Item archiveteam_archivebot_go_20260710041942_d8d02f7a

Filename	Size
archiveteam_archivebot_go_20260710041942_d8d02f7a.cdx.gz	4054439	download
archiveteam_archivebot_go_20260710041942_d8d02f7a.cdx.idx	3709	download
archiveteam_archivebot_go_20260710041942_d8d02f7a_files.xml	0	download
archiveteam_archivebot_go_20260710041942_d8d02f7a_meta.sqlite	110592	download
archiveteam_archivebot_go_20260710041942_d8d02f7a_meta.xml	1046	download
bseu.by-inf-20260709-111219-conz5-00002.warc.gz	5368775542	download job
bseu.by-inf-20260709-111219-conz5-00002.warc.os.cdx.gz	2765564	download
buttmagazine.com-inf-20260710-012659-8i2rb-00002.warc.gz	5800545543	download job
buttmagazine.com-inf-20260710-012659-8i2rb-00002.warc.os.cdx.gz	1400957	download
data.gov.de-inf-20260708-185247-9yjqm-00004.warc.gz	5886393280	download job
exitchatcontrol.org-inf-20260710-023317-ehd6c-00000.warc.gz	2574077982	download job
exitchatcontrol.org-inf-20260710-023317-ehd6c-meta.warc.gz	733420	download job
exitchatcontrol.org-inf-20260710-023317-ehd6c.json	250	download job
idtana.org-inf-20260709-221703-9eed1-00000.warc.gz	3465791571	download job
idtana.org-inf-20260709-221703-9eed1-meta.warc.gz	2544982	download job
idtana.org-inf-20260709-221703-9eed1.json	241	download job
ja.wikinews.org-inf-20260508-131400-eq105-00043.warc.gz	5524714038	download job
mirrors.lolinet.com-inf-20260622-131900-djo4a-02791.warc.gz	8013470057	download job
mirrors.lolinet.com-inf-20260622-131900-djo4a-02792.warc.gz	8013470160	download job
mirrors.lolinet.com-inf-20260622-131900-djo4a-02793.warc.gz	8630812924	download job
momsdemandaction.org-inf-20260709-040631-c4et6-00012.warc.gz	5475160059	download job
momsdemandaction.org-inf-20260709-040631-c4et6-00013.warc.gz	5369717459	download job
momsdemandaction.org-inf-20260709-040631-c4et6-00014.warc.gz	5612611231	download job
onderwijs.coc.nl-inf-20260710-014915-6imi2-00000.warc.gz	1826684247	download job
onderwijs.coc.nl-inf-20260710-014915-6imi2-meta.warc.gz	962047	download job
onderwijs.coc.nl-inf-20260710-014915-6imi2.json	247	download job
photos.rose-hulman.edu-inf-20260709-035417-610am-00023.warc.gz	5369628576	download job
the-moving-finger.diarybackup.space-inf-20260513-193847-7ca6d-00074.warc.gz	5368776549	download job
thequeeragenda.nl-inf-20260710-012355-7aaqt-00000.warc.gz	517652850	download job
thequeeragenda.nl-inf-20260710-012355-7aaqt-meta.warc.gz	64890	download job
thequeeragenda.nl-inf-20260710-012355-7aaqt.json	248	download job
traveloregon.com-inf-20260706-042532-784id-00032.warc.gz	5369205991	download job
urls-nue2.nulldata.foo-github.com_Swordfish90-20260709203515-links.txt-shallow-20260709-204202-3i6ck-00001.warc.gz	1778360633	download job
urls-nue2.nulldata.foo-github.com_Swordfish90-20260709203515-links.txt-shallow-20260709-204202-3i6ck-meta.warc.gz	392390	download job
urls-nue2.nulldata.foo-github.com_Swordfish90-20260709203515-links.txt-shallow-20260709-204202-3i6ck-urls.txt	237550	download
urls-nue2.nulldata.foo-github.com_Swordfish90-20260709203515-links.txt-shallow-20260709-204202-3i6ck.json	387	download job
urls-transfer.archivete.am-c3manu_misc-new-discourse-posts_2026-07-08.txt-shallow-20260709-062523-7k8oh-00001.warc.gz	5368718842	download job
urls-transfer.archivete.am-khabaronline.ir_subdomains.txt-inf-20260131-000430-5jt4t-00257.warc.gz	5772889683	download job
www.bureaubrandeis.fr-inf-20260710-022423-1w1cc-aborted-00000.warc.gz	9579764	download job
www.bureaubrandeis.fr-inf-20260710-022423-1w1cc-aborted-wpull.log.gz	13381	download
www.bureaubrandeis.fr-inf-20260710-022423-1w1cc-aborted.json	251	download job
www.erdosproblems.com-inf-20260709-211947-7d9ua-00001.warc.gz	211890167	download job
www.erdosproblems.com-inf-20260709-211947-7d9ua-meta.warc.gz	2481272	download job
www.erdosproblems.com-inf-20260709-211947-7d9ua.json	252	download job
www.exitchatcontrol.org-inf-20260710-023203-82lgj-00000.warc.gz	14007	download job
www.exitchatcontrol.org-inf-20260710-023203-82lgj-meta.warc.gz	3605	download job
www.exitchatcontrol.org-inf-20260710-023203-82lgj.json	254	download job
www.nato.int-inf-20260709-055051-4291i-00027.warc.gz	5602096064	download job
www.runzero.com-inf-20260709-153026-bk3z0-00002.warc.gz	5404904580	download job
www.zeitschrift-luxemburg.de-inf-20260709-171012-3le4n-00004.warc.gz	5392112517	download job