Item archiveteam_archivebot_go_20191005060003

Filename	Size
ai.googleblog.com-shallow-20191005-052642-7vgjs-00000.warc.gz	6665037	download job
ai.googleblog.com-shallow-20191005-052642-7vgjs-00000.warc.os.cdx.gz	6750	download
ai.googleblog.com-shallow-20191005-052642-7vgjs-meta.warc.gz	7392	download job
ai.googleblog.com-shallow-20191005-052642-7vgjs-meta.warc.os.cdx.gz	47	download
ai.googleblog.com-shallow-20191005-052642-7vgjs.json	293	download job
archiveteam_archivebot_go_20191005060003.cdx.gz	50256131	download
archiveteam_archivebot_go_20191005060003.cdx.idx	50606	download
archiveteam_archivebot_go_20191005060003_files.xml	0	download
archiveteam_archivebot_go_20191005060003_meta.sqlite	152576	download
archiveteam_archivebot_go_20191005060003_meta.xml	1017	download
bg.wikinews.org-inf-20190917-003818-8ljpc-00164.warc.gz	5380506337	download job
bg.wikinews.org-inf-20190917-003818-8ljpc-00164.warc.os.cdx.gz	1018327	download
devblogs.nvidia.com-shallow-20191005-052535-6nrxj-00000.warc.gz	4166211	download job
devblogs.nvidia.com-shallow-20191005-052535-6nrxj-00000.warc.os.cdx.gz	13681	download
devblogs.nvidia.com-shallow-20191005-052535-6nrxj-meta.warc.gz	14028	download job
devblogs.nvidia.com-shallow-20191005-052535-6nrxj-meta.warc.os.cdx.gz	47	download
devblogs.nvidia.com-shallow-20191005-052535-6nrxj.json	284	download job
distill.pub-shallow-20191005-053806-cdwb5-00000.warc.gz	237964	download job
distill.pub-shallow-20191005-053806-cdwb5-00000.warc.os.cdx.gz	1104	download
distill.pub-shallow-20191005-053806-cdwb5-meta.warc.gz	4122	download job
distill.pub-shallow-20191005-053806-cdwb5-meta.warc.os.cdx.gz	47	download
distill.pub-shallow-20191005-053806-cdwb5.json	257	download job
duma.gov.ru-inf-20190927-050108-e8wby-00498.warc.gz	6090963313	download job
duma.gov.ru-inf-20190927-050108-e8wby-00498.warc.os.cdx.gz	863	download
duma.gov.ru-inf-20190927-050108-e8wby-00500.warc.gz	5686598903	download job
duma.gov.ru-inf-20190927-050108-e8wby-00500.warc.os.cdx.gz	744	download
duma.gov.ru-inf-20190927-050108-e8wby-00504.warc.gz	6522821841	download job
duma.gov.ru-inf-20190927-050108-e8wby-00504.warc.os.cdx.gz	892	download
duma.gov.ru-inf-20190927-050108-e8wby-00505.warc.gz	7267359483	download job
duma.gov.ru-inf-20190927-050108-e8wby-00505.warc.os.cdx.gz	953	download
duma.gov.ru-inf-20190927-050108-e8wby-00506.warc.gz	5965550939	download job
duma.gov.ru-inf-20190927-050108-e8wby-00506.warc.os.cdx.gz	31680	download
duma.gov.ru-inf-20190927-050108-e8wby-00507.warc.gz	6761831282	download job
duma.gov.ru-inf-20190927-050108-e8wby-00507.warc.os.cdx.gz	927	download
duma.gov.ru-inf-20190927-050108-e8wby-00508.warc.gz	6268088759	download job
duma.gov.ru-inf-20190927-050108-e8wby-00508.warc.os.cdx.gz	757	download
martin.zinkevich.org-inf-20191005-053217-d57av-00000.warc.gz	109769884	download job
martin.zinkevich.org-inf-20191005-053217-d57av-00000.warc.os.cdx.gz	72597	download
martin.zinkevich.org-inf-20191005-053217-d57av-meta.warc.gz	49616	download job
martin.zinkevich.org-inf-20191005-053217-d57av-meta.warc.os.cdx.gz	47	download
martin.zinkevich.org-inf-20191005-053217-d57av.json	243	download job
martin.zinkevich.org-shallow-20191005-053143-ay7j2-00000.warc.gz	432065	download job
martin.zinkevich.org-shallow-20191005-053143-ay7j2-00000.warc.os.cdx.gz	236	download
martin.zinkevich.org-shallow-20191005-053143-ay7j2-meta.warc.gz	3501	download job
martin.zinkevich.org-shallow-20191005-053143-ay7j2-meta.warc.os.cdx.gz	47	download
martin.zinkevich.org-shallow-20191005-053143-ay7j2.json	274	download job
martin.zinkevich.org-shallow-20191005-053244-22l96-00000.warc.gz	3848	download job
martin.zinkevich.org-shallow-20191005-053244-22l96-00000.warc.os.cdx.gz	224	download
martin.zinkevich.org-shallow-20191005-053244-22l96-meta.warc.gz	3415	download job
martin.zinkevich.org-shallow-20191005-053244-22l96-meta.warc.os.cdx.gz	47	download
martin.zinkevich.org-shallow-20191005-053244-22l96.json	259	download job
medium.com-shallow-20191005-052754-19wu6-00000.warc.gz	4648545	download job
medium.com-shallow-20191005-052754-19wu6-00000.warc.os.cdx.gz	46689	download
medium.com-shallow-20191005-052754-19wu6-meta.warc.gz	27246	download job
medium.com-shallow-20191005-052754-19wu6-meta.warc.os.cdx.gz	47	download
medium.com-shallow-20191005-052754-19wu6.json	289	download job
secure.fangamer.com-inf-20190906-130728-87ymc-00066.warc.gz	5368719296	download job
secure.fangamer.com-inf-20190906-130728-87ymc-00066.warc.os.cdx.gz	3664234	download
techcrunch.com-shallow-20191005-012320-a15a3-00000.warc.gz	55532792	download job
techcrunch.com-shallow-20191005-012320-a15a3-00000.warc.os.cdx.gz	13945	download
techcrunch.com-shallow-20191005-012320-a15a3-meta.warc.gz	12915	download job
techcrunch.com-shallow-20191005-012320-a15a3-meta.warc.os.cdx.gz	47	download
techcrunch.com-shallow-20191005-012320-a15a3.json	279	download job
urls-federico.kapsi.fi-2019-Commons-ImageMatches.txt-shallow-20190731-212532-bixy0-00114.warc.gz	5368821821	download job
urls-federico.kapsi.fi-2019-Commons-ImageMatches.txt-shallow-20190731-212532-bixy0-00114.warc.os.cdx.gz	2687614	download
urls-transfer.notkiska.pw-facebook-@NYCPride-shallow-20191004-133648-ortnl-00009.warc.gz	4670080927	download job
urls-transfer.notkiska.pw-facebook-@NYCPride-shallow-20191004-133648-ortnl-00009.warc.os.cdx.gz	3855548	download
urls-transfer.notkiska.pw-facebook-@NYCPride-shallow-20191004-133648-ortnl-meta.warc.gz	4528853	download job
urls-transfer.notkiska.pw-facebook-@NYCPride-shallow-20191004-133648-ortnl-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@NYCPride-shallow-20191004-133648-ortnl-urls.txt	537600	download
urls-transfer.notkiska.pw-facebook-@NYCPride-shallow-20191004-133648-ortnl.json	330	download job
urls-transfer.notkiska.pw-github.com-chef-inf-20190929-022648-469ub-00012.warc.gz	5551803408	download job
urls-transfer.notkiska.pw-github.com-chef-inf-20190929-022648-469ub-00012.warc.os.cdx.gz	3654050	download
urls-transfer.notkiska.pw-github.com-meteor-inf-20191002-193454-9molm-00005.warc.gz	5389733499	download job
urls-transfer.notkiska.pw-github.com-meteor-inf-20191002-193454-9molm-00005.warc.os.cdx.gz	2419337	download
urls-transfer.notkiska.pw-twitter-@Forever21-shallow-20190930-071335-4bsul-00000.warc.gz	4519684333	download job
urls-transfer.notkiska.pw-twitter-@Forever21-shallow-20190930-071335-4bsul-00000.warc.os.cdx.gz	9350272	download
www.911forum.org.uk-inf-20191001-145544-3mm4q-00029.warc.gz	5597291304	download job
www.911forum.org.uk-inf-20191001-145544-3mm4q-00029.warc.os.cdx.gz	1525284	download
www.911forum.org.uk-inf-20191001-145544-3mm4q-00030.warc.gz	5369605099	download job
www.911forum.org.uk-inf-20191001-145544-3mm4q-00030.warc.os.cdx.gz	1065309	download
www.aosabook.org-shallow-20191005-041941-5mtge-meta.warc.gz	4042	download job
www.aosabook.org-shallow-20191005-041941-5mtge-meta.warc.os.cdx.gz	47	download
www.darkhorseanalytics.com-inf-20191005-041034-1xqgp-00000.warc.gz	966797905	download job
www.darkhorseanalytics.com-inf-20191005-041034-1xqgp-00000.warc.os.cdx.gz	1184939	download
www.darkhorseanalytics.com-inf-20191005-041034-1xqgp-meta.warc.gz	847830	download job
www.darkhorseanalytics.com-inf-20191005-041034-1xqgp-meta.warc.os.cdx.gz	47	download
www.darkhorseanalytics.com-inf-20191005-041034-1xqgp.json	250	download job
www.darkhorseanalytics.com-shallow-20191005-041059-62tgc-00000.warc.gz	8806788	download job
www.darkhorseanalytics.com-shallow-20191005-041059-62tgc-00000.warc.os.cdx.gz	9880	download
www.darkhorseanalytics.com-shallow-20191005-041059-62tgc-meta.warc.gz	56333	download job
www.darkhorseanalytics.com-shallow-20191005-041059-62tgc-meta.warc.os.cdx.gz	47	download
www.darkhorseanalytics.com-shallow-20191005-041059-62tgc.json	268	download job
www.darkhorseanalytics.com-shallow-20191005-041113-7hxsg-meta.warc.gz	55841	download job
www.darkhorseanalytics.com-shallow-20191005-041113-7hxsg-meta.warc.os.cdx.gz	47	download
www.flickr.com-shallow-20191005-053013-4cs1x-00000.warc.gz	29983250	download job
www.flickr.com-shallow-20191005-053013-4cs1x-00000.warc.os.cdx.gz	19728	download
www.flickr.com-shallow-20191005-053013-4cs1x-meta.warc.gz	14644	download job
www.flickr.com-shallow-20191005-053013-4cs1x-meta.warc.os.cdx.gz	47	download
www.flickr.com-shallow-20191005-053013-4cs1x.json	293	download job
www.flickr.com-shallow-20191005-053027-25q63-00000.warc.gz	29982218	download job
www.flickr.com-shallow-20191005-053027-25q63-00000.warc.os.cdx.gz	19755	download
www.flickr.com-shallow-20191005-053027-25q63-meta.warc.gz	14742	download job
www.flickr.com-shallow-20191005-053027-25q63-meta.warc.os.cdx.gz	47	download
www.flickr.com-shallow-20191005-053027-25q63.json	293	download job
www.flickr.com-shallow-20191005-053040-d1x11-00000.warc.gz	30114945	download job
www.flickr.com-shallow-20191005-053040-d1x11-00000.warc.os.cdx.gz	19844	download
www.flickr.com-shallow-20191005-053040-d1x11-meta.warc.gz	14673	download job
www.flickr.com-shallow-20191005-053040-d1x11-meta.warc.os.cdx.gz	47	download
www.flickr.com-shallow-20191005-053040-d1x11.json	293	download job
www.freecodecamp.org-shallow-20191005-013859-d3o21-00000.warc.gz	1872439	download job
www.freecodecamp.org-shallow-20191005-013859-d3o21-00000.warc.os.cdx.gz	5721	download
www.freecodecamp.org-shallow-20191005-013859-d3o21-meta.warc.gz	6769	download job
www.freecodecamp.org-shallow-20191005-013859-d3o21-meta.warc.os.cdx.gz	47	download
www.freecodecamp.org-shallow-20191005-013859-d3o21.json	343	download job
www.igdb.com-inf-20190918-071404-euu3s-00046.warc.gz	5368919205	download job
www.igdb.com-inf-20190918-071404-euu3s-00046.warc.os.cdx.gz	3202896	download
www.interordi.com-inf-20190929-092407-8yi6q-00015.warc.gz	495381778	download job
www.interordi.com-inf-20190929-092407-8yi6q-00015.warc.os.cdx.gz	2262349	download
www.interordi.com-inf-20190929-092407-8yi6q.json	242	download job
www.kaggle.com-shallow-20191005-052937-3ueyf-00000.warc.gz	37242781	download job
www.kaggle.com-shallow-20191005-052937-3ueyf-00000.warc.os.cdx.gz	227383	download
www.kaggle.com-shallow-20191005-052937-3ueyf-meta.warc.gz	109802	download job
www.kaggle.com-shallow-20191005-052937-3ueyf-meta.warc.os.cdx.gz	47	download
www.kaggle.com-shallow-20191005-052937-3ueyf.json	325	download job
www.metroidmetal.com-inf-20191004-025346-9a60m-00000.warc.gz	821569522	download job
www.metroidmetal.com-inf-20191004-025346-9a60m-00000.warc.os.cdx.gz	820386	download
www.metroidmetal.com-inf-20191004-025346-9a60m-meta.warc.gz	635821	download job
www.metroidmetal.com-inf-20191004-025346-9a60m-meta.warc.os.cdx.gz	47	download
www.ndtv.com-inf-20190811-161635-2n7i1-01536.warc.gz	5403763472	download job
www.ndtv.com-inf-20190811-161635-2n7i1-01536.warc.os.cdx.gz	17147	download
www.ndtv.com-inf-20190811-161635-2n7i1-01537.warc.gz	5529161859	download job
www.ndtv.com-inf-20190811-161635-2n7i1-01537.warc.os.cdx.gz	6076	download
www.ndtv.com-inf-20190811-161635-2n7i1-01538.warc.gz	5461342796	download job
www.ndtv.com-inf-20190811-161635-2n7i1-01538.warc.os.cdx.gz	12169	download
www.refinery29.com-inf-20191002-211042-3symg-00013.warc.gz	5373326450	download job
www.refinery29.com-inf-20191002-211042-3symg-00013.warc.os.cdx.gz	1405327	download
www.sbs.com.au-inf-20190921-102041-bcbct-00014.warc.gz	5369671164	download job
www.sbs.com.au-inf-20190921-102041-bcbct-00014.warc.os.cdx.gz	3347912	download
www.sbs.com.au-inf-20190921-102041-bcbct-00015.warc.gz	5406690520	download job
www.sbs.com.au-inf-20190921-102041-bcbct-00015.warc.os.cdx.gz	21185	download
www.smartbrief.com-inf-20190730-200224-592lp-00444.warc.gz	5368882181	download job
www.smartbrief.com-inf-20190730-200224-592lp-00444.warc.os.cdx.gz	1563464	download
www.sunilpatel.co.uk-inf-20191005-020608-6yl83-00002.warc.gz	5368980968	download job
www.sunilpatel.co.uk-inf-20191005-020608-6yl83-00002.warc.os.cdx.gz	509060	download
www.tylervigen.com-shallow-20191005-043418-5ltjo.json	266	download job
www.uel.br-inf-20191003-202822-3peyi-00006.warc.gz	5382102053	download job
www.uel.br-inf-20191003-202822-3peyi-00006.warc.os.cdx.gz	37162	download
www.uepa.br-inf-20191004-073450-c72cp.json	240	download job
www.whatreallyhappened.com-inf-20191001-033014-2hi5l-00044.warc.gz	5403665553	download job
www.whatreallyhappened.com-inf-20191001-033014-2hi5l-00044.warc.os.cdx.gz	3596182	download
www2.uesb.br-inf-20191004-201943-2zt9t-00000.warc.gz	5369178892	download job
www2.uesb.br-inf-20191004-201943-2zt9t-00000.warc.os.cdx.gz	4212958	download