Item archiveteam_archivebot_go_20201106200003

Filename	Size
ad33.asmrc.org-inf-20201106-193608-7wl7z-00000.warc.gz	96819555	download job
ad33.asmrc.org-inf-20201106-193608-7wl7z-00000.warc.os.cdx.gz	230671	download
ad33.asmrc.org-inf-20201106-193608-7wl7z-meta.warc.gz	151102	download job
ad33.asmrc.org-inf-20201106-193608-7wl7z-meta.warc.os.cdx.gz	47	download
archiveteam_archivebot_go_20201106200003.cdx.gz	32538121	download
archiveteam_archivebot_go_20201106200003.cdx.idx	30320	download
archiveteam_archivebot_go_20201106200003_files.xml	0	download
archiveteam_archivebot_go_20201106200003_meta.sqlite	144384	download
archiveteam_archivebot_go_20201106200003_meta.xml	968	download
bellinternational.weebly.com-inf-20201106-193626-33ir6-00000.warc.gz	21985935	download job
bellinternational.weebly.com-inf-20201106-193626-33ir6-00000.warc.os.cdx.gz	30212	download
bellinternational.weebly.com-inf-20201106-193626-33ir6.json	253	download job
cementmarketing.com-inf-20201106-193748-2bmsu-00000.warc.gz	29550001	download job
cementmarketing.com-inf-20201106-193748-2bmsu-00000.warc.os.cdx.gz	53389	download
cementmarketing.com-inf-20201106-193748-2bmsu-meta.warc.gz	34421	download job
cementmarketing.com-inf-20201106-193748-2bmsu-meta.warc.os.cdx.gz	47	download
cementmarketing.com-inf-20201106-193748-2bmsu.json	275	download job
ericearly.com-inf-20201106-173603-epaxm-00004.warc.gz	5428331441	download job
ericearly.com-inf-20201106-173603-epaxm-00004.warc.os.cdx.gz	36659	download
ericearly.com-inf-20201106-173603-epaxm-00006.warc.gz	5379905908	download job
ericearly.com-inf-20201106-173603-epaxm-00006.warc.os.cdx.gz	31640	download
ericearly.com-inf-20201106-173603-epaxm-00007.warc.gz	1516322835	download job
ericearly.com-inf-20201106-173603-epaxm-00007.warc.os.cdx.gz	442039	download
ericearly.com-inf-20201106-173603-epaxm-meta.warc.gz	573874	download job
ericearly.com-inf-20201106-173603-epaxm-meta.warc.os.cdx.gz	47	download
ericearly.com-inf-20201106-173603-epaxm.json	244	download job
furnation.ru-inf-20201022-222612-4k00i-00103.warc.gz	5453940925	download job
furnation.ru-inf-20201022-222612-4k00i-00103.warc.os.cdx.gz	2272940	download
gonzalesforcongress.com-inf-20201106-171226-7mdp1-meta.warc.gz	32750	download job
gonzalesforcongress.com-inf-20201106-171226-7mdp1-meta.warc.os.cdx.gz	47	download
jeffforcongress.com-inf-20201106-193916-efnh9-meta.warc.gz	35107	download job
jeffforcongress.com-inf-20201106-193916-efnh9-meta.warc.os.cdx.gz	47	download
jeffforcongress.com-inf-20201106-193916-efnh9.json	250	download job
jeremystaat.com-inf-20201106-194006-emthz-00000.warc.gz	20033634	download job
jeremystaat.com-inf-20201106-194006-emthz-00000.warc.os.cdx.gz	32631	download
jeremystaat.com-inf-20201106-194006-emthz-meta.warc.gz	23760	download job
jeremystaat.com-inf-20201106-194006-emthz-meta.warc.os.cdx.gz	47	download
jones.cssrc.us-inf-20201106-170543-hsuyj-00000.warc.gz	2409472816	download job
jones.cssrc.us-inf-20201106-170543-hsuyj-00000.warc.os.cdx.gz	1566600	download
jones.cssrc.us-inf-20201106-170543-hsuyj-meta.warc.gz	998835	download job
jones.cssrc.us-inf-20201106-170543-hsuyj-meta.warc.os.cdx.gz	47	download
maryottforcongress.com-inf-20201106-170608-bpldl-00000.warc.gz	5469359516	download job
maryottforcongress.com-inf-20201106-170608-bpldl-00000.warc.os.cdx.gz	555761	download
maryottforcongress.com-inf-20201106-170608-bpldl-00001.warc.gz	1300733656	download job
maryottforcongress.com-inf-20201106-170608-bpldl-00001.warc.os.cdx.gz	450086	download
maryottforcongress.com-inf-20201106-170608-bpldl-meta.warc.gz	687913	download job
maryottforcongress.com-inf-20201106-170608-bpldl-meta.warc.os.cdx.gz	47	download
maryottforcongress.com-inf-20201106-170608-bpldl.json	253	download job
matemulawnyc.com-inf-20201106-194048-bbalu-meta.warc.gz	19725	download job
matemulawnyc.com-inf-20201106-194048-bbalu-meta.warc.os.cdx.gz	47	download
matemulawnyc.com-inf-20201106-194048-bbalu.json	240	download job
medium.com-shallow-20201106-193307-7vbfn-00000.warc.gz	8292053	download job
medium.com-shallow-20201106-193307-7vbfn-00000.warc.os.cdx.gz	10072	download
medium.com-shallow-20201106-193307-7vbfn-meta.warc.gz	9443	download job
medium.com-shallow-20201106-193307-7vbfn-meta.warc.os.cdx.gz	47	download
medium.com-shallow-20201106-193307-7vbfn.json	257	download job
mikelevin.org-inf-20201106-010116-2ao4g-00002.warc.gz	2827984235	download job
mikelevin.org-inf-20201106-010116-2ao4g-00002.warc.os.cdx.gz	1508285	download
mikelevin.org-inf-20201106-010116-2ao4g-meta.warc.gz	3036268	download job
mikelevin.org-inf-20201106-010116-2ao4g-meta.warc.os.cdx.gz	47	download
mikelevin.org-inf-20201106-010116-2ao4g.json	244	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00161.warc.gz	7375635864	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00161.warc.os.cdx.gz	714	download
twitter.com-shallow-20201106-175051-10gjo-00000.warc.gz	1164978	download job
twitter.com-shallow-20201106-175051-10gjo-00000.warc.os.cdx.gz	5553	download
urls-archive.max.fan-twitter-@AyannaPressley-20201104T053325Z.txt-shallow-20201106-062248-5nkeo-00019.warc.gz	5383820279	download job
urls-archive.max.fan-twitter-@AyannaPressley-20201104T053325Z.txt-shallow-20201106-062248-5nkeo-00019.warc.os.cdx.gz	873797	download
urls-archive.max.fan-twitter-@BenSasse-20201104T065731Z.txt-shallow-20201106-083511-7547s-00012.warc.gz	5492181131	download job
urls-archive.max.fan-twitter-@BenSasse-20201104T065731Z.txt-shallow-20201106-083511-7547s-00012.warc.os.cdx.gz	895830	download
urls-archive.max.fan-twitter-@BetsySweetME-20201103T230633Z.txt-shallow-20201106-151345-amdi5-00004.warc.gz	5373821980	download job
urls-archive.max.fan-twitter-@BetsySweetME-20201103T230633Z.txt-shallow-20201106-151345-amdi5-00004.warc.os.cdx.gz	320815	download
urls-archive.max.fan-twitter-@Biggan4Congress-20201104T105850Z.txt-shallow-20201106-155450-9x5qp-00002.warc.gz	5907088252	download job
urls-archive.max.fan-twitter-@Biggan4Congress-20201104T105850Z.txt-shallow-20201106-155450-9x5qp-00002.warc.os.cdx.gz	563543	download
urls-archive.max.fan-twitter-@Biggan4Congress-20201104T105850Z.txt-shallow-20201106-155450-9x5qp-00003.warc.gz	5385716976	download job
urls-archive.max.fan-twitter-@Biggan4Congress-20201104T105850Z.txt-shallow-20201106-155450-9x5qp-00003.warc.os.cdx.gz	90025	download
urls-archive.max.fan-twitter-@BillCassidy-20201103T225324Z.txt-shallow-20201106-162558-ch1v7-00000.warc.gz	5368849346	download job
urls-archive.max.fan-twitter-@BillCassidy-20201103T225324Z.txt-shallow-20201106-162558-ch1v7-00000.warc.os.cdx.gz	2759489	download
urls-archive.max.fan-twitter-@anthonyvclark20-20201103T215905Z.txt-shallow-20201106-042404-19o45-00010.warc.gz	5372073507	download job
urls-archive.max.fan-twitter-@anthonyvclark20-20201103T215905Z.txt-shallow-20201106-042404-19o45-00010.warc.os.cdx.gz	1739667	download
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00009.warc.gz	5393229393	download job
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00009.warc.os.cdx.gz	30444	download
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00010.warc.gz	5376169241	download job
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00010.warc.os.cdx.gz	34989	download
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00011.warc.gz	5377816536	download job
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00011.warc.os.cdx.gz	35613	download
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00012.warc.gz	5373783712	download job
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00012.warc.os.cdx.gz	30573	download
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00013.warc.gz	5423373696	download job
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00013.warc.os.cdx.gz	32073	download
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00014.warc.gz	5511472081	download job
urls-archive.max.fan-twitter-@auctnr1-20201104T064858Z.txt-shallow-20201106-054901-7hqkr-00014.warc.os.cdx.gz	32575	download
urls-archive.max.fan-twitter-@billhuizenga-20201104T055928Z.txt-shallow-20201106-164820-f51tf-00001.warc.gz	48964873	download job
urls-archive.max.fan-twitter-@billhuizenga-20201104T055928Z.txt-shallow-20201106-164820-f51tf-00001.warc.os.cdx.gz	115285	download
urls-archive.max.fan-twitter-@billhuizenga-20201104T055928Z.txt-shallow-20201106-164820-f51tf-meta.warc.gz	1253630	download job
urls-archive.max.fan-twitter-@billhuizenga-20201104T055928Z.txt-shallow-20201106-164820-f51tf-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@billhuizenga-20201104T055928Z.txt-shallow-20201106-164820-f51tf-urls.txt	156145	download
urls-archive.max.fan-twitter-@billhuizenga-20201104T055928Z.txt-shallow-20201106-164820-f51tf.json	379	download job
urls-transfer.notkiska.pw-house.gov-representatives-d-inf-20201027-025523-dgqzt-00050.warc.gz	5369197785	download job
urls-transfer.notkiska.pw-house.gov-representatives-d-inf-20201027-025523-dgqzt-00050.warc.os.cdx.gz	3518544	download
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00069.warc.gz	5370359055	download job
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00069.warc.os.cdx.gz	378449	download
urls-transfer.notkiska.pw-twitter-%23Sharpiegate-shallow-20201106-024509-doej0-00004.warc.gz	5388353514	download job
urls-transfer.notkiska.pw-twitter-%23Sharpiegate-shallow-20201106-024509-doej0-00004.warc.os.cdx.gz	2100793	download
urls-transfer.notkiska.pw-twitter-%23Sharpiegate-shallow-20201106-024509-doej0-00005.warc.gz	5414009767	download job
urls-transfer.notkiska.pw-twitter-%23Sharpiegate-shallow-20201106-024509-doej0-00005.warc.os.cdx.gz	1555243	download
urls-transfer.notkiska.pw-twitter-%23Sharpiegate-shallow-20201106-024509-doej0-00006.warc.gz	5369840704	download job
urls-transfer.notkiska.pw-twitter-%23Sharpiegate-shallow-20201106-024509-doej0-00006.warc.os.cdx.gz	345595	download
urls-transfer.notkiska.pw-twitter-@RepMaryFranson-shallow-20201106-141538-cihp3-00000.warc.gz	5401141791	download job
urls-transfer.notkiska.pw-twitter-@RepMaryFranson-shallow-20201106-141538-cihp3-00000.warc.os.cdx.gz	2498482	download
urls-transfer.notkiska.pw-twitter-@realDonaldTrump-shallow-20201106-064533-5vawi-00004.warc.gz	5412889685	download job
urls-transfer.notkiska.pw-twitter-@realDonaldTrump-shallow-20201106-064533-5vawi-00004.warc.os.cdx.gz	2708628	download
ushouserace2020.blogspot.com-inf-20201106-193755-6ghr0.json	253	download job
www.airdragon.us-inf-20201106-193531-9ty8w-00000.warc.gz	247715605	download job
www.airdragon.us-inf-20201106-193531-9ty8w-00000.warc.os.cdx.gz	160056	download
www.airdragon.us-inf-20201106-193531-9ty8w-meta.warc.gz	101279	download job
www.airdragon.us-inf-20201106-193531-9ty8w-meta.warc.os.cdx.gz	47	download
www.airdragon.us-inf-20201106-193531-9ty8w.json	240	download job
www.cruzusa.org-inf-20201106-193302-921iz.json	246	download job
www.debellocongress.com-inf-20201106-194137-b0iv8.json	254	download job
www.diamondsintheroughballparks.org-inf-20201106-193529-71t2f-00000.warc.gz	392794366	download job
www.diamondsintheroughballparks.org-inf-20201106-193529-71t2f-00000.warc.os.cdx.gz	95370	download
www.diamondsintheroughballparks.org-inf-20201106-193529-71t2f-meta.warc.gz	64267	download job
www.diamondsintheroughballparks.org-inf-20201106-193529-71t2f-meta.warc.os.cdx.gz	47	download
www.diamondsintheroughballparks.org-inf-20201106-193529-71t2f.json	260	download job
www.haggardlaw.com-inf-20201106-193125-ddx47-00000.warc.gz	60587824	download job
www.haggardlaw.com-inf-20201106-193125-ddx47-00000.warc.os.cdx.gz	87819	download
www.haggardlaw.com-inf-20201106-193125-ddx47-meta.warc.gz	57039	download job
www.haggardlaw.com-inf-20201106-193125-ddx47-meta.warc.os.cdx.gz	47	download
www.jacobthomas4congress.com-inf-20201106-193420-1unoz-00000.warc.gz	184490042	download job
www.jacobthomas4congress.com-inf-20201106-193420-1unoz-00000.warc.os.cdx.gz	332845	download
www.jmcpa.com-shallow-20201106-193104-5ehsi-00000.warc.gz	9722577	download job
www.jmcpa.com-shallow-20201106-193104-5ehsi-00000.warc.os.cdx.gz	52713	download
www.jmcpa.com-shallow-20201106-193104-5ehsi-meta.warc.gz	63580	download job
www.jmcpa.com-shallow-20201106-193104-5ehsi-meta.warc.os.cdx.gz	47	download
www.jmcpa.com-shallow-20201106-193104-5ehsi.json	276	download job
www.taringa.net-inf-20190927-205127-2a0h7-00941.warc.gz	5372252591	download job
www.taringa.net-inf-20190927-205127-2a0h7-00941.warc.os.cdx.gz	4800536	download
www.teenvogue.com-inf-20200928-163823-6ac7g-00302.warc.gz	5371970630	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00302.warc.os.cdx.gz	744104	download
www.watersforcongress.com-inf-20201106-193529-4tkid.json	256	download job