Item archiveteam_archivebot_go_20200919170001

Filename	Size
1776unites.com-inf-20200919-152628-4oy7d-00000.warc.gz	89395712	download job
1776unites.com-inf-20200919-152628-4oy7d-00000.warc.os.cdx.gz	64844	download
1776unites.com-inf-20200919-152628-4oy7d-meta.warc.gz	74327	download job
1776unites.com-inf-20200919-152628-4oy7d-meta.warc.os.cdx.gz	47	download
1776unites.com-inf-20200919-152628-4oy7d.json	264	download job
archiveteam_archivebot_go_20200919170001.cdx.gz	77700610	download
archiveteam_archivebot_go_20200919170001.cdx.idx	63638	download
archiveteam_archivebot_go_20200919170001_files.xml	0	download
archiveteam_archivebot_go_20200919170001_meta.sqlite	143360	download
archiveteam_archivebot_go_20200919170001_meta.xml	969	download
cn.weforum.org-inf-20200919-040844-62b7t-00008.warc.gz	5369228424	download job
cn.weforum.org-inf-20200919-040844-62b7t-00008.warc.os.cdx.gz	2879677	download
cn.weforum.org-inf-20200919-040844-62b7t-00009.warc.gz	5371240197	download job
cn.weforum.org-inf-20200919-040844-62b7t-00009.warc.os.cdx.gz	2845892	download
ektoplazm.com-inf-20200704-233408-66i1h-00252.warc.gz	5957986083	download job
ektoplazm.com-inf-20200704-233408-66i1h-00252.warc.os.cdx.gz	11043	download
gleason4wilcosheriff.com-inf-20200919-154023-700kz-00000.warc.gz	7774037	download job
gleason4wilcosheriff.com-inf-20200919-154023-700kz-00000.warc.os.cdx.gz	24067	download
gleason4wilcosheriff.com-inf-20200919-154023-700kz-meta.warc.gz	17801	download job
gleason4wilcosheriff.com-inf-20200919-154023-700kz-meta.warc.os.cdx.gz	47	download
gleason4wilcosheriff.com-inf-20200919-154023-700kz.json	254	download job
jmc417.personal.asu.edu-inf-20200919-093916-7n9if-00006.warc.gz	5368836268	download job
jmc417.personal.asu.edu-inf-20200919-093916-7n9if-00006.warc.os.cdx.gz	1309352	download
pages.cpsc.ucalgary.ca-inf-20200919-065334-ade0k-00005.warc.gz	5368747208	download job
pages.cpsc.ucalgary.ca-inf-20200919-065334-ade0k-00005.warc.os.cdx.gz	2090613	download
player.fm-inf-20200501-233943-6recr-00832.warc.gz	5392059910	download job
player.fm-inf-20200501-233943-6recr-00832.warc.os.cdx.gz	2117291	download
pulitzercenter.org-inf-20200919-152045-5vrtk-00000.warc.gz	40142471	download job
pulitzercenter.org-inf-20200919-152045-5vrtk-00000.warc.os.cdx.gz	86835	download
pulitzercenter.org-inf-20200919-152045-5vrtk-meta.warc.gz	57852	download job
pulitzercenter.org-inf-20200919-152045-5vrtk-meta.warc.os.cdx.gz	47	download
pulitzercenter.org-inf-20200919-152045-5vrtk.json	292	download job
pulitzercenter.org-shallow-20200919-151852-2h0b7-00000.warc.gz	4007499	download job
pulitzercenter.org-shallow-20200919-151852-2h0b7-00000.warc.os.cdx.gz	12863	download
pulitzercenter.org-shallow-20200919-151852-2h0b7-meta.warc.gz	12900	download job
pulitzercenter.org-shallow-20200919-151852-2h0b7-meta.warc.os.cdx.gz	47	download
pulitzercenter.org-shallow-20200919-151852-2h0b7.json	309	download job
reports.weforum.org-inf-20200919-120841-4a3ri-00000.warc.gz	5368742142	download job
reports.weforum.org-inf-20200919-120841-4a3ri-00000.warc.os.cdx.gz	1688169	download
reports.weforum.org-inf-20200919-120841-4a3ri-00001.warc.gz	4385626225	download job
reports.weforum.org-inf-20200919-120841-4a3ri-00001.warc.os.cdx.gz	1584146	download
reports.weforum.org-inf-20200919-120841-4a3ri-meta.warc.gz	1968513	download job
reports.weforum.org-inf-20200919-120841-4a3ri-meta.warc.os.cdx.gz	47	download
reports.weforum.org-inf-20200919-120841-4a3ri.json	249	download job
tribecafilm.com-inf-20200919-051542-czzi8-00007.warc.gz	5369310278	download job
tribecafilm.com-inf-20200919-051542-czzi8-00007.warc.os.cdx.gz	2558827	download
tribecafilm.com-inf-20200919-051542-czzi8-00008.warc.gz	5617142417	download job
tribecafilm.com-inf-20200919-051542-czzi8-00008.warc.os.cdx.gz	5125	download
urls-etc.sanqui.net-webzdarma_catalogue_05-inf-20200909-092656-9nsso-00031.warc.gz	5547980984	download job
urls-etc.sanqui.net-webzdarma_catalogue_05-inf-20200909-092656-9nsso-00031.warc.os.cdx.gz	4100212	download
urls-etc.sanqui.net-webzdarma_catalogue_05-inf-20200909-092656-9nsso-00032.warc.gz	5402441741	download job
urls-etc.sanqui.net-webzdarma_catalogue_05-inf-20200909-092656-9nsso-00032.warc.os.cdx.gz	13057	download
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00019.warc.gz	5369304921	download job
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00019.warc.os.cdx.gz	7357947	download
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00020.warc.gz	5369307867	download job
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00020.warc.os.cdx.gz	8534755	download
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00021.warc.gz	5372666093	download job
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00021.warc.os.cdx.gz	1839430	download
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00022.warc.gz	5372977722	download job
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00022.warc.os.cdx.gz	1333247	download
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00023.warc.gz	5369623378	download job
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00023.warc.os.cdx.gz	1393418	download
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00024.warc.gz	5369540221	download job
urls-transfer.notkiska.pw-assets.weforum.org-shallow-20200919-020838-e1i0e-00024.warc.os.cdx.gz	1460674	download
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00650.warc.gz	5368761262	download job
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00650.warc.os.cdx.gz	2085912	download
urls-transfer.notkiska.pw-twitter-@MikeGleason2020-shallow-20200919-153523-6dkhm-00000.warc.gz	9526729	download job
urls-transfer.notkiska.pw-twitter-@MikeGleason2020-shallow-20200919-153523-6dkhm-00000.warc.os.cdx.gz	31044	download
urls-transfer.notkiska.pw-twitter-@MikeGleason2020-shallow-20200919-153523-6dkhm-meta.warc.gz	21695	download job
urls-transfer.notkiska.pw-twitter-@MikeGleason2020-shallow-20200919-153523-6dkhm-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@MikeGleason2020-shallow-20200919-153523-6dkhm-urls.txt	1862	download
urls-transfer.notkiska.pw-twitter-@MikeGleason2020-shallow-20200919-153523-6dkhm.json	342	download job
urls-transfer.notkiska.pw-twitter-@elegantthemes-shallow-20200919-093138-17faj-00000.warc.gz	5368886488	download job
urls-transfer.notkiska.pw-twitter-@elegantthemes-shallow-20200919-093138-17faj-00000.warc.os.cdx.gz	3576938	download
urls-transfer.notkiska.pw-twitter-@elegantthemes-shallow-20200919-093138-17faj-00001.warc.gz	5368986646	download job
urls-transfer.notkiska.pw-twitter-@elegantthemes-shallow-20200919-093138-17faj-00001.warc.os.cdx.gz	2712520	download
urls-transfer.notkiska.pw-twitter-@wef-shallow-20200918-193712-an5zi-00001.warc.gz	5368737491	download job
urls-transfer.notkiska.pw-twitter-@wef-shallow-20200918-193712-an5zi-00001.warc.os.cdx.gz	11598006	download
www.chinadaily.com.cn-inf-20190927-102302-505np-00567.warc.gz	1073842504	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00567.warc.os.cdx.gz	993695	download
www.dessci.com-inf-20200919-072718-nk5vc-00001.warc.gz	5368755139	download job
www.dessci.com-inf-20200919-072718-nk5vc-00001.warc.os.cdx.gz	3918053	download
www.gla.ac.uk-shallow-20200919-154727-8gxi7-00000.warc.gz	1235437	download job
www.gla.ac.uk-shallow-20200919-154727-8gxi7-00000.warc.os.cdx.gz	5298	download
www.gla.ac.uk-shallow-20200919-154727-8gxi7-meta.warc.gz	6685	download job
www.gla.ac.uk-shallow-20200919-154727-8gxi7-meta.warc.os.cdx.gz	47	download
www.gla.ac.uk-shallow-20200919-154727-8gxi7.json	287	download job
www.hardlefthegar.com-inf-20200919-144951-374ds-00000.warc.gz	36843652	download job
www.hardlefthegar.com-inf-20200919-144951-374ds-00000.warc.os.cdx.gz	44581	download
www.hardlefthegar.com-inf-20200919-144951-374ds-meta.warc.gz	30052	download job
www.hardlefthegar.com-inf-20200919-144951-374ds-meta.warc.os.cdx.gz	47	download
www.hardlefthegar.com-inf-20200919-144951-374ds.json	251	download job
www.hurleyfuneralhome.com-shallow-20200919-144528-sgpo7-00000.warc.gz	2986937	download job
www.hurleyfuneralhome.com-shallow-20200919-144528-sgpo7-00000.warc.os.cdx.gz	4827	download
www.hurleyfuneralhome.com-shallow-20200919-144528-sgpo7-meta.warc.gz	6310	download job
www.hurleyfuneralhome.com-shallow-20200919-144528-sgpo7-meta.warc.os.cdx.gz	47	download
www.hurleyfuneralhome.com-shallow-20200919-144528-sgpo7.json	282	download job
www.hurleyfuneralhome.com-shallow-20200919-144745-2cbir-00000.warc.gz	4159	download job
www.hurleyfuneralhome.com-shallow-20200919-144745-2cbir-00000.warc.os.cdx.gz	243	download
www.hurleyfuneralhome.com-shallow-20200919-144745-2cbir-meta.warc.gz	3531	download job
www.hurleyfuneralhome.com-shallow-20200919-144745-2cbir-meta.warc.os.cdx.gz	47	download
www.hurleyfuneralhome.com-shallow-20200919-144745-2cbir.json	290	download job
www.laraza1023.com-inf-20200919-010510-4pxzz-00004.warc.gz	6033359402	download job
www.laraza1023.com-inf-20200919-010510-4pxzz-00004.warc.os.cdx.gz	700828	download
www.laraza1023.com-inf-20200919-010510-4pxzz-00005.warc.gz	5498896648	download job
www.laraza1023.com-inf-20200919-010510-4pxzz-00005.warc.os.cdx.gz	833968	download
www.laraza1023.com-inf-20200919-010510-4pxzz-00006.warc.gz	5455932431	download job
www.laraza1023.com-inf-20200919-010510-4pxzz-00006.warc.os.cdx.gz	1295749	download
www.laraza1023.com-inf-20200919-010510-4pxzz-00007.warc.gz	5368752856	download job
www.laraza1023.com-inf-20200919-010510-4pxzz-00007.warc.os.cdx.gz	974879	download
www.nature.com-shallow-20200919-154434-2xufu-00000.warc.gz	3083175	download job
www.nature.com-shallow-20200919-154434-2xufu-00000.warc.os.cdx.gz	6309	download
www.nature.com-shallow-20200919-154434-2xufu-meta.warc.gz	7292	download job
www.nature.com-shallow-20200919-154434-2xufu-meta.warc.os.cdx.gz	47	download
www.nature.com-shallow-20200919-154434-2xufu.json	274	download job
www.nature.com-shallow-20200919-154452-8gt36-00000.warc.gz	3105565	download job
www.nature.com-shallow-20200919-154452-8gt36-00000.warc.os.cdx.gz	484	download
www.nature.com-shallow-20200919-154452-8gt36-meta.warc.gz	3708	download job
www.nature.com-shallow-20200919-154452-8gt36-meta.warc.os.cdx.gz	47	download
www.nature.com-shallow-20200919-154452-8gt36.json	278	download job
www.nytimes.com-inf-20200919-152238-dvpkc-00000.warc.gz	391455926	download job
www.nytimes.com-inf-20200919-152238-dvpkc-00000.warc.os.cdx.gz	444149	download
www.nytimes.com-inf-20200919-152238-dvpkc-meta.warc.gz	281851	download job
www.nytimes.com-inf-20200919-152238-dvpkc-meta.warc.os.cdx.gz	47	download
www.nytimes.com-inf-20200919-152238-dvpkc.json	302	download job
www.patreon.com-shallow-20200919-145810-4gk4b-00000.warc.gz	2850183	download job
www.patreon.com-shallow-20200919-145810-4gk4b-00000.warc.os.cdx.gz	6168	download
www.patreon.com-shallow-20200919-145810-4gk4b-meta.warc.gz	6903	download job
www.patreon.com-shallow-20200919-145810-4gk4b-meta.warc.os.cdx.gz	47	download
www.patreon.com-shallow-20200919-145810-4gk4b.json	264	download job
www.rand.org-shallow-20200919-150722-8tmxh-00000.warc.gz	2745395	download job
www.rand.org-shallow-20200919-150722-8tmxh-00000.warc.os.cdx.gz	12185	download
www.rand.org-shallow-20200919-150722-8tmxh-meta.warc.gz	10734	download job
www.rand.org-shallow-20200919-150722-8tmxh-meta.warc.os.cdx.gz	47	download
www.rand.org-shallow-20200919-150722-8tmxh.json	282	download job
www.rand.org-shallow-20200919-150749-5l8rd-00000.warc.gz	1178407	download job
www.rand.org-shallow-20200919-150749-5l8rd-00000.warc.os.cdx.gz	264	download
www.rand.org-shallow-20200919-150749-5l8rd-meta.warc.gz	3514	download job
www.rand.org-shallow-20200919-150749-5l8rd-meta.warc.os.cdx.gz	47	download
www.rand.org-shallow-20200919-150749-5l8rd.json	308	download job
www.slideshare.net-inf-20200812-025135-7aohq-00233.warc.gz	5375226986	download job
www.slideshare.net-inf-20200812-025135-7aohq-00233.warc.os.cdx.gz	4009561	download
www.unicornlove.com-inf-20200917-173934-71sh8-00010.warc.gz	5369119498	download job
www.unicornlove.com-inf-20200917-173934-71sh8-00010.warc.os.cdx.gz	3606479	download