Item archiveteam_archivebot_go_20260406094247_48f3f45b

Filename	Size
appropriations.house.gov-inf-20260406-002803-7u5rk-00005.warc.gz	5371671505	download job
appropriations.house.gov-inf-20260406-002803-7u5rk-00005.warc.os.cdx.gz	4159610	download
archiveteam_archivebot_go_20260406094247_48f3f45b.cdx.gz	63213885	download
archiveteam_archivebot_go_20260406094247_48f3f45b.cdx.idx	74524	download
archiveteam_archivebot_go_20260406094247_48f3f45b_files.xml	0	download
archiveteam_archivebot_go_20260406094247_48f3f45b_meta.sqlite	61440	download
archiveteam_archivebot_go_20260406094247_48f3f45b_meta.xml	915	download
astrein.podigee.io-inf-20260406-091215-1g4k2-00000.warc.gz	150882062	download job
astrein.podigee.io-inf-20260406-091215-1g4k2-00000.warc.os.cdx.gz	131777	download
astrein.podigee.io-inf-20260406-091215-1g4k2-meta.warc.gz	80394	download job
astrein.podigee.io-inf-20260406-091215-1g4k2-meta.warc.os.cdx.gz	47	download
astrein.podigee.io-inf-20260406-091215-1g4k2-wpull.log.gz	77668	download
astrein.podigee.io-inf-20260406-091215-1g4k2.json	246	download job
bugzilla.mozilla.org-shallow-20260406-091250-52zkx-00000.warc.gz	6329375	download job
bugzilla.mozilla.org-shallow-20260406-091250-52zkx-00000.warc.os.cdx.gz	5235	download
bugzilla.mozilla.org-shallow-20260406-091250-52zkx-meta.warc.gz	6495	download job
bugzilla.mozilla.org-shallow-20260406-091250-52zkx-meta.warc.os.cdx.gz	47	download
bugzilla.mozilla.org-shallow-20260406-091250-52zkx.json	275	download job
creators.spotify.com-inf-20260406-085349-2tzee-00000.warc.gz	1480212734	download job
creators.spotify.com-inf-20260406-085349-2tzee-00000.warc.os.cdx.gz	678265	download
creators.spotify.com-inf-20260406-085349-2tzee-meta.warc.gz	404830	download job
creators.spotify.com-inf-20260406-085349-2tzee-meta.warc.os.cdx.gz	47	download
creators.spotify.com-inf-20260406-085349-2tzee.json	276	download job
eh23.easterhegg.eu-inf-20260406-073035-2we24-00000.warc.gz	274068378	download job
eh23.easterhegg.eu-inf-20260406-073035-2we24-00000.warc.os.cdx.gz	446283	download
eh23.easterhegg.eu-inf-20260406-073035-2we24-meta.warc.gz	332376	download job
eh23.easterhegg.eu-inf-20260406-073035-2we24-meta.warc.os.cdx.gz	47	download
eh23.easterhegg.eu-inf-20260406-073035-2we24.json	246	download job
english.shanghai.gov.cn-inf-20260406-090529-1uiay-00000.warc.gz	447608836	download job
english.shanghai.gov.cn-inf-20260406-090529-1uiay-00000.warc.os.cdx.gz	22252	download
english.shanghai.gov.cn-inf-20260406-090529-1uiay-meta.warc.gz	18526	download job
english.shanghai.gov.cn-inf-20260406-090529-1uiay-meta.warc.os.cdx.gz	47	download
english.shanghai.gov.cn-inf-20260406-090529-1uiay.json	276	download job
folieapleasures.wordpress.com-inf-20260404-044634-ddk9q-00008.warc.gz	5368712158	download job
folieapleasures.wordpress.com-inf-20260404-044634-ddk9q-00008.warc.os.cdx.gz	5773213	download
foto.patriarchia.ru-inf-20260406-025907-d1vgb-00005.warc.gz	5369677859	download job
foto.patriarchia.ru-inf-20260406-025907-d1vgb-00005.warc.os.cdx.gz	378945	download
gazette.gov.mv-inf-20260404-105758-dik48-00003.warc.gz	5368802100	download job
gazette.gov.mv-inf-20260404-105758-dik48-00003.warc.os.cdx.gz	1901389	download
graben.uber.space-inf-20260406-091111-aep17-00000.warc.gz	3495962746	download job
graben.uber.space-inf-20260406-091111-aep17-00000.warc.os.cdx.gz	88608	download
graben.uber.space-inf-20260406-091111-aep17-meta.warc.gz	63895	download job
graben.uber.space-inf-20260406-091111-aep17-meta.warc.os.cdx.gz	47	download
graben.uber.space-inf-20260406-091111-aep17.json	245	download job
podcastnik.com-inf-20260406-091013-4prbh-00000.warc.gz	849143317	download job
podcastnik.com-inf-20260406-091013-4prbh-00000.warc.os.cdx.gz	194380	download
podcastnik.com-inf-20260406-091013-4prbh-meta.warc.gz	115095	download job
podcastnik.com-inf-20260406-091013-4prbh-meta.warc.os.cdx.gz	47	download
podcastnik.com-inf-20260406-091013-4prbh.json	261	download job
presidency.gov.mv-inf-20260404-105154-3e07k-00044.warc.gz	5368875580	download job
presidency.gov.mv-inf-20260404-105154-3e07k-00044.warc.os.cdx.gz	668396	download
pretalx.eh23.easterhegg.eu-inf-20260406-074426-2ucik-00000.warc.gz	5370028250	download job
pretalx.eh23.easterhegg.eu-inf-20260406-074426-2ucik-00000.warc.os.cdx.gz	1610867	download
qpress.de-inf-20260404-090738-bd4jd-00026.warc.gz	5530191961	download job
qpress.de-inf-20260404-090738-bd4jd-00026.warc.os.cdx.gz	1440615	download
thirdworldxxx.com-inf-20260308-223712-a31io-00286.warc.gz	5368731125	download job
thirdworldxxx.com-inf-20260308-223712-a31io-00286.warc.os.cdx.gz	7248608	download
tickets.w.icmp.camp-inf-20260406-084316-dordv-00000.warc.gz	601807981	download job
tickets.w.icmp.camp-inf-20260406-084316-dordv-00000.warc.os.cdx.gz	736138	download
tickets.w.icmp.camp-inf-20260406-084316-dordv-meta.warc.gz	414954	download job
tickets.w.icmp.camp-inf-20260406-084316-dordv-meta.warc.os.cdx.gz	47	download
tickets.w.icmp.camp-inf-20260406-084316-dordv.json	247	download job
transfer.archivete.am-shallow-20260406-091525-eey9m-00000.warc.gz	4035	download job
transfer.archivete.am-shallow-20260406-091525-eey9m-00000.warc.os.cdx.gz	260	download
transfer.archivete.am-shallow-20260406-091525-eey9m-meta.warc.gz	3501	download job
transfer.archivete.am-shallow-20260406-091525-eey9m-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20260406-091525-eey9m.json	299	download job
transfer.archivete.am-shallow-20260406-091541-8j5iv-00000.warc.gz	4032	download job
transfer.archivete.am-shallow-20260406-091541-8j5iv-00000.warc.os.cdx.gz	255	download
transfer.archivete.am-shallow-20260406-091541-8j5iv-meta.warc.gz	3497	download job
transfer.archivete.am-shallow-20260406-091541-8j5iv-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20260406-091541-8j5iv.json	294	download job
ukraina.ru-inf-20250930-141349-2jx86-00036.warc.gz	5448587964	download job
ukraina.ru-inf-20250930-141349-2jx86-00036.warc.os.cdx.gz	2105781	download
urls-transfer.archivete.am-bankruptcies-NL-2026-apr06-ref.txt-shallow-20260406-091559-h8lkh-00000.warc.gz	139273443	download job
urls-transfer.archivete.am-bankruptcies-NL-2026-apr06-ref.txt-shallow-20260406-091559-h8lkh-00000.warc.os.cdx.gz	208761	download
urls-transfer.archivete.am-bankruptcies-NL-2026-apr06-ref.txt-shallow-20260406-091559-h8lkh-meta.warc.gz	130869	download job
urls-transfer.archivete.am-bankruptcies-NL-2026-apr06-ref.txt-shallow-20260406-091559-h8lkh-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-bankruptcies-NL-2026-apr06-ref.txt-shallow-20260406-091559-h8lkh-urls.txt	6132	download
urls-transfer.archivete.am-bankruptcies-NL-2026-apr06-ref.txt-shallow-20260406-091559-h8lkh.json	361	download job
urls-transfer.archivete.am-c3manu_misc-new-substack-posts_2026-04-06.txt-shallow-20260406-071617-ahldo-00000.warc.gz	1802976201	download job
urls-transfer.archivete.am-c3manu_misc-new-substack-posts_2026-04-06.txt-shallow-20260406-071617-ahldo-00000.warc.os.cdx.gz	441108	download
urls-transfer.archivete.am-c3manu_misc-new-substack-posts_2026-04-06.txt-shallow-20260406-071617-ahldo-meta.warc.gz	273724	download job
urls-transfer.archivete.am-c3manu_misc-new-substack-posts_2026-04-06.txt-shallow-20260406-071617-ahldo-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-c3manu_misc-new-substack-posts_2026-04-06.txt-shallow-20260406-071617-ahldo-urls.txt	16614	download
urls-transfer.archivete.am-c3manu_misc-new-substack-posts_2026-04-06.txt-shallow-20260406-071617-ahldo.json	383	download job
urls-transfer.archivete.am-momsforliberty.org_m4lacademy.org_m4lfoundation.org_subdomains.txt-inf-20260406-033337-2m20m-00002.warc.gz	5368755860	download job
urls-transfer.archivete.am-momsforliberty.org_m4lacademy.org_m4lfoundation.org_subdomains.txt-inf-20260406-033337-2m20m-00002.warc.os.cdx.gz	1193264	download
urls-transfer.archivete.am-planet.com_misc_subdomains.txt-inf-20260406-000317-6mcpj-00008.warc.gz	7429966499	download job
urls-transfer.archivete.am-planet.com_misc_subdomains.txt-inf-20260406-000317-6mcpj-00008.warc.os.cdx.gz	378479	download
urls-transfer.archivete.am-www.nasa.gov_science.nasa.gov.txt-inf-20260324-233148-4cdjh-00197.warc.gz	5832084379	download job
urls-transfer.archivete.am-www.nasa.gov_science.nasa.gov.txt-inf-20260324-233148-4cdjh-00197.warc.os.cdx.gz	33195	download
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00126.warc.gz	5369271590	download job
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00126.warc.os.cdx.gz	80529	download
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00127.warc.gz	5394567180	download job
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00127.warc.os.cdx.gz	101990	download
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00128.warc.gz	5370823997	download job
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00128.warc.os.cdx.gz	82658	download
urls-transfer.archivete.am-www.svenskalag.se-misc-urls.txt-inf-20260329-200631-8jae9-00063.warc.gz	5368976096	download job
urls-transfer.archivete.am-www.svenskalag.se-misc-urls.txt-inf-20260329-200631-8jae9-00063.warc.os.cdx.gz	5429201	download
urls-transfer.archivete.am-www.weforum.org_es.weforum.org_cn.weforum.org_jp.weforum.org.txt-inf-20260121-202657-e2t29-01827.warc.gz	5369161837	download job
urls-transfer.archivete.am-www.weforum.org_es.weforum.org_cn.weforum.org_jp.weforum.org.txt-inf-20260121-202657-e2t29-01827.warc.os.cdx.gz	3904310	download
usgovernmentofficial.tumblr.com-inf-20251222-061339-b1lo1-02217.warc.gz	5368755148	download job
usgovernmentofficial.tumblr.com-inf-20251222-061339-b1lo1-02217.warc.os.cdx.gz	1493409	download
wiki.ctbk.de-shallow-20260406-093133-46ngh-00000.warc.gz	870008	download job
wiki.ctbk.de-shallow-20260406-093133-46ngh-00000.warc.os.cdx.gz	4815	download
wiki.ctbk.de-shallow-20260406-093133-46ngh-meta.warc.gz	5888	download job
wiki.ctbk.de-shallow-20260406-093133-46ngh-meta.warc.os.cdx.gz	47	download
wiki.ctbk.de-shallow-20260406-093133-46ngh.json	252	download job
www.ausgesprochenalt.com-inf-20260406-092455-7qtgh-00000.warc.gz	12444547	download job
www.ausgesprochenalt.com-inf-20260406-092455-7qtgh-00000.warc.os.cdx.gz	5837	download
www.ausgesprochenalt.com-inf-20260406-092455-7qtgh-meta.warc.gz	6640	download job
www.ausgesprochenalt.com-inf-20260406-092455-7qtgh-meta.warc.os.cdx.gz	47	download
www.ausgesprochenalt.com-inf-20260406-092455-7qtgh.json	252	download job
www.cura-ambulant.nl-inf-20260406-093426-7k0i3-00000.warc.gz	8591	download job
www.cura-ambulant.nl-inf-20260406-093426-7k0i3-00000.warc.os.cdx.gz	354	download
www.cura-ambulant.nl-inf-20260406-093426-7k0i3-meta.warc.gz	3612	download job
www.cura-ambulant.nl-inf-20260406-093426-7k0i3-meta.warc.os.cdx.gz	47	download
www.cura-ambulant.nl-inf-20260406-093426-7k0i3.json	248	download job
www.heise.de-shallow-20260406-091202-e05tq-00000.warc.gz	19193025	download job
www.heise.de-shallow-20260406-091202-e05tq-00000.warc.os.cdx.gz	23367	download
www.heise.de-shallow-20260406-091202-e05tq-meta.warc.gz	18571	download job
www.heise.de-shallow-20260406-091202-e05tq-meta.warc.os.cdx.gz	47	download
www.heise.de-shallow-20260406-091202-e05tq.json	328	download job
www.lubartowiak.com.pl-inf-20260405-224509-9fxdl-00004.warc.gz	5369243212	download job
www.lubartowiak.com.pl-inf-20260405-224509-9fxdl-00004.warc.os.cdx.gz	3497737	download
www.nfsplanet.com-inf-20260403-014717-3oyb5-00016.warc.gz	5368716430	download job
www.nfsplanet.com-inf-20260403-014717-3oyb5-00016.warc.os.cdx.gz	21418745	download