Item archiveteam_archivebot_go_20201111230002

Filename	Size
archiveteam_archivebot_go_20201111230002.cdx.gz	34061717	download
archiveteam_archivebot_go_20201111230002.cdx.idx	36410	download
archiveteam_archivebot_go_20201111230002_files.xml	0	download
archiveteam_archivebot_go_20201111230002_meta.sqlite	235520	download
archiveteam_archivebot_go_20201111230002_meta.xml	968	download
bethforcongress.com-inf-20201111-191906-5md6q-00000.warc.gz	581593794	download job
bethforcongress.com-inf-20201111-191906-5md6q-00000.warc.os.cdx.gz	488718	download
bethforcongress.com-inf-20201111-191906-5md6q-meta.warc.gz	316744	download job
bethforcongress.com-inf-20201111-191906-5md6q-meta.warc.os.cdx.gz	47	download
bethforcongress.com-inf-20201111-191906-5md6q.json	244	download job
blakeforcongress.nyc-inf-20201111-212401-5pfuo-00000.warc.gz	867978	download job
blakeforcongress.nyc-inf-20201111-212401-5pfuo-00000.warc.os.cdx.gz	3666	download
blakeforcongress.nyc-inf-20201111-212401-5pfuo-meta.warc.gz	5539	download job
blakeforcongress.nyc-inf-20201111-212401-5pfuo-meta.warc.os.cdx.gz	47	download
blakeforcongress.nyc-inf-20201111-212401-5pfuo.json	244	download job
catherineforcongress.com-inf-20201111-224518-69do4-meta.warc.gz	50029	download job
catherineforcongress.com-inf-20201111-224518-69do4-meta.warc.os.cdx.gz	47	download
catherineforcongress.com-inf-20201111-224518-69do4.json	249	download job
chaimforcongress.com-inf-20201111-224506-4z8v8-meta.warc.gz	79458	download job
chaimforcongress.com-inf-20201111-224506-4z8v8-meta.warc.os.cdx.gz	47	download
conoleforcongress.com-inf-20201111-222539-byqrf-meta.warc.gz	173414	download job
conoleforcongress.com-inf-20201111-222539-byqrf-meta.warc.os.cdx.gz	47	download
conoleforcongress.com-inf-20201111-222539-byqrf.json	246	download job
davidpfranksjrforcongress.com-inf-20201111-223520-1v72v-meta.warc.gz	3617	download job
davidpfranksjrforcongress.com-inf-20201111-223520-1v72v-meta.warc.os.cdx.gz	47	download
frangellbasora2020.com-inf-20201111-222516-d2dt8.json	246	download job
groups.io-inf-20201111-023117-udsgk-00017.warc.gz	5433397838	download job
groups.io-inf-20201111-023117-udsgk-00017.warc.os.cdx.gz	2023150	download
groups.io-inf-20201111-023117-udsgk-meta.warc.gz	12518364	download job
groups.io-inf-20201111-023117-udsgk-meta.warc.os.cdx.gz	47	download
groups.io-inf-20201111-023117-udsgk.json	250	download job
hrf.org-inf-20201111-143746-b4bht-00009.warc.gz	5368753342	download job
hrf.org-inf-20201111-143746-b4bht-00009.warc.os.cdx.gz	1255160	download
lindseyboylan.com-inf-20201111-213009-dgn43-meta.warc.gz	198923	download job
lindseyboylan.com-inf-20201111-213009-dgn43-meta.warc.os.cdx.gz	47	download
lopezforthepeople.com-inf-20201111-200437-8yr4e-00000.warc.gz	5407048509	download job
lopezforthepeople.com-inf-20201111-200437-8yr4e-00000.warc.os.cdx.gz	1205671	download
lopezforthepeople.com-inf-20201111-200437-8yr4e-00001.warc.gz	2725796113	download job
lopezforthepeople.com-inf-20201111-200437-8yr4e-00001.warc.os.cdx.gz	543616	download
lopezforthepeople.com-inf-20201111-200437-8yr4e-meta.warc.gz	1091808	download job
lopezforthepeople.com-inf-20201111-200437-8yr4e-meta.warc.os.cdx.gz	47	download
lopezforthepeople.com-inf-20201111-200437-8yr4e.json	246	download job
melforprogress.com-inf-20201111-212417-59co0-00000.warc.gz	140689660	download job
melforprogress.com-inf-20201111-212417-59co0-00000.warc.os.cdx.gz	187818	download
melforprogress.com-inf-20201111-212417-59co0-meta.warc.gz	149247	download job
melforprogress.com-inf-20201111-212417-59co0-meta.warc.os.cdx.gz	47	download
melforprogress.com-inf-20201111-212417-59co0.json	243	download job
michellecc2020.com-inf-20201111-210600-9d0ma.json	243	download job
mmvforthebronx.com-inf-20201111-212526-ji7fw-00000.warc.gz	9142	download job
mmvforthebronx.com-inf-20201111-212526-ji7fw-00000.warc.os.cdx.gz	263	download
mmvforthebronx.com-inf-20201111-212526-ji7fw-meta.warc.gz	3569	download job
mmvforthebronx.com-inf-20201111-212526-ji7fw-meta.warc.os.cdx.gz	47	download
mmvforthebronx.com-inf-20201111-212526-ji7fw.json	243	download job
mondaireforcongress.com-inf-20201111-210318-doeoh-00000.warc.gz	1084458386	download job
mondaireforcongress.com-inf-20201111-210318-doeoh-00000.warc.os.cdx.gz	461705	download
mondaireforcongress.com-inf-20201111-210318-doeoh-meta.warc.gz	288676	download job
mondaireforcongress.com-inf-20201111-210318-doeoh-meta.warc.os.cdx.gz	47	download
mondaireforcongress.com-inf-20201111-210318-doeoh.json	248	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00185.warc.gz	6801242527	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00185.warc.os.cdx.gz	10040	download
urls-archive.max.fan-twitter-@DrKiumars-20201104T143556Z.txt-shallow-20201111-192116-bxpi8-00001.warc.gz	5368839162	download job
urls-archive.max.fan-twitter-@DrKiumars-20201104T143556Z.txt-shallow-20201111-192116-bxpi8-00001.warc.os.cdx.gz	337492	download
urls-archive.max.fan-twitter-@DrLarryBucshon-20201103T222852Z.txt-shallow-20201111-192119-8tcqf-00000.warc.gz	2878019112	download job
urls-archive.max.fan-twitter-@DrLarryBucshon-20201103T222852Z.txt-shallow-20201111-192119-8tcqf-00000.warc.os.cdx.gz	1281828	download
urls-archive.max.fan-twitter-@DrLarryBucshon-20201103T222852Z.txt-shallow-20201111-192119-8tcqf-meta.warc.gz	812465	download job
urls-archive.max.fan-twitter-@DrLarryBucshon-20201103T222852Z.txt-shallow-20201111-192119-8tcqf-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrLarryBucshon-20201103T222852Z.txt-shallow-20201111-192119-8tcqf-urls.txt	121935	download
urls-archive.max.fan-twitter-@DrLarryBucshon-20201103T222852Z.txt-shallow-20201111-192119-8tcqf.json	383	download job
urls-archive.max.fan-twitter-@DrMalikR-20201103T213954Z.txt-shallow-20201111-192711-73aun-00000.warc.gz	681143353	download job
urls-archive.max.fan-twitter-@DrMalikR-20201103T213954Z.txt-shallow-20201111-192711-73aun-00000.warc.os.cdx.gz	405932	download
urls-archive.max.fan-twitter-@DrMalikR-20201103T213954Z.txt-shallow-20201111-192711-73aun-meta.warc.gz	293512	download job
urls-archive.max.fan-twitter-@DrMalikR-20201103T213954Z.txt-shallow-20201111-192711-73aun-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrMalikR-20201103T213954Z.txt-shallow-20201111-192711-73aun-urls.txt	91677	download
urls-archive.max.fan-twitter-@DrMalikR-20201103T213954Z.txt-shallow-20201111-192711-73aun.json	371	download job
urls-archive.max.fan-twitter-@DrMannySenate-20201104T102733Z.txt-shallow-20201111-192715-6rson-00001.warc.gz	5445172287	download job
urls-archive.max.fan-twitter-@DrMannySenate-20201104T102733Z.txt-shallow-20201111-192715-6rson-00001.warc.os.cdx.gz	187217	download
urls-archive.max.fan-twitter-@DrMannySenate-20201104T102733Z.txt-shallow-20201111-192715-6rson-00002.warc.gz	3961028092	download job
urls-archive.max.fan-twitter-@DrMannySenate-20201104T102733Z.txt-shallow-20201111-192715-6rson-00002.warc.os.cdx.gz	1492669	download
urls-archive.max.fan-twitter-@DrMannySenate-20201104T102733Z.txt-shallow-20201111-192715-6rson-urls.txt	251811	download
urls-archive.max.fan-twitter-@DrMannySenate-20201104T102733Z.txt-shallow-20201111-192715-6rson.json	381	download job
urls-archive.max.fan-twitter-@DrMarkGreen4TN-20201104T103650Z.txt-shallow-20201111-192730-9i4hk-00001.warc.gz	2018335268	download job
urls-archive.max.fan-twitter-@DrMarkGreen4TN-20201104T103650Z.txt-shallow-20201111-192730-9i4hk-00001.warc.os.cdx.gz	1221295	download
urls-archive.max.fan-twitter-@DrMarkGreen4TN-20201104T103650Z.txt-shallow-20201111-192730-9i4hk-meta.warc.gz	1379006	download job
urls-archive.max.fan-twitter-@DrMarkGreen4TN-20201104T103650Z.txt-shallow-20201111-192730-9i4hk-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrMarkGreen4TN-20201104T103650Z.txt-shallow-20201111-192730-9i4hk-urls.txt	185458	download
urls-archive.max.fan-twitter-@DrMarkGreen4TN-20201104T103650Z.txt-shallow-20201111-192730-9i4hk.json	383	download job
urls-archive.max.fan-twitter-@DrNealDunnFL2-20201103T211542Z.txt-shallow-20201111-192735-4di2w-00000.warc.gz	4260901050	download job
urls-archive.max.fan-twitter-@DrNealDunnFL2-20201103T211542Z.txt-shallow-20201111-192735-4di2w-00000.warc.os.cdx.gz	2165659	download
urls-archive.max.fan-twitter-@DrNealDunnFL2-20201103T211542Z.txt-shallow-20201111-192735-4di2w-meta.warc.gz	1289015	download job
urls-archive.max.fan-twitter-@DrNealDunnFL2-20201103T211542Z.txt-shallow-20201111-192735-4di2w-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrNealDunnFL2-20201103T211542Z.txt-shallow-20201111-192735-4di2w-urls.txt	210622	download
urls-archive.max.fan-twitter-@DrNealDunnFL2-20201103T211542Z.txt-shallow-20201111-192735-4di2w.json	381	download job
urls-archive.max.fan-twitter-@DrVEnoch-20201104T092903Z.txt-shallow-20201111-193911-5v3jv-00001.warc.gz	5373347412	download job
urls-archive.max.fan-twitter-@DrVEnoch-20201104T092903Z.txt-shallow-20201111-193911-5v3jv-00001.warc.os.cdx.gz	1350221	download
urls-archive.max.fan-twitter-@Dude4Liberty-20201104T055950Z.txt-shallow-20201111-194347-8xttx-00001.warc.gz	5428031441	download job
urls-archive.max.fan-twitter-@Dude4Liberty-20201104T055950Z.txt-shallow-20201111-194347-8xttx-00001.warc.os.cdx.gz	522488	download
urls-archive.max.fan-twitter-@Dude4Liberty-20201104T055950Z.txt-shallow-20201111-194347-8xttx-00002.warc.gz	5369191712	download job
urls-archive.max.fan-twitter-@Dude4Liberty-20201104T055950Z.txt-shallow-20201111-194347-8xttx-00002.warc.os.cdx.gz	1384354	download
urls-archive.max.fan-twitter-@Duncan4Congress-20201104T102322Z.txt-shallow-20201111-194404-74k0u-urls.txt	60708	download
urls-archive.max.fan-twitter-@drleovalentin-20201103T211131Z.txt-shallow-20201111-192134-at9q0-00000.warc.gz	5395021721	download job
urls-archive.max.fan-twitter-@drleovalentin-20201103T211131Z.txt-shallow-20201111-192134-at9q0-00000.warc.os.cdx.gz	1217264	download
urls-transfer.notkiska.pw-house.gov-representatives-a-inf-20201027-025500-8hpox-00100.warc.gz	5439510860	download job
urls-transfer.notkiska.pw-house.gov-representatives-a-inf-20201027-025500-8hpox-00100.warc.os.cdx.gz	14428	download
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00103.warc.gz	5369814364	download job
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00103.warc.os.cdx.gz	71710	download
urls-transfer.notkiska.pw-twitter-@DHS_Wolf-shallow-20201111-205329-9i5dj-00000.warc.gz	2117655019	download job
urls-transfer.notkiska.pw-twitter-@DHS_Wolf-shallow-20201111-205329-9i5dj-00000.warc.os.cdx.gz	1538068	download
urls-transfer.notkiska.pw-twitter-@DNI_Ratcliffe-shallow-20201111-205316-taa3d-00000.warc.gz	25903990	download job
urls-transfer.notkiska.pw-twitter-@DNI_Ratcliffe-shallow-20201111-205316-taa3d-00000.warc.os.cdx.gz	54063	download
urls-transfer.notkiska.pw-twitter-@DNI_Ratcliffe-shallow-20201111-205316-taa3d-meta.warc.gz	34521	download job
urls-transfer.notkiska.pw-twitter-@DNI_Ratcliffe-shallow-20201111-205316-taa3d-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@DNI_Ratcliffe-shallow-20201111-205316-taa3d-urls.txt	1294	download
urls-transfer.notkiska.pw-twitter-@DNI_Ratcliffe-shallow-20201111-205316-taa3d.json	338	download job
urls-transfer.notkiska.pw-twitter-@HKGTranslator-shallow-20201111-142122-dnob4-00004.warc.gz	3871337856	download job
urls-transfer.notkiska.pw-twitter-@HKGTranslator-shallow-20201111-142122-dnob4-00004.warc.os.cdx.gz	1937145	download
urls-transfer.notkiska.pw-twitter-@HKGTranslator-shallow-20201111-142122-dnob4-meta.warc.gz	3868661	download job
urls-transfer.notkiska.pw-twitter-@HKGTranslator-shallow-20201111-142122-dnob4-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@HKGTranslator-shallow-20201111-142122-dnob4-urls.txt	682998	download
urls-transfer.notkiska.pw-twitter-@HKGTranslator-shallow-20201111-142122-dnob4.json	340	download job
urls-transfer.notkiska.pw-twitter-@HRF-shallow-20201111-143604-em2pk-00009.warc.gz	5420155340	download job
urls-transfer.notkiska.pw-twitter-@HRF-shallow-20201111-143604-em2pk-00009.warc.os.cdx.gz	32160	download
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00036.warc.gz	5402908534	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00036.warc.os.cdx.gz	2213298	download
urls-transfer.notkiska.pw-twitter-@Kasparov63-shallow-20201111-143631-2avte-00001.warc.gz	5937803783	download job
urls-transfer.notkiska.pw-twitter-@Kasparov63-shallow-20201111-143631-2avte-00001.warc.os.cdx.gz	1658443	download
urls-transfer.notkiska.pw-twitter-@OGA_Ron-shallow-20201111-205134-6kyfg-00000.warc.gz	467450190	download job
urls-transfer.notkiska.pw-twitter-@OGA_Ron-shallow-20201111-205134-6kyfg-00000.warc.os.cdx.gz	870084	download
urls-transfer.notkiska.pw-twitter-@OGA_Ron-shallow-20201111-205134-6kyfg-meta.warc.gz	497610	download job
urls-transfer.notkiska.pw-twitter-@OGA_Ron-shallow-20201111-205134-6kyfg-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@OGA_Ron-shallow-20201111-205134-6kyfg-urls.txt	154547	download
urls-transfer.notkiska.pw-twitter-@OGA_Ron-shallow-20201111-205134-6kyfg.json	326	download job
urls-transfer.notkiska.pw-twitter-@Renew_Democracy-shallow-20201111-143448-aphil-00008.warc.gz	2273724316	download job
urls-transfer.notkiska.pw-twitter-@Renew_Democracy-shallow-20201111-143448-aphil-00008.warc.os.cdx.gz	1163838	download
urls-transfer.notkiska.pw-twitter-@RepCloudTX-shallow-20201111-220134-1jw6f.json	332	download job
urls-transfer.notkiska.pw-twitter-@SASCMajority-shallow-20201111-205316-14s7p-00000.warc.gz	315075512	download job
urls-transfer.notkiska.pw-twitter-@SASCMajority-shallow-20201111-205316-14s7p-00000.warc.os.cdx.gz	526901	download
urls-transfer.notkiska.pw-twitter-@SASCMajority-shallow-20201111-205316-14s7p-meta.warc.gz	322815	download job
urls-transfer.notkiska.pw-twitter-@SASCMajority-shallow-20201111-205316-14s7p-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@SASCMajority-shallow-20201111-205316-14s7p-urls.txt	85963	download
urls-transfer.notkiska.pw-twitter-@SASCMajority-shallow-20201111-205316-14s7p.json	336	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00044.warc.gz	5764188930	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00044.warc.os.cdx.gz	257216	download
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00045.warc.gz	5734801855	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00045.warc.os.cdx.gz	709256	download
weinstockforcongress.com-inf-20201111-212352-ecd5a-00000.warc.gz	2486	download job
weinstockforcongress.com-inf-20201111-212352-ecd5a-00000.warc.os.cdx.gz	47	download
weinstockforcongress.com-inf-20201111-212352-ecd5a-meta.warc.gz	3690	download job
weinstockforcongress.com-inf-20201111-212352-ecd5a-meta.warc.os.cdx.gz	47	download
weinstockforcongress.com-inf-20201111-212352-ecd5a.json	249	download job
www.calfornc.com-inf-20201111-175553-ekbl5-00005.warc.gz	5494385724	download job
www.calfornc.com-inf-20201111-175553-ekbl5-00005.warc.os.cdx.gz	156408	download
www.calfornc.com-inf-20201111-175553-ekbl5-00006.warc.gz	5420770674	download job
www.calfornc.com-inf-20201111-175553-ekbl5-00006.warc.os.cdx.gz	521832	download
www.calfornc.com-inf-20201111-175553-ekbl5-00007.warc.gz	1125612355	download job
www.calfornc.com-inf-20201111-175553-ekbl5-00007.warc.os.cdx.gz	341892	download
www.calfornc.com-inf-20201111-175553-ekbl5-meta.warc.gz	2447479	download job
www.calfornc.com-inf-20201111-175553-ekbl5-meta.warc.os.cdx.gz	47	download
www.calfornc.com-inf-20201111-175553-ekbl5.json	241	download job
www.congressmangregorymeeks.com-inf-20201111-221215-b14ft-meta.warc.gz	24803	download job
www.congressmangregorymeeks.com-inf-20201111-221215-b14ft-meta.warc.os.cdx.gz	47	download
www.darrigo2020.com-inf-20201111-212601-dd5q7-00000.warc.gz	1299669350	download job
www.darrigo2020.com-inf-20201111-212601-dd5q7-00000.warc.os.cdx.gz	681494	download
www.darrigo2020.com-inf-20201111-212601-dd5q7-meta.warc.gz	449966	download job
www.darrigo2020.com-inf-20201111-212601-dd5q7-meta.warc.os.cdx.gz	47	download
www.darrigo2020.com-inf-20201111-212601-dd5q7.json	244	download job
www.davidbuchwaldforcongress.com-inf-20201111-223528-9toic-meta.warc.gz	139690	download job
www.davidbuchwaldforcongress.com-inf-20201111-223528-9toic-meta.warc.os.cdx.gz	47	download
www.herzog2020.com-inf-20201111-215253-26uu8-00000.warc.gz	10519	download job
www.herzog2020.com-inf-20201111-215253-26uu8-00000.warc.os.cdx.gz	296	download
www.herzog2020.com-inf-20201111-215253-26uu8-meta.warc.gz	3478	download job
www.herzog2020.com-inf-20201111-215253-26uu8-meta.warc.os.cdx.gz	47	download
www.herzog2020.com-inf-20201111-215253-26uu8.json	243	download job
www.hmdb.org-inf-20201018-175958-aboei-00315.warc.gz	5370239295	download job
www.hmdb.org-inf-20201018-175958-aboei-00315.warc.os.cdx.gz	151773	download
www.instagram.com-inf-20201111-205020-dnktb-00000.warc.gz	32618824	download job
www.instagram.com-inf-20201111-205020-dnktb-00000.warc.os.cdx.gz	72454	download
www.instagram.com-inf-20201111-205020-dnktb-meta.warc.gz	48553	download job
www.instagram.com-inf-20201111-205020-dnktb-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-205020-dnktb.json	264	download job
www.instagram.com-inf-20201111-211417-7gogx-00000.warc.gz	120225972	download job
www.instagram.com-inf-20201111-211417-7gogx-00000.warc.os.cdx.gz	85663	download
www.instagram.com-inf-20201111-211417-7gogx-meta.warc.gz	58496	download job
www.instagram.com-inf-20201111-211417-7gogx-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-211417-7gogx.json	259	download job
www.instagram.com-inf-20201111-213905-576pk-00000.warc.gz	12638903	download job
www.instagram.com-inf-20201111-213905-576pk-00000.warc.os.cdx.gz	51997	download
www.instagram.com-inf-20201111-213905-576pk-meta.warc.gz	39646	download job
www.instagram.com-inf-20201111-213905-576pk-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-213905-576pk.json	259	download job
www.instagram.com-inf-20201111-215220-equcg-00000.warc.gz	20723861	download job
www.instagram.com-inf-20201111-215220-equcg-00000.warc.os.cdx.gz	73977	download
www.instagram.com-inf-20201111-223759-39xu4.json	262	download job
www.jerrynadler.com-inf-20201111-215253-5ao7v-meta.warc.gz	639588	download job
www.jerrynadler.com-inf-20201111-215253-5ao7v-meta.warc.os.cdx.gz	47	download
www.juliopabon.com-inf-20201111-214016-90klc-meta.warc.gz	238740	download job
www.juliopabon.com-inf-20201111-214016-90klc-meta.warc.os.cdx.gz	47	download
www.marlenetapper.com-inf-20201111-212711-910ue.json	246	download job
www.maxroseforcongress.com-inf-20201111-212642-6329z-00000.warc.gz	5378445666	download job
www.maxroseforcongress.com-inf-20201111-212642-6329z-00000.warc.os.cdx.gz	1063748	download
www.refinery29.com-inf-20191002-211042-3symg-00784.warc.gz	5407712617	download job
www.refinery29.com-inf-20191002-211042-3symg-00784.warc.os.cdx.gz	4175478	download
www.surajpatel.nyc-inf-20201111-195413-1crj2-00000.warc.gz	2698574661	download job
www.surajpatel.nyc-inf-20201111-195413-1crj2-00000.warc.os.cdx.gz	1286968	download
www.surajpatel.nyc-inf-20201111-195413-1crj2-meta.warc.gz	832066	download job
www.surajpatel.nyc-inf-20201111-195413-1crj2-meta.warc.os.cdx.gz	47	download
www.surajpatel.nyc-inf-20201111-195413-1crj2.json	243	download job
www.teamgayot.com-inf-20201111-212838-3od5f-00000.warc.gz	138764191	download job
www.teamgayot.com-inf-20201111-212838-3od5f-00000.warc.os.cdx.gz	219032	download
www.teamgayot.com-inf-20201111-212838-3od5f-meta.warc.gz	174575	download job
www.teamgayot.com-inf-20201111-212838-3od5f-meta.warc.os.cdx.gz	47	download
www.teamgayot.com-inf-20201111-212838-3od5f.json	242	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00352.warc.gz	5369669540	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00352.warc.os.cdx.gz	688812	download
www.tigerforcongress.com-inf-20201111-225048-bc34o-meta.warc.gz	26630	download job
www.tigerforcongress.com-inf-20201111-225048-bc34o-meta.warc.os.cdx.gz	47	download
www.votemorelle.com-inf-20201111-214603-48n3b-00000.warc.gz	57915971	download job
www.votemorelle.com-inf-20201111-214603-48n3b-00000.warc.os.cdx.gz	107287	download
www.votemorelle.com-inf-20201111-214603-48n3b-meta.warc.gz	73097	download job
www.votemorelle.com-inf-20201111-214603-48n3b-meta.warc.os.cdx.gz	47	download
www.votemorelle.com-inf-20201111-214603-48n3b.json	244	download job