Item archiveteam_archivebot_go_20201108080004

Filename	Size
anise4congress.com-inf-20201108-055920-7j7br-00000.warc.gz	30667107	download job
anise4congress.com-inf-20201108-055920-7j7br-00000.warc.os.cdx.gz	37976	download
anise4congress.com-inf-20201108-055920-7j7br-meta.warc.gz	26064	download job
anise4congress.com-inf-20201108-055920-7j7br-meta.warc.os.cdx.gz	47	download
anise4congress.com-inf-20201108-055920-7j7br.json	248	download job
archiveteam_archivebot_go_20201108080004.cdx.gz	62760508	download
archiveteam_archivebot_go_20201108080004.cdx.idx	73596	download
archiveteam_archivebot_go_20201108080004_files.xml	0	download
archiveteam_archivebot_go_20201108080004_meta.sqlite	272384	download
archiveteam_archivebot_go_20201108080004_meta.xml	969	download
blog.travis-ci.com-shallow-20201108-060915-cn5tg-00000.warc.gz	464614	download job
blog.travis-ci.com-shallow-20201108-060915-cn5tg-00000.warc.os.cdx.gz	3030	download
blog.travis-ci.com-shallow-20201108-060915-cn5tg-meta.warc.gz	5080	download job
blog.travis-ci.com-shallow-20201108-060915-cn5tg-meta.warc.os.cdx.gz	47	download
cody-for-congress.tripod.com-inf-20201108-062604-1jju9-meta.warc.gz	93462	download job
cody-for-congress.tripod.com-inf-20201108-062604-1jju9-meta.warc.os.cdx.gz	47	download
discord.qanonanonymous.com-inf-20201108-062818-dv1w1-meta.warc.gz	53194	download job
discord.qanonanonymous.com-inf-20201108-062818-dv1w1-meta.warc.os.cdx.gz	47	download
discord.qanonanonymous.com-inf-20201108-062818-dv1w1.json	250	download job
docs.travis-ci.com-shallow-20201108-060916-8gep4-meta.warc.gz	4912	download job
docs.travis-ci.com-shallow-20201108-060916-8gep4-meta.warc.os.cdx.gz	47	download
games.blog.nl-inf-20201028-205311-2wj7g-00014.warc.gz	4639970856	download job
games.blog.nl-inf-20201028-205311-2wj7g-00014.warc.os.cdx.gz	1992920	download
games.blog.nl-inf-20201028-205311-2wj7g-meta.warc.gz	17906603	download job
games.blog.nl-inf-20201028-205311-2wj7g-meta.warc.os.cdx.gz	47	download
games.blog.nl-inf-20201028-205311-2wj7g.json	238	download job
jennaforsj.com-inf-20201108-063330-9luft-00000.warc.gz	12507	download job
jennaforsj.com-inf-20201108-063330-9luft-00000.warc.os.cdx.gz	325	download
jennaforsj.com-inf-20201108-063330-9luft-meta.warc.gz	3541	download job
jennaforsj.com-inf-20201108-063330-9luft-meta.warc.os.cdx.gz	47	download
jesse4congress.com-inf-20201108-063147-b6s4i-meta.warc.gz	35810	download job
jesse4congress.com-inf-20201108-063147-b6s4i-meta.warc.os.cdx.gz	47	download
jesse4congress.com-inf-20201108-063147-b6s4i.json	247	download job
johnmirrione.com-inf-20201108-063000-4o43k-00000.warc.gz	16739087	download job
johnmirrione.com-inf-20201108-063000-4o43k-00000.warc.os.cdx.gz	70218	download
kathaleenwall.com-inf-20201108-055001-6jf2p-00000.warc.gz	121106086	download job
kathaleenwall.com-inf-20201108-055001-6jf2p-00000.warc.os.cdx.gz	218765	download
kathaleenwall.com-inf-20201108-055001-6jf2p-meta.warc.gz	135216	download job
kathaleenwall.com-inf-20201108-055001-6jf2p-meta.warc.os.cdx.gz	47	download
maggietoulouseoliver.com-shallow-20201108-061100-bxkkk-00000.warc.gz	4186	download job
maggietoulouseoliver.com-shallow-20201108-061100-bxkkk-00000.warc.os.cdx.gz	215	download
maggietoulouseoliver.com-shallow-20201108-061100-bxkkk-meta.warc.gz	3426	download job
maggietoulouseoliver.com-shallow-20201108-061100-bxkkk-meta.warc.os.cdx.gz	47	download
merch.qanonanonymous.com-inf-20201108-062135-dospa-meta.warc.gz	144943	download job
merch.qanonanonymous.com-inf-20201108-062135-dospa-meta.warc.os.cdx.gz	47	download
mickrichforabetteramerica.com-inf-20201108-060502-e0bzn-00000.warc.gz	168632687	download job
mickrichforabetteramerica.com-inf-20201108-060502-e0bzn-00000.warc.os.cdx.gz	114186	download
mickrichforabetteramerica.com-inf-20201108-060502-e0bzn.json	259	download job
njweedmansjoint.com-inf-20201108-061514-9329r-00000.warc.gz	422805356	download job
njweedmansjoint.com-inf-20201108-061514-9329r-00000.warc.os.cdx.gz	309478	download
njweedmansjoint.com-inf-20201108-061514-9329r-meta.warc.gz	212512	download job
njweedmansjoint.com-inf-20201108-061514-9329r-meta.warc.os.cdx.gz	47	download
njweedmansjoint.com-inf-20201108-061514-9329r.json	249	download job
perkinsforsenate.com-inf-20201108-061344-1152r-00000.warc.gz	13700229	download job
perkinsforsenate.com-inf-20201108-061344-1152r-00000.warc.os.cdx.gz	42288	download
perkinsforsenate.com-inf-20201108-061344-1152r-meta.warc.gz	30103	download job
perkinsforsenate.com-inf-20201108-061344-1152r-meta.warc.os.cdx.gz	47	download
perkinsforsenate.com-inf-20201108-061344-1152r.json	250	download job
phoenix.maemo.org-inf-20200926-232644-ektr9-00261.warc.gz	6454320322	download job
phoenix.maemo.org-inf-20200926-232644-ektr9-00261.warc.os.cdx.gz	46614	download
phoenix.maemo.org-inf-20200926-232644-ektr9-00262.warc.gz	5454862626	download job
phoenix.maemo.org-inf-20200926-232644-ektr9-00262.warc.os.cdx.gz	203558	download
ratcliffeforcongress.com-inf-20201108-075449-4ximr.json	248	download job
sanchezfornewmexico.com-inf-20201108-060714-3nnkj.json	253	download job
static01.nyt.com-shallow-20201108-062032-adzce-00000.warc.gz	8881174	download job
static01.nyt.com-shallow-20201108-062032-adzce-00000.warc.os.cdx.gz	8463	download
static01.nyt.com-shallow-20201108-062032-adzce-meta.warc.gz	8437	download job
static01.nyt.com-shallow-20201108-062032-adzce-meta.warc.os.cdx.gz	47	download
static01.nyt.com-shallow-20201108-062032-adzce.json	331	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00173.warc.gz	5652097715	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00173.warc.os.cdx.gz	2058	download
twitter.com-shallow-20201108-065854-ax974-00000.warc.gz	1437032	download job
twitter.com-shallow-20201108-065854-ax974-00000.warc.os.cdx.gz	5868	download
twitter.com-shallow-20201108-065854-ax974-meta.warc.gz	7139	download job
twitter.com-shallow-20201108-065854-ax974-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@BuzzPatterson-20201103T193421Z.txt-shallow-20201107-065815-e9ob8-00021.warc.gz	5377940531	download job
urls-archive.max.fan-twitter-@BuzzPatterson-20201103T193421Z.txt-shallow-20201107-065815-e9ob8-00021.warc.os.cdx.gz	2317748	download
urls-archive.max.fan-twitter-@CJ4Congress2020-20201103T183240Z.txt-shallow-20201108-051810-ch268-00000.warc.gz	5444211342	download job
urls-archive.max.fan-twitter-@CJ4Congress2020-20201103T183240Z.txt-shallow-20201108-051810-ch268-00000.warc.os.cdx.gz	1320256	download
urls-archive.max.fan-twitter-@CJ4Congress2020-20201103T183240Z.txt-shallow-20201108-051810-ch268-00001.warc.gz	2906177755	download job
urls-archive.max.fan-twitter-@CJ4Congress2020-20201103T183240Z.txt-shallow-20201108-051810-ch268-00001.warc.os.cdx.gz	1197246	download
urls-archive.max.fan-twitter-@CJ4Congress2020-20201103T183240Z.txt-shallow-20201108-051810-ch268-meta.warc.gz	1556803	download job
urls-archive.max.fan-twitter-@CJ4Congress2020-20201103T183240Z.txt-shallow-20201108-051810-ch268-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CJBerina-20201103T183242Z.txt-shallow-20201108-052439-dbil6-00000.warc.gz	6413414466	download job
urls-archive.max.fan-twitter-@CJBerina-20201103T183242Z.txt-shallow-20201108-052439-dbil6-00000.warc.os.cdx.gz	187288	download
urls-archive.max.fan-twitter-@ChrisPappasNH-20201104T071705Z.txt-shallow-20201108-013628-1hkzr-00004.warc.gz	2568901247	download job
urls-archive.max.fan-twitter-@ChrisPappasNH-20201104T071705Z.txt-shallow-20201108-013628-1hkzr-00004.warc.os.cdx.gz	1426747	download
urls-archive.max.fan-twitter-@ChuyForCongress-20201103T220533Z.txt-shallow-20201108-042935-90fq3-00000.warc.gz	5384279706	download job
urls-archive.max.fan-twitter-@ChuyForCongress-20201103T220533Z.txt-shallow-20201108-042935-90fq3-00000.warc.os.cdx.gz	1450380	download
urls-archive.max.fan-twitter-@ChuyForCongress-20201103T220533Z.txt-shallow-20201108-042935-90fq3-00002.warc.gz	5485662553	download job
urls-archive.max.fan-twitter-@ChuyForCongress-20201103T220533Z.txt-shallow-20201108-042935-90fq3-00002.warc.os.cdx.gz	482100	download
urls-archive.max.fan-twitter-@ChuyForCongress-20201103T220533Z.txt-shallow-20201108-042935-90fq3-00003.warc.gz	5623931550	download job
urls-archive.max.fan-twitter-@ChuyForCongress-20201103T220533Z.txt-shallow-20201108-042935-90fq3-00003.warc.os.cdx.gz	38247	download
urls-archive.max.fan-twitter-@ClaireChaseNM-20201104T074722Z.txt-shallow-20201108-052751-5kbmi-00000.warc.gz	4580970577	download job
urls-archive.max.fan-twitter-@ClaireChaseNM-20201104T074722Z.txt-shallow-20201108-052751-5kbmi-00000.warc.os.cdx.gz	857371	download
urls-archive.max.fan-twitter-@ClaireChaseNM-20201104T074722Z.txt-shallow-20201108-052751-5kbmi-meta.warc.gz	524952	download job
urls-archive.max.fan-twitter-@ClaireChaseNM-20201104T074722Z.txt-shallow-20201108-052751-5kbmi-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@ClaireGForNJRep-20201104T074121Z.txt-shallow-20201108-052752-36lh8-00000.warc.gz	2208534814	download job
urls-archive.max.fan-twitter-@ClaireGForNJRep-20201104T074121Z.txt-shallow-20201108-052752-36lh8-00000.warc.os.cdx.gz	1309906	download
urls-archive.max.fan-twitter-@ClaireGForNJRep-20201104T074121Z.txt-shallow-20201108-052752-36lh8-meta.warc.gz	782255	download job
urls-archive.max.fan-twitter-@ClaireGForNJRep-20201104T074121Z.txt-shallow-20201108-052752-36lh8-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@ClaireRussoVA-20201104T115324Z.txt-shallow-20201108-055034-45jmo-00000.warc.gz	4473542997	download job
urls-archive.max.fan-twitter-@ClaireRussoVA-20201104T115324Z.txt-shallow-20201108-055034-45jmo-00000.warc.os.cdx.gz	709853	download
urls-archive.max.fan-twitter-@ClaireRussoVA-20201104T115324Z.txt-shallow-20201108-055034-45jmo.json	381	download job
urls-archive.max.fan-twitter-@ClarkPatterson-20201104T114052Z.txt-shallow-20201108-061638-5fnkl.json	383	download job
urls-archive.max.fan-twitter-@ClayChastain1-20201104T135643Z.txt-shallow-20201108-061809-6kqqu-00000.warc.gz	8545283	download job
urls-archive.max.fan-twitter-@ClayChastain1-20201104T135643Z.txt-shallow-20201108-061809-6kqqu-00000.warc.os.cdx.gz	19044	download
urls-archive.max.fan-twitter-@ClayChastain1-20201104T135643Z.txt-shallow-20201108-061809-6kqqu-meta.warc.gz	14953	download job
urls-archive.max.fan-twitter-@ClayChastain1-20201104T135643Z.txt-shallow-20201108-061809-6kqqu-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@ClaytonWBrooks-20201104T085200Z.txt-shallow-20201108-062109-782hp-00000.warc.gz	633684481	download job
urls-archive.max.fan-twitter-@ClaytonWBrooks-20201104T085200Z.txt-shallow-20201108-062109-782hp-00000.warc.os.cdx.gz	756377	download
urls-archive.max.fan-twitter-@ClaytonWBrooks-20201104T085200Z.txt-shallow-20201108-062109-782hp-urls.txt	28668	download
urls-archive.max.fan-twitter-@ClevelandFor30-20201104T110805Z.txt-shallow-20201108-064439-ds52a-00000.warc.gz	6983939	download job
urls-archive.max.fan-twitter-@ClevelandFor30-20201104T110805Z.txt-shallow-20201108-064439-ds52a-00000.warc.os.cdx.gz	14069	download
urls-archive.max.fan-twitter-@Clint4congress-20201103T204444Z.txt-shallow-20201108-064748-71x0l.json	383	download job
urls-archive.max.fan-twitter-@Clint4congress-20201104T042050Z.txt-shallow-20201108-070513-bhfce-00000.warc.gz	12019393	download job
urls-archive.max.fan-twitter-@Clint4congress-20201104T042050Z.txt-shallow-20201108-070513-bhfce-00000.warc.os.cdx.gz	20186	download
urls-archive.max.fan-twitter-@Clint4congress-20201104T042050Z.txt-shallow-20201108-070513-bhfce-meta.warc.gz	15337	download job
urls-archive.max.fan-twitter-@Clint4congress-20201104T042050Z.txt-shallow-20201108-070513-bhfce-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@Clint4congress-20201104T042050Z.txt-shallow-20201108-070513-bhfce-urls.txt	238	download
urls-archive.max.fan-twitter-@ClyburnSC06-20201104T102058Z.txt-shallow-20201108-070708-4imq8-00000.warc.gz	382307449	download job
urls-archive.max.fan-twitter-@ClyburnSC06-20201104T102058Z.txt-shallow-20201108-070708-4imq8-00000.warc.os.cdx.gz	529079	download
urls-archive.max.fan-twitter-@ClyburnSC06-20201104T102058Z.txt-shallow-20201108-070708-4imq8.json	377	download job
urls-archive.max.fan-twitter-@Clyde4Congress-20201104T042339Z.txt-shallow-20201108-072811-9q3j5-00000.warc.gz	10529124	download job
urls-archive.max.fan-twitter-@Clyde4Congress-20201104T042339Z.txt-shallow-20201108-072811-9q3j5-00000.warc.os.cdx.gz	26212	download
urls-archive.max.fan-twitter-@Clyde4Congress-20201104T042339Z.txt-shallow-20201108-072811-9q3j5-meta.warc.gz	19646	download job
urls-archive.max.fan-twitter-@Clyde4Congress-20201104T042339Z.txt-shallow-20201108-072811-9q3j5-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@Clyde4Congress-20201104T042339Z.txt-shallow-20201108-072811-9q3j5-urls.txt	235	download
urls-archive.max.fan-twitter-@cathymcmorris-20201104T122642Z.txt-shallow-20201107-182327-3a2tg-00009.warc.gz	706178938	download job
urls-archive.max.fan-twitter-@cathymcmorris-20201104T122642Z.txt-shallow-20201107-182327-3a2tg-00009.warc.os.cdx.gz	1144089	download
urls-archive.max.fan-twitter-@cathymcmorris-20201104T122642Z.txt-shallow-20201107-182327-3a2tg-meta.warc.gz	6531071	download job
urls-archive.max.fan-twitter-@cathymcmorris-20201104T122642Z.txt-shallow-20201107-182327-3a2tg-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@chrisjollyhale-20201104T102827Z.txt-shallow-20201108-011757-5rxhh-00000.warc.gz	5453600054	download job
urls-archive.max.fan-twitter-@chrisjollyhale-20201104T102827Z.txt-shallow-20201108-011757-5rxhh-00000.warc.os.cdx.gz	3276703	download
urls-archive.max.fan-twitter-@cindyhydesmith-20201104T064105Z.txt-shallow-20201108-050155-b6c61-meta.warc.gz	1568699	download job
urls-archive.max.fan-twitter-@cindyhydesmith-20201104T064105Z.txt-shallow-20201108-050155-b6c61-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@cindyhydesmith-20201104T064105Z.txt-shallow-20201108-050155-b6c61-urls.txt	269008	download
urls-archive.max.fan-twitter-@cindyhydesmith-20201104T064105Z.txt-shallow-20201108-050155-b6c61.json	383	download job
urls-archive.max.fan-twitter-@claraha74184453-20201104T144544Z.txt-shallow-20201108-060300-a6fa3-00000.warc.gz	5428836522	download job
urls-archive.max.fan-twitter-@claraha74184453-20201104T144544Z.txt-shallow-20201108-060300-a6fa3-00000.warc.os.cdx.gz	797759	download
urls-archive.max.fan-twitter-@clarkpatterso12-20201104T114050Z.txt-shallow-20201108-061007-192jw-00000.warc.gz	605555466	download job
urls-archive.max.fan-twitter-@clarkpatterso12-20201104T114050Z.txt-shallow-20201108-061007-192jw-00000.warc.os.cdx.gz	124547	download
urls-archive.max.fan-twitter-@clarkpatterso12-20201104T114050Z.txt-shallow-20201108-061007-192jw-meta.warc.gz	79400	download job
urls-archive.max.fan-twitter-@clarkpatterso12-20201104T114050Z.txt-shallow-20201108-061007-192jw-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@clarkpatterso12-20201104T114050Z.txt-shallow-20201108-061007-192jw-urls.txt	4626	download
urls-archive.max.fan-twitter-@clarkpatterso12-20201104T114050Z.txt-shallow-20201108-061007-192jw.json	385	download job
urls-archive.max.fan-twitter-@cleanupthehouse-20201104T122826Z.txt-shallow-20201108-063004-d9vtf-00000.warc.gz	340638041	download job
urls-archive.max.fan-twitter-@cleanupthehouse-20201104T122826Z.txt-shallow-20201108-063004-d9vtf-00000.warc.os.cdx.gz	188656	download
urls-archive.max.fan-twitter-@cleanupthehouse-20201104T122826Z.txt-shallow-20201108-063004-d9vtf-meta.warc.gz	145567	download job
urls-archive.max.fan-twitter-@cleanupthehouse-20201104T122826Z.txt-shallow-20201108-063004-d9vtf-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@cleanupthehouse-20201104T122826Z.txt-shallow-20201108-063004-d9vtf.json	385	download job
urls-archive.max.fan-twitter-@clintmorgantx-20201104T145036Z.txt-shallow-20201108-070636-4dpqc-urls.txt	111	download
urls-archive.max.fan-twitter-@clintmorgantx-20201104T145036Z.txt-shallow-20201108-070636-4dpqc.json	381	download job
urls-archive.max.fan-twitter-@collincpeterson-20201104T063303Z.txt-shallow-20201108-073742-2pu1t-00000.warc.gz	3749140	download job
urls-archive.max.fan-twitter-@collincpeterson-20201104T063303Z.txt-shallow-20201108-073742-2pu1t-00000.warc.os.cdx.gz	12200	download
urls-archive.max.fan-twitter-@collincpeterson-20201104T063303Z.txt-shallow-20201108-073742-2pu1t-meta.warc.gz	10703	download job
urls-archive.max.fan-twitter-@collincpeterson-20201104T063303Z.txt-shallow-20201108-073742-2pu1t-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@collincpeterson-20201104T063303Z.txt-shallow-20201108-073742-2pu1t-urls.txt	168	download
urls-archive.max.fan-twitter-@collincpeterson-20201104T063303Z.txt-shallow-20201108-073742-2pu1t.json	385	download job
urls-transfer.notkiska.pw-twitter-@Audra4Nm-shallow-20201108-055257-awh16-00000.warc.gz	991787818	download job
urls-transfer.notkiska.pw-twitter-@Audra4Nm-shallow-20201108-055257-awh16-00000.warc.os.cdx.gz	593802	download
urls-transfer.notkiska.pw-twitter-@Audra4Nm-shallow-20201108-055257-awh16-urls.txt	33537	download
urls-transfer.notkiska.pw-twitter-@Audra4Nm-shallow-20201108-055257-awh16.json	328	download job
urls-transfer.notkiska.pw-twitter-@HKrassenstein-shallow-20201107-201602-bjfg9-00001.warc.gz	5368715151	download job
urls-transfer.notkiska.pw-twitter-@HKrassenstein-shallow-20201107-201602-bjfg9-00001.warc.os.cdx.gz	1139061	download
urls-transfer.notkiska.pw-twitter-@HKrassenstein-shallow-20201107-201602-bjfg9-00002.warc.gz	803122794	download job
urls-transfer.notkiska.pw-twitter-@HKrassenstein-shallow-20201107-201602-bjfg9-00002.warc.os.cdx.gz	386991	download
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00002.warc.gz	5528919534	download job
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00002.warc.os.cdx.gz	366724	download
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00004.warc.gz	5397457296	download job
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00004.warc.os.cdx.gz	392852	download
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00005.warc.gz	5563746421	download job
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00005.warc.os.cdx.gz	451192	download
urls-transfer.notkiska.pw-twitter-@aubrey_huff-shallow-20201108-000151-avbbe.json	334	download job
urls-transfer.notkiska.pw-twitter-@eugenegu-shallow-20201107-201711-6czvs-00001.warc.gz	5433675749	download job
urls-transfer.notkiska.pw-twitter-@eugenegu-shallow-20201107-201711-6czvs-00001.warc.os.cdx.gz	3429819	download
urls-transfer.notkiska.pw-twitter-@itsJeffTiedrich-shallow-20201107-195855-9ilxf-00000.warc.gz	5446552190	download job
urls-transfer.notkiska.pw-twitter-@itsJeffTiedrich-shallow-20201107-195855-9ilxf-00000.warc.os.cdx.gz	5450985	download
urls-transfer.notkiska.pw-twitter-@murray_nyc-shallow-20201107-201645-2hkew-00005.warc.gz	5399038471	download job
urls-transfer.notkiska.pw-twitter-@murray_nyc-shallow-20201107-201645-2hkew-00005.warc.os.cdx.gz	4191977	download
wibailoutpeople.org-inf-20201107-152406-7a7zr-00007.warc.gz	5371163721	download job
wibailoutpeople.org-inf-20201107-152406-7a7zr-00007.warc.os.cdx.gz	3080091	download
www.camarilloforcongress.com-inf-20201108-075433-blnf2-00000.warc.gz	7794	download job
www.camarilloforcongress.com-inf-20201108-075433-blnf2-00000.warc.os.cdx.gz	268	download
www.camarilloforcongress.com-inf-20201108-075433-blnf2-meta.warc.gz	3588	download job
www.camarilloforcongress.com-inf-20201108-075433-blnf2-meta.warc.os.cdx.gz	47	download
www.camarilloforcongress.com-inf-20201108-075433-blnf2.json	253	download job
www.capitol.tn.gov-shallow-20201108-061649-eom0l-meta.warc.gz	6957	download job
www.capitol.tn.gov-shallow-20201108-061649-eom0l-meta.warc.os.cdx.gz	47	download
www.capitol.tn.gov-shallow-20201108-061649-eom0l.json	267	download job
www.capitol.tn.gov-shallow-20201108-061906-924st-00000.warc.gz	1725617	download job
www.capitol.tn.gov-shallow-20201108-061906-924st-00000.warc.os.cdx.gz	6266	download
www.capitol.tn.gov-shallow-20201108-061906-924st-meta.warc.gz	6950	download job
www.capitol.tn.gov-shallow-20201108-061906-924st-meta.warc.os.cdx.gz	47	download
www.capitol.tn.gov-shallow-20201108-061906-924st.json	267	download job
www.gao.gov-inf-20201026-025428-c1cke-00026.warc.gz	5368713241	download job
www.gao.gov-inf-20201026-025428-c1cke-00026.warc.os.cdx.gz	22526209	download
www.hmdb.org-inf-20201018-175958-aboei-00274.warc.gz	5374000086	download job
www.hmdb.org-inf-20201018-175958-aboei-00274.warc.os.cdx.gz	137866	download
www.instagram.com-inf-20201108-055156-355zu-00000.warc.gz	96252095	download job
www.instagram.com-inf-20201108-055156-355zu-00000.warc.os.cdx.gz	36856	download
www.instagram.com-inf-20201108-055156-355zu.json	264	download job
www.instagram.com-inf-20201108-060320-ez0qm-00000.warc.gz	16055655	download job
www.instagram.com-inf-20201108-060320-ez0qm-00000.warc.os.cdx.gz	70628	download
www.instagram.com-inf-20201108-062629-b0okq-00000.warc.gz	29656155	download job
www.instagram.com-inf-20201108-062629-b0okq-00000.warc.os.cdx.gz	47996	download
www.instagram.com-inf-20201108-064030-e0veq-00000.warc.gz	11575913	download job
www.instagram.com-inf-20201108-064030-e0veq-00000.warc.os.cdx.gz	33382	download
www.instagram.com-inf-20201108-064030-e0veq-meta.warc.gz	26018	download job
www.instagram.com-inf-20201108-064030-e0veq-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-064030-e0veq.json	264	download job
www.instagram.com-inf-20201108-065110-e7j2n-00000.warc.gz	24282321	download job
www.instagram.com-inf-20201108-065110-e7j2n-00000.warc.os.cdx.gz	34405	download
www.instagram.com-inf-20201108-065110-e7j2n.json	257	download job
www.instagram.com-inf-20201108-070146-5tbrw-meta.warc.gz	39129	download job
www.instagram.com-inf-20201108-070146-5tbrw-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-070146-5tbrw.json	260	download job
www.instagram.com-inf-20201108-072131-312v4-00000.warc.gz	26097832	download job
www.instagram.com-inf-20201108-072131-312v4-00000.warc.os.cdx.gz	32564	download
www.instagram.com-inf-20201108-072131-312v4-meta.warc.gz	25182	download job
www.instagram.com-inf-20201108-072131-312v4-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-073120-tqg02-meta.warc.gz	25676	download job
www.instagram.com-inf-20201108-073120-tqg02-meta.warc.os.cdx.gz	47	download
www.jeffgeerling.com-shallow-20201108-060904-4yszg.json	320	download job
www.joshwinegarner.com-inf-20201108-075257-eg7bq.json	247	download job
www.khaliahforcongress.com-inf-20201108-062440-7oxlf-00000.warc.gz	141675930	download job
www.khaliahforcongress.com-inf-20201108-062440-7oxlf-00000.warc.os.cdx.gz	177313	download
www.khaliahforcongress.com-inf-20201108-062440-7oxlf-meta.warc.gz	127422	download job
www.khaliahforcongress.com-inf-20201108-062440-7oxlf-meta.warc.os.cdx.gz	47	download
www.khaliahforcongress.com-inf-20201108-062440-7oxlf.json	256	download job
www.njweedman.com-inf-20201108-061612-amoah.json	246	download job
www.redstate.com-inf-20201002-220930-4bjxa-00206.warc.gz	5380680366	download job
www.redstate.com-inf-20201002-220930-4bjxa-00206.warc.os.cdx.gz	1574892	download
www.sos.state.nm.us-inf-20201108-061136-3a2u6-00000.warc.gz	3085446176	download job
www.sos.state.nm.us-inf-20201108-061136-3a2u6-00000.warc.os.cdx.gz	1187046	download
www.sos.state.nm.us-inf-20201108-061136-3a2u6-meta.warc.gz	755931	download job
www.sos.state.nm.us-inf-20201108-061136-3a2u6-meta.warc.os.cdx.gz	47	download
www.sos.state.nm.us-inf-20201108-061136-3a2u6.json	249	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00317.warc.gz	5369154297	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00317.warc.os.cdx.gz	845731	download
www.yelp.com-shallow-20201108-073051-3rdwv-00000.warc.gz	4898096	download job
www.yelp.com-shallow-20201108-073051-3rdwv-00000.warc.os.cdx.gz	34009	download
www.yelp.com-shallow-20201108-073051-3rdwv.json	294	download job
www.yelp.com-shallow-20201108-073145-8j2c1.json	303	download job
www.yelp.com-shallow-20201108-073228-bv4b2-00000.warc.gz	7242325	download job
www.yelp.com-shallow-20201108-073228-bv4b2-00000.warc.os.cdx.gz	39721	download
www.yelp.com-shallow-20201108-073228-bv4b2.json	303	download job
www.yelp.com-shallow-20201108-073359-4iz1q.json	293	download job
www.yelp.com-shallow-20201108-073447-bomvj.json	339	download job