +++ b/data/custodian/JP-13-NAK-L-NCSL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-L-NCSL - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-L-NCSL valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-L-NCSL ghcid_numeric: 16074437530097357808 valid_from: '2025-12-06T23:38:43.367605+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakano City Saginomiya Library @@ -151,3 +152,22 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:29:24.619743+00:00' + source_url: https://library.city.tokyo-nakano.lg.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.tokyo-nakano.lg.jp/themes/lib_theme/favicon.ico + source_url: https://library.city.tokyo-nakano.lg.jp + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:29:24.619743+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-L-NL.yaml b/data/custodian/JP-13-NAK-L-NL.yaml index 16f9ea28a0..217ebb0f9a 100644 --- a/data/custodian/JP-13-NAK-L-NL.yaml +++ b/data/custodian/JP-13-NAK-L-NL.yaml @@ -154,3 +154,36 @@ location: geonames_id: 2111749 geonames_name: Naka feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:29:35.003059+00:00' + source_url: http://www.town.tokushima-naka.lg.jp/gyosei/docs/3625.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.town.tokushima-naka.lg.jp/theme/base/img_common/header_logo.png + source_url: http://www.town.tokushima-naka.lg.jp/gyosei/docs/3625.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-25T18:29:35.003059+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: なかちょう 那賀町 + - claim_type: favicon_url + claim_value: http://www.town.tokushima-naka.lg.jp/theme/base/img_common/smartphone.png + source_url: http://www.town.tokushima-naka.lg.jp/gyosei/docs/3625.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:29:35.003059+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.tokushima-naka.lg.jp/theme/base/img_common/ogp_image.png + source_url: http://www.town.tokushima-naka.lg.jp/gyosei/docs/3625.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:29:35.003059+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAK-L-TCSL.yaml b/data/custodian/JP-13-NAK-L-TCSL.yaml index 3a0f7ba0ae..b8981e3500 100644 --- a/data/custodian/JP-13-NAK-L-TCSL.yaml +++ b/data/custodian/JP-13-NAK-L-TCSL.yaml @@ -152,3 +152,28 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:30:13.945222+00:00' + source_url: https://www.tcl.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tcl.or.jp/wp/wp-content/uploads/2017/08/cropped-favicon-3-180x180.png + source_url: https://www.tcl.or.jp + css_selector: '[document] > html > head > link:nth-of-type(22)' + retrieved_on: '2025-12-25T18:30:13.945222+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tcl.or.jp/wp/wp-content/uploads/2017/08/tcl_ogp.jpg + source_url: https://www.tcl.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:30:13.945222+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-NAK-L-TPUNL.yaml b/data/custodian/JP-13-NAK-L-TPUNL.yaml index 1559dec917..db177201e6 100644 --- a/data/custodian/JP-13-NAK-L-TPUNL.yaml +++ b/data/custodian/JP-13-NAK-L-TPUNL.yaml @@ -205,3 +205,28 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:36.457199+00:00' + source_url: http://www.t-kougei.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.t-kougei.ac.jp/apple-touch-icon.png + source_url: http://www.t-kougei.ac.jp/library + css_selector: '[document] > html.ja > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:44:36.457199+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.t-kougei.ac.jp/assets_c/2017/07/img_top_tablet-thumb-728xauto-2224.jpg + source_url: http://www.t-kougei.ac.jp/library + css_selector: '[document] > html.ja > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:44:36.457199+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAK-L-YECTL.yaml b/data/custodian/JP-13-NAK-L-YECTL.yaml index 389de8131c..8e1a84a799 100644 --- a/data/custodian/JP-13-NAK-L-YECTL.yaml +++ b/data/custodian/JP-13-NAK-L-YECTL.yaml @@ -156,3 +156,22 @@ location: geonames_id: 8572857 feature_code: PPL normalization_timestamp: '2025-12-09T06:57:24.324511+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:35:40.144962+00:00' + source_url: http://www.yokogawa.co.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.yokogawa.co.jp/img/ipad3_retina_144x144.png + source_url: http://www.yokogawa.co.jp + css_selector: '#ng-app > head > link:nth-of-type(44)' + retrieved_on: '2025-12-25T18:35:40.144962+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 144x144 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-13-NAK-M-ASMA.yaml b/data/custodian/JP-13-NAK-M-ASMA.yaml index 1387c9d4e9..7be1d7daf2 100644 --- a/data/custodian/JP-13-NAK-M-ASMA.yaml +++ b/data/custodian/JP-13-NAK-M-ASMA.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-M-ASMA - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-M-ASMA valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-M-ASMA ghcid_numeric: 14118579940313792682 valid_from: '2025-12-06T23:38:39.310299+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: AIOI SHINRIN MUSEUM OF ART @@ -214,7 +215,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) wikidata_instance_of: *id005 wikidata_location: coordinates: &id008 @@ -268,3 +270,36 @@ location: postal_code: 771-5411 street_address: YOKOISHI, Naka Gun Naka Cho, Tokushima Ken, 771-5411 normalization_timestamp: '2025-12-09T12:22:02.157414+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:35:56.597544+00:00' + source_url: https://www.town.tokushima-naka.lg.jp/aioi-art + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.tokushima-naka.lg.jp/theme/base/img_common/header_logo.png + source_url: https://www.town.tokushima-naka.lg.jp/aioi-art + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-25T18:35:56.597544+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: なかちょう 那賀町 + - claim_type: favicon_url + claim_value: https://www.town.tokushima-naka.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.tokushima-naka.lg.jp/aioi-art + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:35:56.597544+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.tokushima-naka.lg.jp/theme/base/img_common/ogp_image.png + source_url: https://www.town.tokushima-naka.lg.jp/aioi-art + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:35:56.597544+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAK-M-KDNEM.yaml b/data/custodian/JP-13-NAK-M-KDNEM.yaml index eb03d83acf..dc9e60a9d9 100644 --- a/data/custodian/JP-13-NAK-M-KDNEM.yaml +++ b/data/custodian/JP-13-NAK-M-KDNEM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-M-KDNEM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-M-KDNEM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-M-KDNEM ghcid_numeric: 16401818981938300031 valid_from: '2025-12-06T23:38:39.308007+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KAWAGUCHI DAM NATURAL ENERGY MUSEUM @@ -153,3 +154,22 @@ location: geonames_id: 2111749 geonames_name: Naka feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:04.433048+00:00' + source_url: https://kre-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://kre-museum.jp/wp-content/themes/kawaguchi/commons/images/favicon/apple-touch-icon-180x180.png + source_url: https://kre-museum.jp + css_selector: '[document] > html.js > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:36:04.433048+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAK-M-NMFA.yaml b/data/custodian/JP-13-NAK-M-NMFA.yaml index f4393f488c..091634fa09 100644 --- a/data/custodian/JP-13-NAK-M-NMFA.yaml +++ b/data/custodian/JP-13-NAK-M-NMFA.yaml @@ -154,3 +154,22 @@ location: geonames_id: 1860563 geonames_name: Kamiichi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:17.114898+00:00' + source_url: https://www.nishida-museum.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nishida-museum.com/wp-content/themes/nishida/favicon.ico + source_url: https://www.nishida-museum.com + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:36:17.114898+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-M-NZP.yaml b/data/custodian/JP-13-NAK-M-NZP.yaml index 6dd8ccde54..0586986d85 100644 --- a/data/custodian/JP-13-NAK-M-NZP.yaml +++ b/data/custodian/JP-13-NAK-M-NZP.yaml @@ -152,3 +152,23 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:24.641319+00:00' + source_url: https://www.nicesacademia.jp/zero/planetarium + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.nicesacademia.jp/wp-content/themes/hall_template_v1.2/images/logo.jpg + source_url: https://www.nicesacademia.jp/zero/planetarium + css_selector: '#page > header.site-header > div.inner > h1.site-title > a.home-link + > img' + retrieved_on: '2025-12-25T18:36:24.641319+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: NICES ACADEMIA + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-NAK-M-TMA.yaml b/data/custodian/JP-13-NAK-M-TMA.yaml index 572d259f1c..0c4109be48 100644 --- a/data/custodian/JP-13-NAK-M-TMA.yaml +++ b/data/custodian/JP-13-NAK-M-TMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-M-TMA - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-M-TMA valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-M-TMA ghcid_numeric: 9519693780698691897 valid_from: '2025-12-06T23:38:33.441886+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TOREK MUSEUM OF ART @@ -151,3 +152,23 @@ location: geonames_id: 8715035 geonames_name: Nakano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:44.627745+00:00' + source_url: http://www.museum-art.torek.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.museum-art.torek.jp/favicon.ico + source_url: http://www.museum-art.torek.jp + css_selector: '[document] > html.wf-loading.wf-adobe-garamond-pro-n7-loading > + head > link' + retrieved_on: '2025-12-25T18:36:44.627745+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAK-M-TMT.yaml b/data/custodian/JP-13-NAK-M-TMT.yaml index 22ea0bacc6..fba7c0f517 100644 --- a/data/custodian/JP-13-NAK-M-TMT.yaml +++ b/data/custodian/JP-13-NAK-M-TMT.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-M-TMT - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-M-TMT valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-M-TMT ghcid_numeric: 14572986244127970131 valid_from: '2025-12-06T23:38:34.781875+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TATEYAMA MUSEUM OF TOYAMA @@ -219,8 +220,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance - id: Q4409567 label: prefectural museum description: type of Japanese museum @@ -277,3 +278,28 @@ location: postal_code: 930-1406 street_address: ASHIKURAJI, Nakaniikawa Gun Tateyama Machi, Toyama Ken, 930-1406 normalization_timestamp: '2025-12-09T12:22:02.559743+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:36:53.659628+00:00' + source_url: https://www.pref.toyama.jp/1739/miryokukankou/bunka/bunkazai/home/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.toyama.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.pref.toyama.jp/1739/miryokukankou/bunka/bunkazai/home/index.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T18:36:53.659628+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.pref.toyama.jp/shared/images/sns/ogp.png + source_url: https://www.pref.toyama.jp/1739/miryokukankou/bunka/bunkazai/home/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T18:36:53.659628+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAK-M-TTCAOTLM.yaml b/data/custodian/JP-13-NAK-M-TTCAOTLM.yaml index 623f9e1ef0..c6aadf4184 100644 --- a/data/custodian/JP-13-NAK-M-TTCAOTLM.yaml +++ b/data/custodian/JP-13-NAK-M-TTCAOTLM.yaml @@ -32,20 +32,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-M-TTCAOTLM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-M-TTCAOTLM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-M-TTCAOTLM ghcid_numeric: 9379859140251574779 valid_from: '2025-12-06T23:38:34.787122+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: TATEYAMA TOWN CENTER FOR ARCHAEOLOGICAL OPERATIONS, TATEYAMAMACHI LOCAL MUSEUM + claim_value: TATEYAMA TOWN CENTER FOR ARCHAEOLOGICAL OPERATIONS, TATEYAMAMACHI LOCAL + MUSEUM source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +98,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: TATEYAMA TOWN CENTER FOR ARCHAEOLOGICAL OPERATIONS, TATEYAMAMACHI LOCAL MUSEUM + claim_value: TATEYAMA TOWN CENTER FOR ARCHAEOLOGICAL OPERATIONS, TATEYAMAMACHI + LOCAL MUSEUM property_uri: skos:prefLabel provenance: namespace: glam @@ -153,3 +156,36 @@ location: geonames_id: 1850523 geonames_name: Tateyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:37:08.553735+00:00' + source_url: https://www.town.tateyama.toyama.jp/soshikikarasagasu/kyoikuka/bunkataiikugakari/2/3/5156.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.town.tateyama.toyama.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.town.tateyama.toyama.jp/soshikikarasagasu/kyoikuka/bunkataiikugakari/2/3/5156.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-25T18:37:08.553735+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 富山県立山町 + - claim_type: favicon_url + claim_value: https://www.town.tateyama.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.town.tateyama.toyama.jp/soshikikarasagasu/kyoikuka/bunkataiikugakari/2/3/5156.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:37:08.553735+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.tateyama.toyama.jp/material/images/group/10/shasinn1.JPG + source_url: https://www.town.tateyama.toyama.jp/soshikikarasagasu/kyoikuka/bunkataiikugakari/2/3/5156.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T18:37:08.553735+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAK-M-YHCM.yaml b/data/custodian/JP-13-NAK-M-YHCM.yaml index 0befea6306..41b830e500 100644 --- a/data/custodian/JP-13-NAK-M-YHCM.yaml +++ b/data/custodian/JP-13-NAK-M-YHCM.yaml @@ -41,13 +41,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAK-M-YHCM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAK-M-YHCM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAK-M-YHCM ghcid_numeric: 7564744672557069717 valid_from: '2025-12-06T23:38:34.776953+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: YUMINOSATO HISTORICAL AND CULTURAL MUSEUM @@ -182,8 +183,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance wikidata_instance_of: *id005 wikidata_location: country: &id006 @@ -224,3 +225,22 @@ location: geonames_id: 1860563 geonames_name: Kamiichi feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:37:16.357692+00:00' + source_url: https://www.town.kamiichi.toyama.jp/hp/spot/spot13.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.kamiichi.toyama.jp/apple-touch-icon.png + source_url: https://www.town.kamiichi.toyama.jp/hp/spot/spot13.htm + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:37:16.357692+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-NAM-M-NCM.yaml b/data/custodian/JP-13-NAM-M-NCM.yaml index b6edffeac4..537e9ce57f 100644 --- a/data/custodian/JP-13-NAM-M-NCM.yaml +++ b/data/custodian/JP-13-NAM-M-NCM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAM-M-NCM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAM-M-NCM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAM-M-NCM ghcid_numeric: 17916715908550797096 valid_from: '2025-12-06T23:38:34.703787+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NAMERIKAWA-CITY MUSEUM @@ -199,11 +200,12 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance wikidata_instance_of: *id005 wikidata_location: coordinates: &id008 @@ -245,3 +247,36 @@ location: postal_code: 936-0835 street_address: HIRAKI, Namerikawa Shi, Toyama Ken, 936-0835 normalization_timestamp: '2025-12-09T12:22:03.033068+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:38:00.936560+00:00' + source_url: http://www.city.namerikawa.toyama.jp/museum/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.namerikawa.toyama.jp/theme/base/img_common/pc_header_logo.png + source_url: http://www.city.namerikawa.toyama.jp/museum/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-25T18:38:00.936560+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 強く優しく輝く滑川 滑川市 Namerikawa City + - claim_type: favicon_url + claim_value: http://www.city.namerikawa.toyama.jp/smartphone.png + source_url: http://www.city.namerikawa.toyama.jp/museum/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:38:00.936560+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.namerikawa.toyama.jp/material/images/group/0/top_photo5.jpg + source_url: http://www.city.namerikawa.toyama.jp/museum/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T18:38:00.936560+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAN-L-NCCML.yaml b/data/custodian/JP-13-NAN-L-NCCML.yaml index a36e100b0d..b90e1e7ddf 100644 --- a/data/custodian/JP-13-NAN-L-NCCML.yaml +++ b/data/custodian/JP-13-NAN-L-NCCML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-L-NCCML - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-L-NCCML valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-L-NCCML ghcid_numeric: 10654578577288209786 valid_from: '2025-12-06T23:38:44.448400+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nanto City Central Municipal Library @@ -151,3 +152,31 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:38:11.960343+00:00' + source_url: https://library.city.nanto.toyama.jp/lib_chuo + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.nanto.toyama.jp/assets/img/common/logo-parts.svg + source_url: https://library.city.nanto.toyama.jp/lib_chuo + css_selector: '#header > div.ly_header_sp_inner > div.bl_headerUtils > div.bl_headerUtils_logo + > a > img' + retrieved_on: '2025-12-25T18:38:11.960343+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: ロゴ + - claim_type: favicon_url + claim_value: https://library.city.nanto.toyama.jp/apple-touch-icon.png + source_url: https://library.city.nanto.toyama.jp/lib_chuo + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:38:11.960343+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-13-NAN-L-NCFML.yaml b/data/custodian/JP-13-NAN-L-NCFML.yaml index 3d58af5c92..aa6e4b01d0 100644 --- a/data/custodian/JP-13-NAN-L-NCFML.yaml +++ b/data/custodian/JP-13-NAN-L-NCFML.yaml @@ -152,3 +152,31 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:38:20.703317+00:00' + source_url: https://library.city.nanto.toyama.jp/lib_fukuno + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.nanto.toyama.jp/assets/img/common/logo-parts.svg + source_url: https://library.city.nanto.toyama.jp/lib_fukuno + css_selector: '#header > div.ly_header_sp_inner > div.bl_headerUtils > div.bl_headerUtils_logo + > a > img' + retrieved_on: '2025-12-25T18:38:20.703317+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: ロゴ + - claim_type: favicon_url + claim_value: https://library.city.nanto.toyama.jp/apple-touch-icon.png + source_url: https://library.city.nanto.toyama.jp/lib_fukuno + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:38:20.703317+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-13-NAN-L-NCIL.yaml b/data/custodian/JP-13-NAN-L-NCIL.yaml index 361a509532..7d54158ce5 100644 --- a/data/custodian/JP-13-NAN-L-NCIL.yaml +++ b/data/custodian/JP-13-NAN-L-NCIL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-L-NCIL - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-L-NCIL valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-L-NCIL ghcid_numeric: 2284187037665263002 valid_from: '2025-12-06T23:38:44.450700+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nanto City Inami Library @@ -151,3 +152,31 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:38:29.580389+00:00' + source_url: https://library.city.nanto.toyama.jp/lib_inami + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.nanto.toyama.jp/assets/img/common/logo-parts.svg + source_url: https://library.city.nanto.toyama.jp/lib_inami + css_selector: '#header > div.ly_header_sp_inner > div.bl_headerUtils > div.bl_headerUtils_logo + > a > img' + retrieved_on: '2025-12-25T18:38:29.580389+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: ロゴ + - claim_type: favicon_url + claim_value: https://library.city.nanto.toyama.jp/apple-touch-icon.png + source_url: https://library.city.nanto.toyama.jp/lib_inami + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:38:29.580389+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-13-NAN-L-NCJML.yaml b/data/custodian/JP-13-NAN-L-NCJML.yaml index 78aca1eeb8..ec5894d4f9 100644 --- a/data/custodian/JP-13-NAN-L-NCJML.yaml +++ b/data/custodian/JP-13-NAN-L-NCJML.yaml @@ -152,3 +152,31 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:38:40.508455+00:00' + source_url: https://library.city.nanto.toyama.jp/lib_johana + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.nanto.toyama.jp/assets/img/common/logo-parts.svg + source_url: https://library.city.nanto.toyama.jp/lib_johana + css_selector: '#header > div.ly_header_sp_inner > div.bl_headerUtils > div.bl_headerUtils_logo + > a > img' + retrieved_on: '2025-12-25T18:38:40.508455+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: ロゴ + - claim_type: favicon_url + claim_value: https://library.city.nanto.toyama.jp/apple-touch-icon.png + source_url: https://library.city.nanto.toyama.jp/lib_johana + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:38:40.508455+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-13-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary.yaml b/data/custodian/JP-13-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary.yaml index feb353bea8..8e7df4bb62 100644 --- a/data/custodian/JP-13-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary.yaml +++ b/data/custodian/JP-13-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-L-NFKL-nantoshi_futomiyama_kouryusenta_libarary ghcid_numeric: 11420087403620419945 valid_from: '2025-12-06T23:38:49.620355+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NANTOSHI FUTOMIYAMA KOURYUSENTA LIBARARY @@ -151,3 +152,28 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:38:51.492196+00:00' + source_url: http://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=199 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.nanto.toyama.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=199 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:38:51.492196+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.nanto.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=199 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:38:51.492196+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAN-L-NL.yaml b/data/custodian/JP-13-NAN-L-NL.yaml index e718c7cb1d..fd79511694 100644 --- a/data/custodian/JP-13-NAN-L-NL.yaml +++ b/data/custodian/JP-13-NAN-L-NL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-L-NL - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-L-NL valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-L-NL ghcid_numeric: 4595500826413996390 valid_from: '2025-12-06T23:38:44.455373+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NANTOSHIRITSUTAIRA Library @@ -151,3 +152,31 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:39:07.552275+00:00' + source_url: https://library.city.nanto.toyama.jp/lib_taira + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://library.city.nanto.toyama.jp/assets/img/common/logo-parts.svg + source_url: https://library.city.nanto.toyama.jp/lib_taira + css_selector: '#header > div.ly_header_sp_inner > div.bl_headerUtils > div.bl_headerUtils_logo + > a > img' + retrieved_on: '2025-12-25T18:39:07.552275+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: ロゴ + - claim_type: favicon_url + claim_value: https://library.city.nanto.toyama.jp/apple-touch-icon.png + source_url: https://library.city.nanto.toyama.jp/lib_taira + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:39:07.552275+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-13-NAN-L-NYKL.yaml b/data/custodian/JP-13-NAN-L-NYKL.yaml index 28f7899ce7..26f94d6a45 100644 --- a/data/custodian/JP-13-NAN-L-NYKL.yaml +++ b/data/custodian/JP-13-NAN-L-NYKL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-L-NYKL - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-L-NYKL valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-L-NYKL ghcid_numeric: 11351521526636496837 valid_from: '2025-12-06T23:38:49.627796+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NANTOSHI YOSHIE KOURYUSENTA LIBARARY @@ -151,3 +152,28 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:39:24.336593+00:00' + source_url: http://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=203 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.nanto.toyama.jp/theme/base/img_common/smartphone.png + source_url: http://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=203 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:39:24.336593+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.nanto.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: http://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=203 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:39:24.336593+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAN-M-AFM.yaml b/data/custodian/JP-13-NAN-M-AFM.yaml index 23c313ed06..62c1cdd211 100644 --- a/data/custodian/JP-13-NAN-M-AFM.yaml +++ b/data/custodian/JP-13-NAN-M-AFM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-M-AFM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-M-AFM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-M-AFM ghcid_numeric: 11359492428853937647 valid_from: '2025-12-06T23:38:34.758265+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: AINOKURA FOLK MUSEUM @@ -151,3 +152,22 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:39:31.024509+00:00' + source_url: http://museums.toyamaken.jp/museum/swhm070 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://museums.toyamaken.jp/share/img/base/icon.pngg + source_url: http://museums.toyamaken.jp/museum/swhm070 + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:39:31.024509+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAN-M-FAM.yaml b/data/custodian/JP-13-NAN-M-FAM.yaml index c2804e75bf..75121286e5 100644 --- a/data/custodian/JP-13-NAN-M-FAM.yaml +++ b/data/custodian/JP-13-NAN-M-FAM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-M-FAM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-M-FAM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-M-FAM ghcid_numeric: 374462381391408265 valid_from: '2025-12-06T23:38:34.748756+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Fukumitsu Art Museum @@ -213,7 +214,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) - id: Q10624527 label: biographical museum description: museum dedicated to the life and works of a specific person @@ -272,3 +274,22 @@ location: postal_code: 939-1626 street_address: HORINJI, Nanto Shi, Toyama Ken, 939-1626 normalization_timestamp: '2025-12-09T12:22:03.717668+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:39:39.004347+00:00' + source_url: https://nanto-museum.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nanto-museum.com/wp2023/wp-content/uploads/2023/12/cropped-favicon-180x180.png + source_url: https://nanto-museum.com + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T18:39:39.004347+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAN-M-FCCH.yaml b/data/custodian/JP-13-NAN-M-FCCH.yaml index ee1f3fb18d..34a59efd5b 100644 --- a/data/custodian/JP-13-NAN-M-FCCH.yaml +++ b/data/custodian/JP-13-NAN-M-FCCH.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-M-FCCH - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-M-FCCH valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-M-FCCH ghcid_numeric: 7697474260120302184 valid_from: '2025-12-06T23:38:34.746149+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: FUKUNO CREATIVE CENTER, "HELIOS" @@ -192,8 +193,8 @@ wikidata_enrichment: description: facility where culture and arts are promoted (wide definition) - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance wikidata_instance_of: *id005 wikidata_location: coordinates: &id008 @@ -238,3 +239,22 @@ location: postal_code: 939-1576 street_address: YAKATA, Nanto Shi, Toyama Ken, 939-1576 normalization_timestamp: '2025-12-09T12:22:03.783834+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:39:49.166567+00:00' + source_url: http://nantohelios.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://nantohelios.jp/wp-nantohelios/wp-content/uploads/2022/03/cropped-icon-180x180.png + source_url: http://nantohelios.jp + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T18:39:49.166567+00:00' + extraction_method: 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-13-NAN-M-JHFFM.yaml b/data/custodian/JP-13-NAN-M-JHFFM.yaml index 15224cb489..e5e655b795 100644 --- a/data/custodian/JP-13-NAN-M-JHFFM.yaml +++ b/data/custodian/JP-13-NAN-M-JHFFM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-M-JHFFM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-M-JHFFM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-M-JHFFM ghcid_numeric: 11692262269124781287 valid_from: '2025-12-06T23:38:34.753499+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: JOHANA HIKIYAMA FESTIVAL FLOATS MUSEUM @@ -151,3 +152,28 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:40:06.045968+00:00' + source_url: https://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=222 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.nanto.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=222 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:40:06.045968+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.nanto.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=222 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:40:06.045968+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAN-M-NSE.yaml b/data/custodian/JP-13-NAN-M-NSE.yaml index f9f9ef5fa3..69fa48c8dc 100644 --- a/data/custodian/JP-13-NAN-M-NSE.yaml +++ b/data/custodian/JP-13-NAN-M-NSE.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAN-M-NSE - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAN-M-NSE valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAN-M-NSE ghcid_numeric: 18377531677156756674 valid_from: '2025-12-06T23:38:34.760509+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NANTO-SHI ENSHONOYAKATA @@ -151,3 +152,28 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:40:22.276025+00:00' + source_url: https://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=224 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.nanto.toyama.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=224 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:40:22.276025+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.nanto.toyama.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.nanto.toyama.jp/cms-sypher/www/section/detail.jsp?id=224 + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:40:22.276025+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NAN-M-NSGFMH.yaml b/data/custodian/JP-13-NAN-M-NSGFMH.yaml index 66b075d726..8a1e0a5ec9 100644 --- a/data/custodian/JP-13-NAN-M-NSGFMH.yaml +++ b/data/custodian/JP-13-NAN-M-NSGFMH.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822123 geonames_name: Nanto feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:40:29.726598+00:00' + source_url: https://gokayama-info.jp/archives/1664 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://gokayama-info.jp/wp_j/wp-content/uploads/2017/09/6eb46071b2f52480a4eee90eb83a55fc.png + source_url: https://gokayama-info.jp/archives/1664 + css_selector: '[document] > html > head > link:nth-of-type(16)' + retrieved_on: '2025-12-25T18:40:29.726598+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-NAR-L-NCL.yaml b/data/custodian/JP-13-NAR-L-NCL.yaml index 60b4e2b63c..4246fa9cf6 100644 --- a/data/custodian/JP-13-NAR-L-NCL.yaml +++ b/data/custodian/JP-13-NAR-L-NCL.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAR-L-NCL - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAR-L-NCL valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAR-L-NCL ghcid_numeric: 7880069213595390327 valid_from: '2025-12-06T23:38:47.337954+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Naruto City Library @@ -192,8 +193,9 @@ wikidata_enrichment: instance_of: &id004 - id: Q7075 label: library - description: institution charged with the care of a collection of literary, musical, artistic, or reference materials, - such as books, manuscripts, recordings, or films + description: institution charged with the care of a collection of literary, + musical, artistic, or reference materials, such as books, manuscripts, recordings, + or films wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -234,3 +236,22 @@ location: postal_code: 772-0011 street_address: 49 MUYACHO OKUWAJIMA EBISUYAMA, Naruto Shi, Tokushima Ken, 772-0011 normalization_timestamp: '2025-12-09T12:22:04.107792+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:40:39.171031+00:00' + source_url: http://www.city.naruto.tokushima.jp/manabu/kyoiku/toshokan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.naruto.tokushima.jp/images/apple-touch-icon-180x180.png + source_url: http://www.city.naruto.tokushima.jp/manabu/kyoiku/toshokan + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T18:40:39.171031+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: 11 diff --git a/data/custodian/JP-13-NAR-M-NCKTM.yaml b/data/custodian/JP-13-NAR-M-NCKTM.yaml index ab10a929dc..be6ab71498 100644 --- a/data/custodian/JP-13-NAR-M-NCKTM.yaml +++ b/data/custodian/JP-13-NAR-M-NCKTM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAR-M-NCKTM - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAR-M-NCKTM valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAR-M-NCKTM ghcid_numeric: 5664603076040412675 valid_from: '2025-12-06T23:38:39.280932+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NARUTO CITY KAGAWA TOYOHIKO MUSEUM @@ -244,7 +245,8 @@ wikidata_enrichment: wikidata_media: image: 140712 Naruto City Kagawa Toyohiko Museum Naruto Tokushima pref Japan01s3.jpg commons_category: Naruto City Kagawa Toyohiko Museum - wikidata_image: 140712 Naruto City Kagawa Toyohiko Museum Naruto Tokushima pref Japan01s3.jpg + wikidata_image: 140712 Naruto City Kagawa Toyohiko Museum Naruto Tokushima pref + Japan01s3.jpg location: latitude: 34.163278 longitude: 134.49875 @@ -261,3 +263,28 @@ location: postal_code: 779-0225 street_address: OASACHOHINOKI, Naruto Shi, Tokushima Ken, 779-0225 normalization_timestamp: '2025-12-09T12:22:04.214584+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:40:49.326753+00:00' + source_url: https://www.kagawakan.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: data:image/png;base64,iVBORw0KGgo= + source_url: https://www.kagawakan.com + css_selector: '[document] > html.j-feature-js.j-feature-no-touch > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:40:49.326753+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/dimension=1920x10000:format=jpg/path/s09e409475cb5c37e/image/i7fd66193bd1d3eb1/version/1486615514/image.jpg + source_url: https://www.kagawakan.com + css_selector: '[document] > html.j-feature-js.j-feature-no-touch > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-25T18:40:49.326753+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NAR-M-NGH.yaml b/data/custodian/JP-13-NAR-M-NGH.yaml index 397223d6e5..8988174a47 100644 --- a/data/custodian/JP-13-NAR-M-NGH.yaml +++ b/data/custodian/JP-13-NAR-M-NGH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAR-M-NGH - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAR-M-NGH valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAR-M-NGH ghcid_numeric: 16381732447581760317 valid_from: '2025-12-06T23:38:39.283702+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: THE NARUTO GERMAN HOUSE @@ -151,3 +152,28 @@ location: geonames_id: 2111677 geonames_name: Narutō feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:40:57.786125+00:00' + source_url: http://doitsukan.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://doitsukan.com/img/favicon.ico + source_url: http://doitsukan.com + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:40:57.786125+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://doitsukan.com/img/common/doitsukanogp.jpg + source_url: http://doitsukan.com + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T18:40:57.786125+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NAR-M-OMA.yaml b/data/custodian/JP-13-NAR-M-OMA.yaml index ba8e20d269..f22df61b5d 100644 --- a/data/custodian/JP-13-NAR-M-OMA.yaml +++ b/data/custodian/JP-13-NAR-M-OMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAR-M-OMA - valid_from: "2025-12-10T09:44:09Z" + valid_from: '2025-12-10T09:44:09Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAR-M-OMA valid_from: null - valid_to: "2025-12-10T09:44:09Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:09Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAR-M-OMA ghcid_numeric: 1251716095140508002 valid_from: '2025-12-06T23:38:39.276018+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: THE OTSUKA MUSEUM OF ART @@ -151,3 +152,28 @@ location: geonames_id: 2111677 geonames_name: Narutō feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:41:12.183361+00:00' + source_url: https://o-museum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://o-museum.or.jp/files/favicon/apple-touch-icon.png?cache=1766688062 + source_url: https://o-museum.or.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:41:12.183361+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://o-museum.or.jp/files/site_config/capture.jpg + source_url: https://o-museum.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-25T18:41:12.183361+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NCL.yaml b/data/custodian/JP-13-NAS-L-NCL.yaml index c3e7e47220..62761f3bd0 100644 --- a/data/custodian/JP-13-NAS-L-NCL.yaml +++ b/data/custodian/JP-13-NAS-L-NCL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NCL - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NCL valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NCL ghcid_numeric: 7626061758262311695 valid_from: '2025-12-06T23:38:42.231492+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nasukarasuyama City Library @@ -151,3 +152,24 @@ location: geonames_id: 6822176 geonames_name: Nasukarasuyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:41:36.066004+00:00' + source_url: https://lib-nasukarasuyama.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://lib-nasukarasuyama.jp/wp-content/uploads/2019/03/title_logo.png + source_url: https://lib-nasukarasuyama.jp + css_selector: '[document] > html > body.home.page-template-default > header.navbar.siteHeader + > div.container.siteHeadContainer:nth-of-type(2) > div.navbar-header > h1.navbar-brand.siteHeader_logo + > a > span > img' + retrieved_on: '2025-12-25T18:41:36.066004+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 那須烏山市立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library.yaml b/data/custodian/JP-13-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library.yaml index f3a9985db3..804abe8549 100644 --- a/data/custodian/JP-13-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library.yaml +++ b/data/custodian/JP-13-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NL-nasukarasuyamashiritsuminaminasu_library ghcid_numeric: 10496193890552698965 valid_from: '2025-12-06T23:38:42.233825+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUKARASUYAMASHIRITSUMINAMINASU Library @@ -151,3 +152,24 @@ location: geonames_id: 6822176 geonames_name: Nasukarasuyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:42:27.695594+00:00' + source_url: https://lib-nasukarasuyama.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://lib-nasukarasuyama.jp/wp-content/uploads/2019/03/title_logo.png + source_url: https://lib-nasukarasuyama.jp + css_selector: '[document] > html > body.home.page-template-default > header.navbar.siteHeader + > div.container.siteHeadContainer:nth-of-type(2) > div.navbar-header > h1.navbar-brand.siteHeader_logo + > a > span > img' + retrieved_on: '2025-12-25T18:42:27.695594+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 那須烏山市立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-NAS-L-NL-nasushiobarashinishinasuno_library.yaml b/data/custodian/JP-13-NAS-L-NL-nasushiobarashinishinasuno_library.yaml index edcd52d196..980bea444f 100644 --- a/data/custodian/JP-13-NAS-L-NL-nasushiobarashinishinasuno_library.yaml +++ b/data/custodian/JP-13-NAS-L-NL-nasushiobarashinishinasuno_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NL-nasushiobarashinishinasuno_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NL-nasushiobarashinishinasuno_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NL-nasushiobarashinishinasuno_library ghcid_numeric: 13580850341286424533 valid_from: '2025-12-06T23:38:42.222176+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHINISHINASUNO Library @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:42:35.485362+00:00' + source_url: https://www.nasushiobara-library.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: https://www.nasushiobara-library.jp + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T18:42:35.485362+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NL-nasushiobarashishiobara_library.yaml b/data/custodian/JP-13-NAS-L-NL-nasushiobarashishiobara_library.yaml index 760544e89f..8e1ebaa432 100644 --- a/data/custodian/JP-13-NAS-L-NL-nasushiobarashishiobara_library.yaml +++ b/data/custodian/JP-13-NAS-L-NL-nasushiobarashishiobara_library.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:42:42.095031+00:00' + source_url: https://www.nasushiobara-library.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: https://www.nasushiobara-library.jp + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T18:42:42.095031+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NL.yaml b/data/custodian/JP-13-NAS-L-NL.yaml index 32870c3d0c..1788e9299b 100644 --- a/data/custodian/JP-13-NAS-L-NL.yaml +++ b/data/custodian/JP-13-NAS-L-NL.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:42:48.671852+00:00' + source_url: https://www.nasushiobara-library.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: https://www.nasushiobara-library.jp + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T18:42:48.671852+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLA.yaml b/data/custodian/JP-13-NAS-L-NLA.yaml index e5a959f809..b893c82de1 100644 --- a/data/custodian/JP-13-NAS-L-NLA.yaml +++ b/data/custodian/JP-13-NAS-L-NLA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NLA - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NLA valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NLA ghcid_numeric: 18113028009998344715 valid_from: '2025-12-06T23:38:51.492287+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHIKUROISO Library ATSUSAKIBUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:42:55.801259+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:42:55.801259+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLH.yaml b/data/custodian/JP-13-NAS-L-NLH.yaml index 13f0df2702..6eee01af1b 100644 --- a/data/custodian/JP-13-NAS-L-NLH.yaml +++ b/data/custodian/JP-13-NAS-L-NLH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NLH - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NLH valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NLH ghcid_numeric: 5813626583183870962 valid_from: '2025-12-06T23:38:51.501838+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHIKUROISO Library HIGASHINASUNOBUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:02.919624+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:02.919624+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLI.yaml b/data/custodian/JP-13-NAS-L-NLI.yaml index a7341a6bba..a25aa523ec 100644 --- a/data/custodian/JP-13-NAS-L-NLI.yaml +++ b/data/custodian/JP-13-NAS-L-NLI.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NLI - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NLI valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NLI ghcid_numeric: 16878066834145292496 valid_from: '2025-12-06T23:38:51.494603+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHIKUROISO Library INAMURABUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:10.355425+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:10.355425+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLK.yaml b/data/custodian/JP-13-NAS-L-NLK.yaml index 4ad3f0b7b4..c680fc83ff 100644 --- a/data/custodian/JP-13-NAS-L-NLK.yaml +++ b/data/custodian/JP-13-NAS-L-NLK.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NLK - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NLK valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NLK ghcid_numeric: 10251492459064011938 valid_from: '2025-12-06T23:38:51.480440+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHINISHINASUNO Library KARINOBUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:17.392331+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:17.392331+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits.yaml b/data/custodian/JP-13-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits.yaml index 72862db762..7dc6ebfb74 100644 --- a/data/custodian/JP-13-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits.yaml +++ b/data/custodian/JP-13-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NLM-nasushiobarashinishinasuno_library_mishimabunshits ghcid_numeric: 7360709536912357792 valid_from: '2025-12-06T23:38:51.487532+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHINISHINASUNO Library MISHIMABUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:24.404639+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:24.404639+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLM-nasushiobarashishiobara_library_momijibunshitsu.yaml b/data/custodian/JP-13-NAS-L-NLM-nasushiobarashishiobara_library_momijibunshitsu.yaml index 7ad5d18ee0..6477f91fad 100644 --- a/data/custodian/JP-13-NAS-L-NLM-nasushiobarashishiobara_library_momijibunshitsu.yaml +++ b/data/custodian/JP-13-NAS-L-NLM-nasushiobarashishiobara_library_momijibunshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:32.050785+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:32.050785+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLM.yaml b/data/custodian/JP-13-NAS-L-NLM.yaml index b31e6643fb..ca0e0662ee 100644 --- a/data/custodian/JP-13-NAS-L-NLM.yaml +++ b/data/custodian/JP-13-NAS-L-NLM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NLM - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NLM valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NLM ghcid_numeric: 9341429250124164965 valid_from: '2025-12-06T23:38:51.482734+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHINISHINASUNO Library MINAMIBUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:39.104121+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:39.104121+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLN-nasushiobarashikuroiso_library_nabekakebunshitsu.yaml b/data/custodian/JP-13-NAS-L-NLN-nasushiobarashikuroiso_library_nabekakebunshitsu.yaml index ba35835a2e..31077b2a9d 100644 --- a/data/custodian/JP-13-NAS-L-NLN-nasushiobarashikuroiso_library_nabekakebunshitsu.yaml +++ b/data/custodian/JP-13-NAS-L-NLN-nasushiobarashikuroiso_library_nabekakebunshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:46.311542+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:46.311542+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLN.yaml b/data/custodian/JP-13-NAS-L-NLN.yaml index a43c9c00fe..1e15a1e718 100644 --- a/data/custodian/JP-13-NAS-L-NLN.yaml +++ b/data/custodian/JP-13-NAS-L-NLN.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:43:53.392373+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:43:53.392373+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLO.yaml b/data/custodian/JP-13-NAS-L-NLO.yaml index 8eb118e843..0ebb799ef2 100644 --- a/data/custodian/JP-13-NAS-L-NLO.yaml +++ b/data/custodian/JP-13-NAS-L-NLO.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:00.536824+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:44:00.536824+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_takabayashibunshits.yaml b/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_takabayashibunshits.yaml index 0d9bc106d2..c0ffcfa513 100644 --- a/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_takabayashibunshits.yaml +++ b/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_takabayashibunshits.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:07.680958+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:44:07.680958+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_toyorabunshitsu.yaml b/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_toyorabunshitsu.yaml index 9918ced844..13217f0523 100644 --- a/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_toyorabunshitsu.yaml +++ b/data/custodian/JP-13-NAS-L-NLT-nasushiobarashikuroiso_library_toyorabunshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:14.795473+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:44:14.795473+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NLT.yaml b/data/custodian/JP-13-NAS-L-NLT.yaml index 92a2a9be22..a5932b7806 100644 --- a/data/custodian/JP-13-NAS-L-NLT.yaml +++ b/data/custodian/JP-13-NAS-L-NLT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NLT - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NLT valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NLT ghcid_numeric: 9325028070835504808 valid_from: '2025-12-06T23:38:51.478087+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASUSHIOBARASHINISHINASUNO Library TAYUZUKABUNSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:21.847821+00:00' + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nasushiobara-library.jp/wp-content/uploads/2020/06/cropped-8b0c670e40123c8561e66712dfca9da0-scaled-2-180x180.jpg + source_url: http://www.nasushiobara-library.jp/%E5%9B%B3%E6%9B%B8%E9%A4%A8%E3%83%BB%E5%88%86%E5%AE%A4%E6%A1%88%E5%86%85 + css_selector: '[document] > html > head > link:nth-of-type(13)' + retrieved_on: '2025-12-25T18:44:21.847821+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-NAS-L-NTL.yaml b/data/custodian/JP-13-NAS-L-NTL.yaml index f78652b452..2b64f40019 100644 --- a/data/custodian/JP-13-NAS-L-NTL.yaml +++ b/data/custodian/JP-13-NAS-L-NTL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-L-NTL - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-L-NTL valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-L-NTL ghcid_numeric: 13315906795065713288 valid_from: '2025-12-06T23:38:42.261370+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nasu Town Library @@ -153,3 +154,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:29.966628+00:00' + source_url: https://www.library.nasu.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.library.nasu.tochigi.jp/images/header_logo.png + source_url: https://www.library.nasu.tochigi.jp + css_selector: '#index > header > div.block.clearfix > div.logo > a > img' + retrieved_on: '2025-12-25T18:44:29.966628+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 那須町立図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-NAS-M-NH.yaml b/data/custodian/JP-13-NAS-M-NH.yaml index e9d1485673..67bed5c579 100644 --- a/data/custodian/JP-13-NAS-M-NH.yaml +++ b/data/custodian/JP-13-NAS-M-NH.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-M-NH - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-M-NH valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-M-NH ghcid_numeric: 8798968538362765842 valid_from: '2025-12-06T23:38:31.900307+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NOGIJINJA HOUMOTSUKAN @@ -228,3 +229,20 @@ location: postal_code: 329-2711 street_address: ISHIBAYASHI, Nasushiobara Shi, Tochigi Ken, 329-2711 normalization_timestamp: '2025-12-09T12:22:05.350039+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:44:59.916093+00:00' + source_url: https://www.nasu-nogijinja.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://nasu-nogijinja.jp/ogp.png + source_url: https://www.nasu-nogijinja.jp + css_selector: '[document] > html.chrome.notouch > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T18:44:59.916093+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-NAS-M-NMBHMA.yaml b/data/custodian/JP-13-NAS-M-NMBHMA.yaml index 1fbaab0034..07a45da3d7 100644 --- a/data/custodian/JP-13-NAS-M-NMBHMA.yaml +++ b/data/custodian/JP-13-NAS-M-NMBHMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-M-NMBHMA - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-M-NMBHMA valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-M-NMBHMA ghcid_numeric: 15545011353778657034 valid_from: '2025-12-06T23:38:31.968745+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Nakagawa-machi Bato Hiroshige Museum of Art @@ -153,3 +154,22 @@ location: geonames_id: 1855988 geonames_name: Nakagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:13.375905+00:00' + source_url: http://www.hiroshige.bato.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.hiroshige.bato.tochigi.jp/wp-content/themes/batohiroshige/images/favicon.ico + source_url: http://www.hiroshige.bato.tochigi.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:45:13.375905+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NAS-M-NOM.yaml b/data/custodian/JP-13-NAS-M-NOM.yaml index 0a9e90ed3b..521e6b129b 100644 --- a/data/custodian/JP-13-NAS-M-NOM.yaml +++ b/data/custodian/JP-13-NAS-M-NOM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-M-NOM - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-M-NOM valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-M-NOM ghcid_numeric: 6656382832710217560 valid_from: '2025-12-06T23:38:31.951453+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASU ORGEL MUSEUM @@ -153,3 +154,22 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:27.149580+00:00' + source_url: http://nasuorgel.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://nasuorgel.jp/img/logo.png?1 + source_url: http://nasuorgel.jp + css_selector: '#header > div.logo > a > img' + retrieved_on: '2025-12-25T18:45:27.149580+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: ロゴ + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-NAS-M-NPWM.yaml b/data/custodian/JP-13-NAS-M-NPWM.yaml index 5e4355a695..964060604d 100644 --- a/data/custodian/JP-13-NAS-M-NPWM.yaml +++ b/data/custodian/JP-13-NAS-M-NPWM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-M-NPWM - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-M-NPWM valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-M-NPWM ghcid_numeric: 8369131755945965018 valid_from: '2025-12-06T23:38:31.946244+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NASU PARK OF WORLD MONKEY @@ -153,3 +154,20 @@ location: geonames_id: 6822174 geonames_name: Nasushiobara feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:39.754908+00:00' + source_url: https://www.nasumonkey.com + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://www.nasumonkey.com/common/images/ogp.png + source_url: https://www.nasumonkey.com + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T18:45:39.754908+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-NAS-M-SFM.yaml b/data/custodian/JP-13-NAS-M-SFM.yaml index 53d3b48234..ab9c1eff5c 100644 --- a/data/custodian/JP-13-NAS-M-SFM.yaml +++ b/data/custodian/JP-13-NAS-M-SFM.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NAS-M-SFM - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NAS-M-SFM valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NAS-M-SFM ghcid_numeric: 15217251111820156451 valid_from: '2025-12-06T23:38:31.948852+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Seiji Fujishiro Museum @@ -205,7 +206,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) - id: Q10624527 label: biographical museum description: museum dedicated to the life and works of a specific person @@ -265,3 +267,28 @@ location: postal_code: 325-0301 street_address: YUMOTO, Nasu Gun Nasu Machi, Tochigi Ken, 325-0301 normalization_timestamp: '2025-12-09T12:22:05.713752+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:45:58.211572+00:00' + source_url: http://fujishiro-seiji-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://fujishiro-seiji-museum.jp/files/favicon/favicon.ico?cache=1766688350 + source_url: http://fujishiro-seiji-museum.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:45:58.211572+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://fujishiro-seiji-museum.jp/files/site_config/capture.jpg + source_url: http://fujishiro-seiji-museum.jp + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-25T18:45:58.211572+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NER-L-LRLJILPT.yaml b/data/custodian/JP-13-NER-L-LRLJILPT.yaml index 86e3a793ed..8c7b8f4c96 100644 --- a/data/custodian/JP-13-NER-L-LRLJILPT.yaml +++ b/data/custodian/JP-13-NER-L-LRLJILPT.yaml @@ -32,20 +32,22 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-L-LRLJILPT - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-L-LRLJILPT valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-L-LRLJILPT ghcid_numeric: 11903320152260686074 valid_from: '2025-12-06T23:38:57.961320+00:00' reason: Initial GHCID from CH-Annotator (japan_complete_ch_annotator.yaml) custodian_name: claim_type: custodian_name - claim_value: Labour Research Library, The Japan Institute for Labour Policy and Training + claim_value: Labour Research Library, The Japan Institute for Labour Policy and + Training source_type: ch_annotator identifiers: - identifier_scheme: GHCID @@ -96,11 +98,12 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name - claim_value: Labour Research Library, The Japan Institute for Labour Policy and Training + claim_value: Labour Research Library, The Japan Institute for Labour Policy and + Training property_uri: skos:prefLabel provenance: namespace: glam @@ -151,3 +154,22 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:05.985837+00:00' + source_url: http://www.jil.go.jp/lib + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.jil.go.jp/favicon.ico + source_url: http://www.jil.go.jp/lib + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:46:05.985837+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/ico + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NER-L-MLE.yaml b/data/custodian/JP-13-NER-L-MLE.yaml index 3ea03502a0..f7629bcaeb 100644 --- a/data/custodian/JP-13-NER-L-MLE.yaml +++ b/data/custodian/JP-13-NER-L-MLE.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-L-MLE - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-L-MLE valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-L-MLE ghcid_numeric: 11087920933259221481 valid_from: '2025-12-06T23:38:55.283957+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: MUSASHINONGAKUDAIGAKU Library EKODAKYAMPASU @@ -204,3 +205,28 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:14.341969+00:00' + source_url: http://www.musashino-music.ac.jp/guide/facilities/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.musashino-music.ac.jp/application/files/3116/2797/2394/iPhone.png + source_url: http://www.musashino-music.ac.jp/guide/facilities/library + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T18:46:14.341969+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.musashino-music.ac.jp/application/files/6116/3175/7033/musashino_music.png + source_url: http://www.musashino-music.ac.jp/guide/facilities/library + css_selector: '[document] > html > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-25T18:46:14.341969+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NER-L-MUL.yaml b/data/custodian/JP-13-NER-L-MUL.yaml index 9a9f587beb..079422a332 100644 --- a/data/custodian/JP-13-NER-L-MUL.yaml +++ b/data/custodian/JP-13-NER-L-MUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-L-MUL - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-L-MUL valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-L-MUL ghcid_numeric: 13848102333018527256 valid_from: '2025-12-06T23:38:55.273441+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: Musashi University Library @@ -209,3 +210,28 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:46:22.982027+00:00' + source_url: http://www.musashi.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.musashi.ac.jp/library/common/img/touch-icon.png + source_url: http://www.musashi.ac.jp/library + css_selector: '[document] > html.no-js > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:46:22.982027+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.musashi.ac.jp/library/common/img/musashi_official.jpg + source_url: http://www.musashi.ac.jp/library + css_selector: '[document] > html.no-js > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T18:46:22.982027+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NER-L-NL-nerimakuritsukasugacho_library.yaml b/data/custodian/JP-13-NER-L-NL-nerimakuritsukasugacho_library.yaml index f3909f632d..fd3b53681d 100644 --- a/data/custodian/JP-13-NER-L-NL-nerimakuritsukasugacho_library.yaml +++ b/data/custodian/JP-13-NER-L-NL-nerimakuritsukasugacho_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-L-NL-nerimakuritsukasugacho_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-L-NL-nerimakuritsukasugacho_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-L-NL-nerimakuritsukasugacho_library ghcid_numeric: 1879011643027470355 valid_from: '2025-12-06T23:38:43.517942+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NERIMAKURITSUKASUGACHO Library @@ -151,3 +152,22 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:51.301657+00:00' + source_url: https://www.lib.nerima.tokyo.jp/viewer/genre.html?id=15 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.nerima.tokyo.jp/c1/img/favicon.ico + source_url: https://www.lib.nerima.tokyo.jp/viewer/genre.html?id=15 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:49:51.301657+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NER-L-NL-nerimakuritsuminamitanaka_library.yaml b/data/custodian/JP-13-NER-L-NL-nerimakuritsuminamitanaka_library.yaml index cacac8c047..81e79e9818 100644 --- a/data/custodian/JP-13-NER-L-NL-nerimakuritsuminamitanaka_library.yaml +++ b/data/custodian/JP-13-NER-L-NL-nerimakuritsuminamitanaka_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-L-NL-nerimakuritsuminamitanaka_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-L-NL-nerimakuritsuminamitanaka_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-L-NL-nerimakuritsuminamitanaka_library ghcid_numeric: 783532925953511218 valid_from: '2025-12-06T23:38:43.520191+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NERIMAKURITSUMINAMITANAKA Library @@ -151,3 +152,22 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:47:27.267698+00:00' + source_url: https://www.lib.nerima.tokyo.jp/viewer/genre.html?id=16 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.nerima.tokyo.jp/c1/img/favicon.ico + source_url: https://www.lib.nerima.tokyo.jp/viewer/genre.html?id=16 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:47:27.267698+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NER-L-NLE.yaml b/data/custodian/JP-13-NER-L-NLE.yaml index a64fcd5f19..c2b1a587f6 100644 --- a/data/custodian/JP-13-NER-L-NLE.yaml +++ b/data/custodian/JP-13-NER-L-NLE.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-L-NLE - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-L-NLE valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-L-NLE ghcid_numeric: 11474336160508355999 valid_from: '2025-12-06T23:38:54.683393+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: NIHONDAIGAKUGEIJUTSUGAKUBU Library (EKODAKOSHA) @@ -204,3 +205,28 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:20.315805+00:00' + source_url: http://www.art.nihon-u.ac.jp/library/use.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.art.nihon-u.ac.jp/img-com/favicon.ico + source_url: http://www.art.nihon-u.ac.jp/library/use.html + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T18:48:20.315805+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.art.nihon-u.ac.jp/upload/logo.png + source_url: http://www.art.nihon-u.ac.jp/library/use.html + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T18:48:20.315805+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NER-M-AMNUCA.yaml b/data/custodian/JP-13-NER-M-AMNUCA.yaml index ee056dcabd..3404a9907f 100644 --- a/data/custodian/JP-13-NER-M-AMNUCA.yaml +++ b/data/custodian/JP-13-NER-M-AMNUCA.yaml @@ -152,3 +152,22 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:45.600611+00:00' + source_url: https://www.art.nihon-u.ac.jp/facility/attached/archives + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.art.nihon-u.ac.jp/img-com/favicon.ico + source_url: https://www.art.nihon-u.ac.jp/facility/attached/archives + css_selector: '[document] > html > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T18:48:45.600611+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-NER-M-CAMT.yaml b/data/custodian/JP-13-NER-M-CAMT.yaml index de4a244aef..f143c5975b 100644 --- a/data/custodian/JP-13-NER-M-CAMT.yaml +++ b/data/custodian/JP-13-NER-M-CAMT.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-M-CAMT - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-M-CAMT valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-M-CAMT ghcid_numeric: 9889573449267568754 valid_from: '2025-12-06T23:38:33.515139+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: CHIHIRO ART MUSEUM TOKYO @@ -222,7 +223,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q11606865 label: picture book museum - description: type of museum; institution that collects and exhibits picture books + description: type of museum; institution that collects and exhibits picture + books - id: Q10624527 label: biographical museum description: museum dedicated to the life and works of a specific person @@ -295,3 +297,20 @@ location: postal_code: 177-0042 street_address: SHIMOSHAKUJII, Nerima Ku, Tokyo To, 177-0042 normalization_timestamp: '2025-12-09T12:22:06.481363+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:48:57.436321+00:00' + source_url: https://chihiro.jp/tokyo + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://chihiro.jp/wp-content/uploads/2017/05/index_mainvisual.jpg + source_url: https://chihiro.jp/tokyo + css_selector: '[document] > html.no-js.chrome > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T18:48:57.436321+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-NER-M-HMA.yaml b/data/custodian/JP-13-NER-M-HMA.yaml index 9b3b4aa3a2..22ce262759 100644 --- a/data/custodian/JP-13-NER-M-HMA.yaml +++ b/data/custodian/JP-13-NER-M-HMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-M-HMA - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-M-HMA valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-M-HMA ghcid_numeric: 9614294784813711511 valid_from: '2025-12-06T23:38:33.517681+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HIKARIGAOKA MUSEUM OF ART @@ -151,3 +152,28 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:04.258554+00:00' + source_url: https://hikari-m-art.org + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://hikari-m-art.org/wp/wp-content/uploads/2024/06/cropped-fb-180x180.png + source_url: https://hikari-m-art.org + css_selector: '[document] > html.showPage > head > link:nth-of-type(24)' + retrieved_on: '2025-12-25T18:49:04.258554+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://hikari-m-art.org/wp/wp-content/themes/hikari-m-art/img/common/logo.png + source_url: https://hikari-m-art.org + css_selector: '[document] > html.showPage > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:49:04.258554+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-NER-M-KM.yaml b/data/custodian/JP-13-NER-M-KM.yaml index 666a25fb1b..e345d5da69 100644 --- a/data/custodian/JP-13-NER-M-KM.yaml +++ b/data/custodian/JP-13-NER-M-KM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NER-M-KM - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NER-M-KM valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NER-M-KM ghcid_numeric: 7618389024492212454 valid_from: '2025-12-06T23:38:33.503318+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KARASAWA MUSEUM @@ -151,3 +152,20 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:10.491926+00:00' + source_url: https://karasawamuseum.com + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://karasawamuseum.com/bdflashinfo/thumbnail-large.png + source_url: https://karasawamuseum.com + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:49:10.491926+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-NER-M-MAMMMI.yaml b/data/custodian/JP-13-NER-M-MAMMMI.yaml index 0c96e25f01..7a878a9e00 100644 --- a/data/custodian/JP-13-NER-M-MAMMMI.yaml +++ b/data/custodian/JP-13-NER-M-MAMMMI.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790394 geonames_name: Nerima feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:49:18.974584+00:00' + source_url: https://www.musashino-music.ac.jp/guide/facilities/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.musashino-music.ac.jp/application/files/3116/2797/2394/iPhone.png + source_url: https://www.musashino-music.ac.jp/guide/facilities/museum + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T18:49:18.974584+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.musashino-music.ac.jp/application/files/6116/3175/7033/musashino_music.png + source_url: https://www.musashino-music.ac.jp/guide/facilities/museum + css_selector: '[document] > html > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-25T18:49:18.974584+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NII-M-NMM.yaml b/data/custodian/JP-13-NII-M-NMM.yaml index 57b4621eb5..267308eb64 100644 --- a/data/custodian/JP-13-NII-M-NMM.yaml +++ b/data/custodian/JP-13-NII-M-NMM.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NII-M-NMM - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NII-M-NMM valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NII-M-NMM ghcid_numeric: 7693907497864096779 valid_from: '2025-12-06T23:38:33.759461+00:00' @@ -152,3 +153,22 @@ geocoding: resolved_place: Honson resolved_city: Niijima Mura timestamp: '2025-12-09T23:13:34.415381+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:06.182796+00:00' + source_url: http://www.niijima.com/facility/community/hakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.niijima.com/images/base/webclip.png + source_url: http://www.niijima.com/facility/community/hakubutsukan + css_selector: '[document] > html > head > link:nth-of-type(11)' + retrieved_on: '2025-12-25T18:50:06.182796+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-NIK-M-NBGGSSUT.yaml b/data/custodian/JP-13-NIK-M-NBGGSSUT.yaml index 14698dfc4c..e59891c656 100644 --- a/data/custodian/JP-13-NIK-M-NBGGSSUT.yaml +++ b/data/custodian/JP-13-NIK-M-NBGGSSUT.yaml @@ -268,3 +268,37 @@ location: postal_code: 321-1435 street_address: HANAISHICHO, Nikko Shi, Tochigi Ken, 321-1435 normalization_timestamp: '2025-12-09T12:22:06.962005+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:46.842040+00:00' + source_url: https://www.bg.s.u-tokyo.ac.jp/nikko + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://nikko-bg.jp/wp/wp-content/themes/nikko.wp/asset/images/logo.svg?1 + source_url: https://www.bg.s.u-tokyo.ac.jp/nikko + css_selector: '#top > header.header > div.box:nth-of-type(2) > div.inner > h1 + > a > img' + retrieved_on: '2025-12-25T18:50:46.842040+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日光植物園 + - claim_type: favicon_url + claim_value: https://nikko-bg.jp/wp/wp-content/themes/nikko.wp/asset/images/favicon.ico + source_url: https://www.bg.s.u-tokyo.ac.jp/nikko + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:50:46.842040+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://nikko-bg.jp/wp/wp-content/themes/nikko.wp/asset/images/ogp.png + source_url: https://www.bg.s.u-tokyo.ac.jp/nikko + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T18:50:46.842040+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NIK-M-NCLMNSMM.yaml b/data/custodian/JP-13-NIK-M-NCLMNSMM.yaml index 18e98bbc10..1ef6da868a 100644 --- a/data/custodian/JP-13-NIK-M-NCLMNSMM.yaml +++ b/data/custodian/JP-13-NIK-M-NCLMNSMM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIK-M-NCLMNSMM - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIK-M-NCLMNSMM valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIK-M-NCLMNSMM ghcid_numeric: 10673384577440436330 valid_from: '2025-12-06T23:38:31.848406+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NIKKO CITY LOCAL MUSEUM & NINOMIYA SONTOKU MEMORIAL MUSEUM @@ -151,3 +152,36 @@ location: geonames_id: 1855395 geonames_name: Nikkō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:50:55.982808+00:00' + source_url: https://www.city.nikko.lg.jp/bunkazai/guide/kyouiku/shiryoukan/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.nikko.lg.jp/theme/base/img_common/pc_header_logo.png + source_url: https://www.city.nikko.lg.jp/bunkazai/guide/kyouiku/shiryoukan/index.html + css_selector: '#header-logo > a > img' + retrieved_on: '2025-12-25T18:50:55.982808+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 日光市 + - claim_type: favicon_url + claim_value: https://www.city.nikko.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.nikko.lg.jp/bunkazai/guide/kyouiku/shiryoukan/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:50:55.982808+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.nikko.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.nikko.lg.jp/bunkazai/guide/kyouiku/shiryoukan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:50:55.982808+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NIS-L-HL-hinoharasonritsu_library.yaml b/data/custodian/JP-13-NIS-L-HL-hinoharasonritsu_library.yaml index 5b6b3f9447..900443f918 100644 --- a/data/custodian/JP-13-NIS-L-HL-hinoharasonritsu_library.yaml +++ b/data/custodian/JP-13-NIS-L-HL-hinoharasonritsu_library.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIS-L-HL-hinoharasonritsu_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIS-L-HL-hinoharasonritsu_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIS-L-HL-hinoharasonritsu_library ghcid_numeric: 15432465430940101547 valid_from: '2025-12-06T23:38:43.977318+00:00' @@ -152,3 +153,28 @@ geocoding: resolved_place: Motoshuku resolved_city: 'Nishitama Gun ' timestamp: '2025-12-09T23:13:34.434082+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:15.374191+00:00' + source_url: https://www.vill.hinohara.tokyo.jp/0000000054.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.vill.hinohara.tokyo.jp/css/img/apple-touch-icon.png + source_url: https://www.vill.hinohara.tokyo.jp/0000000054.html + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T18:51:15.374191+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.vill.hinohara.tokyo.jp/design_img/og_image.png + source_url: https://www.vill.hinohara.tokyo.jp/0000000054.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T18:51:15.374191+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NIS-L-HL.yaml b/data/custodian/JP-13-NIS-L-HL.yaml index 9e15e7165a..e2a2a62ce6 100644 --- a/data/custodian/JP-13-NIS-L-HL.yaml +++ b/data/custodian/JP-13-NIS-L-HL.yaml @@ -154,3 +154,28 @@ location: geonames_id: 2130075 geonames_name: Hinode feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:23.965356+00:00' + source_url: https://www.town.hinode.tokyo.jp/soshiki/15-0-0-0-0_2.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.town.hinode.tokyo.jp/design_img/favicon.ico + source_url: https://www.town.hinode.tokyo.jp/soshiki/15-0-0-0-0_2.html + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:51:23.965356+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.hinode.tokyo.jp/design_img/og_image.png + source_url: https://www.town.hinode.tokyo.jp/soshiki/15-0-0-0-0_2.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T18:51:23.965356+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NIS-L-HLO.yaml b/data/custodian/JP-13-NIS-L-HLO.yaml index b5ebbff492..34543bf78e 100644 --- a/data/custodian/JP-13-NIS-L-HLO.yaml +++ b/data/custodian/JP-13-NIS-L-HLO.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIS-L-HLO - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIS-L-HLO valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIS-L-HLO ghcid_numeric: 4782848925984783810 valid_from: '2025-12-06T23:38:49.207569+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HINODECHORITSU Library OGUNOBUNSHITSU @@ -153,3 +154,28 @@ location: geonames_id: 2130075 geonames_name: Hinode feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:30.847178+00:00' + source_url: http://www.town.hinode.tokyo.jp/0000000190.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.hinode.tokyo.jp/design_img/apple-touch-icon.png + source_url: http://www.town.hinode.tokyo.jp/0000000190.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T18:51:30.847178+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: http://www.xxx.jp/img/xxx.png + source_url: http://www.town.hinode.tokyo.jp/0000000190.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T18:51:30.847178+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NIS-L-M.yaml b/data/custodian/JP-13-NIS-L-M.yaml index afa5f5c618..934bdfef73 100644 --- a/data/custodian/JP-13-NIS-L-M.yaml +++ b/data/custodian/JP-13-NIS-L-M.yaml @@ -154,3 +154,28 @@ location: geonames_id: 11612473 geonames_name: Mizuho feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:46.021615+00:00' + source_url: http://www.town.mizuho.tokyo.jp/tyosei/022/004/p002868.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.mizuho.tokyo.jp/share/imgs/apple-touch-icon.png + source_url: http://www.town.mizuho.tokyo.jp/tyosei/022/004/p002868.html + css_selector: '[document] > html.canvas.svg > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:51:46.021615+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.town.mizuho.tokyo.jp/share/imgs/image-cover.jpg + source_url: http://www.town.mizuho.tokyo.jp/tyosei/022/004/p002868.html + css_selector: '[document] > html.canvas.svg > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:51:46.021615+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-NIS-L-ML.yaml b/data/custodian/JP-13-NIS-L-ML.yaml index 488bb87c16..4f1b8f2b65 100644 --- a/data/custodian/JP-13-NIS-L-ML.yaml +++ b/data/custodian/JP-13-NIS-L-ML.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIS-L-ML - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIS-L-ML valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIS-L-ML ghcid_numeric: 6772801101558017390 valid_from: '2025-12-06T23:38:55.289072+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: MUSASHINODAIGAKU Library @@ -204,3 +205,28 @@ location: geonames_id: 11611931 geonames_name: Nishitōkyō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:51:54.688389+00:00' + source_url: http://www.musashino-u.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.musashino-u.ac.jp/apple-touch-icon-180x180.png + source_url: http://www.musashino-u.ac.jp/library + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:51:54.688389+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://lib.musashino-u.ac.jp/ogp.jpg + source_url: http://www.musashino-u.ac.jp/library + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-25T18:51:54.688389+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-NIS-L-MUNRA.yaml b/data/custodian/JP-13-NIS-L-MUNRA.yaml index 6e0a14b1da..cd0a0cd2df 100644 --- a/data/custodian/JP-13-NIS-L-MUNRA.yaml +++ b/data/custodian/JP-13-NIS-L-MUNRA.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIS-L-MUNRA - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIS-L-MUNRA valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIS-L-MUNRA ghcid_numeric: 2043326558958871392 valid_from: '2025-12-06T23:38:58.971801+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: Musashino University The Noh Research Archives @@ -204,3 +205,28 @@ location: geonames_id: 11611931 geonames_name: Nishitōkyō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:52:10.066059+00:00' + source_url: http://www.musashino-u.ac.jp/facilities/noh_research_archives.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.musashino-u.ac.jp/assets/img/common/apple-touch-icon_180x180.png + source_url: http://www.musashino-u.ac.jp/facilities/noh_research_archives.html + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:52:10.066059+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/png + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.musashino-u.ac.jp/ogp.jpg + source_url: http://www.musashino-u.ac.jp/facilities/noh_research_archives.html + css_selector: '[document] > html > head > meta:nth-of-type(15)' + retrieved_on: '2025-12-25T18:52:10.066059+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-NIS-L-WUA.yaml b/data/custodian/JP-13-NIS-L-WUA.yaml index dab60e91eb..d110176757 100644 --- a/data/custodian/JP-13-NIS-L-WUA.yaml +++ b/data/custodian/JP-13-NIS-L-WUA.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIS-L-WUA - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIS-L-WUA valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIS-L-WUA ghcid_numeric: 12858603784532353527 valid_from: '2025-12-06T23:38:55.360720+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: Waseda Unevercity Archives @@ -204,3 +205,28 @@ location: geonames_id: 11611931 geonames_name: Nishitōkyō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:46.321191+00:00' + source_url: http://www.waseda.jp/culture/archives + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.waseda.jp/culture/archives/assets/themes/waseda-template-engine-alt/img/icons/favicon_32.png + source_url: http://www.waseda.jp/culture/archives + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T18:53:46.321191+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.waseda.jp/culture/archives/assets/themes/waseda-template-engine-alt/img/og_image.png + source_url: http://www.waseda.jp/culture/archives + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T18:53:46.321191+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-NIS-M-FMUT.yaml b/data/custodian/JP-13-NIS-M-FMUT.yaml index ffcf635ea5..e9a8c0156a 100644 --- a/data/custodian/JP-13-NIS-M-FMUT.yaml +++ b/data/custodian/JP-13-NIS-M-FMUT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIS-M-FMUT - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIS-M-FMUT valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIS-M-FMUT ghcid_numeric: 16978234978889990787 valid_from: '2025-12-06T23:38:33.738423+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: FARM MUSEUM, THE UNIVERSITY OF TOKYO @@ -151,3 +152,22 @@ location: geonames_id: 11611931 geonames_name: Nishitōkyō feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:53:54.666892+00:00' + source_url: https://www.isas.a.u-tokyo.ac.jp/museum/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.isas.a.u-tokyo.ac.jp/museum/apple-touch-icon.png + source_url: https://www.isas.a.u-tokyo.ac.jp/museum/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:53:54.666892+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-NIS-M-KKMMLHM.yaml b/data/custodian/JP-13-NIS-M-KKMMLHM.yaml index bb735cf86f..861ac99cc7 100644 --- a/data/custodian/JP-13-NIS-M-KKMMLHM.yaml +++ b/data/custodian/JP-13-NIS-M-KKMMLHM.yaml @@ -489,3 +489,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/Vys5Ldqlplw/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:12.958517+00:00' + source_url: https://www.mizuhokyodo.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://mizuhokyodo.jp/wp-content/themes/koshinkan/img/webclip.png + source_url: https://www.mizuhokyodo.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:54:12.958517+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-NIS-M-OVC.yaml b/data/custodian/JP-13-NIS-M-OVC.yaml index 96017d9fa4..7973bc50fd 100644 --- a/data/custodian/JP-13-NIS-M-OVC.yaml +++ b/data/custodian/JP-13-NIS-M-OVC.yaml @@ -34,13 +34,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-NIS-M-OVC - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-NIS-M-OVC valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-NIS-M-OVC ghcid_numeric: 11809162318036887743 valid_from: '2025-12-06T23:38:33.746558+00:00' @@ -152,3 +153,37 @@ geocoding: resolved_place: Hikawa resolved_city: 'Nishitama Gun ' timestamp: '2025-12-09T23:13:34.498695+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:28.930181+00:00' + source_url: https://www.ces-net.jp/okutamavc + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.ces-net.jp/okutamavc/wp-content/themes/okutamavc/assets/images/logo.svg + source_url: https://www.ces-net.jp/okutamavc + css_selector: '#js-header > div.l-header_inner:nth-of-type(2) > h1.l-header_logo + > a > img.l-header_logo_image' + retrieved_on: '2025-12-25T18:54:28.930181+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 奥多摩ビジターセンター + - claim_type: favicon_url + claim_value: https://www.ces-net.jp/okutamavc/favicon.ico + source_url: https://www.ces-net.jp/okutamavc + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T18:54:28.930181+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.ces-net.jp//asset/img/common/opg.png + source_url: https://www.ces-net.jp/okutamavc + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:54:28.930181+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-NIS-M-TSC.yaml b/data/custodian/JP-13-NIS-M-TSC.yaml index 06e81eab26..f15741c94f 100644 --- a/data/custodian/JP-13-NIS-M-TSC.yaml +++ b/data/custodian/JP-13-NIS-M-TSC.yaml @@ -1219,3 +1219,22 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/ROTRqcif_f0/hqdefault_live.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:35.506265+00:00' + source_url: https://www.tamarokuto.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tamarokuto.or.jp/img/rokuto.ico + source_url: https://www.tamarokuto.or.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T18:54:35.506265+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OGA-M-OMC.yaml b/data/custodian/JP-13-OGA-M-OMC.yaml index b1d006da48..2a6a3c4da5 100644 --- a/data/custodian/JP-13-OGA-M-OMC.yaml +++ b/data/custodian/JP-13-OGA-M-OMC.yaml @@ -152,3 +152,23 @@ location: geonames_id: 11611621 geonames_name: Ogasawara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:46.524439+00:00' + source_url: https://bonin-ocean.net + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://bonin-ocean.net/wp-content/uploads/fbrfg/favicon.svg + source_url: https://bonin-ocean.net + css_selector: '[document] > html.avada-html-layout-wide.avada-html-header-position-top + > head > link:nth-of-type(28)' + retrieved_on: '2025-12-25T18:54:46.524439+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 7 diff --git a/data/custodian/JP-13-OGI-L-LMSKU-library_for_maritime_sciences_kobe_university.yaml b/data/custodian/JP-13-OGI-L-LMSKU-library_for_maritime_sciences_kobe_university.yaml index f06d2011f2..2af65a9c3e 100644 --- a/data/custodian/JP-13-OGI-L-LMSKU-library_for_maritime_sciences_kobe_university.yaml +++ b/data/custodian/JP-13-OGI-L-LMSKU-library_for_maritime_sciences_kobe_university.yaml @@ -229,3 +229,28 @@ location: geonames_id: 9290114 feature_code: PPL normalization_timestamp: '2025-12-09T06:53:34.501251+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:54:59.346439+00:00' + source_url: http://lib.kobe-u.ac.jp/www/modules/kaiji + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://lib.kobe-u.ac.jp/media/common/apple-touch-icon.png + source_url: http://lib.kobe-u.ac.jp/www/modules/kaiji + css_selector: '[document] > html > head > link:nth-of-type(4)' + retrieved_on: '2025-12-25T18:54:59.346439+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://lib.kobe-u.ac.jp/media/sites/2/img-uriko02j.jpg + source_url: http://lib.kobe-u.ac.jp/www/modules/kaiji + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:54:59.346439+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OME-L-OL-omeshibaigo_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshibaigo_library.yaml index f354416370..3b7ce19aeb 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshibaigo_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshibaigo_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshibaigo_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshibaigo_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshibaigo_library ghcid_numeric: 5781070394108754241 valid_from: '2025-12-06T23:38:43.670332+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHIBAIGO Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:19.570177+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/baigou.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/baigou.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:55:19.570177+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshidaimon_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshidaimon_library.yaml index 483cec3245..2eb89de04b 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshidaimon_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshidaimon_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshidaimon_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshidaimon_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshidaimon_library ghcid_numeric: 10477511909132657147 valid_from: '2025-12-06T23:38:43.663557+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHIDAIMON Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:29.479694+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/daimon.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/daimon.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:55:29.479694+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshiimai_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshiimai_library.yaml index d9efd38f81..062d1608eb 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshiimai_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshiimai_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshiimai_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshiimai_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshiimai_library ghcid_numeric: 5371654403838145075 valid_from: '2025-12-06T23:38:43.679651+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHIIMAI Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:38.337597+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/imai.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/imai.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:55:38.337597+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshinagabuchi_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshinagabuchi_library.yaml index 0d972a70c9..31c901e4de 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshinagabuchi_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshinagabuchi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshinagabuchi_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshinagabuchi_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshinagabuchi_library ghcid_numeric: 16420937014065392319 valid_from: '2025-12-06T23:38:43.668071+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHINAGABUCHI Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:47.516209+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/nagabuchi.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/nagabuchi.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:55:47.516209+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshinariki_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshinariki_library.yaml index 609f7bb0c2..7415a4691f 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshinariki_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshinariki_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshinariki_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshinariki_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshinariki_library ghcid_numeric: 6376029043041158828 valid_from: '2025-12-06T23:38:43.675072+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHINARIKI Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:55:56.546196+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/nariki.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/nariki.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:55:56.546196+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshiome_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshiome_library.yaml index 60c1e90082..be8602d787 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshiome_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshiome_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshiome_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshiome_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshiome_library ghcid_numeric: 16403033753743993385 valid_from: '2025-12-06T23:38:43.681885+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHIOME Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:06.076880+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/ome.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/ome.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:56:06.076880+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshiosoki_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshiosoki_library.yaml index 834a598048..f947bde094 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshiosoki_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshiosoki_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshiosoki_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshiosoki_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshiosoki_library ghcid_numeric: 4877902044463344428 valid_from: '2025-12-06T23:38:43.672564+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHIOSOKI Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:15.392277+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/osoki.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/osoki.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:56:15.392277+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshisawai_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshisawai_library.yaml index ea085a0fc4..8caaf97125 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshisawai_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshisawai_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshisawai_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshisawai_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshisawai_library ghcid_numeric: 11718314575825860345 valid_from: '2025-12-06T23:38:43.665813+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHISAWAI Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:23.851930+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/sawai.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/sawai.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:56:23.851930+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL-omeshishimmachi_library.yaml b/data/custodian/JP-13-OME-L-OL-omeshishimmachi_library.yaml index 3b6f850f6e..7ce41d2c66 100644 --- a/data/custodian/JP-13-OME-L-OL-omeshishimmachi_library.yaml +++ b/data/custodian/JP-13-OME-L-OL-omeshishimmachi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL-omeshishimmachi_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL-omeshishimmachi_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL-omeshishimmachi_library ghcid_numeric: 9982337478912732490 valid_from: '2025-12-06T23:38:43.677403+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHISHIMMACHI Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:32.782981+00:00' + source_url: https://www.library.ome.tokyo.jp/facility/shinmachi.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/facility/shinmachi.html + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:56:32.782981+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-L-OL.yaml b/data/custodian/JP-13-OME-L-OL.yaml index 9be925f008..fc19fb14f0 100644 --- a/data/custodian/JP-13-OME-L-OL.yaml +++ b/data/custodian/JP-13-OME-L-OL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-L-OL - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-L-OL valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-L-OL ghcid_numeric: 7874717944193048575 valid_from: '2025-12-06T23:38:43.661310+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OMESHICHUO Library @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:56:41.896983+00:00' + source_url: https://www.library.ome.tokyo.jp/index.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.library.ome.tokyo.jp/themes/lib_theme/favicon.ico + source_url: https://www.library.ome.tokyo.jp/index.php + css_selector: '[document] > html > head.notranslate > link' + retrieved_on: '2025-12-25T18:56:41.896983+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OME-M-OMMAKZMG.yaml b/data/custodian/JP-13-OME-M-OMMAKZMG.yaml index 10bbe91abd..62d357560a 100644 --- a/data/custodian/JP-13-OME-M-OMMAKZMG.yaml +++ b/data/custodian/JP-13-OME-M-OMMAKZMG.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-M-OMMAKZMG - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-M-OMMAKZMG valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-M-OMMAKZMG ghcid_numeric: 10707929147069628611 valid_from: '2025-12-06T23:38:33.610744+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OME MUNICIPAL MUSEUM OF ART, KOJIMA ZENTARO MEMORIAL GALLERY @@ -151,3 +152,22 @@ location: geonames_id: 1854162 geonames_name: Ōme feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:01.359320+00:00' + source_url: https://www.city.ome.tokyo.jp/site/art-museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.ome.tokyo.jp/img/icon/apple-touch-icon.png + source_url: https://www.city.ome.tokyo.jp/site/art-museum + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:57:01.359320+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-OME-M-OMMPH.yaml b/data/custodian/JP-13-OME-M-OMMPH.yaml index da1c79d23b..c88b7b86ee 100644 --- a/data/custodian/JP-13-OME-M-OMMPH.yaml +++ b/data/custodian/JP-13-OME-M-OMMPH.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OME-M-OMMPH - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OME-M-OMMPH valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OME-M-OMMPH ghcid_numeric: 10532669352840867689 valid_from: '2025-12-06T23:38:33.600563+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OME MUNICIPAL MUSEUM OF PROVINCIAL HISTORY @@ -243,3 +244,22 @@ location: postal_code: 198-0053 street_address: KOMAKICHO, Ome Shi, Tokyo To, 198-0053 normalization_timestamp: '2025-12-09T12:22:08.690135+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:08.593480+00:00' + source_url: https://www.city.ome.tokyo.jp/site/provincial-history-museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.ome.tokyo.jp/img/icon/apple-touch-icon.png + source_url: https://www.city.ome.tokyo.jp/site/provincial-history-museum + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T18:57:08.593480+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-OSH-M-OP.yaml b/data/custodian/JP-13-OSH-M-OP.yaml index c718d8a23b..b0c81ec886 100644 --- a/data/custodian/JP-13-OSH-M-OP.yaml +++ b/data/custodian/JP-13-OSH-M-OP.yaml @@ -224,3 +224,28 @@ location: postal_code: 100-0103 street_address: SENZU, Oshima Machi, Tokyo To, 100-0103 normalization_timestamp: '2025-12-09T12:22:08.935762+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:30.881506+00:00' + source_url: https://www.soumu.metro.tokyo.lg.jp/11osima/park/www/htdocs/parkindex.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.metro.tokyo.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.soumu.metro.tokyo.lg.jp/11osima/park/www/htdocs/parkindex.html + css_selector: '[document] > html.ltr.yui3-js-enabled > head > link:nth-of-type(11)' + retrieved_on: '2025-12-25T18:57:30.881506+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.soumu.metro.tokyo.lg.jp/documents/38289461/43891254/2797_adcabace73746cba446984f8776560f0.jpg/8add0506-ad09-4a29-0d28-00fce6ed4a5e?version=1.0&t=1721124758442&imagePreview=1 + source_url: https://www.soumu.metro.tokyo.lg.jp/11osima/park/www/htdocs/parkindex.html + css_selector: '[document] > html.ltr.yui3-js-enabled > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T18:57:30.881506+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu.yaml b/data/custodian/JP-13-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu.yaml index 8e719445ba..8ce4a376ae 100644 --- a/data/custodian/JP-13-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu.yaml +++ b/data/custodian/JP-13-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-O-otakuritsushinkamatafukushisentakoenotoshoshitsu ghcid_numeric: 2229168320054367376 valid_from: '2025-12-06T23:38:59.528851+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTAKURITSUSHINKAMATAFUKUSHISENTAKOENOTOSHOSHITSU @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:45.042540+00:00' + source_url: http://www.city.ota.tokyo.jp/shisetsu/fukushi/shougai/support-pia.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: http://www.city.ota.tokyo.jp/shisetsu/fukushi/shougai/support-pia.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:57:45.042540+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: http://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: http://www.city.ota.tokyo.jp/shisetsu/fukushi/shougai/support-pia.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:57:45.042540+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.city.ota.tokyo.jp/images/ogp.png + source_url: http://www.city.ota.tokyo.jp/shisetsu/fukushi/shougai/support-pia.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T18:57:45.042540+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-O-otakusangyopurazakankosangyojohokona.yaml b/data/custodian/JP-13-OTA-L-O-otakusangyopurazakankosangyojohokona.yaml index 37d415dc86..80a2632e39 100644 --- a/data/custodian/JP-13-OTA-L-O-otakusangyopurazakankosangyojohokona.yaml +++ b/data/custodian/JP-13-OTA-L-O-otakusangyopurazakankosangyojohokona.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-O-otakusangyopurazakankosangyojohokona - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-O-otakusangyopurazakankosangyojohokona valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-O-otakusangyopurazakankosangyojohokona ghcid_numeric: 11981881186502686491 valid_from: '2025-12-06T23:38:58.701867+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTAKUSANGYOPURAZAKANKOSANGYOJOHOKONA @@ -151,3 +152,31 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:57:50.781466+00:00' + source_url: http://www.city.ota.tokyo.jp/kanko/ota_tourist_information/touristinformation_pio.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: http://www.city.ota.tokyo.jp/kanko/ota_tourist_information/touristinformation_pio.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:57:50.781466+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: http://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: http://www.city.ota.tokyo.jp/kanko/ota_tourist_information/touristinformation_pio.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:57:50.781466+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCHL-ota_city_haneda_library.yaml b/data/custodian/JP-13-OTA-L-OCHL-ota_city_haneda_library.yaml index bfe0617dd9..572fd23afa 100644 --- a/data/custodian/JP-13-OTA-L-OCHL-ota_city_haneda_library.yaml +++ b/data/custodian/JP-13-OTA-L-OCHL-ota_city_haneda_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OCHL-ota_city_haneda_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OCHL-ota_city_haneda_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OCHL-ota_city_haneda_library ghcid_numeric: 17670698115262209004 valid_from: '2025-12-06T23:38:43.308537+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ota City Haneda Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:05.533531+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/haneda.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/haneda.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:05.533531+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/haneda.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:05.533531+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/haneda.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:05.533531+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCHL.yaml b/data/custodian/JP-13-OTA-L-OCHL.yaml index 935a54e6d1..4ad5b53b30 100644 --- a/data/custodian/JP-13-OTA-L-OCHL.yaml +++ b/data/custodian/JP-13-OTA-L-OCHL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OCHL - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OCHL valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OCHL ghcid_numeric: 5168973598959785925 valid_from: '2025-12-06T23:38:43.289881+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ota City Hamatake Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:11.797954+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/hamatake.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/hamatake.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:11.797954+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/hamatake.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:11.797954+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/hamatake.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:11.797954+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCIL-ota_city_iriarai_library.yaml b/data/custodian/JP-13-OTA-L-OCIL-ota_city_iriarai_library.yaml index e843e832af..754dd5ae88 100644 --- a/data/custodian/JP-13-OTA-L-OCIL-ota_city_iriarai_library.yaml +++ b/data/custodian/JP-13-OTA-L-OCIL-ota_city_iriarai_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OCIL-ota_city_iriarai_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OCIL-ota_city_iriarai_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OCIL-ota_city_iriarai_library ghcid_numeric: 8489923451325319984 valid_from: '2025-12-06T23:38:43.278718+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ota City Iriarai Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:18.156938+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/iriarai.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/iriarai.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:18.156938+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/iriarai.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:18.156938+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/iriarai.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:18.156938+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCIL.yaml b/data/custodian/JP-13-OTA-L-OCIL.yaml index 6feb23cf1b..6938cccbc6 100644 --- a/data/custodian/JP-13-OTA-L-OCIL.yaml +++ b/data/custodian/JP-13-OTA-L-OCIL.yaml @@ -152,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:24.644161+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/ikegami.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/ikegami.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:24.644161+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/ikegami.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:24.644161+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/ikegami.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:24.644161+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCKL-ota_city_kugahara_library.yaml b/data/custodian/JP-13-OTA-L-OCKL-ota_city_kugahara_library.yaml index 1512f810c7..90657b3f36 100644 --- a/data/custodian/JP-13-OTA-L-OCKL-ota_city_kugahara_library.yaml +++ b/data/custodian/JP-13-OTA-L-OCKL-ota_city_kugahara_library.yaml @@ -152,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:30.962458+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kugahara.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kugahara.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:30.962458+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kugahara.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:30.962458+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kugahara.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:30.962458+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCKL.yaml b/data/custodian/JP-13-OTA-L-OCKL.yaml index e43f1eef39..6e40b278cb 100644 --- a/data/custodian/JP-13-OTA-L-OCKL.yaml +++ b/data/custodian/JP-13-OTA-L-OCKL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OCKL - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OCKL valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OCKL ghcid_numeric: 572255396980942115 valid_from: '2025-12-06T23:38:43.283192+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ota City Kamata Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:37.310698+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamata.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamata.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:37.310698+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamata.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:37.310698+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamata.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:37.310698+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCML.yaml b/data/custodian/JP-13-OTA-L-OCML.yaml index 9f457eb1c7..e9177b6cb5 100644 --- a/data/custodian/JP-13-OTA-L-OCML.yaml +++ b/data/custodian/JP-13-OTA-L-OCML.yaml @@ -152,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:43.682930+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/magome.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/magome.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:43.682930+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/magome.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:43.682930+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/magome.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:43.682930+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCOL-ota_city_omorinishi_library.yaml b/data/custodian/JP-13-OTA-L-OCOL-ota_city_omorinishi_library.yaml index d13b79eed9..7ddb96c994 100644 --- a/data/custodian/JP-13-OTA-L-OCOL-ota_city_omorinishi_library.yaml +++ b/data/custodian/JP-13-OTA-L-OCOL-ota_city_omorinishi_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OCOL-ota_city_omorinishi_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OCOL-ota_city_omorinishi_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OCOL-ota_city_omorinishi_library ghcid_numeric: 4431952322566915725 valid_from: '2025-12-06T23:38:43.306265+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ota City Omorinishi Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:58:50.147400+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_nishi.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_nishi.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:58:50.147400+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_nishi.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:58:50.147400+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_nishi.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:58:50.147400+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCOL.yaml b/data/custodian/JP-13-OTA-L-OCOL.yaml index bf4caeb5c0..aff710a587 100644 --- a/data/custodian/JP-13-OTA-L-OCOL.yaml +++ b/data/custodian/JP-13-OTA-L-OCOL.yaml @@ -152,3 +152,20 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:00.772571+00:00' + source_url: https://www.lib.city.ota.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://www.lib.city.ota.tokyo.jp/images/ogimage.png + source_url: https://www.lib.city.ota.tokyo.jp + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T18:59:00.772571+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-OTA-L-OCRL.yaml b/data/custodian/JP-13-OTA-L-OCRL.yaml index a100e40c4f..a6922a3a49 100644 --- a/data/custodian/JP-13-OTA-L-OCRL.yaml +++ b/data/custodian/JP-13-OTA-L-OCRL.yaml @@ -152,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:07.245371+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/rokugou.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/rokugou.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:59:07.245371+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/rokugou.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:59:07.245371+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/rokugou.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:07.245371+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCSL-ota_city_senzokuike_library.yaml b/data/custodian/JP-13-OTA-L-OCSL-ota_city_senzokuike_library.yaml index 8e0e2ded5c..e398be315f 100644 --- a/data/custodian/JP-13-OTA-L-OCSL-ota_city_senzokuike_library.yaml +++ b/data/custodian/JP-13-OTA-L-OCSL-ota_city_senzokuike_library.yaml @@ -152,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:13.534078+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/senzokuike.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/senzokuike.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:59:13.534078+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/senzokuike.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:59:13.534078+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/senzokuike.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:13.534078+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCSL.yaml b/data/custodian/JP-13-OTA-L-OCSL.yaml index 154a907ac9..f67ce0c18a 100644 --- a/data/custodian/JP-13-OTA-L-OCSL.yaml +++ b/data/custodian/JP-13-OTA-L-OCSL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OCSL - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OCSL valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OCSL ghcid_numeric: 15599799666466820327 valid_from: '2025-12-06T23:38:43.285348+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Ota City Shimomaruko Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:19.857424+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/shimomaruko.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/shimomaruko.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:59:19.857424+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/shimomaruko.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:59:19.857424+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/shimomaruko.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:19.857424+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OCTL.yaml b/data/custodian/JP-13-OTA-L-OCTL.yaml index b7e3dab92f..42448cb555 100644 --- a/data/custodian/JP-13-OTA-L-OCTL.yaml +++ b/data/custodian/JP-13-OTA-L-OCTL.yaml @@ -152,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:26.549772+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/tamagawa.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/tamagawa.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:59:26.549772+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/tamagawa.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:59:26.549772+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/tamagawa.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:26.549772+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OL-otakuritsukamataekimae_library.yaml b/data/custodian/JP-13-OTA-L-OL-otakuritsukamataekimae_library.yaml index f713ca0f59..65aa450d83 100644 --- a/data/custodian/JP-13-OTA-L-OL-otakuritsukamataekimae_library.yaml +++ b/data/custodian/JP-13-OTA-L-OL-otakuritsukamataekimae_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OL-otakuritsukamataekimae_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OL-otakuritsukamataekimae_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OL-otakuritsukamataekimae_library ghcid_numeric: 15307233966364731333 valid_from: '2025-12-06T23:38:43.296820+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTAKURITSUKAMATAEKIMAE Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:32.827713+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamataekimae.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamataekimae.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:59:32.827713+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamataekimae.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:59:32.827713+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/kamataekimae.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:32.827713+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OL-otakuritsuomorihigashi_library.yaml b/data/custodian/JP-13-OTA-L-OL-otakuritsuomorihigashi_library.yaml index bbc702ec18..f6983e4a15 100644 --- a/data/custodian/JP-13-OTA-L-OL-otakuritsuomorihigashi_library.yaml +++ b/data/custodian/JP-13-OTA-L-OL-otakuritsuomorihigashi_library.yaml @@ -152,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:39.160016+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_higashi.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_higashi.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:59:39.160016+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_higashi.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:59:39.160016+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_higashi.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:39.160016+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-OL-otakuritsuomoriminami_library.yaml b/data/custodian/JP-13-OTA-L-OL-otakuritsuomoriminami_library.yaml index ea1f7bd55f..d0cdc17f99 100644 --- a/data/custodian/JP-13-OTA-L-OL-otakuritsuomoriminami_library.yaml +++ b/data/custodian/JP-13-OTA-L-OL-otakuritsuomoriminami_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-OL-otakuritsuomoriminami_library - valid_from: "2025-12-10T09:44:10Z" + valid_from: '2025-12-10T09:44:10Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-OL-otakuritsuomoriminami_library valid_from: null - valid_to: "2025-12-10T09:44:10Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:10Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-OL-otakuritsuomoriminami_library ghcid_numeric: 9313761471338901632 valid_from: '2025-12-06T23:38:43.280972+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTAKURITSUOMORIMINAMI Library @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T18:59:45.511882+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_minami.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_minami.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T18:59:45.511882+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_minami.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T18:59:45.511882+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/toshokan/omori_minami.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T18:59:45.511882+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-L-T.yaml b/data/custodian/JP-13-OTA-L-T.yaml index 355f87216c..66868dae0e 100644 --- a/data/custodian/JP-13-OTA-L-T.yaml +++ b/data/custodian/JP-13-OTA-L-T.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-L-T - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-L-T valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-L-T ghcid_numeric: 6748767569563599796 valid_from: '2025-12-06T23:38:58.882017+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: TOHODAIGAKUIRYOSENTAOMORIBYOINKARADANOTOSHOSHITSU @@ -204,3 +205,22 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:08.405056+00:00' + source_url: http://www.mnc.toho-u.ac.jp/mmc/karada + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mnc.toho-u.ac.jp/mmc/img/favicon.ico + source_url: http://www.mnc.toho-u.ac.jp/mmc/karada + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:00:08.405056+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OTA-L-TUMMC.yaml b/data/custodian/JP-13-OTA-L-TUMMC.yaml index b1165cdf23..214b2ac859 100644 --- a/data/custodian/JP-13-OTA-L-TUMMC.yaml +++ b/data/custodian/JP-13-OTA-L-TUMMC.yaml @@ -210,3 +210,22 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:20.488265+00:00' + source_url: http://www.mnc.toho-u.ac.jp/mmc + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mnc.toho-u.ac.jp/img/favicon.ico + source_url: http://www.mnc.toho-u.ac.jp/mmc + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:00:20.488265+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OTA-M-IR.yaml b/data/custodian/JP-13-OTA-M-IR.yaml index f2c5ea96b5..1a9e6bd0f1 100644 --- a/data/custodian/JP-13-OTA-M-IR.yaml +++ b/data/custodian/JP-13-OTA-M-IR.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-M-IR - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-M-IR valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-M-IR ghcid_numeric: 2808479320880495146 valid_from: '2025-12-06T23:38:33.346250+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: IKEGAMIHONMONJI REIHOUDEN @@ -151,3 +152,22 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:27.698540+00:00' + source_url: https://honmonji.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://honmonji.jp/img/favicon/apple-touch-icon.png + source_url: https://honmonji.jp + css_selector: '[document] > html.js.flexbox > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:00:27.698540+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-M-KTEROCTP.yaml b/data/custodian/JP-13-OTA-M-KTEROCTP.yaml index df898ac5fc..5c09867841 100644 --- a/data/custodian/JP-13-OTA-M-KTEROCTP.yaml +++ b/data/custodian/JP-13-OTA-M-KTEROCTP.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-M-KTEROCTP - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-M-KTEROCTP valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-M-KTEROCTP ghcid_numeric: 5599918548780139295 valid_from: '2025-12-06T23:38:33.343676+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: THE KOFUN TOMB EXHIBITION ROOM IN OTA CITY TAMAGAWADAI PARK @@ -239,3 +240,37 @@ location: postal_code: 145-0071 street_address: DENENCHOFU, Ota Ku, Tokyo To, 145-0071 normalization_timestamp: '2025-12-09T12:22:10.099749+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:34.209844+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/kofuntejishitsu.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/kofuntejishitsu.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T19:00:34.209844+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/kofuntejishitsu.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:00:34.209844+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/kofuntejishitsu.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T19:00:34.209844+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-M-OCFM.yaml b/data/custodian/JP-13-OTA-M-OCFM.yaml index 638b2791f2..8b74643cc0 100644 --- a/data/custodian/JP-13-OTA-M-OCFM.yaml +++ b/data/custodian/JP-13-OTA-M-OCFM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-M-OCFM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-M-OCFM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-M-OCFM ghcid_numeric: 1920995794155605044 valid_from: '2025-12-06T23:38:33.338412+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTA CITY FOLK MUSEUM @@ -243,3 +244,37 @@ location: postal_code: 143-0025 street_address: MINAMIMAGOME, Ota Ku, Tokyo To, 143-0025 normalization_timestamp: '2025-12-09T12:22:10.160335+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:40.553468+00:00' + source_url: https://www.city.ota.tokyo.jp/seikatsu/manabu/hakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/seikatsu/manabu/hakubutsukan + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T19:00:40.553468+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/seikatsu/manabu/hakubutsukan + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:00:40.553468+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/seikatsu/manabu/hakubutsukan + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T19:00:40.553468+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-M-OCKKMM.yaml b/data/custodian/JP-13-OTA-M-OCKKMM.yaml index f5c1df9628..fc27b1486b 100644 --- a/data/custodian/JP-13-OTA-M-OCKKMM.yaml +++ b/data/custodian/JP-13-OTA-M-OCKKMM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-M-OCKKMM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-M-OCKKMM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-M-OCKKMM ghcid_numeric: 14732442643771750807 valid_from: '2025-12-06T23:38:33.341294+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OTA CITY KATSU KAISHU MEMORIAL MUSEUM @@ -151,3 +152,37 @@ location: geonames_id: 8469289 geonames_name: Ōta feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:00:46.708568+00:00' + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/katsu_kinenkan/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.ota.tokyo.jp/images/t-logo2025.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/katsu_kinenkan/index.html + css_selector: '#mainback-other > header > div.header-wp > div.header-left > div.header-logo + > a > img' + retrieved_on: '2025-12-25T19:00:46.708568+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 大田区 心やすらぎ未来へはばたく笑顔のまち大田区 + - claim_type: favicon_url + claim_value: https://www.city.ota.tokyo.jp/images/apple-touch-icon.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/katsu_kinenkan/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:00:46.708568+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.ota.tokyo.jp/images/ogp.png + source_url: https://www.city.ota.tokyo.jp/shisetsu/hakubutsukan/katsu_kinenkan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:00:46.708568+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OTA-M-ONM.yaml b/data/custodian/JP-13-OTA-M-ONM.yaml index 4d112f65e7..53be0a0605 100644 --- a/data/custodian/JP-13-OTA-M-ONM.yaml +++ b/data/custodian/JP-13-OTA-M-ONM.yaml @@ -715,3 +715,28 @@ youtube_enrichment: comments: [] thumbnail_url: https://i.ytimg.com/vi/XW2_JBvTocY/hqdefault.jpg status: SUCCESS +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:01.486155+00:00' + source_url: https://www.norimuseum.com + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://u.jimcdn.com/cms/o/s6395b903d72379e4/img/favicon.png?t=1562218930 + source_url: https://www.norimuseum.com + css_selector: '[document] > html.j-feature-js.j-feature-no-touch > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T19:01:01.486155+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://image.jimcdn.com/app/cms/image/transf/none/path/s6395b903d72379e4/backgroundarea/i708187c18c695521/version/1599178879/image.jpg + source_url: https://www.norimuseum.com + css_selector: '[document] > html.j-feature-js.j-feature-no-touch > head > meta:nth-of-type(18)' + retrieved_on: '2025-12-25T19:01:01.486155+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-OTA-M-OSHFMH.yaml b/data/custodian/JP-13-OTA-M-OSHFMH.yaml index 77bb2d9448..06f2444cff 100644 --- a/data/custodian/JP-13-OTA-M-OSHFMH.yaml +++ b/data/custodian/JP-13-OTA-M-OSHFMH.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OTA-M-OSHFMH - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OTA-M-OSHFMH valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OTA-M-OSHFMH ghcid_numeric: 7679192535292218632 valid_from: '2025-12-06T23:38:31.888521+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OHTAWARA-SHI HISTORICAL FOLK MATERIAL HALL @@ -151,3 +152,22 @@ location: geonames_id: 2111325 geonames_name: Ōtawara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:11.467293+00:00' + source_url: http://www.city.ohtawara.tochigi.jp/docs/2013082772237 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.city.ohtawara.tochigi.jp/apple-touch-icon-180x180.png + source_url: http://www.city.ohtawara.tochigi.jp/docs/2013082772237 + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T19:01:11.467293+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: 37 diff --git a/data/custodian/JP-13-OTA-M-OSNLMH.yaml b/data/custodian/JP-13-OTA-M-OSNLMH.yaml index c90d56eba3..565d3b1fea 100644 --- a/data/custodian/JP-13-OTA-M-OSNLMH.yaml +++ b/data/custodian/JP-13-OTA-M-OSNLMH.yaml @@ -152,3 +152,22 @@ location: geonames_id: 2111325 geonames_name: Ōtawara feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:01:19.439256+00:00' + source_url: https://www.city.ohtawara.tochigi.jp/docs/2013082772084 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.ohtawara.tochigi.jp/apple-touch-icon-180x180.png + source_url: https://www.city.ohtawara.tochigi.jp/docs/2013082772084 + css_selector: '[document] > html > head > link:nth-of-type(18)' + retrieved_on: '2025-12-25T19:01:19.439256+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: 37 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu.yaml index 65591a7acd..9d36aada3c 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyabeshiritsuarakawakominkantoshoshitsu ghcid_numeric: 14397640747122986674 valid_from: '2025-12-06T23:38:49.586308+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYABESHIRITSUARAKAWAKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:02:56.097330+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0913&stdycd=C0000537 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0913&stdycd=C0000537 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:02:56.097330+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhanyukominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhanyukominkantoshoshitsu.yaml index 16d5abb0cb..5a2b10899a 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhanyukominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhanyukominkantoshoshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:10.061220+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0916&stdycd=C0000540 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0916&stdycd=C0000540 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:03:10.061220+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhigashikandakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhigashikandakominkantoshoshitsu.yaml index 989338abd6..a0f5e08096 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhigashikandakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuhigashikandakominkantoshoshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:27.975088+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0923&stdycd=C0000562 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0923&stdycd=C0000562 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:03:27.975088+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu.yaml index f51471cf12..bdefe54315 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyabeshiritsukitakandakominkantoshoshitsu ghcid_numeric: 12063831703643794499 valid_from: '2025-12-06T23:38:49.593235+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYABESHIRITSUKITAKANDAKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:42.212128+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0925&stdycd=C0000536 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0925&stdycd=C0000536 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:03:42.212128+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsumatsuzawakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsumatsuzawakominkantoshoshitsu.yaml index 7ea85ed291..8ba31e68ff 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsumatsuzawakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsumatsuzawakominkantoshoshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:03:55.712450+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0915&stdycd=C0000539 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0915&stdycd=C0000539 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:03:55.712450+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsumiyajimakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsumiyajimakominkantoshoshitsu.yaml index 67ef858acf..3563190aa1 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsumiyajimakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsumiyajimakominkantoshoshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:08.791713+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0912&stdycd=C0000553 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0912&stdycd=C0000553 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:04:08.791713+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu.yaml index 4d9c14a0f8..adb423dc62 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyabeshiritsushotokukominkantoshoshitsu ghcid_numeric: 3453798297023936633 valid_from: '2025-12-06T23:38:49.583980+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYABESHIRITSUSHOTOKUKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:22.407073+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0917&stdycd=C0000538 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0917&stdycd=C0000538 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:04:22.407073+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu.yaml index 2c50bcb3d0..eb6fcfbefa 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyabeshiritsutobukominkantoshoshitsu ghcid_numeric: 2045405362392318873 valid_from: '2025-12-06T23:38:49.588613+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYABESHIRITSUTOBUKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:35.660603+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0924&stdycd=C0000554 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0924&stdycd=C0000554 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:04:35.660603+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu.yaml index 9d5d66a4ff..d9d723879c 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyabeshiritsutsuzawakominkantoshoshitsu ghcid_numeric: 1062211052535260571 valid_from: '2025-12-06T23:38:49.597906+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYABESHIRITSUTSUZAWAKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:04:48.748453+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0887&stdycd=C0000555 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0887&stdycd=C0000555 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:04:48.748453+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu.yaml index 1421a24c91..5a6aa3cf17 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyabeshiritsuwakabayashikominkantoshoshitsu ghcid_numeric: 4054742368410327919 valid_from: '2025-12-06T23:38:49.595500+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYABESHIRITSUWAKABAYASHIKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:06.028959+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0914&stdycd=C0000556 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0914&stdycd=C0000556 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:05:06.028959+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuyabunamikominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuyabunamikominkantoshoshitsu.yaml index 4cffea34ee..c38f13ff74 100644 --- a/data/custodian/JP-13-OYA-L-O-oyabeshiritsuyabunamikominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyabeshiritsuyabunamikominkantoshoshitsu.yaml @@ -152,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:17.628920+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0920&stdycd=C0000534 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0920&stdycd=C0000534 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:05:17.628920+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-O-oyamashikinukominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyamashikinukominkantoshoshitsu.yaml index 34abe48f08..ae2c945e9d 100644 --- a/data/custodian/JP-13-OYA-L-O-oyamashikinukominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyamashikinukominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyamashikinukominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyamashikinukominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyamashikinukominkantoshoshitsu ghcid_numeric: 12516717421094287522 valid_from: '2025-12-06T23:38:51.459605+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYAMASHIKINUKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:28.052857+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:05:28.052857+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-O-oyamashinakakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyamashinakakominkantoshoshitsu.yaml index fbcf6dbdb2..b8551da8b3 100644 --- a/data/custodian/JP-13-OYA-L-O-oyamashinakakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyamashinakakominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyamashinakakominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyamashinakakominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyamashinakakominkantoshoshitsu ghcid_numeric: 12135455500780350273 valid_from: '2025-12-06T23:38:51.466555+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYAMASHINAKAKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:36.498616+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:05:36.498616+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-O-oyamashinamaikominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyamashinamaikominkantoshoshitsu.yaml index 4118ee50e8..ee8394e3e8 100644 --- a/data/custodian/JP-13-OYA-L-O-oyamashinamaikominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyamashinamaikominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyamashinamaikominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyamashinamaikominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyamashinamaikominkantoshoshitsu ghcid_numeric: 14037555530029133159 valid_from: '2025-12-06T23:38:51.464163+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYAMASHINAMAIKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:45.001801+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:05:45.001801+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-O-oyamashisangawakominkantoshoshitsu.yaml b/data/custodian/JP-13-OYA-L-O-oyamashisangawakominkantoshoshitsu.yaml index ab51db212c..58b6b1716e 100644 --- a/data/custodian/JP-13-OYA-L-O-oyamashisangawakominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-OYA-L-O-oyamashisangawakominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O-oyamashisangawakominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O-oyamashisangawakominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O-oyamashisangawakominkantoshoshitsu ghcid_numeric: 7687677627301043834 valid_from: '2025-12-06T23:38:51.461872+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYAMASHISANGAWAKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:05:53.131002+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:05:53.131002+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-O.yaml b/data/custodian/JP-13-OYA-L-O.yaml index 946fce2865..91bf989622 100644 --- a/data/custodian/JP-13-OYA-L-O.yaml +++ b/data/custodian/JP-13-OYA-L-O.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-O - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-O valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-O ghcid_numeric: 11527162249340015853 valid_from: '2025-12-06T23:38:49.576525+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYABESHIRITSUMINAMIDANIKOMINKANTOSHOSHITSU @@ -151,3 +152,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:05.829459+00:00' + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0919&stdycd=C0000552 + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: http://www2.tkc.pref.toyama.jp/kouminkan/info/svOrgDtl.aspx?orgcd=0919&stdycd=C0000552 + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:06:05.829459+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-OCCLKBL.yaml b/data/custodian/JP-13-OYA-L-OCCLKBL.yaml index 2c7e333c05..9938994813 100644 --- a/data/custodian/JP-13-OYA-L-OCCLKBL.yaml +++ b/data/custodian/JP-13-OYA-L-OCCLKBL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-OCCLKBL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-OCCLKBL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-OCCLKBL ghcid_numeric: 3717645144857366478 valid_from: '2025-12-06T23:38:52.799835+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Oyama City Central Library Kuwa Branch Library @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:14.248772+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:06:14.248772+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-OCCLOBL.yaml b/data/custodian/JP-13-OYA-L-OCCLOBL.yaml index 69b7826e60..9b42df5105 100644 --- a/data/custodian/JP-13-OYA-L-OCCLOBL.yaml +++ b/data/custodian/JP-13-OYA-L-OCCLOBL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-OCCLOBL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-OCCLOBL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-OCCLOBL ghcid_numeric: 15291853163984417425 valid_from: '2025-12-06T23:38:51.468870+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Oyama City Central Library Oya Branch Library @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:22.308068+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:06:22.308068+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-OCL.yaml b/data/custodian/JP-13-OYA-L-OCL.yaml index 5706063b91..69a8555010 100644 --- a/data/custodian/JP-13-OYA-L-OCL.yaml +++ b/data/custodian/JP-13-OYA-L-OCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-OCL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-OCL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-OCL ghcid_numeric: 8342667223509442212 valid_from: '2025-12-06T23:38:44.443594+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: OYABE CITY LIBRARY @@ -168,8 +169,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q28564 label: public library - description: free community resource offering access to books, media, and information, promoting literacy and education - for all ages + description: free community resource offering access to books, media, and information, + promoting literacy and education for all ages wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -195,3 +196,22 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:29.261504+00:00' + source_url: https://oyabe-lib.jp/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://oyabe-lib.jp/img/logo.png + source_url: https://oyabe-lib.jp/index.html + css_selector: '#sitename > a > img' + retrieved_on: '2025-12-25T19:06:29.261504+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 小矢部市民図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-OYA-L-OL.yaml b/data/custodian/JP-13-OYA-L-OL.yaml index d70214f3a9..2aeb17b9de 100644 --- a/data/custodian/JP-13-OYA-L-OL.yaml +++ b/data/custodian/JP-13-OYA-L-OL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-OL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-OL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-OL ghcid_numeric: 14847339365503667487 valid_from: '2025-12-06T23:38:42.203460+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYAMASHIRITSUCHUO Library @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:37.388863+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:06:37.388863+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-OLM.yaml b/data/custodian/JP-13-OYA-L-OLM.yaml index 1a90bde74c..93b57ec060 100644 --- a/data/custodian/JP-13-OYA-L-OLM.yaml +++ b/data/custodian/JP-13-OYA-L-OLM.yaml @@ -152,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:45.933455+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:06:45.933455+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-OLO.yaml b/data/custodian/JP-13-OYA-L-OLO.yaml index 1ee30b9dbd..9542f52ead 100644 --- a/data/custodian/JP-13-OYA-L-OLO.yaml +++ b/data/custodian/JP-13-OYA-L-OLO.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-OLO - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-OLO valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-OLO ghcid_numeric: 12928620841002665364 valid_from: '2025-12-06T23:38:42.205744+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYAMASHIRITSUCHUO Library OYAMABUNKAN @@ -151,3 +152,22 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:53.859267+00:00' + source_url: https://library.city.oyama.tochigi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://library.city.oyama.tochigi.jp/apple-touch-icon.png + source_url: https://library.city.oyama.tochigi.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:06:53.859267+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-OYA-L-ONCTL.yaml b/data/custodian/JP-13-OYA-L-ONCTL.yaml index 81733f88b8..f6f9ee8567 100644 --- a/data/custodian/JP-13-OYA-L-ONCTL.yaml +++ b/data/custodian/JP-13-OYA-L-ONCTL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-L-ONCTL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-L-ONCTL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-L-ONCTL ghcid_numeric: 17778722758955713917 valid_from: '2025-12-06T23:38:57.386762+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Oyama National College of Technology Library @@ -151,3 +152,30 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:06:59.691480+00:00' + source_url: http://www.oyama-ct.ac.jp/tosyo + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.oyama-ct.ac.jp/images/logo.png + source_url: http://www.oyama-ct.ac.jp/tosyo + css_selector: '[document] > html > body > header.page-header > a > img.logo' + retrieved_on: '2025-12-25T19:06:59.691480+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 図書館ホーム + - claim_type: favicon_url + claim_value: http://www.oyama-ct.ac.jp/images/index.ico + source_url: http://www.oyama-ct.ac.jp/tosyo + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T19:06:59.691480+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 2 + has_primary_logo: true + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-OYA-M-MAFO.yaml b/data/custodian/JP-13-OYA-M-MAFO.yaml index cd133bb0b6..3d212bd5a6 100644 --- a/data/custodian/JP-13-OYA-M-MAFO.yaml +++ b/data/custodian/JP-13-OYA-M-MAFO.yaml @@ -152,3 +152,30 @@ location: geonames_id: 6822124 geonames_name: Oyabe feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:07.815383+00:00' + source_url: http://www.city.oyabe.toyama.jp/soshiki/kyouikuiinkai/bunspo/shougaigakusyubunka/shisetsu/furusatorekishikan/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.city.oyabe.toyama.jp/_template_/_site_/_default_/_res/design/images/header/tlogo.svg + source_url: http://www.city.oyabe.toyama.jp/soshiki/kyouikuiinkai/bunspo/shougaigakusyubunka/shisetsu/furusatorekishikan/index.html + css_selector: '#tlogo > p > a > img' + retrieved_on: '2025-12-25T19:07:07.815383+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 小矢部市トップページ + - claim_type: favicon_url + claim_value: https://www.city.oyabe.toyama.jp/_template_/_site_/_default_/_res/favicon.ico + source_url: http://www.city.oyabe.toyama.jp/soshiki/kyouikuiinkai/bunspo/shougaigakusyubunka/shisetsu/furusatorekishikan/index.html + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:07:07.815383+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-13-OYA-M-OCM.yaml b/data/custodian/JP-13-OYA-M-OCM.yaml index 28f415bb92..0ff28f81d8 100644 --- a/data/custodian/JP-13-OYA-M-OCM.yaml +++ b/data/custodian/JP-13-OYA-M-OCM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-M-OCM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-M-OCM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-M-OCM ghcid_numeric: 3671280629757839440 valid_from: '2025-12-06T23:38:31.871042+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: OYAMA CITY MUSEUM @@ -270,3 +271,28 @@ location: postal_code: 329-0214 street_address: OTOME, Oyama Shi, Tochigi Ken, 329-0214 normalization_timestamp: '2025-12-09T12:22:11.537240+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:15.559530+00:00' + source_url: https://www.city.oyama.tochigi.jp/site/hakubutu + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.oyama.tochigi.jp/web_clip_icon.png + source_url: https://www.city.oyama.tochigi.jp/site/hakubutu + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:07:15.559530+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.oyama.tochigi.jp/web_clip_icon.png + source_url: https://www.city.oyama.tochigi.jp/site/hakubutu + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:07:15.559530+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-OYA-M-THRM.yaml b/data/custodian/JP-13-OYA-M-THRM.yaml index 5f7dcbb717..8ba2492284 100644 --- a/data/custodian/JP-13-OYA-M-THRM.yaml +++ b/data/custodian/JP-13-OYA-M-THRM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-OYA-M-THRM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-OYA-M-THRM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-OYA-M-THRM ghcid_numeric: 18290034025258208951 valid_from: '2025-12-06T23:38:31.866151+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TERANO-HIGASHIISEKI REMAIN MUSEUM @@ -151,3 +152,28 @@ location: geonames_id: 1853483 geonames_name: Oyama feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:22.912088+00:00' + source_url: https://www.city.oyama.tochigi.jp/soshiki/5/366.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.oyama.tochigi.jp/soshiki/web_clip_icon.png + source_url: https://www.city.oyama.tochigi.jp/soshiki/5/366.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:07:22.912088+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.oyama.tochigi.jp/web_clip_icon.png + source_url: https://www.city.oyama.tochigi.jp/soshiki/5/366.html + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:07:22.912088+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAI-L-DLD.yaml b/data/custodian/JP-13-SAI-L-DLD.yaml index 778c3108ae..fba957b76d 100644 --- a/data/custodian/JP-13-SAI-L-DLD.yaml +++ b/data/custodian/JP-13-SAI-L-DLD.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-L-DLD - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-L-DLD valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-L-DLD ghcid_numeric: 2215783896195186693 valid_from: '2025-12-06T23:38:46.772307+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: DAISENCHORITSU Library DAISEMBUNKAN @@ -153,3 +154,28 @@ location: geonames_id: 6822199 geonames_name: Daisen feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:31.096734+00:00' + source_url: http://library.daisen.jp/47.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.daisen.jp/common/img/favicon.ico + source_url: http://library.daisen.jp/47.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:07:31.096734+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://library.daisen.jp/common/img/ogp.png + source_url: http://library.daisen.jp/47.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T19:07:31.096734+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SAI-L-DLN.yaml b/data/custodian/JP-13-SAI-L-DLN.yaml index 6b79b81d83..b18134ef1b 100644 --- a/data/custodian/JP-13-SAI-L-DLN.yaml +++ b/data/custodian/JP-13-SAI-L-DLN.yaml @@ -154,3 +154,28 @@ location: geonames_id: 6822199 geonames_name: Daisen feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:39.199234+00:00' + source_url: http://library.daisen.jp/46.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.daisen.jp/common/img/favicon.ico + source_url: http://library.daisen.jp/46.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:07:39.199234+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://library.daisen.jp/common/img/ogp.png + source_url: http://library.daisen.jp/46.html + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T19:07:39.199234+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SAI-L-DML.yaml b/data/custodian/JP-13-SAI-L-DML.yaml index 75915edcbb..5d7b052f62 100644 --- a/data/custodian/JP-13-SAI-L-DML.yaml +++ b/data/custodian/JP-13-SAI-L-DML.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-L-DML - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-L-DML valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-L-DML ghcid_numeric: 15580746600248152514 valid_from: '2025-12-06T23:38:46.769739+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Daisen Municipal Library @@ -153,3 +154,28 @@ location: geonames_id: 6822199 geonames_name: Daisen feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:49.504907+00:00' + source_url: http://library.daisen.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.daisen.jp/common/img/favicon.ico + source_url: http://library.daisen.jp + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:07:49.504907+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://library.daisen.jp/common/img/ogp.png + source_url: http://library.daisen.jp + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T19:07:49.504907+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SAI-L-H-hokichoritsunikkokominkantoshoshitsu.yaml b/data/custodian/JP-13-SAI-L-H-hokichoritsunikkokominkantoshoshitsu.yaml index 75c656641b..d0cf90228c 100644 --- a/data/custodian/JP-13-SAI-L-H-hokichoritsunikkokominkantoshoshitsu.yaml +++ b/data/custodian/JP-13-SAI-L-H-hokichoritsunikkokominkantoshoshitsu.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-L-H-hokichoritsunikkokominkantoshoshitsu - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-L-H-hokichoritsunikkokominkantoshoshitsu valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-L-H-hokichoritsunikkokominkantoshoshitsu ghcid_numeric: 12640031566269443075 valid_from: '2025-12-06T23:38:51.948107+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HOKICHORITSUNIKKOKOMINKANTOSHOSHITSU @@ -153,3 +154,22 @@ location: geonames_id: 1862278 geonames_name: Hōki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:07:58.611651+00:00' + source_url: http://www.houki-town.jp/p/book/2/4 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.houki-town.jp/book/favicon.ico + source_url: http://www.houki-town.jp/p/book/2/4 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:07:58.611651+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SAI-L-H.yaml b/data/custodian/JP-13-SAI-L-H.yaml index 981866d41a..7cbff25be9 100644 --- a/data/custodian/JP-13-SAI-L-H.yaml +++ b/data/custodian/JP-13-SAI-L-H.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-L-H - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-L-H valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-L-H ghcid_numeric: 16770578842957568816 valid_from: '2025-12-06T23:38:51.945789+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HOKICHORITSUNIBUKOMINKANTOSHOSHITSU @@ -153,3 +154,22 @@ location: geonames_id: 1862278 geonames_name: Hōki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:08:07.870835+00:00' + source_url: http://www.houki-town.jp/p/book/2/3 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.houki-town.jp/book/favicon.ico + source_url: http://www.houki-town.jp/p/book/2/3 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:08:07.870835+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SAI-L-HL-hokichokishimoto_library.yaml b/data/custodian/JP-13-SAI-L-HL-hokichokishimoto_library.yaml index 779c045fa7..545de5f6cf 100644 --- a/data/custodian/JP-13-SAI-L-HL-hokichokishimoto_library.yaml +++ b/data/custodian/JP-13-SAI-L-HL-hokichokishimoto_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-L-HL-hokichokishimoto_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-L-HL-hokichokishimoto_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-L-HL-hokichokishimoto_library ghcid_numeric: 16820262579499684775 valid_from: '2025-12-06T23:38:48.604775+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HOKICHOKISHIMOTO Library @@ -153,3 +154,22 @@ location: geonames_id: 1862278 geonames_name: Hōki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:49:02.994091+00:00' + source_url: http://www.houki-town.jp/book/2/2 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.houki-town.jp/book/favicon.ico + source_url: http://www.houki-town.jp/book/2/2 + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:49:02.994091+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SAI-L-HL.yaml b/data/custodian/JP-13-SAI-L-HL.yaml index 9e92f37e34..19a7e6ac2d 100644 --- a/data/custodian/JP-13-SAI-L-HL.yaml +++ b/data/custodian/JP-13-SAI-L-HL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-L-HL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-L-HL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-L-HL ghcid_numeric: 7539542959896068761 valid_from: '2025-12-06T23:38:46.780005+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HOKICHOMIZOKUCHI Library @@ -153,3 +154,22 @@ location: geonames_id: 1862278 geonames_name: Hōki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:49:10.634149+00:00' + source_url: http://www.houki-town.jp/book + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.houki-town.jp/book/favicon.ico + source_url: http://www.houki-town.jp/book + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:49:10.634149+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SAI-L-NL-nambuchoritsutemman_library.yaml b/data/custodian/JP-13-SAI-L-NL-nambuchoritsutemman_library.yaml index fb3443c26e..216bba9a3e 100644 --- a/data/custodian/JP-13-SAI-L-NL-nambuchoritsutemman_library.yaml +++ b/data/custodian/JP-13-SAI-L-NL-nambuchoritsutemman_library.yaml @@ -154,3 +154,28 @@ location: geonames_id: 1855697 geonames_name: Nambu feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:23:32.306606+00:00' + source_url: http://www.town.nanbu.tottori.jp/book + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.nanbu.tottori.jp/user/book/2015/images/i_icon.png + source_url: http://www.town.nanbu.tottori.jp/book + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:23:32.306606+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.nanbu.tottori.jp/user/book/2015/images/ogp_image.png + source_url: http://www.town.nanbu.tottori.jp/book + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T19:23:32.306606+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAI-L-NL.yaml b/data/custodian/JP-13-SAI-L-NL.yaml index e56d3fcbfc..90c2ced7ac 100644 --- a/data/custodian/JP-13-SAI-L-NL.yaml +++ b/data/custodian/JP-13-SAI-L-NL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-L-NL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-L-NL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-L-NL ghcid_numeric: 12732508908093653773 valid_from: '2025-12-06T23:38:46.777667+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: NAMBUCHORITSUHOSSHOJI Library @@ -153,3 +154,28 @@ location: geonames_id: 1855697 geonames_name: Nambu feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:23:40.574162+00:00' + source_url: http://www.town.nanbu.tottori.jp/book + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.town.nanbu.tottori.jp/user/book/2015/images/i_icon.png + source_url: http://www.town.nanbu.tottori.jp/book + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:23:40.574162+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.town.nanbu.tottori.jp/user/book/2015/images/ogp_image.png + source_url: http://www.town.nanbu.tottori.jp/book + css_selector: '[document] > html > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T19:23:40.574162+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAI-M-SUMP.yaml b/data/custodian/JP-13-SAI-M-SUMP.yaml index 5ee0f0592b..566599bb8e 100644 --- a/data/custodian/JP-13-SAI-M-SUMP.yaml +++ b/data/custodian/JP-13-SAI-M-SUMP.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-M-SUMP - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-M-SUMP valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-M-SUMP ghcid_numeric: 8429640776827886256 valid_from: '2025-12-06T23:38:38.459773+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SHOJI UEDA MUSEUM OF PHOTOGRAPHY @@ -153,3 +154,28 @@ location: geonames_id: 1862278 geonames_name: Hōki feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:23:57.465797+00:00' + source_url: http://www.houki-town.jp/ueda + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.houki-town.jp/user/ueda2/common/images/i_icon.png + source_url: http://www.houki-town.jp/ueda + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T19:23:57.465797+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.houki-town.jp/user/ueda2/common/images/ogp_image.png + source_url: http://www.houki-town.jp/ueda + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-25T19:23:57.465797+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAI-M-THDT.yaml b/data/custodian/JP-13-SAI-M-THDT.yaml index 9dd9dd854f..1dee51d857 100644 --- a/data/custodian/JP-13-SAI-M-THDT.yaml +++ b/data/custodian/JP-13-SAI-M-THDT.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAI-M-THDT - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAI-M-THDT valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAI-M-THDT ghcid_numeric: 7694123307941624497 valid_from: '2025-12-06T23:38:38.450163+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: TREASURE HOUSE OF THE DAISEN TEMPLE @@ -153,3 +154,28 @@ location: geonames_id: 6822199 geonames_name: Daisen feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:49:42.920255+00:00' + source_url: https://www.daisen.jp/p/kankou/4/yamagawa/48 + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.daisen.jp/user/common/images/i_icon.png + source_url: https://www.daisen.jp/p/kankou/4/yamagawa/48 + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T19:49:42.920255+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://tourismdaisen.com/user/common/images/ogp_image.png + source_url: https://www.daisen.jp/p/kankou/4/yamagawa/48 + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-25T19:49:42.920255+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAI-M-TPMHP.yaml b/data/custodian/JP-13-SAI-M-TPMHP.yaml index 422795044f..f269b77214 100644 --- a/data/custodian/JP-13-SAI-M-TPMHP.yaml +++ b/data/custodian/JP-13-SAI-M-TPMHP.yaml @@ -232,3 +232,22 @@ location: geonames_id: 6822199 geonames_name: Daisen feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:39:11.487871+00:00' + source_url: https://www.pref.tottori.lg.jp/mukibanda + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.pref.tottori.lg.jp/topimage/toripy_n.gif + source_url: https://www.pref.tottori.lg.jp/mukibanda + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:39:11.487871+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SAI-M-TT.yaml b/data/custodian/JP-13-SAI-M-TT.yaml index 4a2d5b0e23..797f406111 100644 --- a/data/custodian/JP-13-SAI-M-TT.yaml +++ b/data/custodian/JP-13-SAI-M-TT.yaml @@ -260,3 +260,28 @@ location: postal_code: 683-0217 street_address: TSURUDA, Saihaku Gun Nambu Cho, Tottori Ken, 683-0217 normalization_timestamp: '2025-12-09T12:22:12.225592+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:39:21.369493+00:00' + source_url: https://www.tottorihanakairou.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.tottorihanakairou.or.jp/user/common/images/i_icon.png + source_url: https://www.tottorihanakairou.or.jp + css_selector: '[document] > html.js.flexbox > head > link' + retrieved_on: '2025-12-25T19:39:21.369493+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.tottorihanakairou.or.jp/user/common/images/ogp_image.jpg + source_url: https://www.tottorihanakairou.or.jp + css_selector: '[document] > html.js.flexbox > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-25T19:39:21.369493+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAK-L-SCL.yaml b/data/custodian/JP-13-SAK-L-SCL.yaml index 10aabb7316..6fba6a4bb3 100644 --- a/data/custodian/JP-13-SAK-L-SCL.yaml +++ b/data/custodian/JP-13-SAK-L-SCL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAK-L-SCL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAK-L-SCL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAK-L-SCL ghcid_numeric: 5065178014061400904 valid_from: '2025-12-06T23:38:46.745489+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Sakaiminato Civic Library @@ -153,3 +154,22 @@ location: geonames_id: 1853174 geonames_name: Sakaiminato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:39:32.670675+00:00' + source_url: https://lib.city.sakaiminato.tottori.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lib.city.sakaiminato.tottori.jp/!cache/favicon/safari-pinned-tab.svg + source_url: https://lib.city.sakaiminato.tottori.jp + css_selector: '[document] > html.server-public.js > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T19:39:32.670675+00:00' + extraction_method: 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-13-SAK-M-MSM.yaml b/data/custodian/JP-13-SAK-M-MSM.yaml index 4704673e30..dfe230f398 100644 --- a/data/custodian/JP-13-SAK-M-MSM.yaml +++ b/data/custodian/JP-13-SAK-M-MSM.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAK-M-MSM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAK-M-MSM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAK-M-MSM ghcid_numeric: 1921051447213017079 valid_from: '2025-12-06T23:38:38.435178+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: MIZUKI SIGERU MUSEUM @@ -249,3 +250,28 @@ location: geonames_id: 1853174 geonames_name: Sakaiminato feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:39:47.683380+00:00' + source_url: http://mizuki.sakaiminato.net + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://mizuki.sakaiminato.net/user/common2024/images/i_icon.png + source_url: http://mizuki.sakaiminato.net + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:39:47.683380+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://mizuki.sakaiminato.net/user/common2024/images/ogp_image.jpg + source_url: http://mizuki.sakaiminato.net + css_selector: '[document] > html > head > meta:nth-of-type(5)' + retrieved_on: '2025-12-25T19:39:47.683380+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAK-M-SCMMKA.yaml b/data/custodian/JP-13-SAK-M-SCMMKA.yaml index 5af09a0fab..05ef019512 100644 --- a/data/custodian/JP-13-SAK-M-SCMMKA.yaml +++ b/data/custodian/JP-13-SAK-M-SCMMKA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAK-M-SCMMKA - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAK-M-SCMMKA valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAK-M-SCMMKA ghcid_numeric: 1922311105119966118 valid_from: '2025-12-06T23:38:31.910688+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SAKURA CITY MUSEUM MEMORIAL OF KAMPO ARAI @@ -151,3 +152,22 @@ location: geonames_id: 2111220 geonames_name: Sakura feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:40:00.779993+00:00' + source_url: https://www.city.tochigi-sakura.lg.jp/museum/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.tochigi-sakura.lg.jp/apple-touch-icon.png + source_url: https://www.city.tochigi-sakura.lg.jp/museum/index.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T19:40:00.779993+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SAN-L-SL-sanotankidaigaku_library.yaml b/data/custodian/JP-13-SAN-L-SL-sanotankidaigaku_library.yaml index 3af2ca9a5c..fdb3921ba8 100644 --- a/data/custodian/JP-13-SAN-L-SL-sanotankidaigaku_library.yaml +++ b/data/custodian/JP-13-SAN-L-SL-sanotankidaigaku_library.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAN-L-SL-sanotankidaigaku_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAN-L-SL-sanotankidaigaku_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAN-L-SL-sanotankidaigaku_library ghcid_numeric: 6695655201883232465 valid_from: '2025-12-06T23:38:56.866945+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: SANOTANKIDAIGAKU Library @@ -204,3 +205,22 @@ location: geonames_id: 1852964 geonames_name: Sano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:40:21.846693+00:00' + source_url: http://sanotan.jp/campus_library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://sanotan.jp/media/uploads/2022/04/cropped-favicon-180x180.png + source_url: http://sanotan.jp/campus_library.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T19:40:21.846693+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SAN-M-AYSHMA.yaml b/data/custodian/JP-13-SAN-M-AYSHMA.yaml index 95ba836273..6fcacb7dbc 100644 --- a/data/custodian/JP-13-SAN-M-AYSHMA.yaml +++ b/data/custodian/JP-13-SAN-M-AYSHMA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAN-M-AYSHMA - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAN-M-AYSHMA valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAN-M-AYSHMA ghcid_numeric: 14019181104421919176 valid_from: '2025-12-06T23:38:31.830055+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ANDO YUJI SHONEN-NO-HI MUSEUM OF ART @@ -151,3 +152,22 @@ location: geonames_id: 1852964 geonames_name: Sano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:40:39.267876+00:00' + source_url: http://www.shonennohi.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.shonennohi.jp/wp-content/uploads/2025/09/cropped-favicon-180x180.png + source_url: http://www.shonennohi.jp + css_selector: '[document] > html.mobile > head > link:nth-of-type(23)' + retrieved_on: '2025-12-25T19:40:39.267876+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SAN-M-KTMCA.yaml b/data/custodian/JP-13-SAN-M-KTMCA.yaml index e4f6b6979d..8c797e7c52 100644 --- a/data/custodian/JP-13-SAN-M-KTMCA.yaml +++ b/data/custodian/JP-13-SAN-M-KTMCA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAN-M-KTMCA - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAN-M-KTMCA valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAN-M-KTMCA ghcid_numeric: 16715689709691961313 valid_from: '2025-12-06T23:38:31.827592+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KOICHI TAMURA MUSEUM OF CERAMIC ART @@ -151,3 +152,28 @@ location: geonames_id: 1852964 geonames_name: Sano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:40:47.495608+00:00' + source_url: https://www.city.sano.lg.jp/sp/tamurakoichitogeikan/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sano.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.sano.lg.jp/sp/tamurakoichitogeikan/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:40:47.495608+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sano.lg.jp/material/images/group/1/1200x450.png + source_url: https://www.city.sano.lg.jp/sp/tamurakoichitogeikan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T19:40:47.495608+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAN-M-KUFMS.yaml b/data/custodian/JP-13-SAN-M-KUFMS.yaml index fee6f58293..45bf9f0098 100644 --- a/data/custodian/JP-13-SAN-M-KUFMS.yaml +++ b/data/custodian/JP-13-SAN-M-KUFMS.yaml @@ -267,3 +267,28 @@ location: postal_code: 327-0501 street_address: KUZUHIGASHI, Sano Shi, Tochigi Ken, 327-0501 normalization_timestamp: '2025-12-09T12:22:12.771924+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:40:54.982667+00:00' + source_url: https://www.city.sano.lg.jp/sp/kuzuukasekikan/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sano.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.sano.lg.jp/sp/kuzuukasekikan/index.html + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:40:54.982667+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sano.lg.jp/material/images/group/85/g-kaseki-mv.png + source_url: https://www.city.sano.lg.jp/sp/kuzuukasekikan/index.html + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T19:40:54.982667+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAN-M-SCM.yaml b/data/custodian/JP-13-SAN-M-SCM.yaml index 33e33b92ca..f98b876596 100644 --- a/data/custodian/JP-13-SAN-M-SCM.yaml +++ b/data/custodian/JP-13-SAN-M-SCM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAN-M-SCM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAN-M-SCM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAN-M-SCM ghcid_numeric: 7295339772279323518 valid_from: '2025-12-06T23:38:31.821856+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SANO CITY MUSEUM @@ -267,3 +268,28 @@ location: postal_code: 327-0003 street_address: OHASHICHO, Sano Shi, Tochigi Ken, 327-0003 normalization_timestamp: '2025-12-09T12:22:12.831553+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:41:04.871260+00:00' + source_url: https://www.city.sano.lg.jp/sp/kyodohakubutsukan + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.sano.lg.jp/theme/base/img_common/smartphone.png + source_url: https://www.city.sano.lg.jp/sp/kyodohakubutsukan + css_selector: '[document] > html > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:41:04.871260+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.sano.lg.jp/theme/base/img_common/ogp_noimage.png + source_url: https://www.city.sano.lg.jp/sp/kyodohakubutsukan + css_selector: '[document] > html > head > meta:nth-of-type(7)' + retrieved_on: '2025-12-25T19:41:04.871260+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SAN-M-STAM.yaml b/data/custodian/JP-13-SAN-M-STAM.yaml index 6463ed62bc..a14ebea458 100644 --- a/data/custodian/JP-13-SAN-M-STAM.yaml +++ b/data/custodian/JP-13-SAN-M-STAM.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SAN-M-STAM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SAN-M-STAM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SAN-M-STAM ghcid_numeric: 1510317516184098589 valid_from: '2025-12-06T23:38:31.824811+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: SANO TOSEKI ART MUSEUM @@ -182,7 +183,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) wikidata_instance_of: *id004 wikidata_location: country: &id005 @@ -226,3 +228,28 @@ location: geonames_id: 1852964 geonames_name: Sano feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:41:18.339483+00:00' + source_url: http://www.toseki.com/museum/museum.htm + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.toseki.com/apple-touch-icon.png + source_url: http://www.toseki.com/museum/museum.htm + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:41:18.339483+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://skyterrace.toseki.com/wp-content/uploads/2025/04/ogp.jpg + source_url: http://www.toseki.com/museum/museum.htm + css_selector: '[document] > html > head > meta:nth-of-type(12)' + retrieved_on: '2025-12-25T19:41:18.339483+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SET-L-HRFL.yaml b/data/custodian/JP-13-SET-L-HRFL.yaml index 7fe121a432..4fda1d3a6c 100644 --- a/data/custodian/JP-13-SET-L-HRFL.yaml +++ b/data/custodian/JP-13-SET-L-HRFL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-HRFL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-HRFL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-HRFL ghcid_numeric: 9811420198533592595 valid_from: '2025-12-06T23:38:57.772843+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Housing Research Foundation Library @@ -151,3 +152,22 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:41:59.540190+00:00' + source_url: http://www.jusoken.or.jp/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.jusoken.or.jp/library/../apple-touch-icon.png + source_url: http://www.jusoken.or.jp/library/index.html + css_selector: '[document] > html > head > link:nth-of-type(10)' + retrieved_on: '2025-12-25T19:41:59.540190+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SET-L-IESSU.yaml b/data/custodian/JP-13-SET-L-IESSU.yaml index cbb9e12108..3bd8fcd687 100644 --- a/data/custodian/JP-13-SET-L-IESSU.yaml +++ b/data/custodian/JP-13-SET-L-IESSU.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-IESSU - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-IESSU valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-IESSU ghcid_numeric: 15450004996164911467 valid_from: '2025-12-06T23:38:58.813632+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Institute for Economic Studies Seijo University @@ -204,3 +205,37 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:42:06.939597+00:00' + source_url: http://www.seijo.ac.jp/keiken/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.seijo.ac.jp/renew_assets/common/img/main-logo-ft.png + source_url: http://www.seijo.ac.jp/keiken/index.html + css_selector: '#tpl-footer > nav.footer-lists > div.item.sp-footer-cont > h1.footer-logo + > a > img.only-pc' + retrieved_on: '2025-12-25T19:42:06.939597+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 成城大学 + - claim_type: favicon_url + claim_value: http://www.seijo.ac.jp/favicon.ico + source_url: http://www.seijo.ac.jp/keiken/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:42:06.939597+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.seijo.ac.jp/asset/common/img/og-image.gif + source_url: http://www.seijo.ac.jp/keiken/index.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T19:42:06.939597+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-L-IFSSU.yaml b/data/custodian/JP-13-SET-L-IFSSU.yaml index 87349a50c8..00d47e5395 100644 --- a/data/custodian/JP-13-SET-L-IFSSU.yaml +++ b/data/custodian/JP-13-SET-L-IFSSU.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-IFSSU - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-IFSSU valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-IFSSU ghcid_numeric: 2717458589612482841 valid_from: '2025-12-06T23:38:58.816252+00:00' @@ -101,8 +102,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: The Institute of Folklore Studies Seijo University @@ -207,3 +208,37 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:42:12.669237+00:00' + source_url: http://www.seijo.ac.jp/minken/index.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.seijo.ac.jp/renew_assets/common/img/main-logo-ft.png + source_url: http://www.seijo.ac.jp/minken/index.html + css_selector: '#tpl-footer > nav.footer-lists > div.item.sp-footer-cont > h1.footer-logo + > a > img.only-pc' + retrieved_on: '2025-12-25T19:42:12.669237+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 成城大学 + - claim_type: favicon_url + claim_value: http://www.seijo.ac.jp/favicon.ico + source_url: http://www.seijo.ac.jp/minken/index.html + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:42:12.669237+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/vnd.microsoft.icon + favicon_sizes: '' + - claim_type: og_image_url + claim_value: http://www.seijo.ac.jp/asset/common/img/og-image.gif + source_url: http://www.seijo.ac.jp/minken/index.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T19:42:12.669237+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-L-KLJ.yaml b/data/custodian/JP-13-SET-L-KLJ.yaml index 770e94c91f..10bc4b5eb0 100644 --- a/data/custodian/JP-13-SET-L-KLJ.yaml +++ b/data/custodian/JP-13-SET-L-KLJ.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-KLJ - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-KLJ valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-KLJ ghcid_numeric: 5258722895622817757 valid_from: '2025-12-06T23:38:54.891503+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: KOKUSHIKANDAIGAKU Library ・JOHOMEDEIASENTA @@ -204,3 +205,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:42:52.031742+00:00' + source_url: https://www.kokushikan.ac.jp/education/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.kokushikan.ac.jp/favicon.ico + source_url: https://www.kokushikan.ac.jp/education/library + css_selector: '[document] > html.is-loaded.is-scroll > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:42:52.031742+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.kokushikan.ac.jp/assets/img/common/ogp_image.jpg + source_url: https://www.kokushikan.ac.jp/education/library + css_selector: '[document] > html.is-loaded.is-scroll > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:42:52.031742+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-L-KUL.yaml b/data/custodian/JP-13-SET-L-KUL.yaml index a093c7932a..91056babea 100644 --- a/data/custodian/JP-13-SET-L-KUL.yaml +++ b/data/custodian/JP-13-SET-L-KUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-KUL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-KUL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-KUL ghcid_numeric: 4885135360654448110 valid_from: '2025-12-06T23:38:54.899194+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: Komazawa University Library @@ -209,3 +210,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:43:04.934074+00:00' + source_url: http://www.komazawa-u.ac.jp/cms/library + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.komazawa-u.ac.jp/favicon.ico + source_url: http://www.komazawa-u.ac.jp/cms/library + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:43:04.934074+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.komazawa-u.ac.jp/facilities/library/img/common/ogp.png + source_url: http://www.komazawa-u.ac.jp/cms/library + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:43:04.934074+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-L-NL.yaml b/data/custodian/JP-13-SET-L-NL.yaml index cb83c4f6d7..ef55a68294 100644 --- a/data/custodian/JP-13-SET-L-NL.yaml +++ b/data/custodian/JP-13-SET-L-NL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-NL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-NL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-NL ghcid_numeric: 4693783214733576322 valid_from: '2025-12-06T23:38:54.675732+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: NIHONDAIGAKUBUNRIGAKUBU Library @@ -204,3 +205,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:43:18.648873+00:00' + source_url: http://www.chs.nihon-u.ac.jp/opac + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.chs.nihon-u.ac.jp/assets/images/common/webclip.png + source_url: http://www.chs.nihon-u.ac.jp/opac + css_selector: '[document] > html.win.win10 > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:43:18.648873+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://chs.nihon-u.ac.jp/assets/images/common/ogp_chs.png + source_url: http://www.chs.nihon-u.ac.jp/opac + css_selector: '[document] > html.win.win10 > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T19:43:18.648873+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SET-L-SAMAL.yaml b/data/custodian/JP-13-SET-L-SAMAL.yaml index 70d8bf6ba9..d364213ff5 100644 --- a/data/custodian/JP-13-SET-L-SAMAL.yaml +++ b/data/custodian/JP-13-SET-L-SAMAL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SAMAL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SAMAL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SAMAL ghcid_numeric: 13152764153302452538 valid_from: '2025-12-06T23:38:58.821082+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SETAGAYA ART MUSEUM ART LIBRARY @@ -151,3 +152,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:03.232447+00:00' + source_url: http://www.setagayaartmuseum.or.jp/mguide/art_library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.setagayaartmuseum.or.jp/cmn/favicon/apple-touch-icon-180x180.png + source_url: http://www.setagayaartmuseum.or.jp/mguide/art_library.html + css_selector: '[document] > html.with_announce > head > link:nth-of-type(16)' + retrieved_on: '2025-12-25T19:44:03.232447+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: https://www.setagayaartmuseum.or.jp/cmn/img/icn_sns_noimg.png + source_url: http://www.setagayaartmuseum.or.jp/mguide/art_library.html + css_selector: '[document] > html.with_announce > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:44:03.232447+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 18 diff --git a/data/custodian/JP-13-SET-L-SCDL.yaml b/data/custodian/JP-13-SET-L-SCDL.yaml index a33a0bb8ae..2a0acff221 100644 --- a/data/custodian/JP-13-SET-L-SCDL.yaml +++ b/data/custodian/JP-13-SET-L-SCDL.yaml @@ -152,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:11.360640+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?23&pid=53 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?23&pid=53 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:44:11.360640+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCFL.yaml b/data/custodian/JP-13-SET-L-SCFL.yaml index d7dd2ae965..8faa2aeeb9 100644 --- a/data/custodian/JP-13-SET-L-SCFL.yaml +++ b/data/custodian/JP-13-SET-L-SCFL.yaml @@ -152,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:19.027648+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?32&pid=56 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?32&pid=56 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:44:19.027648+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCKKL.yaml b/data/custodian/JP-13-SET-L-SCKKL.yaml index 209b379eac..87e520ded1 100644 --- a/data/custodian/JP-13-SET-L-SCKKL.yaml +++ b/data/custodian/JP-13-SET-L-SCKKL.yaml @@ -152,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:26.622989+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?41&pid=59 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?41&pid=59 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:44:26.622989+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kamata_library.yaml b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kamata_library.yaml index 4f851410de..135ec4570e 100644 --- a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kamata_library.yaml +++ b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kamata_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCKL-setagaya_city_kamata_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCKL-setagaya_city_kamata_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCKL-setagaya_city_kamata_library ghcid_numeric: 11611036755799538964 valid_from: '2025-12-06T23:38:43.343181+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Kamata Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:34.078486+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?47&pid=61 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?47&pid=61 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:44:34.078486+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kasuya_library.yaml b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kasuya_library.yaml index 47e74cc383..adb13e34e7 100644 --- a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kasuya_library.yaml +++ b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kasuya_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCKL-setagaya_city_kasuya_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCKL-setagaya_city_kasuya_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCKL-setagaya_city_kasuya_library ghcid_numeric: 1189674514172546872 valid_from: '2025-12-06T23:38:43.340898+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Kasuya Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:42.077839+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?44&pid=60 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?44&pid=60 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:44:42.077839+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kinuta_library.yaml b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kinuta_library.yaml index 5865c4ae0b..36434c3f2e 100644 --- a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kinuta_library.yaml +++ b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kinuta_library.yaml @@ -152,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:50.064329+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?14&pid=50 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?14&pid=50 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:44:50.064329+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kyodo_library.yaml b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kyodo_library.yaml index 85a87af2d3..eef2d54723 100644 --- a/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kyodo_library.yaml +++ b/data/custodian/JP-13-SET-L-SCKL-setagaya_city_kyodo_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCKL-setagaya_city_kyodo_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCKL-setagaya_city_kyodo_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCKL-setagaya_city_kyodo_library ghcid_numeric: 8402956192719837365 valid_from: '2025-12-06T23:38:43.345518+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Kyodo Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:44:57.815254+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?50&pid=62 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?50&pid=62 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:44:57.815254+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCKL.yaml b/data/custodian/JP-13-SET-L-SCKL.yaml index 81b68c4df5..ec5dc9a3d6 100644 --- a/data/custodian/JP-13-SET-L-SCKL.yaml +++ b/data/custodian/JP-13-SET-L-SCKL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCKL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCKL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCKL ghcid_numeric: 6612880137196637133 valid_from: '2025-12-06T23:38:43.317547+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Karasuyama Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:05.525991+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?11&pid=54 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?11&pid=54 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:05.525991+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCL.yaml b/data/custodian/JP-13-SET-L-SCL.yaml index 1ee823d2e0..0b8bf6bae9 100644 --- a/data/custodian/JP-13-SET-L-SCL.yaml +++ b/data/custodian/JP-13-SET-L-SCL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCL ghcid_numeric: 12161919225210655082 valid_from: '2025-12-06T23:38:43.310826+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya Central Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:13.322161+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:13.322161+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCOL-setagaya_city_oyamadai_library.yaml b/data/custodian/JP-13-SET-L-SCOL-setagaya_city_oyamadai_library.yaml index 9de517d374..79f1cdd3b6 100644 --- a/data/custodian/JP-13-SET-L-SCOL-setagaya_city_oyamadai_library.yaml +++ b/data/custodian/JP-13-SET-L-SCOL-setagaya_city_oyamadai_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCOL-setagaya_city_oyamadai_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCOL-setagaya_city_oyamadai_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCOL-setagaya_city_oyamadai_library ghcid_numeric: 10879933023179782904 valid_from: '2025-12-06T23:38:43.329060+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Oyamadai Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:21.046692+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?26&pid=58 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?26&pid=58 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:21.046692+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCOL.yaml b/data/custodian/JP-13-SET-L-SCOL.yaml index a907d91cca..c0b3a21047 100644 --- a/data/custodian/JP-13-SET-L-SCOL.yaml +++ b/data/custodian/JP-13-SET-L-SCOL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCOL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCOL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCOL ghcid_numeric: 15345906940284007836 valid_from: '2025-12-06T23:38:43.315304+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Okusawa Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:28.868778+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?8&pid=51 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?8&pid=51 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:28.868778+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCSL-setagaya_city_sakuragaoka_library.yaml b/data/custodian/JP-13-SET-L-SCSL-setagaya_city_sakuragaoka_library.yaml index a41839cc2c..382e04f0d0 100644 --- a/data/custodian/JP-13-SET-L-SCSL-setagaya_city_sakuragaoka_library.yaml +++ b/data/custodian/JP-13-SET-L-SCSL-setagaya_city_sakuragaoka_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCSL-setagaya_city_sakuragaoka_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCSL-setagaya_city_sakuragaoka_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCSL-setagaya_city_sakuragaoka_library ghcid_numeric: 5978131453306953094 valid_from: '2025-12-06T23:38:43.336352+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Sakuragaoka Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:36.415195+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?36&pid=57 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?36&pid=57 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:36.415195+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCSL-setagaya_city_setagaya_library.yaml b/data/custodian/JP-13-SET-L-SCSL-setagaya_city_setagaya_library.yaml index b4b84ec096..d9a48840cc 100644 --- a/data/custodian/JP-13-SET-L-SCSL-setagaya_city_setagaya_library.yaml +++ b/data/custodian/JP-13-SET-L-SCSL-setagaya_city_setagaya_library.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCSL-setagaya_city_setagaya_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCSL-setagaya_city_setagaya_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCSL-setagaya_city_setagaya_library ghcid_numeric: 13710360339113365563 valid_from: '2025-12-06T23:38:43.324568+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Setagaya Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:44.093962+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?20&pid=49 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?20&pid=49 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:44.093962+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCSL.yaml b/data/custodian/JP-13-SET-L-SCSL.yaml index 3c6ddc5a41..293f8261a9 100644 --- a/data/custodian/JP-13-SET-L-SCSL.yaml +++ b/data/custodian/JP-13-SET-L-SCSL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCSL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCSL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCSL ghcid_numeric: 3463275462259453003 valid_from: '2025-12-06T23:38:43.322275+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Shimouma Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:51.871893+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?17&pid=55 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?17&pid=55 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:51.871893+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCTL.yaml b/data/custodian/JP-13-SET-L-SCTL.yaml index 04109697f7..f380a6603f 100644 --- a/data/custodian/JP-13-SET-L-SCTL.yaml +++ b/data/custodian/JP-13-SET-L-SCTL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCTL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCTL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCTL ghcid_numeric: 7897687334392585283 valid_from: '2025-12-06T23:38:43.331320+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Tamagawadai Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:45:59.610463+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?29&pid=52 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?29&pid=52 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:45:59.610463+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SCUL.yaml b/data/custodian/JP-13-SET-L-SCUL.yaml index d1073ff7b2..12897e2068 100644 --- a/data/custodian/JP-13-SET-L-SCUL.yaml +++ b/data/custodian/JP-13-SET-L-SCUL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SCUL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SCUL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SCUL ghcid_numeric: 8062141404116141805 valid_from: '2025-12-06T23:38:43.313064+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Setagaya City Umegaoka Library @@ -151,3 +152,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:46:07.197302+00:00' + source_url: https://libweb.city.setagaya.tokyo.jp/contents?5&pid=48 + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: https://libweb.city.setagaya.tokyo.jp/images/ogimage.png + source_url: https://libweb.city.setagaya.tokyo.jp/contents?5&pid=48 + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:46:07.197302+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-SFSBL.yaml b/data/custodian/JP-13-SET-L-SFSBL.yaml index 184c4ea572..e0f4bf75a6 100644 --- a/data/custodian/JP-13-SET-L-SFSBL.yaml +++ b/data/custodian/JP-13-SET-L-SFSBL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SFSBL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SFSBL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SFSBL ghcid_numeric: 1693632209564121338 valid_from: '2025-12-06T23:38:58.808895+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SEIKADO FOUNDATION SEIKADO BUNKO LIBRARY @@ -151,3 +152,36 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:53:03.735323+00:00' + source_url: http://www.seikado.or.jp/about/seikadoubunko.html + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.seikado.or.jp/file/wp-content/themes/seikado/images/common/x_logo.svg + source_url: http://www.seikado.or.jp/about/seikadoubunko.html + css_selector: '#sns-iconlist > li > a > noscript > img' + retrieved_on: '2025-12-25T19:53:03.735323+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: X@静嘉堂文庫美術館 + - claim_type: favicon_url + claim_value: https://www.seikado.or.jp/file/wp-content/uploads/2022/06/cropped-favicon-180x180.png + source_url: http://www.seikado.or.jp/about/seikadoubunko.html + css_selector: '[document] > html > head > link:nth-of-type(19)' + retrieved_on: '2025-12-25T19:53:03.735323+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.seikado.or.jp/file/wp-content/uploads/2024/08/ogp_img.jpg + source_url: http://www.seikado.or.jp/about/seikadoubunko.html + css_selector: '[document] > html > head > meta:nth-of-type(11)' + retrieved_on: '2025-12-25T19:53:03.735323+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 3 + has_primary_logo: true + has_favicon: true + has_og_image: true + favicon_count: 3 diff --git a/data/custodian/JP-13-SET-L-SL.yaml b/data/custodian/JP-13-SET-L-SL.yaml index fe3ce19fc4..35bd2be93b 100644 --- a/data/custodian/JP-13-SET-L-SL.yaml +++ b/data/custodian/JP-13-SET-L-SL.yaml @@ -216,3 +216,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:53:08.631066+00:00' + source_url: http://www.sanno.ac.jp/univ/library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.sanno.ac.jp/favicon.ico + source_url: http://www.sanno.ac.jp/univ/library/index.html + css_selector: '[document] > html > head > link:nth-of-type(7)' + retrieved_on: '2025-12-25T19:53:08.631066+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.sanno.ac.jp/img/common/sanno_emblem.png + source_url: http://www.sanno.ac.jp/univ/library/index.html + css_selector: '[document] > html > head > meta:nth-of-type(19)' + retrieved_on: '2025-12-25T19:53:08.631066+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-L-SUL.yaml b/data/custodian/JP-13-SET-L-SUL.yaml index ee35fab3cb..2f7f68109a 100644 --- a/data/custodian/JP-13-SET-L-SUL.yaml +++ b/data/custodian/JP-13-SET-L-SUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-SUL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-SUL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-SUL ghcid_numeric: 2058663733041157894 valid_from: '2025-12-06T23:38:54.909463+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: Seijo University Library @@ -190,7 +191,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://www.lib.seijo.ac.jp/ wikidata_official_website: http://www.lib.seijo.ac.jp/ @@ -212,3 +214,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:53:17.319646+00:00' + source_url: http://www.lib.seijo.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.lib.seijo.ac.jp/assets/img/apple-touch-icon.png + source_url: http://www.lib.seijo.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:53:17.319646+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.lib.seijo.ac.jp/assets/img/ogp.jpg + source_url: http://www.lib.seijo.ac.jp + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T19:53:17.319646+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library.yaml b/data/custodian/JP-13-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library.yaml index e90bd0630c..4dc68c9169 100644 --- a/data/custodian/JP-13-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library.yaml +++ b/data/custodian/JP-13-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-TL-tokyoiryohokendaigakufuzokusetagaya_library ghcid_numeric: 6826116227899113659 valid_from: '2025-12-06T23:38:55.439803+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: TOKYOIRYOHOKENDAIGAKUFUZOKUSETAGAYA Library @@ -215,3 +216,20 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:53:35.435282+00:00' + source_url: http://www.thcu.ac.jp/facilities/library + extraction_method: crawl4ai + claims: + - claim_type: og_image_url + claim_value: http://thcu.ac.jp/img/asset/ogp.png + source_url: http://www.thcu.ac.jp/facilities/library + css_selector: '[document] > html.other > head > meta:nth-of-type(9)' + retrieved_on: '2025-12-25T19:53:35.435282+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: false + has_og_image: true + favicon_count: 0 diff --git a/data/custodian/JP-13-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library.yaml b/data/custodian/JP-13-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library.yaml index 1c787bc84a..108c1d2720 100644 --- a/data/custodian/JP-13-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library.yaml +++ b/data/custodian/JP-13-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-TL-tokyotoshidaigakutodorokikyampasu_library ghcid_numeric: 16172791521318400936 valid_from: '2025-12-06T23:38:55.281351+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: TOKYOTOSHIDAIGAKUTODOROKIKYAMPASU Library @@ -204,3 +205,22 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:54:28.315974+00:00' + source_url: http://library.tcu.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.lib.tcu.ac.jp/iwjs0017opc/image/favicon.ico + source_url: http://library.tcu.ac.jp + css_selector: '[document] > html.ng-scope > head > link' + retrieved_on: '2025-12-25T19:54:28.315974+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-L-TL.yaml b/data/custodian/JP-13-SET-L-TL.yaml index c5231a2018..20c364635a 100644 --- a/data/custodian/JP-13-SET-L-TL.yaml +++ b/data/custodian/JP-13-SET-L-TL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-TL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-TL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-TL ghcid_numeric: 16772289228179276339 valid_from: '2025-12-06T23:38:55.020147+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: TAMABIJUTSUDAIGAKUKAMINOGE Library @@ -204,3 +205,22 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:54:23.833952+00:00' + source_url: http://library.tamabi.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://library.tamabi.ac.jp/opac/images/cyan/favicon.ico + source_url: http://library.tamabi.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T19:54:23.833952+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-L-TMIMS.yaml b/data/custodian/JP-13-SET-L-TMIMS.yaml index 866a2b8eb6..3bbbdd6b26 100644 --- a/data/custodian/JP-13-SET-L-TMIMS.yaml +++ b/data/custodian/JP-13-SET-L-TMIMS.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-L-TMIMS - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-L-TMIMS valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-L-TMIMS ghcid_numeric: 3998176758240669179 valid_from: '2025-12-06T23:38:58.334016+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Tokyo Metropolitan Institute of Medical Science @@ -151,3 +152,22 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:54:31.554886+00:00' + source_url: http://www.igakuken.or.jp/center/basic/library.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.igakuken.or.jp/images/apple-touch-icon-180x180.png + source_url: http://www.igakuken.or.jp/center/basic/library.html + css_selector: '[document] > html > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:54:31.554886+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-13-SET-M-FAMTUA.yaml b/data/custodian/JP-13-SET-M-FAMTUA.yaml index 6283baa177..ca0ec0385d 100644 --- a/data/custodian/JP-13-SET-M-FAMTUA.yaml +++ b/data/custodian/JP-13-SET-M-FAMTUA.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-M-FAMTUA - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-M-FAMTUA valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-M-FAMTUA ghcid_numeric: 1176392430464467487 valid_from: '2025-12-06T23:38:33.379327+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Food and Agriculture Museum Tokyo University of Agriculture @@ -151,3 +152,22 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:55:12.791152+00:00' + source_url: https://www.nodai.ac.jp/campus/facilities/syokutonou + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.nodai.ac.jp/application/files/4014/8211/2652/favicon.ico + source_url: https://www.nodai.ac.jp/campus/facilities/syokutonou + css_selector: '[document] > html.js > head > link' + retrieved_on: '2025-12-25T19:55:12.791152+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-M-GM.yaml b/data/custodian/JP-13-SET-M-GM.yaml index 824684c5fb..30a23901fd 100644 --- a/data/custodian/JP-13-SET-M-GM.yaml +++ b/data/custodian/JP-13-SET-M-GM.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-M-GM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-M-GM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-M-GM ghcid_numeric: 590083106792168153 valid_from: '2025-12-06T23:38:33.381672+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: THE GOTOH MUSEUM @@ -242,7 +243,8 @@ wikidata_enrichment: instance_of: &id005 - id: Q207694 label: art museum - description: building or space for the exhibition of art (for institution, use Q3196771) + description: building or space for the exhibition of art (for institution, use + Q3196771) wikidata_instance_of: *id005 wikidata_location: coordinates: &id008 @@ -305,3 +307,28 @@ location: postal_code: 158-8510 street_address: KAMINOGE, Setagaya Ku, Tokyo To, 158-8510 normalization_timestamp: '2025-12-09T12:22:14.817638+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:55:29.059263+00:00' + source_url: https://www.gotoh-museum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.gotoh-museum.or.jp/wp-content/uploads/2020/06/icon_logo.png + source_url: https://www.gotoh-museum.or.jp + css_selector: '[document] > html > head > link:nth-of-type(25)' + retrieved_on: '2025-12-25T19:55:29.059263+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 32x32 + - claim_type: og_image_url + claim_value: https://www.gotoh-museum.or.jp/wp-content/uploads/2020/06/logo.svg + source_url: https://www.gotoh-museum.or.jp + css_selector: '[document] > html > head > meta:nth-of-type(14)' + retrieved_on: '2025-12-25T19:55:29.059263+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-M-HMAM.yaml b/data/custodian/JP-13-SET-M-HMAM.yaml index a1d63491db..489305892e 100644 --- a/data/custodian/JP-13-SET-M-HMAM.yaml +++ b/data/custodian/JP-13-SET-M-HMAM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-M-HMAM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-M-HMAM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-M-HMAM ghcid_numeric: 7470883532751537106 valid_from: '2025-12-06T23:38:33.348490+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: HASEGAWA MACHIKO ART MUSEUM @@ -151,3 +152,23 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:55:36.471950+00:00' + source_url: https://www.hasegawamachiko.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.hasegawamachiko.jp/wp-content/uploads/2020/07/favicon.png + source_url: https://www.hasegawamachiko.jp + css_selector: '[document] > html.wf-tbudrgothic-std-n4-active.wf-tbudrgothic-std-n7-active + > head > link:nth-of-type(17)' + retrieved_on: '2025-12-25T19:55:36.471950+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 192x192 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SET-M-JPSOFHG.yaml b/data/custodian/JP-13-SET-M-JPSOFHG.yaml index ae94fa209d..bd3c317305 100644 --- a/data/custodian/JP-13-SET-M-JPSOFHG.yaml +++ b/data/custodian/JP-13-SET-M-JPSOFHG.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:55:49.716331+00:00' + source_url: https://www.city.setagaya.lg.jp/theme/kanko/003/003/d00122208.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.setagaya.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.setagaya.lg.jp/theme/kanko/003/003/d00122208.html + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T19:55:49.716331+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.setagaya.lg.jp/shared/images/sns/logo.jpg + source_url: https://www.city.setagaya.lg.jp/theme/kanko/003/003/d00122208.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T19:55:49.716331+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SET-M-KARC.yaml b/data/custodian/JP-13-SET-M-KARC.yaml index 22734a4f02..dd6c9cb5d1 100644 --- a/data/custodian/JP-13-SET-M-KARC.yaml +++ b/data/custodian/JP-13-SET-M-KARC.yaml @@ -39,13 +39,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-M-KARC - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-M-KARC valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-M-KARC ghcid_numeric: 2607452473711122013 valid_from: '2025-12-06T23:38:33.361154+00:00' @@ -103,8 +104,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: KAGAWA ARCHIVES & RESOURCE CENTER @@ -175,8 +176,8 @@ wikidata_enrichment: instance_of: &id004 - id: Q33506 label: museum - description: institution that holds artifacts and other objects of scientific, artistic, cultural, historical, or other - importance + description: institution that holds artifacts and other objects of scientific, + artistic, cultural, historical, or other importance wikidata_instance_of: *id004 wikidata_location: coordinates: &id007 @@ -218,3 +219,28 @@ location: postal_code: 156-0057 street_address: KAMIKITAZAWA, Setagaya Ku, Tokyo To, 156-0057 normalization_timestamp: '2025-12-09T12:22:14.926891+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:55:55.572494+00:00' + source_url: https://www.t-kagawa.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://cdn.prod.website-files.com/611355694ea5a53302a00def/612254435c8d9757b8e001be_clip.png + source_url: https://www.t-kagawa.or.jp + css_selector: '[document] > html.w-mod-js.w-mod-ix > head > link:nth-of-type(6)' + retrieved_on: '2025-12-25T19:55:55.572494+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://cdn.prod.website-files.com/5c6eb5400253230156de2bd6/5cdc268dd7274d5c05c6009a_Business%20SEO.jpg + source_url: https://www.t-kagawa.or.jp + css_selector: '[document] > html.w-mod-js.w-mod-ix > head > meta:nth-of-type(3)' + retrieved_on: '2025-12-25T19:55:55.572494+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SET-M-MZCHKU.yaml b/data/custodian/JP-13-SET-M-MZCHKU.yaml index 08cc7f858c..d9a7744d36 100644 --- a/data/custodian/JP-13-SET-M-MZCHKU.yaml +++ b/data/custodian/JP-13-SET-M-MZCHKU.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-M-MZCHKU - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-M-MZCHKU valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-M-MZCHKU ghcid_numeric: 4012341132944545744 valid_from: '2025-12-06T23:38:33.353553+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: THE MUSEUM OF ZEN CULTURE AND HISTORY, KOMAZAWA UNIVERSITY @@ -151,3 +152,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:56:10.024437+00:00' + source_url: https://www.komazawa-u.ac.jp/facilities/museum + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.komazawa-u.ac.jp/favicon.ico + source_url: https://www.komazawa-u.ac.jp/facilities/museum + css_selector: '[document] > html > head > link' + retrieved_on: '2025-12-25T19:56:10.024437+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.komazawa-u.ac.jp/img/fb_ogp.png + source_url: https://www.komazawa-u.ac.jp/facilities/museum + css_selector: '[document] > html > head > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T19:56:10.024437+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 1 diff --git a/data/custodian/JP-13-SET-M-OPSOFHG.yaml b/data/custodian/JP-13-SET-M-OPSOFHG.yaml index ecf01fbc8d..a16aec110b 100644 --- a/data/custodian/JP-13-SET-M-OPSOFHG.yaml +++ b/data/custodian/JP-13-SET-M-OPSOFHG.yaml @@ -152,3 +152,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:56:50.461789+00:00' + source_url: https://www.city.setagaya.lg.jp/mokuji/kusei/012/011/002/d00122210.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.setagaya.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.setagaya.lg.jp/mokuji/kusei/012/011/002/d00122210.html + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T19:56:50.461789+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.setagaya.lg.jp/shared/images/sns/logo.jpg + source_url: https://www.city.setagaya.lg.jp/mokuji/kusei/012/011/002/d00122210.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T19:56:50.461789+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SET-M-SAM.yaml b/data/custodian/JP-13-SET-M-SAM.yaml index 41a891ce43..8709ccf693 100644 --- a/data/custodian/JP-13-SET-M-SAM.yaml +++ b/data/custodian/JP-13-SET-M-SAM.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-M-SAM - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-M-SAM valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-M-SAM ghcid_numeric: 17189518824705329164 valid_from: '2025-12-06T23:38:33.372197+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SETAGAYA ART MUSEUM @@ -151,3 +152,28 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:56:58.708875+00:00' + source_url: https://www.setagayaartmuseum.or.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.setagayaartmuseum.or.jp/cmn/favicon/apple-touch-icon-180x180.png + source_url: https://www.setagayaartmuseum.or.jp + css_selector: '[document] > html.with_announce > head > link:nth-of-type(16)' + retrieved_on: '2025-12-25T19:56:58.708875+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + - claim_type: og_image_url + claim_value: http://www.setagayaartmuseum.or.jp/cmn/img/icn_sns_noimg.png + source_url: https://www.setagayaartmuseum.or.jp + css_selector: '[document] > html.with_announce > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T19:56:58.708875+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 18 diff --git a/data/custodian/JP-13-SET-M-SM.yaml b/data/custodian/JP-13-SET-M-SM.yaml index d5e4010409..b14c0d1b36 100644 --- a/data/custodian/JP-13-SET-M-SM.yaml +++ b/data/custodian/JP-13-SET-M-SM.yaml @@ -152,3 +152,22 @@ location: geonames_id: 11790342 geonames_name: Setagaya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:57:13.497569+00:00' + source_url: https://saita-museum.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://saita-museum.jp/mente/wp-content/themes/saitamuseum/apple-touch-icon.png + source_url: https://saita-museum.jp + css_selector: '[document] > html.no-js.no-svg > head > link:nth-of-type(3)' + retrieved_on: '2025-12-25T19:57:13.497569+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: 180x180 + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 2 diff --git a/data/custodian/JP-13-SET-M-SMH.yaml b/data/custodian/JP-13-SET-M-SMH.yaml index 5efc608e4c..846edb68e8 100644 --- a/data/custodian/JP-13-SET-M-SMH.yaml +++ b/data/custodian/JP-13-SET-M-SMH.yaml @@ -43,13 +43,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SET-M-SMH - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SET-M-SMH valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SET-M-SMH ghcid_numeric: 12514971727675477489 valid_from: '2025-12-06T23:38:33.350861+00:00' @@ -108,8 +109,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: SETAGAYA MUSEUM OF HISTORY @@ -263,3 +264,28 @@ location: postal_code: 154-0017 street_address: SETAGAYA, Setagaya Ku, Tokyo To, 154-0017 normalization_timestamp: '2025-12-09T12:22:15.161173+00:00' +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:57:22.111801+00:00' + source_url: https://www.city.setagaya.lg.jp/mokuji/kusei/012/011/002/d00138265.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.city.setagaya.lg.jp/shared/images/favicon/apple-touch-icon-precomposed.png + source_url: https://www.city.setagaya.lg.jp/mokuji/kusei/012/011/002/d00138265.html + css_selector: '[document] > html > head > link:nth-of-type(9)' + retrieved_on: '2025-12-25T19:57:22.111801+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.city.setagaya.lg.jp/shared/images/sns/logo.jpg + source_url: https://www.city.setagaya.lg.jp/mokuji/kusei/012/011/002/d00138265.html + css_selector: '[document] > html > head > meta:nth-of-type(6)' + retrieved_on: '2025-12-25T19:57:22.111801+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 2 diff --git a/data/custodian/JP-13-SHI-L-A.yaml b/data/custodian/JP-13-SHI-L-A.yaml index 0d0f3535b2..c5a5002d5e 100644 --- a/data/custodian/JP-13-SHI-L-A.yaml +++ b/data/custodian/JP-13-SHI-L-A.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-A - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-A valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-A ghcid_numeric: 12203761144736089892 valid_from: '2025-12-06T23:38:49.671365+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ASAHIMACHIGOKASHOKOMINKANTOSHOSHITSU @@ -153,3 +154,22 @@ location: geonames_id: 2113077 geonames_name: Asahi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:58:15.684283+00:00' + source_url: https://www.tkc.pref.toyama.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://www.tkc.pref.toyama.jp/design/img/idx/h_logo_sp.png + source_url: https://www.tkc.pref.toyama.jp + css_selector: '#sp_header > h1.hsp_logo > a > img' + retrieved_on: '2025-12-25T19:58:15.684283+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: とやま学遊ネット + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-AGWSJCL.yaml b/data/custodian/JP-13-SHI-L-AGWSJCL.yaml index 766b2a5e12..b3baa4da2b 100644 --- a/data/custodian/JP-13-SHI-L-AGWSJCL.yaml +++ b/data/custodian/JP-13-SHI-L-AGWSJCL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-AGWSJCL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-AGWSJCL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-AGWSJCL ghcid_numeric: 6323242321569265983 valid_from: '2025-12-06T23:38:56.937162+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: Aoyama Gakuin Women's Junior College Library @@ -204,3 +205,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:59:12.485652+00:00' + source_url: https://www.agulin.aoyama.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://opac.agulin.aoyama.ac.jp/iwjs0011opc/image/favicon.ico + source_url: https://www.agulin.aoyama.ac.jp + css_selector: '[document] > html.ng-scope > head > link' + retrieved_on: '2025-12-25T19:59:12.485652+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/x-icon + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 1 diff --git a/data/custodian/JP-13-SHI-L-AL.yaml b/data/custodian/JP-13-SHI-L-AL.yaml index 94a93a3e91..57c543bea9 100644 --- a/data/custodian/JP-13-SHI-L-AL.yaml +++ b/data/custodian/JP-13-SHI-L-AL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-AL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-AL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-AL ghcid_numeric: 10452760347509425425 valid_from: '2025-12-06T23:38:44.476711+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: ASAHIMACHI Library @@ -153,3 +154,23 @@ location: geonames_id: 2113077 geonames_name: Asahi feature_code: PPLA2 +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:59:31.574391+00:00' + source_url: https://lib.town.asahi.toyama.jp + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: https://lib.town.asahi.toyama.jp/common/img/gl/logo.png + source_url: https://lib.town.asahi.toyama.jp + css_selector: '[document] > html > body > header.global > div.container > h1 > + a > img' + retrieved_on: '2025-12-25T19:59:31.574391+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 富山県 朝日町図書館 + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-APCCUAL.yaml b/data/custodian/JP-13-SHI-L-APCCUAL.yaml index 1912818d39..81c278c8ea 100644 --- a/data/custodian/JP-13-SHI-L-APCCUAL.yaml +++ b/data/custodian/JP-13-SHI-L-APCCUAL.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-APCCUAL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-APCCUAL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-APCCUAL ghcid_numeric: 1728153617216972199 valid_from: '2025-12-06T23:38:58.976484+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: Asia-Pacific Cultural Centre for UNESCO ACCU Library @@ -151,3 +152,23 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:59:44.673984+00:00' + source_url: http://www.accu.or.jp/jp/accu_library/index.html + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://www.accu.or.jp/cms/wp-content/themes/unesco/assets/images/common/apple-touch-icon.png + source_url: http://www.accu.or.jp/jp/accu_library/index.html + css_selector: '[document] > html.wf-semplicitapro-n4-active.wf-semplicitapro-n6-active + > head > link:nth-of-type(2)' + retrieved_on: '2025-12-25T19:59:44.673984+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 5 diff --git a/data/custodian/JP-13-SHI-L-BGUL.yaml b/data/custodian/JP-13-SHI-L-BGUL.yaml index 88974b44f0..a076c65183 100644 --- a/data/custodian/JP-13-SHI-L-BGUL.yaml +++ b/data/custodian/JP-13-SHI-L-BGUL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-BGUL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-BGUL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-BGUL ghcid_numeric: 2787001745472101139 valid_from: '2025-12-06T23:38:55.209306+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: Bunka Gakuen University Library @@ -190,7 +191,8 @@ wikidata_enrichment: description: organisatie uit Japan - id: Q56056912 label: Japan Consortium for Open Access Repository - description: promotes open access and open science in Japan with knowledge dissemination via digital repositories + description: promotes open access and open science in Japan with knowledge dissemination + via digital repositories wikidata_web: official_website: http://lib.bunka.ac.jp/ wikidata_official_website: http://lib.bunka.ac.jp/ @@ -212,3 +214,22 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T19:59:58.705823+00:00' + source_url: http://lib.bunka.ac.jp + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: https://lib.bunka.ac.jp/web_admin/wp-content/uploads/2022/06/cropped-favicon-180x180.png + source_url: http://lib.bunka.ac.jp + css_selector: '[document] > html > head > link:nth-of-type(8)' + retrieved_on: '2025-12-25T19:59:58.705823+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + summary: + total_claims: 1 + has_primary_logo: false + has_favicon: true + has_og_image: false + favicon_count: 3 diff --git a/data/custodian/JP-13-SHI-L-BMFJINF.yaml b/data/custodian/JP-13-SHI-L-BMFJINF.yaml index 1205af691b..1ae5d1e0c4 100644 --- a/data/custodian/JP-13-SHI-L-BMFJINF.yaml +++ b/data/custodian/JP-13-SHI-L-BMFJINF.yaml @@ -32,13 +32,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-BMFJINF - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-BMFJINF valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-BMFJINF ghcid_numeric: 6536865378927706048 valid_from: '2025-12-06T23:38:57.883273+00:00' @@ -96,8 +97,8 @@ ch_annotator: annotation_metadata: confidence_score: 0.98 verified: false - verification_date: - verified_by: + verification_date: null + verified_by: null entity_claims: - claim_type: full_name claim_value: BIBLIOTHEQUE DE LA MAISON FRANCO-JAPONAISE　（Institution name in French） @@ -151,3 +152,28 @@ location: geonames_id: 11808021 geonames_name: Shibuya feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:00:05.685088+00:00' + source_url: http://www.mfj.gr.jp/bibliotheque/presentation/index_ja.php + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.mfj.gr.jp/assets/favicon/favicon.svg + source_url: http://www.mfj.gr.jp/bibliotheque/presentation/index_ja.php + css_selector: '[document] > html > head > link:nth-of-type(5)' + retrieved_on: '2025-12-25T20:00:05.685088+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: image/svg+xml + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.mfj.gr.jp/assets/images/share-og.png + source_url: http://www.mfj.gr.jp/bibliotheque/presentation/index_ja.php + css_selector: '[document] > html > head > meta:nth-of-type(8)' + retrieved_on: '2025-12-25T20:00:05.685088+00:00' + extraction_method: crawl4ai_meta_og + summary: + total_claims: 2 + has_primary_logo: false + has_favicon: true + has_og_image: true + favicon_count: 4 diff --git a/data/custodian/JP-13-SHI-L-CIMOL.yaml b/data/custodian/JP-13-SHI-L-CIMOL.yaml index 725c96e25c..45bd9f1d28 100644 --- a/data/custodian/JP-13-SHI-L-CIMOL.yaml +++ b/data/custodian/JP-13-SHI-L-CIMOL.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-CIMOL - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-CIMOL valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-CIMOL ghcid_numeric: 10829657522271008240 valid_from: '2025-12-06T23:38:55.320482+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: Center for Information and Media Osaki Library @@ -204,3 +205,22 @@ location: geonames_id: 1852139 geonames_name: Shinagawa feature_code: PPL +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:00:19.578313+00:00' + source_url: http://www.ris.ac.jp/library + extraction_method: crawl4ai + claims: + - claim_type: logo_url + claim_value: http://www.ris.ac.jp/WSR/logo.png + source_url: http://www.ris.ac.jp/library + css_selector: '[document] > html > body > header > div.inner > h1 > a > img' + retrieved_on: '2025-12-25T20:00:19.578313+00:00' + extraction_method: crawl4ai_header_logo + detection_confidence: high + alt_text: 立正大学図書館サイト + summary: + total_claims: 1 + has_primary_logo: true + has_favicon: false + has_og_image: false + favicon_count: 0 diff --git a/data/custodian/JP-13-SHI-L-DHT.yaml b/data/custodian/JP-13-SHI-L-DHT.yaml index e73b7e62d4..9cf060f10f 100644 --- a/data/custodian/JP-13-SHI-L-DHT.yaml +++ b/data/custodian/JP-13-SHI-L-DHT.yaml @@ -37,13 +37,14 @@ ghcid: method: CH_ANNOTATOR_SOURCE ghcid_history: - ghcid: JP-13-SHI-L-DHT - valid_from: "2025-12-10T09:44:11Z" + valid_from: '2025-12-10T09:44:11Z' valid_to: null - reason: "Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO 3166-2:JP" + reason: Corrected region code from JP-TO (abbreviation) to JP-13 (Tokyo) per ISO + 3166-2:JP - ghcid: JP-TO-SHI-L-DHT valid_from: null - valid_to: "2025-12-10T09:44:11Z" - reason: "Previous GHCID with incorrect region code" + valid_to: '2025-12-10T09:44:11Z' + reason: Previous GHCID with incorrect region code - ghcid: JP-TO-SHI-L-DHT ghcid_numeric: 13281966420962438079 valid_from: '2025-12-06T23:38:55.004842+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: DAITOBUNKADAIGAKUDAIGAKUINHOMUKENKYUKA(HOKADAIGAKUIN)TOSHOSHITSU @@ -204,3 +205,28 @@ location: geonames_id: 11790353 geonames_name: Shinjuku feature_code: PPLX +logo_enrichment: + enrichment_timestamp: '2025-12-25T20:00:37.233730+00:00' + source_url: http://www.daito.ac.jp/lawschool/lawlibrary + extraction_method: crawl4ai + claims: + - claim_type: favicon_url + claim_value: http://www.daito.ac.jp/education/graduate_school/assets/img/apple-touch-icon.png + source_url: http://www.daito.ac.jp/lawschool/lawlibrary + css_selector: '[document] > html > body > link:nth-of-type(2)' + retrieved_on: '2025-12-25T20:00:37.233730+00:00' + extraction_method: crawl4ai_link_rel + favicon_type: '' + favicon_sizes: '' + - claim_type: og_image_url + claim_value: https://www.daito.ac.jp/assets/img/img_logo_ogp.jpg + source_url: http://www.daito.ac.jp/lawschool/lawlibrary + css_selector: '[document] > html > body > meta:nth-of-type(10)' + retrieved_on: '2025-12-25T20:00:37.233730+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