Item archiveteam_archivebot_go_20261003084504_5b2326e8

Filename	Size
2045.ru-inf-20261002-144111-a79jh-00003.warc.gz	5369065597	download job
2045.ru-inf-20261002-144111-a79jh-00003.warc.os.cdx.gz	2620942	download
aptaujas.austsaule.lv-inf-20261003-083002-8mcsr-00000.warc.gz	82765204	download job
aptaujas.austsaule.lv-inf-20261003-083002-8mcsr-00000.warc.os.cdx.gz	88614	download
aptaujas.austsaule.lv-inf-20261003-083002-8mcsr-meta.warc.gz	58567	download job
aptaujas.austsaule.lv-inf-20261003-083002-8mcsr-meta.warc.os.cdx.gz	47	download
aptaujas.austsaule.lv-inf-20261003-083002-8mcsr.json	249	download job
archiveteam_archivebot_go_20261003084504_5b2326e8.cdx.gz	2672895	download
archiveteam_archivebot_go_20261003084504_5b2326e8.cdx.idx	2611	download
archiveteam_archivebot_go_20261003084504_5b2326e8_files.xml	0	download
archiveteam_archivebot_go_20261003084504_5b2326e8_meta.sqlite	221184	download
archiveteam_archivebot_go_20261003084504_5b2326e8_meta.xml	1046	download
austsaule.lv-inf-20261003-081252-3bydi-00000.warc.gz	15027100	download job
austsaule.lv-inf-20261003-081252-3bydi-00000.warc.os.cdx.gz	21460	download
austsaule.lv-inf-20261003-081252-3bydi-meta.warc.gz	15346	download job
austsaule.lv-inf-20261003-081252-3bydi-meta.warc.os.cdx.gz	47	download
austsaule.lv-inf-20261003-081252-3bydi.json	240	download job
balso.mmn.lv-inf-20261003-083245-2cgc2-00000.warc.gz	3531694	download job
balso.mmn.lv-inf-20261003-083245-2cgc2-00000.warc.os.cdx.gz	10567	download
balso.mmn.lv-inf-20261003-083245-2cgc2-meta.warc.gz	9671	download job
balso.mmn.lv-inf-20261003-083245-2cgc2-meta.warc.os.cdx.gz	47	download
balso.mmn.lv-inf-20261003-083245-2cgc2.json	240	download job
cordis.europa.eu-inf-20260819-053344-a3je4-00035.warc.gz	5368723639	download job
cordis.europa.eu-inf-20260819-053344-a3je4-00035.warc.os.cdx.gz	12610460	download
das.sdss.org-inf-20250226-051304-5s39o-09946.warc.gz	5371378139	download job
das.sdss.org-inf-20250226-051304-5s39o-09946.warc.os.cdx.gz	472361	download
europeanjournalists.org-inf-20261003-023855-371qm-00002.warc.gz	5427545207	download job
europeanjournalists.org-inf-20261003-023855-371qm-00002.warc.os.cdx.gz	1050344	download
focus.fromthehipphoto.com-inf-20261003-032818-2rvsr-00002.warc.gz	5369113921	download job
focus.fromthehipphoto.com-inf-20261003-032818-2rvsr-00002.warc.os.cdx.gz	2306727	download
forums.austsaule.lv-inf-20261003-083034-cgbzd-00000.warc.gz	33344	download job
forums.austsaule.lv-inf-20261003-083034-cgbzd-00000.warc.os.cdx.gz	626	download
forums.austsaule.lv-inf-20261003-083034-cgbzd-meta.warc.gz	3790	download job
forums.austsaule.lv-inf-20261003-083034-cgbzd-meta.warc.os.cdx.gz	47	download
forums.austsaule.lv-inf-20261003-083034-cgbzd.json	247	download job
getlofi.com-inf-20261002-150616-ocicu-00001.warc.gz	5382546473	download job
getlofi.com-inf-20261002-150616-ocicu-00001.warc.os.cdx.gz	5382012	download
headline.nolog.cz-inf-20260919-111604-avyi8-00383.warc.gz	5750450444	download job
headline.nolog.cz-inf-20260919-111604-avyi8-00383.warc.os.cdx.gz	453559	download
laiks.mmn.lv-inf-20261003-083257-5s8dv-00000.warc.gz	4340639	download job
laiks.mmn.lv-inf-20261003-083257-5s8dv-00000.warc.os.cdx.gz	8746	download
laiks.mmn.lv-inf-20261003-083257-5s8dv-meta.warc.gz	8542	download job
laiks.mmn.lv-inf-20261003-083257-5s8dv-meta.warc.os.cdx.gz	47	download
laiks.mmn.lv-inf-20261003-083257-5s8dv.json	240	download job
linksunten.tachanka.org-inf-20260831-131310-36rlu-00026.warc.gz	5671412848	download job
linksunten.tachanka.org-inf-20260831-131310-36rlu-00026.warc.os.cdx.gz	1059938	download
matsda2sh.com-inf-20261002-074628-arb57-00007.warc.gz	5373687443	download job
matsda2sh.com-inf-20261002-074628-arb57-00007.warc.os.cdx.gz	3627341	download
mo-sys.com-inf-20261003-045544-4cqty-meta.warc.gz	1882220	download job
mo-sys.com-inf-20261003-045544-4cqty-meta.warc.os.cdx.gz	47	download
mo-sys.com-inf-20261003-045544-4cqty.json	241	download job
nacionalaapvieniba.lv-inf-20261003-065438-e1xc4-00000.warc.gz	1158823335	download job
nacionalaapvieniba.lv-inf-20261003-065438-e1xc4-00000.warc.os.cdx.gz	1141754	download
nacionalaapvieniba.lv-inf-20261003-065438-e1xc4-meta.warc.gz	891151	download job
nacionalaapvieniba.lv-inf-20261003-065438-e1xc4-meta.warc.os.cdx.gz	47	download
nacionalaapvieniba.lv-inf-20261003-065438-e1xc4.json	249	download job
paraksties.mmn.lv-inf-20261003-083421-39e1r-00000.warc.gz	3047703	download job
paraksties.mmn.lv-inf-20261003-083421-39e1r-00000.warc.os.cdx.gz	3498	download
paraksties.mmn.lv-inf-20261003-083421-39e1r-meta.warc.gz	5334	download job
paraksties.mmn.lv-inf-20261003-083421-39e1r-meta.warc.os.cdx.gz	47	download
paraksties.mmn.lv-inf-20261003-083421-39e1r.json	245	download job
proceedings.neurips.cc-inf-20261003-034133-z44gf-00007.warc.gz	5369003356	download job
proceedings.neurips.cc-inf-20261003-034133-z44gf-00007.warc.os.cdx.gz	393200	download
proceedings.neurips.cc-inf-20261003-034133-z44gf-00008.warc.gz	5371400396	download job
proceedings.neurips.cc-inf-20261003-034133-z44gf-00008.warc.os.cdx.gz	316508	download
programma.mmn.lv-inf-20261003-083428-3txpx-00000.warc.gz	530213	download job
programma.mmn.lv-inf-20261003-083428-3txpx-00000.warc.os.cdx.gz	1243	download
programma.mmn.lv-inf-20261003-083428-3txpx-meta.warc.gz	4125	download job
programma.mmn.lv-inf-20261003-083428-3txpx-meta.warc.os.cdx.gz	47	download
programma.mmn.lv-inf-20261003-083428-3txpx.json	244	download job
radiodiscussions.com-inf-20260921-032744-q4f14-00200.warc.gz	5375118040	download job
radiodiscussions.com-inf-20260921-032744-q4f14-00200.warc.os.cdx.gz	1170144	download
simbolika.mmn.lv-inf-20261003-083456-2u6xs-00000.warc.gz	7048941	download job
simbolika.mmn.lv-inf-20261003-083456-2u6xs-00000.warc.os.cdx.gz	20326	download
simbolika.mmn.lv-inf-20261003-083456-2u6xs-meta.warc.gz	19775	download job
simbolika.mmn.lv-inf-20261003-083456-2u6xs-meta.warc.os.cdx.gz	47	download
simbolika.mmn.lv-inf-20261003-083456-2u6xs.json	244	download job
smiltens.lv-inf-20261003-082458-134g2-00000.warc.gz	26241096	download job
smiltens.lv-inf-20261003-082458-134g2-00000.warc.os.cdx.gz	51083	download
smiltens.lv-inf-20261003-082458-134g2-meta.warc.gz	37348	download job
smiltens.lv-inf-20261003-082458-134g2-meta.warc.os.cdx.gz	47	download
smiltens.lv-inf-20261003-082458-134g2.json	238	download job
studyfinds.com-inf-20260922-030220-8q9yf-00141.warc.gz	5368746466	download job
studyfinds.com-inf-20260922-030220-8q9yf-00141.warc.os.cdx.gz	1759692	download
tjacovandenhout.com-inf-20261003-082713-a95ap-00000.warc.gz	8148161	download job
tjacovandenhout.com-inf-20261003-082713-a95ap-00000.warc.os.cdx.gz	16471	download
tjacovandenhout.com-inf-20261003-082713-a95ap-meta.warc.gz	12996	download job
tjacovandenhout.com-inf-20261003-082713-a95ap-meta.warc.os.cdx.gz	47	download
tjacovandenhout.com-inf-20261003-082713-a95ap.json	247	download job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_3.10.06.txt-shallow-20261003-080139-5m99u-00000.warc.gz	4674866	download job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_3.10.06.txt-shallow-20261003-080139-5m99u-00000.warc.os.cdx.gz	17879	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_3.10.06.txt-shallow-20261003-080139-5m99u-meta.warc.gz	12860	download job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_3.10.06.txt-shallow-20261003-080139-5m99u-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_3.10.06.txt-shallow-20261003-080139-5m99u-urls.txt	29944	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_3.10.06.txt-shallow-20261003-080139-5m99u.json	378	download job
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00488.warc.gz	5371870692	download job
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00488.warc.os.cdx.gz	98761	download
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00489.warc.gz	5370804457	download job
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00489.warc.os.cdx.gz	85578	download
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00490.warc.gz	5374684993	download job
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00490.warc.os.cdx.gz	113058	download
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00491.warc.gz	5370219194	download job
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00491.warc.os.cdx.gz	86913	download
waisn.org-inf-20261002-011606-5hpvr-00003.warc.gz	242773150	download job
waisn.org-inf-20261002-011606-5hpvr-00003.warc.os.cdx.gz	513617	download
waisn.org-inf-20261002-011606-5hpvr-meta.warc.gz	16120125	download job
waisn.org-inf-20261002-011606-5hpvr-meta.warc.os.cdx.gz	47	download
waisn.org-inf-20261002-011606-5hpvr.json	240	download job
www.asuvictas.com.au-inf-20261003-054102-bzppe-00000.warc.gz	1519271024	download job
www.asuvictas.com.au-inf-20261003-054102-bzppe-00000.warc.os.cdx.gz	1900834	download
www.cardkingdom.com-inf-20260916-065210-2gjye-00008.warc.gz	5368765673	download job
www.cardkingdom.com-inf-20260916-065210-2gjye-00008.warc.os.cdx.gz	2627607	download
www.enac.gov.it-inf-20261001-121048-8l0hf-00003.warc.gz	4067615380	download job
www.enac.gov.it-inf-20261001-121048-8l0hf-00003.warc.os.cdx.gz	4250655	download
www.enac.gov.it-inf-20261001-121048-8l0hf-meta.warc.gz	7408366	download job
www.enac.gov.it-inf-20261001-121048-8l0hf-meta.warc.os.cdx.gz	47	download
www.enac.gov.it-inf-20261001-121048-8l0hf.json	242	download job
www.forums.austsaule.lv-inf-20261003-083136-276uo-00000.warc.gz	2477	download job
www.forums.austsaule.lv-inf-20261003-083136-276uo-00000.warc.os.cdx.gz	47	download
www.forums.austsaule.lv-inf-20261003-083136-276uo-meta.warc.gz	3554	download job
www.forums.austsaule.lv-inf-20261003-083136-276uo-meta.warc.os.cdx.gz	47	download
www.forums.austsaule.lv-inf-20261003-083136-276uo.json	251	download job
www.jaunlatviesi.lv-inf-20261003-075150-e7pfe-00000.warc.gz	351120332	download job
www.jaunlatviesi.lv-inf-20261003-075150-e7pfe-00000.warc.os.cdx.gz	347957	download
www.jaunlatviesi.lv-inf-20261003-075150-e7pfe-meta.warc.gz	210728	download job
www.jaunlatviesi.lv-inf-20261003-075150-e7pfe-meta.warc.os.cdx.gz	47	download
www.jaunlatviesi.lv-inf-20261003-075150-e7pfe.json	247	download job
www.julijastepanenko.lv-inf-20261003-081708-ecdxe-00000.warc.gz	11317396	download job
www.julijastepanenko.lv-inf-20261003-081708-ecdxe-00000.warc.os.cdx.gz	7913	download
www.julijastepanenko.lv-inf-20261003-081708-ecdxe-meta.warc.gz	8013	download job
www.julijastepanenko.lv-inf-20261003-081708-ecdxe-meta.warc.os.cdx.gz	47	download
www.julijastepanenko.lv-inf-20261003-081708-ecdxe.json	251	download job
www.lg.com-inf-20260420-102409-9z7tb-00556.warc.gz	5368882347	download job
www.lg.com-inf-20260420-102409-9z7tb-00556.warc.os.cdx.gz	1973528	download
www.mmn.lv-inf-20261003-080241-yghuq-00000.warc.gz	4318032	download job
www.mmn.lv-inf-20261003-080241-yghuq-00000.warc.os.cdx.gz	8694	download
www.mmn.lv-inf-20261003-080241-yghuq-meta.warc.gz	8516	download job
www.mmn.lv-inf-20261003-080241-yghuq-meta.warc.os.cdx.gz	47	download
www.mmn.lv-inf-20261003-080241-yghuq.json	238	download job
www.pluggakuten.se-inf-20261002-113254-7jztk-00006.warc.gz	5400901495	download job
www.pluggakuten.se-inf-20261002-113254-7jztk-00006.warc.os.cdx.gz	3750902	download
www.republika2030.lv-inf-20261003-080130-3l52m-00000.warc.gz	2471	download job
www.republika2030.lv-inf-20261003-080130-3l52m-00000.warc.os.cdx.gz	47	download
www.republika2030.lv-inf-20261003-080130-3l52m-meta.warc.gz	3500	download job
www.republika2030.lv-inf-20261003-080130-3l52m-meta.warc.os.cdx.gz	47	download
www.republika2030.lv-inf-20261003-080130-3l52m.json	248	download job
www.smiltens.lv-inf-20261003-082445-30y86-00000.warc.gz	26425751	download job
www.smiltens.lv-inf-20261003-082445-30y86-00000.warc.os.cdx.gz	50832	download
www.smiltens.lv-inf-20261003-082445-30y86-meta.warc.gz	36636	download job
www.smiltens.lv-inf-20261003-082445-30y86-meta.warc.os.cdx.gz	47	download
www.smiltens.lv-inf-20261003-082445-30y86.json	242	download job
www.tjacovandenhout.com-shallow-20261003-082640-7kmt6-00000.warc.gz	713396	download job
www.tjacovandenhout.com-shallow-20261003-082640-7kmt6-00000.warc.os.cdx.gz	2191	download
www.tjacovandenhout.com-shallow-20261003-082640-7kmt6-meta.warc.gz	4798	download job
www.tjacovandenhout.com-shallow-20261003-082640-7kmt6-meta.warc.os.cdx.gz	47	download
zzs.lv-inf-20261003-062533-9h9oj-00000.warc.gz	1403402552	download job
zzs.lv-inf-20261003-062533-9h9oj-00000.warc.os.cdx.gz	1313366	download
zzs.lv-inf-20261003-062533-9h9oj-meta.warc.gz	835127	download job
zzs.lv-inf-20261003-062533-9h9oj-meta.warc.os.cdx.gz	47	download
zzs.lv-inf-20261003-062533-9h9oj.json	234	download job