Item archiveteam_archivebot_go_20241116193754_47f05ca0

Filename	Size
apsadgil.info-inf-20241116-144558-du0ec-00000.warc.gz	5368759410	download job
apsadgil.info-inf-20241116-144558-du0ec-00000.warc.os.cdx.gz	4432986	download
archive.curbed.com-inf-20241107-213124-39x9w-00070.warc.gz	5372201533	download job
archive.curbed.com-inf-20241107-213124-39x9w-00070.warc.os.cdx.gz	4520637	download
archiveteam_archivebot_go_20241116193754_47f05ca0.cdx.gz	32504949	download
archiveteam_archivebot_go_20241116193754_47f05ca0.cdx.idx	34056	download
archiveteam_archivebot_go_20241116193754_47f05ca0_files.xml	0	download
archiveteam_archivebot_go_20241116193754_47f05ca0_meta.sqlite	147456	download
archiveteam_archivebot_go_20241116193754_47f05ca0_meta.xml	1047	download
cdnpdf.com-inf-20241103-215615-dfa0n-00192.warc.gz	5368915581	download job
cdnpdf.com-inf-20241103-215615-dfa0n-00192.warc.os.cdx.gz	767754	download
ciidta.communities.ed.gov-inf-20241116-190237-beu8z-00000.warc.gz	45536784	download job
ciidta.communities.ed.gov-inf-20241116-190237-beu8z-00000.warc.os.cdx.gz	81574	download
ciidta.communities.ed.gov-inf-20241116-190237-beu8z-meta.warc.gz	55636	download job
ciidta.communities.ed.gov-inf-20241116-190237-beu8z-meta.warc.os.cdx.gz	47	download
ciidta.communities.ed.gov-inf-20241116-190237-beu8z.json	256	download job
civilrightsdata.ed.gov-inf-20241116-184642-7dku1-00000.warc.gz	2577228905	download job
civilrightsdata.ed.gov-inf-20241116-184642-7dku1-00000.warc.os.cdx.gz	734497	download
civilrightsdata.ed.gov-inf-20241116-184642-7dku1-meta.warc.gz	675193	download job
civilrightsdata.ed.gov-inf-20241116-184642-7dku1-meta.warc.os.cdx.gz	47	download
civilrightsdata.ed.gov-inf-20241116-184642-7dku1.json	253	download job
college.nuph.edu.ua-inf-20241116-151355-8czc1-00001.warc.gz	3495220218	download job
college.nuph.edu.ua-inf-20241116-151355-8czc1-00001.warc.os.cdx.gz	2443548	download
college.nuph.edu.ua-inf-20241116-151355-8czc1-meta.warc.gz	2108644	download job
college.nuph.edu.ua-inf-20241116-151355-8czc1-meta.warc.os.cdx.gz	47	download
college.nuph.edu.ua-inf-20241116-151355-8czc1.json	247	download job
collegescorecard.ed.gov-inf-20241116-181832-ehz2e-00000.warc.gz	358630512	download job
collegescorecard.ed.gov-inf-20241116-181832-ehz2e-00000.warc.os.cdx.gz	730217	download
collegescorecard.ed.gov-inf-20241116-181832-ehz2e-meta.warc.gz	539795	download job
collegescorecard.ed.gov-inf-20241116-181832-ehz2e-meta.warc.os.cdx.gz	47	download
collegescorecard.ed.gov-inf-20241116-181832-ehz2e.json	254	download job
daniel-baldy.de-inf-20241116-181140-7cewd-00000.warc.gz	438866488	download job
daniel-baldy.de-inf-20241116-181140-7cewd-00000.warc.os.cdx.gz	499489	download
daniel-baldy.de-inf-20241116-181140-7cewd-meta.warc.gz	349544	download job
daniel-baldy.de-inf-20241116-181140-7cewd-meta.warc.os.cdx.gz	47	download
daniel-baldy.de-inf-20241116-181140-7cewd.json	243	download job
data.gov.tw-inf-20241014-134906-5rv4f-00004.warc.gz	5380420737	download job
data.gov.tw-inf-20241014-134906-5rv4f-00004.warc.os.cdx.gz	574025	download
druckschriften-digital.marchivum.de-inf-20241017-120730-ejb47-00777.warc.gz	5376215252	download job
druckschriften-digital.marchivum.de-inf-20241017-120730-ejb47-00777.warc.os.cdx.gz	135083	download
druckschriften-digital.marchivum.de-inf-20241017-120730-ejb47-00778.warc.gz	5370810346	download job
druckschriften-digital.marchivum.de-inf-20241017-120730-ejb47-00778.warc.os.cdx.gz	135897	download
en.kremlin.ru-inf-20241024-161818-58qmr-00337.warc.gz	6113889792	download job
en.kremlin.ru-inf-20241024-161818-58qmr-00337.warc.os.cdx.gz	128633	download
flibusta.is-inf-20240924-060021-7gpwv-00536.warc.gz	5372469783	download job
flibusta.is-inf-20240924-060021-7gpwv-00536.warc.os.cdx.gz	772822	download
garnix.io-inf-20241116-182711-60mx5-00000.warc.gz	363425243	download job
garnix.io-inf-20241116-182711-60mx5-00000.warc.os.cdx.gz	672104	download
garnix.io-inf-20241116-182711-60mx5-meta.warc.gz	416147	download job
garnix.io-inf-20241116-182711-60mx5-meta.warc.os.cdx.gz	47	download
garnix.io-inf-20241116-182711-60mx5.json	237	download job
jwlss.pw-inf-20241116-185941-8nk0a-00000.warc.gz	2501088878	download job
jwlss.pw-inf-20241116-185941-8nk0a-00000.warc.os.cdx.gz	169902	download
jwlss.pw-inf-20241116-185941-8nk0a-meta.warc.gz	109475	download job
jwlss.pw-inf-20241116-185941-8nk0a-meta.warc.os.cdx.gz	47	download
jwlss.pw-inf-20241116-185941-8nk0a.json	233	download job
katharina-beck.de-inf-20241116-181814-cv7t7-00000.warc.gz	5368810488	download job
katharina-beck.de-inf-20241116-181814-cv7t7-00000.warc.os.cdx.gz	1327202	download
listserv.ed.gov-inf-20241115-170437-176e7-00025.warc.gz	5368853170	download job
listserv.ed.gov-inf-20241115-170437-176e7-00025.warc.os.cdx.gz	4477795	download
maxkarson.com-inf-20241116-192106-2ar45-00000.warc.gz	325187551	download job
maxkarson.com-inf-20241116-192106-2ar45-00000.warc.os.cdx.gz	206999	download
maxkarson.com-inf-20241116-192106-2ar45-meta.warc.gz	131798	download job
maxkarson.com-inf-20241116-192106-2ar45-meta.warc.os.cdx.gz	47	download
maxkarson.com-inf-20241116-192106-2ar45.json	241	download job
ncsrcseacop.groupsite.com-inf-20241116-190329-577dy-00000.warc.gz	44066116	download job
ncsrcseacop.groupsite.com-inf-20241116-190329-577dy-00000.warc.os.cdx.gz	61188	download
ncsrcseacop.groupsite.com-inf-20241116-190329-577dy-meta.warc.gz	39498	download job
ncsrcseacop.groupsite.com-inf-20241116-190329-577dy-meta.warc.os.cdx.gz	47	download
ncsrcseacop.groupsite.com-inf-20241116-190329-577dy.json	256	download job
problogger.com-inf-20241029-035452-cspxx-00068.warc.gz	6286471678	download job
problogger.com-inf-20241029-035452-cspxx-00068.warc.os.cdx.gz	425565	download
seattleglobalist.com-inf-20241115-190314-69tsc-00016.warc.gz	5427952075	download job
seattleglobalist.com-inf-20241115-190314-69tsc-00016.warc.os.cdx.gz	1647940	download
vamers.com-inf-20241115-211328-101yg-00009.warc.gz	5408908872	download job
vamers.com-inf-20241115-211328-101yg-00009.warc.os.cdx.gz	2056214	download
www.army.lk-inf-20241115-152803-eolyd-00004.warc.gz	5369120097	download job
www.army.lk-inf-20241115-152803-eolyd-00004.warc.os.cdx.gz	1893863	download
www.bayram-gruene.de-inf-20241116-193541-e3wfn-00000.warc.gz	1952649	download job
www.bayram-gruene.de-inf-20241116-193541-e3wfn-00000.warc.os.cdx.gz	2749	download
www.bayram-gruene.de-inf-20241116-193541-e3wfn-meta.warc.gz	4968	download job
www.bayram-gruene.de-inf-20241116-193541-e3wfn-meta.warc.os.cdx.gz	47	download
www.bayram-gruene.de-inf-20241116-193541-e3wfn.json	248	download job
www.curezone.org-inf-20241012-075457-1j4w1-00128.warc.gz	5368740564	download job
www.curezone.org-inf-20241012-075457-1j4w1-00128.warc.os.cdx.gz	2378346	download
www.felixbanaszak.de-inf-20241116-172153-cyetx-00000.warc.gz	5402191549	download job
www.felixbanaszak.de-inf-20241116-172153-cyetx-00000.warc.os.cdx.gz	1632372	download
www.felixbanaszak.de-inf-20241116-172153-cyetx-00001.warc.gz	2109959	download job
www.felixbanaszak.de-inf-20241116-172153-cyetx-00001.warc.os.cdx.gz	14921	download
www.felixbanaszak.de-inf-20241116-172153-cyetx-meta.warc.gz	1049284	download job
www.felixbanaszak.de-inf-20241116-172153-cyetx-meta.warc.os.cdx.gz	47	download
www.felixbanaszak.de-inf-20241116-172153-cyetx.json	248	download job
www.flickr.com-inf-20241107-034128-au6xx-00273.warc.gz	5377013548	download job
www.flickr.com-inf-20241107-034128-au6xx-00273.warc.os.cdx.gz	342923	download
www.maxkarson.com-inf-20241116-192058-6mbb4-00000.warc.gz	39316430	download job
www.maxkarson.com-inf-20241116-192058-6mbb4-00000.warc.os.cdx.gz	23593	download
www.maxkarson.com-inf-20241116-192058-6mbb4-meta.warc.gz	19996	download job
www.maxkarson.com-inf-20241116-192058-6mbb4-meta.warc.os.cdx.gz	47	download
www.maxkarson.com-inf-20241116-192058-6mbb4.json	245	download job
www.mediamatters.org-inf-20241031-091638-8i8rn-00665.warc.gz	5700421337	download job
www.mediamatters.org-inf-20241031-091638-8i8rn-00665.warc.os.cdx.gz	516812	download
www.tenddeapact.com-inf-20241116-190055-4i9wu-00000.warc.gz	24051824	download job
www.tenddeapact.com-inf-20241116-190055-4i9wu-00000.warc.os.cdx.gz	58422	download
www.tenddeapact.com-inf-20241116-190055-4i9wu-meta.warc.gz	40181	download job
www.tenddeapact.com-inf-20241116-190055-4i9wu-meta.warc.os.cdx.gz	47	download
www.tenddeapact.com-inf-20241116-190055-4i9wu.json	244	download job