Item archiveteam_archivebot_go_20240610164532_e79e48cb

Filename	Size
7rdj.com-inf-20240527-195302-f1gwl-00057.warc.gz	5410736501	download job
7rdj.com-inf-20240527-195302-f1gwl-00057.warc.os.cdx.gz	7726	download
archiveteam_archivebot_go_20240610164532_e79e48cb.cdx.gz	69207115	download
archiveteam_archivebot_go_20240610164532_e79e48cb.cdx.idx	85162	download
archiveteam_archivebot_go_20240610164532_e79e48cb_files.xml	0	download
archiveteam_archivebot_go_20240610164532_e79e48cb_meta.sqlite	266240	download
archiveteam_archivebot_go_20240610164532_e79e48cb_meta.xml	881	download
aztecmuseum.org-inf-20240610-154138-e5p1g-00000.warc.gz	312317213	download job
aztecmuseum.org-inf-20240610-154138-e5p1g-00000.warc.os.cdx.gz	392574	download
aztecmuseum.org-inf-20240610-154138-e5p1g-meta.warc.gz	234336	download job
aztecmuseum.org-inf-20240610-154138-e5p1g-meta.warc.os.cdx.gz	47	download
aztecmuseum.org-inf-20240610-154138-e5p1g.json	240	download job
citeseerx.ist.psu.edu-shallow-20240610-161000-al343-00000.warc.gz	4602241	download job
citeseerx.ist.psu.edu-shallow-20240610-161000-al343-00000.warc.os.cdx.gz	294	download
citeseerx.ist.psu.edu-shallow-20240610-161000-al343-meta.warc.gz	3559	download job
citeseerx.ist.psu.edu-shallow-20240610-161000-al343-meta.warc.os.cdx.gz	47	download
citeseerx.ist.psu.edu-shallow-20240610-161000-al343.json	332	download job
data.worldpop.org-inf-20240515-011446-esx2x-00808.warc.gz	5969642923	download job
data.worldpop.org-inf-20240515-011446-esx2x-00808.warc.os.cdx.gz	555	download
data.worldpop.org-inf-20240515-011446-esx2x-00809.warc.gz	5969713933	download job
data.worldpop.org-inf-20240515-011446-esx2x-00809.warc.os.cdx.gz	552	download
discussmormonism.com-inf-20240508-044003-4x6i5-00235.warc.gz	5410754667	download job
discussmormonism.com-inf-20240508-044003-4x6i5-00235.warc.os.cdx.gz	677788	download
forum.porteus.org-inf-20240429-005533-6ibgl-00549.warc.gz	5368746366	download job
forum.porteus.org-inf-20240429-005533-6ibgl-00549.warc.os.cdx.gz	2515464	download
fotos.cheatha.de-inf-20240610-104115-7bvy2-00003.warc.gz	5368720287	download job
fotos.cheatha.de-inf-20240610-104115-7bvy2-00003.warc.os.cdx.gz	495313	download
ftp.ten-heggeler.nl-inf-20240610-163836-4zftw-00000.warc.gz	2475	download job
ftp.ten-heggeler.nl-inf-20240610-163836-4zftw-00000.warc.os.cdx.gz	47	download
ftp.ten-heggeler.nl-inf-20240610-163836-4zftw-meta.warc.gz	3507	download job
ftp.ten-heggeler.nl-inf-20240610-163836-4zftw-meta.warc.os.cdx.gz	47	download
ftp.ten-heggeler.nl-inf-20240610-163836-4zftw.json	247	download job
heggeler.nl-inf-20240610-163950-b0z5t-00000.warc.gz	2461	download job
heggeler.nl-inf-20240610-163950-b0z5t-00000.warc.os.cdx.gz	47	download
heggeler.nl-inf-20240610-163950-b0z5t-meta.warc.gz	3593	download job
heggeler.nl-inf-20240610-163950-b0z5t-meta.warc.os.cdx.gz	47	download
heggeler.nl-inf-20240610-163950-b0z5t.json	239	download job
heggeler.nl-inf-20240610-164032-9gmwe-00000.warc.gz	1232660	download job
heggeler.nl-inf-20240610-164032-9gmwe-00000.warc.os.cdx.gz	3344	download
heggeler.nl-inf-20240610-164032-9gmwe-meta.warc.gz	5152	download job
heggeler.nl-inf-20240610-164032-9gmwe-meta.warc.os.cdx.gz	47	download
heggeler.nl-inf-20240610-164032-9gmwe.json	238	download job
hromadske.radio-inf-20240510-124506-27o5p-00216.warc.gz	5368734873	download job
hromadske.radio-inf-20240510-124506-27o5p-00216.warc.os.cdx.gz	1486780	download
iranvisitor.com-inf-20240610-155304-6qp8c-aborted-00000.warc.gz	114177667	download job
iranvisitor.com-inf-20240610-155304-6qp8c-aborted-00000.warc.os.cdx.gz	192236	download
iranvisitor.com-inf-20240610-155304-6qp8c-aborted-wpull.log.gz	120011	download
iranvisitor.com-inf-20240610-155304-6qp8c-aborted.json	239	download job
learn.microsoft.com-inf-20240606-084119-1y7vh-00026.warc.gz	5379521029	download job
learn.microsoft.com-inf-20240606-084119-1y7vh-00026.warc.os.cdx.gz	3148464	download
lhs.tuk.mybluehost.me-inf-20240610-162916-ccmhl-aborted-00000.warc.gz	26061987	download job
lhs.tuk.mybluehost.me-inf-20240610-162916-ccmhl-aborted-00000.warc.os.cdx.gz	28927	download
lhs.tuk.mybluehost.me-inf-20240610-162916-ccmhl-aborted-wpull.log.gz	21615	download
lhs.tuk.mybluehost.me-inf-20240610-162916-ccmhl-aborted.json	269	download job
lhs.tuk.mybluehost.me-inf-20240610-163206-ccmhl-00000.warc.gz	53451869	download job
lhs.tuk.mybluehost.me-inf-20240610-163206-ccmhl-00000.warc.os.cdx.gz	75198	download
lhs.tuk.mybluehost.me-inf-20240610-163206-ccmhl-meta.warc.gz	49539	download job
lhs.tuk.mybluehost.me-inf-20240610-163206-ccmhl-meta.warc.os.cdx.gz	47	download
lhs.tuk.mybluehost.me-inf-20240610-163206-ccmhl.json	270	download job
lhs.tuk.mybluehost.me-inf-20240610-163609-b127t-00000.warc.gz	36727275	download job
lhs.tuk.mybluehost.me-inf-20240610-163609-b127t-00000.warc.os.cdx.gz	63766	download
lhs.tuk.mybluehost.me-inf-20240610-163609-b127t-meta.warc.gz	42391	download job
lhs.tuk.mybluehost.me-inf-20240610-163609-b127t-meta.warc.os.cdx.gz	47	download
lhs.tuk.mybluehost.me-inf-20240610-163609-b127t.json	266	download job
longnow.org-inf-20240609-230423-9ouyg-00022.warc.gz	5399031853	download job
longnow.org-inf-20240609-230423-9ouyg-00022.warc.os.cdx.gz	1097707	download
mail.ten-heggeler.nl-inf-20240610-163805-7c6hr-00000.warc.gz	6391	download job
mail.ten-heggeler.nl-inf-20240610-163805-7c6hr-00000.warc.os.cdx.gz	304	download
mail.ten-heggeler.nl-inf-20240610-163805-7c6hr-meta.warc.gz	3552	download job
mail.ten-heggeler.nl-inf-20240610-163805-7c6hr-meta.warc.os.cdx.gz	47	download
mail.ten-heggeler.nl-inf-20240610-163805-7c6hr.json	248	download job
noemme.nl-inf-20240610-164248-5x6a9-00000.warc.gz	14843433	download job
noemme.nl-inf-20240610-164248-5x6a9-00000.warc.os.cdx.gz	10599	download
noemme.nl-inf-20240610-164248-5x6a9-meta.warc.gz	9730	download job
noemme.nl-inf-20240610-164248-5x6a9-meta.warc.os.cdx.gz	47	download
noemme.nl-inf-20240610-164248-5x6a9.json	237	download job
pop.ten-heggeler.nl-inf-20240610-163854-bnepg-00000.warc.gz	2474	download job
pop.ten-heggeler.nl-inf-20240610-163854-bnepg-00000.warc.os.cdx.gz	47	download
pop.ten-heggeler.nl-inf-20240610-163854-bnepg-meta.warc.gz	3487	download job
pop.ten-heggeler.nl-inf-20240610-163854-bnepg-meta.warc.os.cdx.gz	47	download
pop.ten-heggeler.nl-inf-20240610-163854-bnepg.json	247	download job
ri.conicet.gov.ar-inf-20240131-015554-6z8he-00064.warc.gz	5383387150	download job
ri.conicet.gov.ar-inf-20240131-015554-6z8he-00064.warc.os.cdx.gz	5438388	download
richardnryanbooks.com-inf-20240610-164102-6r7l5-00000.warc.gz	14525927	download job
richardnryanbooks.com-inf-20240610-164102-6r7l5-00000.warc.os.cdx.gz	42752	download
richardnryanbooks.com-inf-20240610-164102-6r7l5-meta.warc.gz	30132	download job
richardnryanbooks.com-inf-20240610-164102-6r7l5-meta.warc.os.cdx.gz	47	download
richardnryanbooks.com-inf-20240610-164102-6r7l5.json	246	download job
sleepingbearinn.org-inf-20240610-153932-ammo6-00000.warc.gz	712918642	download job
sleepingbearinn.org-inf-20240610-153932-ammo6-00000.warc.os.cdx.gz	349551	download
sleepingbearinn.org-inf-20240610-153932-ammo6-meta.warc.gz	229004	download job
sleepingbearinn.org-inf-20240610-153932-ammo6-meta.warc.os.cdx.gz	47	download
sleepingbearinn.org-inf-20240610-153932-ammo6.json	244	download job
smtp.ten-heggeler.nl-inf-20240610-163923-7h7ck-00000.warc.gz	2475	download job
smtp.ten-heggeler.nl-inf-20240610-163923-7h7ck-00000.warc.os.cdx.gz	47	download
smtp.ten-heggeler.nl-inf-20240610-163923-7h7ck-meta.warc.gz	3501	download job
smtp.ten-heggeler.nl-inf-20240610-163923-7h7ck-meta.warc.os.cdx.gz	47	download
smtp.ten-heggeler.nl-inf-20240610-163923-7h7ck.json	248	download job
ten-heggeler.nl-inf-20240610-163703-af0n9-00000.warc.gz	39872793	download job
ten-heggeler.nl-inf-20240610-163703-af0n9-00000.warc.os.cdx.gz	27996	download
ten-heggeler.nl-inf-20240610-163703-af0n9-meta.warc.gz	20564	download job
ten-heggeler.nl-inf-20240610-163703-af0n9-meta.warc.os.cdx.gz	47	download
ten-heggeler.nl-inf-20240610-163703-af0n9.json	243	download job
truthout.org-inf-20240408-165731-16a89-00625.warc.gz	5579214419	download job
truthout.org-inf-20240408-165731-16a89-00625.warc.os.cdx.gz	683724	download
urls-transfer.archivete.am-bankruptcies-NL-2024-week23-ref.txt-shallow-20240610-122130-6d5b8-00000.warc.gz	1458531654	download job
urls-transfer.archivete.am-bankruptcies-NL-2024-week23-ref.txt-shallow-20240610-122130-6d5b8-00000.warc.os.cdx.gz	2091955	download
urls-transfer.archivete.am-bankruptcies-NL-2024-week23-ref.txt-shallow-20240610-122130-6d5b8-meta.warc.gz	1201541	download job
urls-transfer.archivete.am-bankruptcies-NL-2024-week23-ref.txt-shallow-20240610-122130-6d5b8-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-bankruptcies-NL-2024-week23-ref.txt-shallow-20240610-122130-6d5b8-urls.txt	35169	download
urls-transfer.archivete.am-bankruptcies-NL-2024-week23-ref.txt-shallow-20240610-122130-6d5b8.json	363	download job
viditelny-macek.cz-inf-20240506-182506-8qguw-00027.warc.gz	5369069307	download job
viditelny-macek.cz-inf-20240506-182506-8qguw-00027.warc.os.cdx.gz	40027831	download
vunderke.nl-inf-20240610-164112-d0dlc-00000.warc.gz	2204328	download job
vunderke.nl-inf-20240610-164112-d0dlc-00000.warc.os.cdx.gz	6779	download
vunderke.nl-inf-20240610-164112-d0dlc-meta.warc.gz	6800	download job
vunderke.nl-inf-20240610-164112-d0dlc-meta.warc.os.cdx.gz	47	download
vunderke.nl-inf-20240610-164112-d0dlc.json	239	download job
www.americanexpress.com-inf-20240604-005006-8i00z-00007.warc.gz	5368712324	download job
www.americanexpress.com-inf-20240604-005006-8i00z-00007.warc.os.cdx.gz	5749236	download
www.cs.cmu.edu-inf-20240609-135415-7wa5x-00007.warc.gz	6021576647	download job
www.cs.cmu.edu-inf-20240609-135415-7wa5x-00007.warc.os.cdx.gz	1145923	download
www.cs.cmu.edu-inf-20240609-135415-7wa5x-00008.warc.gz	5454311169	download job
www.cs.cmu.edu-inf-20240609-135415-7wa5x-00008.warc.os.cdx.gz	174867	download
www.gtagaming.com-inf-20240609-022251-7s96c-00013.warc.gz	5381024263	download job
www.gtagaming.com-inf-20240609-022251-7s96c-00013.warc.os.cdx.gz	570082	download
www.haarnaamislola.nl-inf-20240610-164319-1sjz8-00000.warc.gz	9782951	download job
www.haarnaamislola.nl-inf-20240610-164319-1sjz8-00000.warc.os.cdx.gz	2315	download
www.haarnaamislola.nl-inf-20240610-164319-1sjz8-meta.warc.gz	4902	download job
www.haarnaamislola.nl-inf-20240610-164319-1sjz8-meta.warc.os.cdx.gz	47	download
www.haarnaamislola.nl-inf-20240610-164319-1sjz8.json	249	download job
www.heggeler.nl-inf-20240610-163942-mchql-00000.warc.gz	2468	download job
www.heggeler.nl-inf-20240610-163942-mchql-00000.warc.os.cdx.gz	47	download
www.heggeler.nl-inf-20240610-163942-mchql-meta.warc.gz	3602	download job
www.heggeler.nl-inf-20240610-163942-mchql-meta.warc.os.cdx.gz	47	download
www.heggeler.nl-inf-20240610-163942-mchql.json	243	download job
www.heggeler.nl-inf-20240610-164009-6dicb-00000.warc.gz	2641333	download job
www.heggeler.nl-inf-20240610-164009-6dicb-00000.warc.os.cdx.gz	14190	download
www.heggeler.nl-inf-20240610-164009-6dicb-meta.warc.gz	11688	download job
www.heggeler.nl-inf-20240610-164009-6dicb-meta.warc.os.cdx.gz	47	download
www.heggeler.nl-inf-20240610-164009-6dicb.json	242	download job
www.infolibertaire.net-inf-20240528-153803-2mfkg-00170.warc.gz	5381403171	download job
www.infolibertaire.net-inf-20240528-153803-2mfkg-00170.warc.os.cdx.gz	871496	download
www.mixesdb.com-inf-20240603-014940-tfwdm-00023.warc.gz	5369049788	download job
www.mixesdb.com-inf-20240603-014940-tfwdm-00023.warc.os.cdx.gz	3226763	download
www.nasa.gov-shallow-20240610-160947-9fwl7-00000.warc.gz	30015	download job
www.nasa.gov-shallow-20240610-160947-9fwl7-00000.warc.os.cdx.gz	525	download
www.nasa.gov-shallow-20240610-160947-9fwl7-meta.warc.gz	3699	download job
www.nasa.gov-shallow-20240610-160947-9fwl7-meta.warc.os.cdx.gz	47	download
www.nasa.gov-shallow-20240610-160947-9fwl7.json	269	download job
www.pennyhero.net-inf-20240610-163751-arw7r-00000.warc.gz	191506378	download job
www.pennyhero.net-inf-20240610-163751-arw7r-00000.warc.os.cdx.gz	95362	download
www.pennyhero.net-inf-20240610-163751-arw7r-meta.warc.gz	59540	download job
www.pennyhero.net-inf-20240610-163751-arw7r-meta.warc.os.cdx.gz	47	download
www.pennyhero.net-inf-20240610-163751-arw7r.json	242	download job
www.sheetmusicplus.com-inf-20240512-212156-pg1ia-00465.warc.gz	5368718430	download job
www.sheetmusicplus.com-inf-20240512-212156-pg1ia-00465.warc.os.cdx.gz	1096400	download
www.ten-heggeler.nl-inf-20240610-163620-84hmv-00000.warc.gz	5262705	download job
www.ten-heggeler.nl-inf-20240610-163620-84hmv-00000.warc.os.cdx.gz	6973	download
www.ten-heggeler.nl-inf-20240610-163620-84hmv-meta.warc.gz	7391	download job
www.ten-heggeler.nl-inf-20240610-163620-84hmv-meta.warc.os.cdx.gz	47	download
www.ten-heggeler.nl-inf-20240610-163620-84hmv.json	247	download job
www.theruralconnection.com-inf-20240610-162627-45o9n-00000.warc.gz	8170	download job
www.theruralconnection.com-inf-20240610-162627-45o9n-00000.warc.os.cdx.gz	47	download
www.theruralconnection.com-inf-20240610-162627-45o9n-meta.warc.gz	3635	download job
www.theruralconnection.com-inf-20240610-162627-45o9n-meta.warc.os.cdx.gz	47	download
www.theruralconnection.com-inf-20240610-162627-45o9n.json	251	download job
www.vprogids.nl-shallow-20240610-160817-9b24j-00000.warc.gz	33808596	download job
www.vprogids.nl-shallow-20240610-160817-9b24j-00000.warc.os.cdx.gz	19257	download
www.vprogids.nl-shallow-20240610-160817-9b24j-meta.warc.gz	18267	download job
www.vprogids.nl-shallow-20240610-160817-9b24j-meta.warc.os.cdx.gz	47	download
www.vprogids.nl-shallow-20240610-160817-9b24j.json	375	download job
www.vprogids.nl-shallow-20240610-160817-a25xn-00000.warc.gz	17407106	download job
www.vprogids.nl-shallow-20240610-160817-a25xn-00000.warc.os.cdx.gz	18118	download
www.vprogids.nl-shallow-20240610-160817-a25xn-meta.warc.gz	17614	download job
www.vprogids.nl-shallow-20240610-160817-a25xn-meta.warc.os.cdx.gz	47	download
www.vprogids.nl-shallow-20240610-160817-a25xn.json	365	download job
www.vprogids.nl-shallow-20240610-160823-2z5kv-00000.warc.gz	25447712	download job
www.vprogids.nl-shallow-20240610-160823-2z5kv-00000.warc.os.cdx.gz	19200	download
www.vprogids.nl-shallow-20240610-160823-2z5kv-meta.warc.gz	17772	download job
www.vprogids.nl-shallow-20240610-160823-2z5kv-meta.warc.os.cdx.gz	47	download
www.vprogids.nl-shallow-20240610-160823-2z5kv.json	370	download job
www.vprogids.nl-shallow-20240610-160825-ajcjg-00000.warc.gz	14900243	download job
www.vprogids.nl-shallow-20240610-160825-ajcjg-00000.warc.os.cdx.gz	18336	download
www.vprogids.nl-shallow-20240610-160825-ajcjg-meta.warc.gz	17602	download job
www.vprogids.nl-shallow-20240610-160825-ajcjg-meta.warc.os.cdx.gz	47	download
www.vprogids.nl-shallow-20240610-160825-ajcjg.json	374	download job
www.vunderke.nl-inf-20240610-164109-1stis-00000.warc.gz	2211113	download job
www.vunderke.nl-inf-20240610-164109-1stis-00000.warc.os.cdx.gz	6779	download
www.vunderke.nl-inf-20240610-164109-1stis-meta.warc.gz	6799	download job
www.vunderke.nl-inf-20240610-164109-1stis-meta.warc.os.cdx.gz	47	download
www.vunderke.nl-inf-20240610-164109-1stis.json	243	download job