Item archiveteam_archivebot_go_20250325193750_de531946

Filename	Size
archiveteam_archivebot_go_20250325193750_de531946.cdx.gz	13504692	download
archiveteam_archivebot_go_20250325193750_de531946.cdx.idx	13802	download
archiveteam_archivebot_go_20250325193750_de531946_files.xml	0	download
archiveteam_archivebot_go_20250325193750_de531946_meta.sqlite	147456	download
archiveteam_archivebot_go_20250325193750_de531946_meta.xml	881	download
bragadistrito.bloco.org-inf-20250325-173304-74ud5-00000.warc.gz	989278571	download job
bragadistrito.bloco.org-inf-20250325-173304-74ud5-00000.warc.os.cdx.gz	1181572	download
bragadistrito.bloco.org-inf-20250325-173304-74ud5-meta.warc.gz	823103	download job
bragadistrito.bloco.org-inf-20250325-173304-74ud5-meta.warc.os.cdx.gz	47	download
bragadistrito.bloco.org-inf-20250325-173304-74ud5.json	251	download job
cascais.bloco.org-inf-20250325-185250-13xew-00000.warc.gz	307102042	download job
cascais.bloco.org-inf-20250325-185250-13xew-00000.warc.os.cdx.gz	438137	download
cascais.bloco.org-inf-20250325-185250-13xew-meta.warc.gz	279285	download job
cascais.bloco.org-inf-20250325-185250-13xew-meta.warc.os.cdx.gz	47	download
cascais.bloco.org-inf-20250325-185250-13xew.json	245	download job
cdsarc.cds.unistra.fr-inf-20250316-091614-2ddo1-00313.warc.gz	5689867725	download job
cdsarc.cds.unistra.fr-inf-20250316-091614-2ddo1-00313.warc.os.cdx.gz	592	download
cirrus.ucsd.edu-inf-20250204-222623-178n0-04196.warc.gz	5383297197	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-04196.warc.os.cdx.gz	1053	download
codepink.org-inf-20250325-193413-22ofb-00000.warc.gz	203603	download job
codepink.org-inf-20250325-193413-22ofb-00000.warc.os.cdx.gz	414	download
codepink.org-inf-20250325-193413-22ofb-meta.warc.gz	3559	download job
codepink.org-inf-20250325-193413-22ofb-meta.warc.os.cdx.gz	47	download
codepink.org-inf-20250325-193413-22ofb.json	240	download job
coimbradistrito.bloco.org-inf-20250325-190204-dz7be-00000.warc.gz	402006885	download job
coimbradistrito.bloco.org-inf-20250325-190204-dz7be-00000.warc.os.cdx.gz	305890	download
coimbradistrito.bloco.org-inf-20250325-190204-dz7be-meta.warc.gz	196449	download job
coimbradistrito.bloco.org-inf-20250325-190204-dz7be-meta.warc.os.cdx.gz	47	download
coimbradistrito.bloco.org-inf-20250325-190204-dz7be.json	253	download job
concelho.bloco.org-inf-20250325-191225-3d4m1-00000.warc.gz	210633007	download job
concelho.bloco.org-inf-20250325-191225-3d4m1-00000.warc.os.cdx.gz	396260	download
concelho.bloco.org-inf-20250325-191225-3d4m1-meta.warc.gz	244413	download job
concelho.bloco.org-inf-20250325-191225-3d4m1-meta.warc.os.cdx.gz	47	download
concelho.bloco.org-inf-20250325-191225-3d4m1.json	246	download job
condeixaanova.bloco.org-inf-20250325-191602-39cuj-00000.warc.gz	101390435	download job
condeixaanova.bloco.org-inf-20250325-191602-39cuj-00000.warc.os.cdx.gz	193693	download
condeixaanova.bloco.org-inf-20250325-191602-39cuj-meta.warc.gz	115209	download job
condeixaanova.bloco.org-inf-20250325-191602-39cuj-meta.warc.os.cdx.gz	47	download
condeixaanova.bloco.org-inf-20250325-191602-39cuj.json	251	download job
cultura.bloco.org-inf-20250325-191912-6hfgg-00000.warc.gz	1100921	download job
cultura.bloco.org-inf-20250325-191912-6hfgg-00000.warc.os.cdx.gz	11571	download
cultura.bloco.org-inf-20250325-191912-6hfgg-meta.warc.gz	10546	download job
cultura.bloco.org-inf-20250325-191912-6hfgg-meta.warc.os.cdx.gz	47	download
cultura.bloco.org-inf-20250325-191912-6hfgg.json	245	download job
das.sdss.org-inf-20250226-051304-5s39o-00411.warc.gz	5368813981	download job
das.sdss.org-inf-20250226-051304-5s39o-00411.warc.os.cdx.gz	307699	download
en.tejasbarrios.org-inf-20250325-182616-afxf5-00000.warc.gz	57455025	download job
en.tejasbarrios.org-inf-20250325-182616-afxf5-00000.warc.os.cdx.gz	95916	download
en.tejasbarrios.org-inf-20250325-182616-afxf5-meta.warc.gz	53113	download job
en.tejasbarrios.org-inf-20250325-182616-afxf5-meta.warc.os.cdx.gz	47	download
en.tejasbarrios.org-inf-20250325-182616-afxf5.json	250	download job
hi.tejasbarrios.org-inf-20250325-182555-1ttgr-00000.warc.gz	11063	download job
hi.tejasbarrios.org-inf-20250325-182555-1ttgr-00000.warc.os.cdx.gz	325	download
hi.tejasbarrios.org-inf-20250325-182555-1ttgr-meta.warc.gz	3554	download job
hi.tejasbarrios.org-inf-20250325-182555-1ttgr-meta.warc.os.cdx.gz	47	download
hi.tejasbarrios.org-inf-20250325-182555-1ttgr.json	250	download job
ithelpdesk.paterson.k12.nj.us-inf-20250325-183445-rc7gu-00000.warc.gz	10056	download job
ithelpdesk.paterson.k12.nj.us-inf-20250325-183445-rc7gu-00000.warc.os.cdx.gz	382	download
ithelpdesk.paterson.k12.nj.us-inf-20250325-183445-rc7gu-meta.warc.gz	3565	download job
ithelpdesk.paterson.k12.nj.us-inf-20250325-183445-rc7gu-meta.warc.os.cdx.gz	47	download
ithelpdesk.paterson.k12.nj.us-inf-20250325-183445-rc7gu.json	260	download job
leeshaukee.crazybillionaire.org-shallow-20250325-183631-8pl3e-00000.warc.gz	2478	download job
leeshaukee.crazybillionaire.org-shallow-20250325-183631-8pl3e-00000.warc.os.cdx.gz	47	download
leeshaukee.crazybillionaire.org-shallow-20250325-183631-8pl3e-meta.warc.gz	3475	download job
leeshaukee.crazybillionaire.org-shallow-20250325-183631-8pl3e-meta.warc.os.cdx.gz	47	download
leeshaukee.crazybillionaire.org-shallow-20250325-183631-8pl3e.json	280	download job
mbertram.de-inf-20250325-192613-d7gxe-00000.warc.gz	39396678	download job
mbertram.de-inf-20250325-192613-d7gxe-00000.warc.os.cdx.gz	8234	download
mbertram.de-inf-20250325-192613-d7gxe-meta.warc.gz	8216	download job
mbertram.de-inf-20250325-192613-d7gxe-meta.warc.os.cdx.gz	47	download
mbertram.de-inf-20250325-192613-d7gxe.json	239	download job
menadonate.greenpeace.org-inf-20250325-191834-3f63l-00000.warc.gz	9568583	download job
menadonate.greenpeace.org-inf-20250325-191834-3f63l-00000.warc.os.cdx.gz	12444	download
menadonate.greenpeace.org-inf-20250325-191834-3f63l-meta.warc.gz	11066	download job
menadonate.greenpeace.org-inf-20250325-191834-3f63l-meta.warc.os.cdx.gz	47	download
menadonate.greenpeace.org-inf-20250325-191834-3f63l.json	253	download job
mypetfootprint.greenpeace.org-inf-20250325-192325-8epnn-00000.warc.gz	141212825	download job
mypetfootprint.greenpeace.org-inf-20250325-192325-8epnn-00000.warc.os.cdx.gz	196963	download
mypetfootprint.greenpeace.org-inf-20250325-192325-8epnn-meta.warc.gz	111790	download job
mypetfootprint.greenpeace.org-inf-20250325-192325-8epnn-meta.warc.os.cdx.gz	47	download
mypetfootprint.greenpeace.org-inf-20250325-192325-8epnn.json	257	download job
niks.greenpeace.org-inf-20250325-192347-2ls5y-00000.warc.gz	25016235	download job
niks.greenpeace.org-inf-20250325-192347-2ls5y-00000.warc.os.cdx.gz	15320	download
niks.greenpeace.org-inf-20250325-192347-2ls5y-meta.warc.gz	12800	download job
niks.greenpeace.org-inf-20250325-192347-2ls5y-meta.warc.os.cdx.gz	47	download
niks.greenpeace.org-inf-20250325-192347-2ls5y.json	247	download job
nrc.paterson.k12.nj.us-inf-20250325-171533-3ccuw-00000.warc.gz	1389179109	download job
nrc.paterson.k12.nj.us-inf-20250325-171533-3ccuw-00000.warc.os.cdx.gz	726653	download
nrc.paterson.k12.nj.us-inf-20250325-171533-3ccuw-meta.warc.gz	417015	download job
nrc.paterson.k12.nj.us-inf-20250325-171533-3ccuw-meta.warc.os.cdx.gz	47	download
nrc.paterson.k12.nj.us-inf-20250325-171533-3ccuw.json	253	download job
physics.illinois.edu-shallow-20250325-184221-1b599-00000.warc.gz	8840908	download job
physics.illinois.edu-shallow-20250325-184221-1b599-00000.warc.os.cdx.gz	13096	download
physics.illinois.edu-shallow-20250325-184221-1b599-meta.warc.gz	10513	download job
physics.illinois.edu-shallow-20250325-184221-1b599-meta.warc.os.cdx.gz	47	download
physics.illinois.edu-shallow-20250325-184221-1b599.json	287	download job
readovka67.ru-inf-20250319-161000-4y0gb-00015.warc.gz	5368868902	download job
readovka67.ru-inf-20250319-161000-4y0gb-00015.warc.os.cdx.gz	2760752	download
seb.omao.noaa.gov-inf-20250228-042858-3xzji-00945.warc.gz	9635965568	download job
seb.omao.noaa.gov-inf-20250228-042858-3xzji-00945.warc.os.cdx.gz	3265	download
seb.omao.noaa.gov-inf-20250228-042858-3xzji-00946.warc.gz	8216844181	download job
seb.omao.noaa.gov-inf-20250228-042858-3xzji-00946.warc.os.cdx.gz	430	download
transfer.archivete.am-shallow-20250325-173155-ycumd-00000.warc.gz	23681	download job
transfer.archivete.am-shallow-20250325-173155-ycumd-00000.warc.os.cdx.gz	247	download
transfer.archivete.am-shallow-20250325-173155-ycumd-meta.warc.gz	3516	download job
transfer.archivete.am-shallow-20250325-173155-ycumd-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20250325-173155-ycumd.json	281	download job
transfer.archivete.am-shallow-20250325-185433-doqi5-00000.warc.gz	4153	download job
transfer.archivete.am-shallow-20250325-185433-doqi5-00000.warc.os.cdx.gz	235	download
transfer.archivete.am-shallow-20250325-185433-doqi5-meta.warc.gz	3476	download job
transfer.archivete.am-shallow-20250325-185433-doqi5-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20250325-185433-doqi5.json	269	download job
urls-transfer.archivete.am-digital.mooresvillenc.gov_urls.txt-shallow-20250321-205527-796ax-00114.warc.gz	5372412943	download job
urls-transfer.archivete.am-digital.mooresvillenc.gov_urls.txt-shallow-20250321-205527-796ax-00114.warc.os.cdx.gz	286703	download
urls-transfer.archivete.am-mchs.gov.ru_seed-urls.txt-inf-20250221-133328-259v3-00019.warc.gz	5394275273	download job
urls-transfer.archivete.am-mchs.gov.ru_seed-urls.txt-inf-20250221-133328-259v3-00019.warc.os.cdx.gz	482889	download
urls-transfer.archivete.am-www.circuitousroot.com.txt-inf-20250325-164322-b2lf6-00010.warc.gz	5381575866	download job
urls-transfer.archivete.am-www.circuitousroot.com.txt-inf-20250325-164322-b2lf6-00010.warc.os.cdx.gz	190006	download
urls-transfer.archivete.am-www.circuitousroot.com.txt-inf-20250325-164322-b2lf6-00011.warc.gz	5458529568	download job
urls-transfer.archivete.am-www.circuitousroot.com.txt-inf-20250325-164322-b2lf6-00011.warc.os.cdx.gz	21661	download
urls-transfer.archivete.am-www.circuitousroot.com.txt-inf-20250325-164322-b2lf6-00012.warc.gz	5462187733	download job
urls-transfer.archivete.am-www.circuitousroot.com.txt-inf-20250325-164322-b2lf6-00012.warc.os.cdx.gz	16122	download
v.redd.it-shallow-20250325-182026-2szv3-00000.warc.gz	6692175	download job
v.redd.it-shallow-20250325-182026-2szv3-00000.warc.os.cdx.gz	240	download
v.redd.it-shallow-20250325-182026-2szv3-meta.warc.gz	3411	download job
v.redd.it-shallow-20250325-182026-2szv3-meta.warc.os.cdx.gz	47	download
v.redd.it-shallow-20250325-182026-2szv3.json	264	download job
vantagepointmedia.com-inf-20250325-181951-e94c9-00000.warc.gz	11692154	download job
vantagepointmedia.com-inf-20250325-181951-e94c9-00000.warc.os.cdx.gz	15913	download
vantagepointmedia.com-inf-20250325-181951-e94c9-meta.warc.gz	12271	download job
vantagepointmedia.com-inf-20250325-181951-e94c9-meta.warc.os.cdx.gz	47	download
vantagepointmedia.com-inf-20250325-181951-e94c9.json	252	download job
www.content.net.ua-shallow-20250325-183611-7uehu-00000.warc.gz	35242	download job
www.content.net.ua-shallow-20250325-183611-7uehu-00000.warc.os.cdx.gz	738	download
www.content.net.ua-shallow-20250325-183611-7uehu-meta.warc.gz	3855	download job
www.content.net.ua-shallow-20250325-183611-7uehu-meta.warc.os.cdx.gz	47	download
www.content.net.ua-shallow-20250325-183611-7uehu.json	282	download job
www.hpjc.org-inf-20250325-182102-67389-00000.warc.gz	257335763	download job
www.hpjc.org-inf-20250325-182102-67389-00000.warc.os.cdx.gz	79243	download
www.hpjc.org-inf-20250325-182102-67389-meta.warc.gz	49215	download job
www.hpjc.org-inf-20250325-182102-67389-meta.warc.os.cdx.gz	47	download
www.hpjc.org-inf-20250325-182102-67389.json	243	download job
www.mariagustafsson.com-inf-20250325-183508-1is4r-00000.warc.gz	213079144	download job
www.mariagustafsson.com-inf-20250325-183508-1is4r-00000.warc.os.cdx.gz	464001	download
www.mariagustafsson.com-inf-20250325-183508-1is4r-meta.warc.gz	272090	download job
www.mariagustafsson.com-inf-20250325-183508-1is4r-meta.warc.os.cdx.gz	47	download
www.mariagustafsson.com-inf-20250325-183508-1is4r.json	254	download job
www.newyorkalmanack.com-inf-20250322-075213-cee6l-00026.warc.gz	5369465753	download job
www.newyorkalmanack.com-inf-20250322-075213-cee6l-00026.warc.os.cdx.gz	3682790	download
www.sciencebase.gov-inf-20250204-024621-3gyep-01480.warc.gz	5390291100	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-01480.warc.os.cdx.gz	89846	download
www.sciencebase.gov-inf-20250204-024621-3gyep-01481.warc.gz	5385718689	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-01481.warc.os.cdx.gz	73899	download
www.sciencebase.gov-inf-20250204-024621-3gyep-01482.warc.gz	5406811411	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-01482.warc.os.cdx.gz	77695	download
www.theduckwebcomics.com-inf-20250324-203438-3ocqe-00006.warc.gz	5416792709	download job
www.theduckwebcomics.com-inf-20250324-203438-3ocqe-00006.warc.os.cdx.gz	298418	download
www.vantagepointmedia.com-inf-20250325-181913-9o6nq-00000.warc.gz	1809470	download job
www.vantagepointmedia.com-inf-20250325-181913-9o6nq-00000.warc.os.cdx.gz	4500	download
www.vantagepointmedia.com-inf-20250325-181913-9o6nq-meta.warc.gz	6136	download job
www.vantagepointmedia.com-inf-20250325-181913-9o6nq-meta.warc.os.cdx.gz	47	download
www.vantagepointmedia.com-inf-20250325-181913-9o6nq.json	255	download job
www.voaafrica.com-inf-20250318-081912-1fye9-00992.warc.gz	5459904877	download job
www.voaafrica.com-inf-20250318-081912-1fye9-00992.warc.os.cdx.gz	13178	download
www.voaafrica.com-inf-20250318-081912-1fye9-00993.warc.gz	5371778403	download job
www.voaafrica.com-inf-20250318-081912-1fye9-00993.warc.os.cdx.gz	10021	download
www.voadeewanews.com-inf-20250318-081603-6w6oc-00514.warc.gz	5370002086	download job
www.voadeewanews.com-inf-20250318-081603-6w6oc-00514.warc.os.cdx.gz	141702	download
www.wired.com-inf-20250222-101923-dg2iq-00265.warc.gz	5383128261	download job
www.wired.com-inf-20250222-101923-dg2iq-00265.warc.os.cdx.gz	1822057	download