Item archiveteam_archivebot_go_20260408005238_47d54401

Filename	Size
akronartmuseum.org-inf-20260407-150912-wbz4a-00004.warc.gz	5410248223	download job
akronartmuseum.org-inf-20260407-150912-wbz4a-00004.warc.os.cdx.gz	1078770	download
archivesfoundation.org-inf-20260408-004006-4qxaq-00000.warc.gz	19154	download job
archivesfoundation.org-inf-20260408-004006-4qxaq-00000.warc.os.cdx.gz	388	download
archivesfoundation.org-inf-20260408-004006-4qxaq-meta.warc.gz	3525	download job
archivesfoundation.org-inf-20260408-004006-4qxaq-meta.warc.os.cdx.gz	47	download
archivesfoundation.org-inf-20260408-004006-4qxaq.json	253	download job
archiveteam_archivebot_go_20260408005238_47d54401.cdx.gz	27755786	download
archiveteam_archivebot_go_20260408005238_47d54401.cdx.idx	27705	download
archiveteam_archivebot_go_20260408005238_47d54401_files.xml	0	download
archiveteam_archivebot_go_20260408005238_47d54401_meta.sqlite	143360	download
archiveteam_archivebot_go_20260408005238_47d54401_meta.xml	1047	download
blog.archivesfoundation.org-inf-20260408-003756-7z9s5-00000.warc.gz	10665	download job
blog.archivesfoundation.org-inf-20260408-003756-7z9s5-00000.warc.os.cdx.gz	349	download
blog.archivesfoundation.org-inf-20260408-003756-7z9s5-meta.warc.gz	3582	download job
blog.archivesfoundation.org-inf-20260408-003756-7z9s5-meta.warc.os.cdx.gz	47	download
blog.archivesfoundation.org-inf-20260408-003756-7z9s5.json	258	download job
boardofpeace.org-inf-20260408-002437-5vxwl-00000.warc.gz	107467691	download job
boardofpeace.org-inf-20260408-002437-5vxwl-00000.warc.os.cdx.gz	72664	download
boardofpeace.org-inf-20260408-002437-5vxwl-meta.warc.gz	57479	download job
boardofpeace.org-inf-20260408-002437-5vxwl-meta.warc.os.cdx.gz	47	download
boardofpeace.org-inf-20260408-002437-5vxwl.json	247	download job
boardofpeace.org-inf-20260408-002506-b2gg6-00000.warc.gz	105232332	download job
boardofpeace.org-inf-20260408-002506-b2gg6-00000.warc.os.cdx.gz	68379	download
boardofpeace.org-inf-20260408-002506-b2gg6-meta.warc.gz	55584	download job
boardofpeace.org-inf-20260408-002506-b2gg6-meta.warc.os.cdx.gz	47	download
boardofpeace.org-inf-20260408-002506-b2gg6.json	249	download job
developer.nvidia.com-inf-20260401-145920-ej5mh-00164.warc.gz	5370531221	download job
developer.nvidia.com-inf-20260401-145920-ej5mh-00164.warc.os.cdx.gz	1840454	download
folieapleasures.wordpress.com-inf-20260404-044634-ddk9q-00015.warc.gz	5368723505	download job
folieapleasures.wordpress.com-inf-20260404-044634-ddk9q-00015.warc.os.cdx.gz	6136288	download
foto.patriarchia.ru-inf-20260406-025907-d1vgb-00057.warc.gz	5396459772	download job
foto.patriarchia.ru-inf-20260406-025907-d1vgb-00057.warc.os.cdx.gz	92467	download
info.archivesfoundation.org-shallow-20260408-003724-9g1fj-00000.warc.gz	7031	download job
info.archivesfoundation.org-shallow-20260408-003724-9g1fj-00000.warc.os.cdx.gz	227	download
info.archivesfoundation.org-shallow-20260408-003724-9g1fj-meta.warc.gz	3484	download job
info.archivesfoundation.org-shallow-20260408-003724-9g1fj-meta.warc.os.cdx.gz	47	download
info.archivesfoundation.org-shallow-20260408-003724-9g1fj.json	262	download job
knowunity.co.uk-inf-20260406-144715-eezzf-00016.warc.gz	5369030302	download job
knowunity.co.uk-inf-20260406-144715-eezzf-00016.warc.os.cdx.gz	1318578	download
nowiny24.pl-inf-20260310-123849-19bim-00184.warc.gz	5368909274	download job
nowiny24.pl-inf-20260310-123849-19bim-00184.warc.os.cdx.gz	2812834	download
planeta.ge-inf-20260328-135947-cqxeu-00020.warc.gz	5375433587	download job
planeta.ge-inf-20260328-135947-cqxeu-00020.warc.os.cdx.gz	6007100	download
portal.cardplayer.com-inf-20260407-234239-4lkvu-00000.warc.gz	162166723	download job
portal.cardplayer.com-inf-20260407-234239-4lkvu-00000.warc.os.cdx.gz	649010	download
portal.cardplayer.com-inf-20260407-234239-4lkvu-meta.warc.gz	280604	download job
portal.cardplayer.com-inf-20260407-234239-4lkvu-meta.warc.os.cdx.gz	47	download
portal.cardplayer.com-inf-20260407-234239-4lkvu.json	246	download job
smileysmile.net-inf-20260329-153732-7gh56-00070.warc.gz	5457205817	download job
smileysmile.net-inf-20260329-153732-7gh56-00070.warc.os.cdx.gz	9723	download
smileysmile.net-inf-20260329-153732-7gh56-00071.warc.gz	5574748522	download job
smileysmile.net-inf-20260329-153732-7gh56-00071.warc.os.cdx.gz	12013	download
smileysmile.net-inf-20260329-153732-7gh56-00072.warc.gz	5520602659	download job
smileysmile.net-inf-20260329-153732-7gh56-00072.warc.os.cdx.gz	13958	download
tehranpodcast.ir-inf-20260407-191953-730zl-00018.warc.gz	5386781653	download job
tehranpodcast.ir-inf-20260407-191953-730zl-00018.warc.os.cdx.gz	132577	download
tehranpodcast.ir-inf-20260407-191953-730zl-00019.warc.gz	5373376948	download job
tehranpodcast.ir-inf-20260407-191953-730zl-00019.warc.os.cdx.gz	119752	download
tehranpodcast.ir-inf-20260407-191953-730zl-00020.warc.gz	5405808332	download job
tehranpodcast.ir-inf-20260407-191953-730zl-00020.warc.os.cdx.gz	61225	download
text.archivesfoundation.org-inf-20260408-003752-9s7ys-00000.warc.gz	287405	download job
text.archivesfoundation.org-inf-20260408-003752-9s7ys-00000.warc.os.cdx.gz	5479	download
text.archivesfoundation.org-inf-20260408-003752-9s7ys-meta.warc.gz	7707	download job
text.archivesfoundation.org-inf-20260408-003752-9s7ys-meta.warc.os.cdx.gz	47	download
text.archivesfoundation.org-inf-20260408-003752-9s7ys.json	258	download job
thecage.co-inf-20260406-120018-7qbiu-00138.warc.gz	5383190330	download job
thecage.co-inf-20260406-120018-7qbiu-00138.warc.os.cdx.gz	79397	download
thecage.co-inf-20260406-120018-7qbiu-00139.warc.gz	5373075574	download job
thecage.co-inf-20260406-120018-7qbiu-00139.warc.os.cdx.gz	125088	download
training.esports-news.co.uk-inf-20260407-233738-97erl-00000.warc.gz	856633767	download job
training.esports-news.co.uk-inf-20260407-233738-97erl-00000.warc.os.cdx.gz	733607	download
training.esports-news.co.uk-inf-20260407-233738-97erl-meta.warc.gz	461641	download job
training.esports-news.co.uk-inf-20260407-233738-97erl-meta.warc.os.cdx.gz	47	download
training.esports-news.co.uk-inf-20260407-233738-97erl.json	252	download job
unbounce.archivesfoundation.org-inf-20260408-003805-awk2y-00000.warc.gz	14314	download job
unbounce.archivesfoundation.org-inf-20260408-003805-awk2y-00000.warc.os.cdx.gz	344	download
unbounce.archivesfoundation.org-inf-20260408-003805-awk2y-meta.warc.gz	3535	download job
unbounce.archivesfoundation.org-inf-20260408-003805-awk2y-meta.warc.os.cdx.gz	47	download
unbounce.archivesfoundation.org-inf-20260408-003805-awk2y.json	262	download job
urls-transfer.archivete.am-scusd.edu_subdomains.txt-inf-20260407-193202-atwyc-00000.warc.gz	11290226523	download job
urls-transfer.archivete.am-scusd.edu_subdomains.txt-inf-20260407-193202-atwyc-00000.warc.os.cdx.gz	3607993	download
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00243.warc.gz	5385066739	download job
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00243.warc.os.cdx.gz	140331	download
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00244.warc.gz	5370012673	download job
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00244.warc.os.cdx.gz	133506	download
www.archivesfoundation.org-inf-20260408-003928-dykf6-00000.warc.gz	6871590	download job
www.archivesfoundation.org-inf-20260408-003928-dykf6-00000.warc.os.cdx.gz	12009	download
www.archivesfoundation.org-inf-20260408-003928-dykf6-meta.warc.gz	10817	download job
www.archivesfoundation.org-inf-20260408-003928-dykf6-meta.warc.os.cdx.gz	47	download
www.archivesfoundation.org-inf-20260408-003928-dykf6.json	257	download job
www.astralcodexten.com-inf-20260301-072913-amp6a-00063.warc.gz	5378596429	download job
www.astralcodexten.com-inf-20260301-072913-amp6a-00063.warc.os.cdx.gz	1239513	download
www.bryanschwartzlaw.com-inf-20260407-215646-7zj6j-00000.warc.gz	5441570207	download job
www.bryanschwartzlaw.com-inf-20260407-215646-7zj6j-00000.warc.os.cdx.gz	1597235	download
www.childrensmn.org-inf-20260407-200434-c1nh4-00002.warc.gz	6431806629	download job
www.childrensmn.org-inf-20260407-200434-c1nh4-00002.warc.os.cdx.gz	521381	download
www.clubforgrowthfoundation.org-inf-20260408-002349-4vp29-00000.warc.gz	9402929	download job
www.clubforgrowthfoundation.org-inf-20260408-002349-4vp29-00000.warc.os.cdx.gz	15741	download
www.clubforgrowthfoundation.org-inf-20260408-002349-4vp29-meta.warc.gz	12253	download job
www.clubforgrowthfoundation.org-inf-20260408-002349-4vp29-meta.warc.os.cdx.gz	47	download
www.clubforgrowthfoundation.org-inf-20260408-002349-4vp29.json	262	download job
www.shanghai.gov.cn-inf-20260406-122938-2yb1e-00013.warc.gz	6203140187	download job
www.shanghai.gov.cn-inf-20260406-122938-2yb1e-00013.warc.os.cdx.gz	12315	download