Item archiveteam_archivebot_go_20231218014404_6f1a9b09

View on Internet Archive

Filename	Size
27.tumblr.com-inf-20230809-001840-cywaz-03759.warc.gz	5369073370	download   job
27.tumblr.com-inf-20230809-001840-cywaz-03759.warc.os.cdx.gz	2122490	download
archive.mozilla.org-inf-20231116-153031-a7e1p-03701.warc.gz	5430311152	download   job
archive.mozilla.org-inf-20231116-153031-a7e1p-03701.warc.os.cdx.gz	68536	download
archive.mozilla.org-inf-20231116-153031-a7e1p-03702.warc.gz	5627836525	download   job
archive.mozilla.org-inf-20231116-153031-a7e1p-03702.warc.os.cdx.gz	52776	download
archive.mozilla.org-inf-20231116-153031-a7e1p-03703.warc.gz	5368915294	download   job
archive.mozilla.org-inf-20231116-153031-a7e1p-03703.warc.os.cdx.gz	57950	download
archiveteam_archivebot_go_20231218014404_6f1a9b09.cdx.gz	49378722	download
archiveteam_archivebot_go_20231218014404_6f1a9b09.cdx.idx	84499	download
archiveteam_archivebot_go_20231218014404_6f1a9b09_files.xml	0	download
archiveteam_archivebot_go_20231218014404_6f1a9b09_meta.sqlite	323584	download
archiveteam_archivebot_go_20231218014404_6f1a9b09_meta.xml	830	download
blog.clark.re-inf-20231218-013442-5ea7d-00000.warc.gz	2629561	download   job
blog.clark.re-inf-20231218-013442-5ea7d-00000.warc.os.cdx.gz	14174	download
blog.clark.re-inf-20231218-013442-5ea7d-meta.warc.gz	11630	download   job
blog.clark.re-inf-20231218-013442-5ea7d-meta.warc.os.cdx.gz	47	download
blog.clark.re-inf-20231218-013442-5ea7d.json	246	download   job
blog.dhchoi82.xyz-inf-20231218-010817-56xac-00000.warc.gz	129197630	download   job
blog.dhchoi82.xyz-inf-20231218-010817-56xac-00000.warc.os.cdx.gz	229096	download
blog.dhchoi82.xyz-inf-20231218-010817-56xac-meta.warc.gz	150541	download   job
blog.dhchoi82.xyz-inf-20231218-010817-56xac-meta.warc.os.cdx.gz	47	download
blog.dhchoi82.xyz-inf-20231218-010817-56xac.json	250	download   job
blog.falcondai.com-inf-20231218-005359-66vx1-00000.warc.gz	1600437379	download   job
blog.falcondai.com-inf-20231218-005359-66vx1-00000.warc.os.cdx.gz	772999	download
blog.falcondai.com-inf-20231218-005359-66vx1-meta.warc.gz	494998	download   job
blog.falcondai.com-inf-20231218-005359-66vx1-meta.warc.os.cdx.gz	47	download
blog.falcondai.com-inf-20231218-005359-66vx1.json	251	download   job
blog.jasonrumney.net-inf-20231218-011350-akc5l-00000.warc.gz	173341638	download   job
blog.jasonrumney.net-inf-20231218-011350-akc5l-00000.warc.os.cdx.gz	371490	download
blog.jasonrumney.net-inf-20231218-011350-akc5l-meta.warc.gz	232538	download   job
blog.jasonrumney.net-inf-20231218-011350-akc5l-meta.warc.os.cdx.gz	47	download
blog.jasonrumney.net-inf-20231218-011350-akc5l.json	253	download   job
blog.mysimplyperfect.com-inf-20231218-001344-efoot-00001.warc.gz	4921998036	download   job
blog.mysimplyperfect.com-inf-20231218-001344-efoot-00001.warc.os.cdx.gz	818060	download
blog.mysimplyperfect.com-inf-20231218-001344-efoot-meta.warc.gz	1702070	download   job
blog.mysimplyperfect.com-inf-20231218-001344-efoot-meta.warc.os.cdx.gz	47	download
blog.mysimplyperfect.com-inf-20231218-001344-efoot.json	256	download   job
blog.richardbrownphoto.ca-inf-20231218-011504-9lk64-00000.warc.gz	51954493	download   job
blog.richardbrownphoto.ca-inf-20231218-011504-9lk64-00000.warc.os.cdx.gz	82972	download
blog.richardbrownphoto.ca-inf-20231218-011504-9lk64-meta.warc.gz	54943	download   job
blog.richardbrownphoto.ca-inf-20231218-011504-9lk64-meta.warc.os.cdx.gz	47	download
blog.richardbrownphoto.ca-inf-20231218-011504-9lk64.json	257	download   job
cefsapprenticeblog.wordpress.com-inf-20231218-001748-9k3cj-00000.warc.gz	1325522800	download   job
cefsapprenticeblog.wordpress.com-inf-20231218-001748-9k3cj-00000.warc.os.cdx.gz	668511	download
cefsapprenticeblog.wordpress.com-inf-20231218-001748-9k3cj-meta.warc.gz	433901	download   job
cefsapprenticeblog.wordpress.com-inf-20231218-001748-9k3cj-meta.warc.os.cdx.gz	47	download
cefsapprenticeblog.wordpress.com-inf-20231218-001748-9k3cj.json	263	download   job
communities.bentley.com-inf-20230908-050158-2petl-00051.warc.gz	5368721282	download   job
communities.bentley.com-inf-20230908-050158-2petl-00051.warc.os.cdx.gz	15036606	download
communityfoodstrategies.org-inf-20231218-010944-57fv9-00000.warc.gz	8183	download   job
communityfoodstrategies.org-inf-20231218-010944-57fv9-00000.warc.os.cdx.gz	47	download
communityfoodstrategies.org-inf-20231218-010944-57fv9-meta.warc.gz	3636	download   job
communityfoodstrategies.org-inf-20231218-010944-57fv9-meta.warc.os.cdx.gz	47	download
communityfoodstrategies.org-inf-20231218-010944-57fv9.json	258	download   job
digitallibrary.un.org-inf-20231205-122636-th9ph-00104.warc.gz	5369834407	download   job
digitallibrary.un.org-inf-20231205-122636-th9ph-00104.warc.os.cdx.gz	2103354	download
edicionesanteriores.revistawhatsup.com-inf-20231218-005559-3auyx-00000.warc.gz	354489664	download   job
edicionesanteriores.revistawhatsup.com-inf-20231218-005559-3auyx-00000.warc.os.cdx.gz	488459	download
edicionesanteriores.revistawhatsup.com-inf-20231218-005559-3auyx-meta.warc.gz	300377	download   job
edicionesanteriores.revistawhatsup.com-inf-20231218-005559-3auyx-meta.warc.os.cdx.gz	47	download
edicionesanteriores.revistawhatsup.com-inf-20231218-005559-3auyx.json	271	download   job
jezebel.com-inf-20231110-162659-439f7-00661.warc.gz	5373022564	download   job
jezebel.com-inf-20231110-162659-439f7-00661.warc.os.cdx.gz	2247900	download
linux.amitmaheshwari.in-inf-20231218-013500-46h14-00000.warc.gz	68995082	download   job
linux.amitmaheshwari.in-inf-20231218-013500-46h14-00000.warc.os.cdx.gz	164416	download
linux.amitmaheshwari.in-inf-20231218-013500-46h14-meta.warc.gz	124821	download   job
linux.amitmaheshwari.in-inf-20231218-013500-46h14-meta.warc.os.cdx.gz	47	download
linux.amitmaheshwari.in-inf-20231218-013500-46h14.json	256	download   job
tech.4pi.si-inf-20231218-005450-dmqyo-00000.warc.gz	409462520	download   job
tech.4pi.si-inf-20231218-005450-dmqyo-00000.warc.os.cdx.gz	645470	download
tech.4pi.si-inf-20231218-005450-dmqyo-meta.warc.gz	392020	download   job
tech.4pi.si-inf-20231218-005450-dmqyo-meta.warc.os.cdx.gz	47	download
tech.4pi.si-inf-20231218-005450-dmqyo.json	243	download   job
urls-transfer.archivete.am-photography-on-the.net-20231117-192655-e4bdk-flickr-shallow-20231202-015745-85n6d-00810.warc.gz	5370051253	download   job
urls-transfer.archivete.am-photography-on-the.net-20231117-192655-e4bdk-flickr-shallow-20231202-015745-85n6d-00810.warc.os.cdx.gz	866700	download
urls-transfer.archivete.am-photography-on-the.net-20231117-192655-e4bdk-flickr-shallow-20231202-015745-85n6d-00811.warc.gz	5369712844	download   job
urls-transfer.archivete.am-photography-on-the.net-20231117-192655-e4bdk-flickr-shallow-20231202-015745-85n6d-00811.warc.os.cdx.gz	770850	download
www.6w2h.org-inf-20231218-003424-6w9a9-00000.warc.gz	1041766325	download   job
www.6w2h.org-inf-20231218-003424-6w9a9-00000.warc.os.cdx.gz	1393939	download
www.6w2h.org-inf-20231218-003424-6w9a9-meta.warc.gz	791174	download   job
www.6w2h.org-inf-20231218-003424-6w9a9-meta.warc.os.cdx.gz	47	download
www.6w2h.org-inf-20231218-003424-6w9a9.json	244	download   job
www.abulakaarchaida.com-inf-20231218-013749-bx91k-00000.warc.gz	130851471	download   job
www.abulakaarchaida.com-inf-20231218-013749-bx91k-00000.warc.os.cdx.gz	170022	download
www.abulakaarchaida.com-inf-20231218-013749-bx91k-meta.warc.gz	116212	download   job
www.abulakaarchaida.com-inf-20231218-013749-bx91k-meta.warc.os.cdx.gz	47	download
www.abulakaarchaida.com-inf-20231218-013749-bx91k.json	255	download   job
www.adsanjaya.com-inf-20231217-235217-cridr-00000.warc.gz	1951535661	download   job
www.adsanjaya.com-inf-20231217-235217-cridr-00000.warc.os.cdx.gz	2091725	download
www.adsanjaya.com-inf-20231217-235217-cridr-meta.warc.gz	2444664	download   job
www.adsanjaya.com-inf-20231217-235217-cridr-meta.warc.os.cdx.gz	47	download
www.adsanjaya.com-inf-20231217-235217-cridr.json	250	download   job
www.apsrtconline.info-inf-20231218-013208-3v6j1-00000.warc.gz	149197287	download   job
www.apsrtconline.info-inf-20231218-013208-3v6j1-00000.warc.os.cdx.gz	159920	download
www.apsrtconline.info-inf-20231218-013208-3v6j1-meta.warc.gz	121542	download   job
www.apsrtconline.info-inf-20231218-013208-3v6j1-meta.warc.os.cdx.gz	47	download
www.apsrtconline.info-inf-20231218-013208-3v6j1.json	254	download   job
www.ashleymay.co.uk-inf-20231218-012401-bncni-00000.warc.gz	10570152	download   job
www.ashleymay.co.uk-inf-20231218-012401-bncni-00000.warc.os.cdx.gz	33950	download
www.ashleymay.co.uk-inf-20231218-012401-bncni-meta.warc.gz	25646	download   job
www.ashleymay.co.uk-inf-20231218-012401-bncni-meta.warc.os.cdx.gz	47	download
www.ashleymay.co.uk-inf-20231218-012401-bncni.json	251	download   job
www.bentbutnotbroken.net-inf-20231218-011116-1ierm-00000.warc.gz	226242438	download   job
www.bentbutnotbroken.net-inf-20231218-011116-1ierm-00000.warc.os.cdx.gz	367734	download
www.bentbutnotbroken.net-inf-20231218-011116-1ierm-meta.warc.gz	240132	download   job
www.bentbutnotbroken.net-inf-20231218-011116-1ierm-meta.warc.os.cdx.gz	47	download
www.bentbutnotbroken.net-inf-20231218-011116-1ierm.json	257	download   job
www.besameapzvalgos.lt-inf-20231217-225037-6agf6-00000.warc.gz	5368805367	download   job
www.besameapzvalgos.lt-inf-20231217-225037-6agf6-00000.warc.os.cdx.gz	3207547	download
www.cabas1997.com-inf-20231217-153334-2pgyt-00007.warc.gz	5484004158	download   job
www.cabas1997.com-inf-20231217-153334-2pgyt-00007.warc.os.cdx.gz	1669872	download
www.cantiquedot.com-inf-20231218-013031-59gpx-00000.warc.gz	222284748	download   job
www.cantiquedot.com-inf-20231218-013031-59gpx-00000.warc.os.cdx.gz	291604	download
www.cantiquedot.com-inf-20231218-013031-59gpx-meta.warc.gz	197806	download   job
www.cantiquedot.com-inf-20231218-013031-59gpx-meta.warc.os.cdx.gz	47	download
www.cantiquedot.com-inf-20231218-013031-59gpx.json	251	download   job
www.cgrecord.net-inf-20231217-175451-8e1i1-00003.warc.gz	5528877987	download   job
www.cgrecord.net-inf-20231217-175451-8e1i1-00003.warc.os.cdx.gz	1814100	download
www.daihatsujogjahargakredit.com-inf-20231218-012228-83zgi-00000.warc.gz	24000993	download   job
www.daihatsujogjahargakredit.com-inf-20231218-012228-83zgi-00000.warc.os.cdx.gz	43317	download
www.daihatsujogjahargakredit.com-inf-20231218-012228-83zgi-meta.warc.gz	30343	download   job
www.daihatsujogjahargakredit.com-inf-20231218-012228-83zgi-meta.warc.os.cdx.gz	47	download
www.daihatsujogjahargakredit.com-inf-20231218-012228-83zgi.json	265	download   job
www.diamondkonveksi.com-inf-20231218-011833-1dj4l-00000.warc.gz	191791543	download   job
www.diamondkonveksi.com-inf-20231218-011833-1dj4l-00000.warc.os.cdx.gz	192894	download
www.diamondkonveksi.com-inf-20231218-011833-1dj4l-meta.warc.gz	119069	download   job
www.diamondkonveksi.com-inf-20231218-011833-1dj4l-meta.warc.os.cdx.gz	47	download
www.diamondkonveksi.com-inf-20231218-011833-1dj4l.json	255	download   job
www.dressesarabia.com-inf-20231218-012259-wp79t-00000.warc.gz	176181102	download   job
www.dressesarabia.com-inf-20231218-012259-wp79t-00000.warc.os.cdx.gz	294365	download
www.dressesarabia.com-inf-20231218-012259-wp79t-meta.warc.gz	188480	download   job
www.dressesarabia.com-inf-20231218-012259-wp79t-meta.warc.os.cdx.gz	47	download
www.dressesarabia.com-inf-20231218-012259-wp79t.json	254	download   job
www.elledecor.com-inf-20231201-200809-4s52c-00118.warc.gz	5369339745	download   job
www.elledecor.com-inf-20231201-200809-4s52c-00118.warc.os.cdx.gz	983067	download
www.evangelisch.de-inf-20231202-091601-703g0-00122.warc.gz	5368828914	download   job
www.evangelisch.de-inf-20231202-091601-703g0-00122.warc.os.cdx.gz	262835	download
www.evangelisch.de-inf-20231202-091601-703g0-00123.warc.gz	5375329307	download   job
www.evangelisch.de-inf-20231202-091601-703g0-00123.warc.os.cdx.gz	272721	download
www.ferret-farm.com-inf-20231218-011516-cixoz-00000.warc.gz	1139213262	download   job
www.ferret-farm.com-inf-20231218-011516-cixoz-00000.warc.os.cdx.gz	599788	download
www.ferret-farm.com-inf-20231218-011516-cixoz-meta.warc.gz	364041	download   job
www.ferret-farm.com-inf-20231218-011516-cixoz-meta.warc.os.cdx.gz	47	download
www.ferret-farm.com-inf-20231218-011516-cixoz.json	252	download   job
www.highriverarmycadets.com-inf-20231218-013306-bv4rc-00000.warc.gz	11850104	download   job
www.highriverarmycadets.com-inf-20231218-013306-bv4rc-00000.warc.os.cdx.gz	54040	download
www.highriverarmycadets.com-inf-20231218-013306-bv4rc-meta.warc.gz	35129	download   job
www.highriverarmycadets.com-inf-20231218-013306-bv4rc-meta.warc.os.cdx.gz	47	download
www.highriverarmycadets.com-inf-20231218-013306-bv4rc.json	259	download   job
www.hingevikerkaar.ee-inf-20231218-011440-cyyk6-00000.warc.gz	111810915	download   job
www.hingevikerkaar.ee-inf-20231218-011440-cyyk6-00000.warc.os.cdx.gz	283478	download
www.hingevikerkaar.ee-inf-20231218-011440-cyyk6-meta.warc.gz	173382	download   job
www.hingevikerkaar.ee-inf-20231218-011440-cyyk6-meta.warc.os.cdx.gz	47	download
www.hingevikerkaar.ee-inf-20231218-011440-cyyk6.json	253	download   job
www.jellygamatmedan.com-inf-20231218-013028-cunhz-00000.warc.gz	108972	download   job
www.jellygamatmedan.com-inf-20231218-013028-cunhz-00000.warc.os.cdx.gz	796	download
www.jellygamatmedan.com-inf-20231218-013028-cunhz-meta.warc.gz	3970	download   job
www.jellygamatmedan.com-inf-20231218-013028-cunhz-meta.warc.os.cdx.gz	47	download
www.jellygamatmedan.com-inf-20231218-013028-cunhz.json	255	download   job
www.joyfulsundiaries.com-inf-20231218-011619-45uxm-00000.warc.gz	179669627	download   job
www.joyfulsundiaries.com-inf-20231218-011619-45uxm-00000.warc.os.cdx.gz	161496	download
www.joyfulsundiaries.com-inf-20231218-011619-45uxm-meta.warc.gz	113289	download   job
www.joyfulsundiaries.com-inf-20231218-011619-45uxm-meta.warc.os.cdx.gz	47	download
www.joyfulsundiaries.com-inf-20231218-011619-45uxm.json	257	download   job
www.justbejess.com-inf-20231218-001901-924qe-00000.warc.gz	2588215662	download   job
www.justbejess.com-inf-20231218-001901-924qe-00000.warc.os.cdx.gz	2368159	download
www.justbejess.com-inf-20231218-001901-924qe-meta.warc.gz	1408741	download   job
www.justbejess.com-inf-20231218-001901-924qe-meta.warc.os.cdx.gz	47	download
www.justbejess.com-inf-20231218-001901-924qe.json	250	download   job
www.kindtoself.com-inf-20231218-013405-a6e6f-00000.warc.gz	7275338	download   job
www.kindtoself.com-inf-20231218-013405-a6e6f-00000.warc.os.cdx.gz	19656	download
www.kindtoself.com-inf-20231218-013405-a6e6f-meta.warc.gz	15214	download   job
www.kindtoself.com-inf-20231218-013405-a6e6f-meta.warc.os.cdx.gz	47	download
www.kindtoself.com-inf-20231218-013405-a6e6f.json	250	download   job
www.lamanchamedia.org-inf-20231218-005138-19bm3-00000.warc.gz	2163345058	download   job
www.lamanchamedia.org-inf-20231218-005138-19bm3-00000.warc.os.cdx.gz	977465	download
www.lamanchamedia.org-inf-20231218-005138-19bm3-meta.warc.gz	689720	download   job
www.lamanchamedia.org-inf-20231218-005138-19bm3-meta.warc.os.cdx.gz	47	download
www.lamanchamedia.org-inf-20231218-005138-19bm3.json	253	download   job
www.microinvest-rzn.ru-inf-20231218-012752-cfqqr-00000.warc.gz	34022734	download   job
www.microinvest-rzn.ru-inf-20231218-012752-cfqqr-00000.warc.os.cdx.gz	27353	download
www.microinvest-rzn.ru-inf-20231218-012752-cfqqr-meta.warc.gz	20043	download   job
www.microinvest-rzn.ru-inf-20231218-012752-cfqqr-meta.warc.os.cdx.gz	47	download
www.microinvest-rzn.ru-inf-20231218-012752-cfqqr.json	255	download   job
www.microspot.ch-inf-20231011-111910-5kblu-00300.warc.gz	5368768592	download   job
www.microspot.ch-inf-20231011-111910-5kblu-00300.warc.os.cdx.gz	2924739	download
www.moetenglishclub.com-inf-20231218-010507-5ifn9-00000.warc.gz	390355198	download   job
www.moetenglishclub.com-inf-20231218-010507-5ifn9-00000.warc.os.cdx.gz	724090	download
www.moetenglishclub.com-inf-20231218-010507-5ifn9-meta.warc.gz	424710	download   job
www.moetenglishclub.com-inf-20231218-010507-5ifn9-meta.warc.os.cdx.gz	47	download
www.moetenglishclub.com-inf-20231218-010507-5ifn9.json	256	download   job
www.pondicherrywiki.com-inf-20231218-010135-7h90q-00000.warc.gz	1117940931	download   job
www.pondicherrywiki.com-inf-20231218-010135-7h90q-00000.warc.os.cdx.gz	1181498	download
www.pondicherrywiki.com-inf-20231218-010135-7h90q-meta.warc.gz	737246	download   job
www.pondicherrywiki.com-inf-20231218-010135-7h90q-meta.warc.os.cdx.gz	47	download
www.pondicherrywiki.com-inf-20231218-010135-7h90q.json	256	download   job
www.quanlanaegreen.com-inf-20231218-010006-28zyf-00000.warc.gz	747796223	download   job
www.quanlanaegreen.com-inf-20231218-010006-28zyf-00000.warc.os.cdx.gz	823185	download
www.quanlanaegreen.com-inf-20231218-010006-28zyf-meta.warc.gz	558709	download   job
www.quanlanaegreen.com-inf-20231218-010006-28zyf-meta.warc.os.cdx.gz	47	download
www.quanlanaegreen.com-inf-20231218-010006-28zyf.json	254	download   job
www.shawnbuttrick.com-inf-20231218-011537-27l23-00000.warc.gz	382263777	download   job
www.shawnbuttrick.com-inf-20231218-011537-27l23-00000.warc.os.cdx.gz	453746	download
www.shawnbuttrick.com-inf-20231218-011537-27l23-meta.warc.gz	303295	download   job
www.shawnbuttrick.com-inf-20231218-011537-27l23-meta.warc.os.cdx.gz	47	download
www.shawnbuttrick.com-inf-20231218-011537-27l23.json	253	download   job
www.simdev.me-inf-20231218-011726-4px6t-00000.warc.gz	2741056	download   job
www.simdev.me-inf-20231218-011726-4px6t-00000.warc.os.cdx.gz	14778	download
www.simdev.me-inf-20231218-011726-4px6t-meta.warc.gz	12466	download   job
www.simdev.me-inf-20231218-011726-4px6t-meta.warc.os.cdx.gz	47	download
www.simdev.me-inf-20231218-011726-4px6t.json	245	download   job
www.tgphoto.co.za-inf-20231218-012555-ejpto-00000.warc.gz	1136560431	download   job
www.tgphoto.co.za-inf-20231218-012555-ejpto-00000.warc.os.cdx.gz	582020	download
www.tgphoto.co.za-inf-20231218-012555-ejpto-meta.warc.gz	349163	download   job
www.tgphoto.co.za-inf-20231218-012555-ejpto-meta.warc.os.cdx.gz	47	download
www.tgphoto.co.za-inf-20231218-012555-ejpto.json	249	download   job
www.thucdonbabau.com-inf-20231218-011806-w2l3g-00000.warc.gz	293263846	download   job
www.thucdonbabau.com-inf-20231218-011806-w2l3g-00000.warc.os.cdx.gz	280217	download
www.thucdonbabau.com-inf-20231218-011806-w2l3g-meta.warc.gz	166618	download   job
www.thucdonbabau.com-inf-20231218-011806-w2l3g-meta.warc.os.cdx.gz	47	download
www.thucdonbabau.com-inf-20231218-011806-w2l3g.json	252	download   job
www.urbanglitch.com-inf-20231218-000158-eisd1-meta.warc.gz	860314	download   job
www.urbanglitch.com-inf-20231218-000158-eisd1-meta.warc.os.cdx.gz	47	download
www.urbanglitch.com-inf-20231218-000158-eisd1.json	251	download   job
www.wacomp.web.id-inf-20231218-010413-1fteq-00000.warc.gz	240281415	download   job
www.wacomp.web.id-inf-20231218-010413-1fteq-00000.warc.os.cdx.gz	236130	download
www.wacomp.web.id-inf-20231218-010413-1fteq-meta.warc.gz	155120	download   job
www.wacomp.web.id-inf-20231218-010413-1fteq-meta.warc.os.cdx.gz	47	download
www.wacomp.web.id-inf-20231218-010413-1fteq.json	249	download   job
www.warli.in-inf-20231218-010925-bfs7z-00000.warc.gz	125387050	download   job
www.warli.in-inf-20231218-010925-bfs7z-00000.warc.os.cdx.gz	254947	download
www.warli.in-inf-20231218-010925-bfs7z-meta.warc.gz	161838	download   job
www.warli.in-inf-20231218-010925-bfs7z-meta.warc.os.cdx.gz	47	download
www.warli.in-inf-20231218-010925-bfs7z.json	244	download   job