Item archiveteam_archivebot_go_20201108200004

Filename	Size
apnews.com-shallow-20201108-190237-7hlkr.json	339	download job
archiveteam_archivebot_go_20201108200004.cdx.gz	51135744	download
archiveteam_archivebot_go_20201108200004.cdx.idx	52813	download
archiveteam_archivebot_go_20201108200004_files.xml	0	download
archiveteam_archivebot_go_20201108200004_meta.sqlite	320512	download
archiveteam_archivebot_go_20201108200004_meta.xml	968	download
creativedestructionmedia.com-inf-20201107-145916-dnvdd-00015.warc.gz	7529103294	download job
creativedestructionmedia.com-inf-20201107-145916-dnvdd-00015.warc.os.cdx.gz	3871389	download
cubash.com-inf-20201106-174205-93mse.json	235	download job
events.jo20.com-inf-20201108-152801-bsykm.json	247	download job
hastebin.com-shallow-20201108-170300-3zj96-00000.warc.gz	101771	download job
hastebin.com-shallow-20201108-170300-3zj96-00000.warc.os.cdx.gz	720	download
hastebin.com-shallow-20201108-170300-3zj96-meta.warc.gz	3768	download job
hastebin.com-shallow-20201108-170300-3zj96-meta.warc.os.cdx.gz	47	download
it-support.tomsteyer.com-inf-20201108-145640-b4ihk-meta.warc.gz	65082	download job
it-support.tomsteyer.com-inf-20201108-145640-b4ihk-meta.warc.os.cdx.gz	47	download
it-support.tomsteyer.com-inf-20201108-145640-b4ihk-wpull.log.gz	62359	download
it-support.tomsteyer.com-inf-20201108-145640-b4ihk.json	256	download job
sanjanettabarnes.com-inf-20201108-184736-dd2o9-meta.warc.gz	9921	download job
sanjanettabarnes.com-inf-20201108-184736-dd2o9-meta.warc.os.cdx.gz	47	download
sanjanettabarnes.com-inf-20201108-184736-dd2o9.json	244	download job
seanpaulsegura.com-inf-20201108-184656-6gpfr-meta.warc.gz	63683	download job
seanpaulsegura.com-inf-20201108-184656-6gpfr-meta.warc.os.cdx.gz	47	download
seanpaulsegura.com-inf-20201108-184656-6gpfr.json	243	download job
shannonhutcheson.com-inf-20201108-184650-1ziku-00000.warc.gz	10739	download job
shannonhutcheson.com-inf-20201108-184650-1ziku-00000.warc.os.cdx.gz	259	download
shannonhutcheson.com-inf-20201108-184650-1ziku.json	244	download job
simafortx.com-inf-20201108-184559-7qcc0-00000.warc.gz	127369512	download job
simafortx.com-inf-20201108-184559-7qcc0-00000.warc.os.cdx.gz	227101	download
simafortx.com-inf-20201108-184559-7qcc0.json	238	download job
stephendaniel.com-inf-20201108-184515-3vlmg-00000.warc.gz	116681523	download job
stephendaniel.com-inf-20201108-184515-3vlmg-00000.warc.os.cdx.gz	117750	download
stephendaniel.com-inf-20201108-184515-3vlmg-meta.warc.gz	104994	download job
stephendaniel.com-inf-20201108-184515-3vlmg-meta.warc.os.cdx.gz	47	download
stephendaniel.com-inf-20201108-184515-3vlmg.json	242	download job
urls-archive.max.fan-twitter-@CMonday4Liberty-20201104T104011Z.txt-shallow-20201108-072826-ade8e.json	385	download job
urls-archive.max.fan-twitter-@CheleFarley-20201104T083545Z.txt-shallow-20201107-232253-dsmeh-00001.warc.gz	4246745926	download job
urls-archive.max.fan-twitter-@CheleFarley-20201104T083545Z.txt-shallow-20201107-232253-dsmeh-00001.warc.os.cdx.gz	1835030	download
urls-archive.max.fan-twitter-@CheleFarley-20201104T083545Z.txt-shallow-20201107-232253-dsmeh-urls.txt	234892	download
urls-archive.max.fan-twitter-@CheleFarley-20201104T083545Z.txt-shallow-20201107-232253-dsmeh.json	377	download job
urls-archive.max.fan-twitter-@Cody4CongressNJ-20201104T141215Z.txt-shallow-20201108-073056-8enuf-00001.warc.gz	2576188895	download job
urls-archive.max.fan-twitter-@Cody4CongressNJ-20201104T141215Z.txt-shallow-20201108-073056-8enuf-00001.warc.os.cdx.gz	799845	download
urls-archive.max.fan-twitter-@Cody4CongressNJ-20201104T141215Z.txt-shallow-20201108-073056-8enuf-meta.warc.gz	606356	download job
urls-archive.max.fan-twitter-@Cody4CongressNJ-20201104T141215Z.txt-shallow-20201108-073056-8enuf-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@Cody4CongressNJ-20201104T141215Z.txt-shallow-20201108-073056-8enuf-urls.txt	35813	download
urls-archive.max.fan-twitter-@Cody4CongressNJ-20201104T141215Z.txt-shallow-20201108-073056-8enuf.json	385	download job
urls-archive.max.fan-twitter-@CongPalazzo-20201104T064221Z.txt-shallow-20201108-144713-2qgko-00004.warc.gz	5377241912	download job
urls-archive.max.fan-twitter-@CongPalazzo-20201104T064221Z.txt-shallow-20201108-144713-2qgko-00004.warc.os.cdx.gz	212145	download
urls-archive.max.fan-twitter-@Congress4_IDLaw-20201104T042450Z.txt-shallow-20201108-145349-a655y-00000.warc.gz	2941145	download job
urls-archive.max.fan-twitter-@Congress4_IDLaw-20201104T042450Z.txt-shallow-20201108-145349-a655y-00000.warc.os.cdx.gz	9939	download
urls-archive.max.fan-twitter-@Congress4_IDLaw-20201104T042450Z.txt-shallow-20201108-145349-a655y.json	385	download job
urls-archive.max.fan-twitter-@CongressLawton4-20201103T201059Z.txt-shallow-20201108-151812-3j48j-meta.warc.gz	1904302	download job
urls-archive.max.fan-twitter-@CongressLawton4-20201103T201059Z.txt-shallow-20201108-151812-3j48j-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CongressLawton4-20201103T201059Z.txt-shallow-20201108-151812-3j48j-urls.txt	164161	download
urls-archive.max.fan-twitter-@CongressLawton4-20201104T041937Z.txt-shallow-20201108-183642-7tdw5-00000.warc.gz	6892156	download job
urls-archive.max.fan-twitter-@CongressLawton4-20201104T041937Z.txt-shallow-20201108-183642-7tdw5-00000.warc.os.cdx.gz	19653	download
urls-archive.max.fan-twitter-@CongressLawton4-20201104T041937Z.txt-shallow-20201108-183642-7tdw5-meta.warc.gz	14886	download job
urls-archive.max.fan-twitter-@CongressLawton4-20201104T041937Z.txt-shallow-20201108-183642-7tdw5-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CongressLawton4-20201104T041937Z.txt-shallow-20201108-183642-7tdw5-urls.txt	232	download
urls-archive.max.fan-twitter-@CongressLawton4-20201104T041937Z.txt-shallow-20201108-183642-7tdw5.json	385	download job
urls-archive.max.fan-twitter-@CongressNikki-20201104T134826Z.txt-shallow-20201108-192808-55udz.json	381	download job
urls-archive.max.fan-twitter-@CongressRuth-20201103T221935Z.txt-shallow-20201108-193247-62sm0-00000.warc.gz	55564450	download job
urls-archive.max.fan-twitter-@CongressRuth-20201103T221935Z.txt-shallow-20201108-193247-62sm0-00000.warc.os.cdx.gz	101017	download
urls-archive.max.fan-twitter-@CongressRuth-20201103T221935Z.txt-shallow-20201108-193247-62sm0-meta.warc.gz	62692	download job
urls-archive.max.fan-twitter-@CongressRuth-20201103T221935Z.txt-shallow-20201108-193247-62sm0-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CongressRuth-20201103T221935Z.txt-shallow-20201108-193247-62sm0-urls.txt	7562	download
urls-archive.max.fan-twitter-@CongressRuth-20201103T221935Z.txt-shallow-20201108-193247-62sm0.json	379	download job
urls-archive.max.fan-twitter-@CongressSonny4-20201104T102501Z.txt-shallow-20201108-193247-6l0dz-00000.warc.gz	7442262	download job
urls-archive.max.fan-twitter-@CongressSonny4-20201104T102501Z.txt-shallow-20201108-193247-6l0dz-00000.warc.os.cdx.gz	19086	download
urls-archive.max.fan-twitter-@CongressSonny4-20201104T102501Z.txt-shallow-20201108-193247-6l0dz-meta.warc.gz	14863	download job
urls-archive.max.fan-twitter-@CongressSonny4-20201104T102501Z.txt-shallow-20201108-193247-6l0dz-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CongressSonny4-20201104T102501Z.txt-shallow-20201108-193247-6l0dz.json	383	download job
urls-archive.max.fan-twitter-@CongressTurner-20201104T135406Z.txt-shallow-20201108-193409-3uv7m-00000.warc.gz	6190319	download job
urls-archive.max.fan-twitter-@CongressTurner-20201104T135406Z.txt-shallow-20201108-193409-3uv7m-00000.warc.os.cdx.gz	15682	download
urls-archive.max.fan-twitter-@CongressTurner-20201104T135406Z.txt-shallow-20201108-193409-3uv7m.json	383	download job
urls-archive.max.fan-twitter-@CongressmanHice-20201104T042401Z.txt-shallow-20201108-183807-4ch2r-meta.warc.gz	10407	download job
urls-archive.max.fan-twitter-@CongressmanHice-20201104T042401Z.txt-shallow-20201108-183807-4ch2r-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CongressmanHice-20201104T042401Z.txt-shallow-20201108-183807-4ch2r.json	385	download job
urls-archive.max.fan-twitter-@CongressmanJVD-20201104T074146Z.txt-shallow-20201108-183914-9ns9t-meta.warc.gz	2867504	download job
urls-archive.max.fan-twitter-@CongressmanJVD-20201104T074146Z.txt-shallow-20201108-183914-9ns9t-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CongressmanJVD-20201104T074146Z.txt-shallow-20201108-183914-9ns9t-urls.txt	76275	download
urls-archive.max.fan-twitter-@CongressmanJVD-20201104T074146Z.txt-shallow-20201108-183914-9ns9t.json	383	download job
urls-archive.max.fan-twitter-@CongressmanRaja-20201104T042534Z.txt-shallow-20201108-192807-3cqsb-meta.warc.gz	31681	download job
urls-archive.max.fan-twitter-@CongressmanRaja-20201104T042534Z.txt-shallow-20201108-192807-3cqsb-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CongressmanRaja-20201104T042534Z.txt-shallow-20201108-192807-3cqsb-urls.txt	238	download
urls-archive.max.fan-twitter-@CongressmanRaja-20201104T042534Z.txt-shallow-20201108-192807-3cqsb.json	385	download job
urls-archive.max.fan-twitter-@CopeTN2020-20201104T102744Z.txt-shallow-20201108-193915-9h8uq-00000.warc.gz	122109424	download job
urls-archive.max.fan-twitter-@CopeTN2020-20201104T102744Z.txt-shallow-20201108-193915-9h8uq-00000.warc.os.cdx.gz	157465	download
urls-archive.max.fan-twitter-@CopeTN2020-20201104T102744Z.txt-shallow-20201108-193915-9h8uq-meta.warc.gz	98956	download job
urls-archive.max.fan-twitter-@CopeTN2020-20201104T102744Z.txt-shallow-20201108-193915-9h8uq-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CopeTN2020-20201104T102744Z.txt-shallow-20201108-193915-9h8uq-urls.txt	4576	download
urls-archive.max.fan-twitter-@CopeTN2020-20201104T102744Z.txt-shallow-20201108-193915-9h8uq.json	375	download job
urls-archive.max.fan-twitter-@CornwellforNY-20201104T142608Z.txt-shallow-20201108-195141-8eq04-meta.warc.gz	31124	download job
urls-archive.max.fan-twitter-@CornwellforNY-20201104T142608Z.txt-shallow-20201108-195141-8eq04-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CornwellforNY-20201104T142608Z.txt-shallow-20201108-195141-8eq04-urls.txt	2820	download
urls-archive.max.fan-twitter-@CornwellforNY-20201104T142608Z.txt-shallow-20201108-195141-8eq04.json	381	download job
urls-archive.max.fan-twitter-@chrisjollyhale-20201104T102827Z.txt-shallow-20201108-011757-5rxhh-00007.warc.gz	5451562804	download job
urls-archive.max.fan-twitter-@chrisjollyhale-20201104T102827Z.txt-shallow-20201108-011757-5rxhh-00007.warc.os.cdx.gz	6703171	download
urls-archive.max.fan-twitter-@chrisjollyhale-20201104T102827Z.txt-shallow-20201108-011757-5rxhh-00008.warc.gz	5394802305	download job
urls-archive.max.fan-twitter-@chrisjollyhale-20201104T102827Z.txt-shallow-20201108-011757-5rxhh-00008.warc.os.cdx.gz	556224	download
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb-00000.warc.gz	5406859203	download job
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb-00000.warc.os.cdx.gz	760025	download
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb-00001.warc.gz	5368820682	download job
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb-00001.warc.os.cdx.gz	1910125	download
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb-meta.warc.gz	2425068	download job
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb-urls.txt	268190	download
urls-archive.max.fan-twitter-@cindyscorners-20201104T083604Z.txt-shallow-20201108-050216-c2owb.json	381	download job
urls-transfer.notkiska.pw-house.gov-representatives-e-inf-20201027-025529-5nh3t-00102.warc.gz	5368803181	download job
urls-transfer.notkiska.pw-house.gov-representatives-e-inf-20201027-025529-5nh3t-00102.warc.os.cdx.gz	1744584	download
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00086.warc.gz	5369482437	download job
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00086.warc.os.cdx.gz	1817864	download
urls-transfer.notkiska.pw-twitter-@ClimateWarrior7-shallow-20201108-151026-9617i-00001.warc.gz	5400802126	download job
urls-transfer.notkiska.pw-twitter-@ClimateWarrior7-shallow-20201108-151026-9617i-00001.warc.os.cdx.gz	2478525	download
urls-transfer.notkiska.pw-twitter-@ElectionTask-shallow-20201108-170213-6ruj1-00001.warc.gz	4103754131	download job
urls-transfer.notkiska.pw-twitter-@ElectionTask-shallow-20201108-170213-6ruj1-00001.warc.os.cdx.gz	122784	download
urls-transfer.notkiska.pw-twitter-@ElectionTask-shallow-20201108-170213-6ruj1-meta.warc.gz	489253	download job
urls-transfer.notkiska.pw-twitter-@ElectionTask-shallow-20201108-170213-6ruj1-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@ElectionTask-shallow-20201108-170213-6ruj1-urls.txt	21411	download
urls-transfer.notkiska.pw-twitter-@ElectionTask-shallow-20201108-170213-6ruj1.json	338	download job
urls-transfer.notkiska.pw-twitter-@HariSevugan-shallow-20201108-150914-d6a1c-00001.warc.gz	5500495329	download job
urls-transfer.notkiska.pw-twitter-@HariSevugan-shallow-20201108-150914-d6a1c-00001.warc.os.cdx.gz	1250916	download
urls-transfer.notkiska.pw-twitter-@HariSevugan-shallow-20201108-150914-d6a1c-00002.warc.gz	5643228509	download job
urls-transfer.notkiska.pw-twitter-@HariSevugan-shallow-20201108-150914-d6a1c-00002.warc.os.cdx.gz	1513797	download
urls-transfer.notkiska.pw-twitter-@HowieHawkins-shallow-20201108-160036-a68ef-00000.warc.gz	5444893170	download job
urls-transfer.notkiska.pw-twitter-@HowieHawkins-shallow-20201108-160036-a68ef-00000.warc.os.cdx.gz	3536937	download
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00021.warc.gz	5534376407	download job
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00021.warc.os.cdx.gz	472003	download
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00022.warc.gz	5432261369	download job
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00022.warc.os.cdx.gz	698473	download
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00023.warc.gz	5404640669	download job
urls-transfer.notkiska.pw-twitter-@MaxBoot-shallow-20201107-201453-5og92-00023.warc.os.cdx.gz	882540	download
urls-transfer.notkiska.pw-twitter-@TAAP2020-shallow-20201108-151210-361ob-meta.warc.gz	184695	download job
urls-transfer.notkiska.pw-twitter-@TAAP2020-shallow-20201108-151210-361ob-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@TAAP2020-shallow-20201108-151210-361ob-urls.txt	14269	download
wibailoutpeople.org-inf-20201107-152406-7a7zr-00015.warc.gz	5390097850	download job
wibailoutpeople.org-inf-20201107-152406-7a7zr-00015.warc.os.cdx.gz	1866719	download
wibailoutpeople.org-inf-20201107-152406-7a7zr-00016.warc.gz	4257306360	download job
wibailoutpeople.org-inf-20201107-152406-7a7zr-00016.warc.os.cdx.gz	97160	download
wibailoutpeople.org-inf-20201107-152406-7a7zr-meta.warc.gz	23729238	download job
wibailoutpeople.org-inf-20201107-152406-7a7zr-meta.warc.os.cdx.gz	47	download
wibailoutpeople.org-inf-20201107-152406-7a7zr.json	249	download job
www.360haven.com-inf-20201031-180433-1l7vz-00016.warc.gz	5368715466	download job
www.360haven.com-inf-20201031-180433-1l7vz-00016.warc.os.cdx.gz	13985371	download
www.americansocialists.org-inf-20201108-173230-5xrxp-meta.warc.gz	125508	download job
www.americansocialists.org-inf-20201108-173230-5xrxp-meta.warc.os.cdx.gz	47	download
www.augustpfluger.com-inf-20201108-085031-479q7-meta.warc.gz	417073	download job
www.augustpfluger.com-inf-20201108-085031-479q7-meta.warc.os.cdx.gz	47	download
www.augustpfluger.com-inf-20201108-085031-479q7.json	246	download job
www.avapateforuscongress.com-inf-20201108-084912-kkd6w-meta.warc.gz	10335	download job
www.avapateforuscongress.com-inf-20201108-084912-kkd6w-meta.warc.os.cdx.gz	47	download
www.avapateforuscongress.com-inf-20201108-084912-kkd6w.json	253	download job
www.cindysiegel.com-inf-20201108-082904-eq8n1-meta.warc.gz	3695	download job
www.cindysiegel.com-inf-20201108-082904-eq8n1-meta.warc.os.cdx.gz	47	download
www.cindysiegel.com-inf-20201108-082904-eq8n1.json	243	download job
www.clevelandfor30.com-inf-20201108-184602-arggv-00000.warc.gz	13456552	download job
www.clevelandfor30.com-inf-20201108-184602-arggv-00000.warc.os.cdx.gz	41528	download
www.clevelandfor30.com-inf-20201108-184602-arggv-meta.warc.gz	28770	download job
www.clevelandfor30.com-inf-20201108-184602-arggv-meta.warc.os.cdx.gz	47	download
www.danmathews2020.com-inf-20201108-082630-d73p8-00000.warc.gz	873632	download job
www.danmathews2020.com-inf-20201108-082630-d73p8-00000.warc.os.cdx.gz	1225	download
www.danmathews2020.com-inf-20201108-082630-d73p8-meta.warc.gz	4181	download job
www.danmathews2020.com-inf-20201108-082630-d73p8-meta.warc.os.cdx.gz	47	download
www.danmathews2020.com-inf-20201108-082630-d73p8.json	247	download job
www.darwinfor23.com-inf-20201108-082622-94a83-00000.warc.gz	2481	download job
www.darwinfor23.com-inf-20201108-082622-94a83-00000.warc.os.cdx.gz	47	download
www.darwinfor23.com-inf-20201108-082622-94a83-meta.warc.gz	3567	download job
www.darwinfor23.com-inf-20201108-082622-94a83-meta.warc.os.cdx.gz	47	download
www.darwinfor23.com-inf-20201108-082622-94a83.json	244	download job
www.desiforcongress.com-inf-20201108-082334-aiaxw-00000.warc.gz	16486392	download job
www.desiforcongress.com-inf-20201108-082334-aiaxw-00000.warc.os.cdx.gz	49153	download
www.desiforcongress.com-inf-20201108-082334-aiaxw-meta.warc.gz	31278	download job
www.desiforcongress.com-inf-20201108-082334-aiaxw-meta.warc.os.cdx.gz	47	download
www.desiforcongress.com-inf-20201108-082334-aiaxw.json	247	download job
www.electiontaskforce.org-inf-20201108-170139-4cura-00000.warc.gz	1725594663	download job
www.electiontaskforce.org-inf-20201108-170139-4cura-00000.warc.os.cdx.gz	676093	download
www.electiontaskforce.org-inf-20201108-170139-4cura-meta.warc.gz	475374	download job
www.electiontaskforce.org-inf-20201108-170139-4cura-meta.warc.os.cdx.gz	47	download
www.electiontaskforce.org-inf-20201108-170139-4cura.json	255	download job
www.electtimothygassaway.com-inf-20201108-091826-8l546-00000.warc.gz	15674977	download job
www.electtimothygassaway.com-inf-20201108-091826-8l546-00000.warc.os.cdx.gz	37505	download
www.feganforcongress.com-inf-20201108-082436-5hi27-meta.warc.gz	254010	download job
www.feganforcongress.com-inf-20201108-082436-5hi27-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20201108-180629-edux2-00000.warc.gz	414814134	download job
www.flickr.com-inf-20201108-180629-edux2-00000.warc.os.cdx.gz	209585	download
www.flickr.com-inf-20201108-180629-edux2-meta.warc.gz	125722	download job
www.flickr.com-inf-20201108-180629-edux2-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20201108-180643-9137d-00000.warc.gz	5369428944	download job
www.flickr.com-inf-20201108-180643-9137d-00000.warc.os.cdx.gz	695216	download
www.flickr.com-inf-20201108-180643-9137d-00001.warc.gz	5370141889	download job
www.flickr.com-inf-20201108-180643-9137d-00001.warc.os.cdx.gz	652669	download
www.flickr.com-inf-20201108-180643-9137d-00002.warc.gz	5373407391	download job
www.flickr.com-inf-20201108-180643-9137d-00002.warc.os.cdx.gz	333826	download
www.flickr.com-inf-20201108-180643-9137d-00003.warc.gz	5368977646	download job
www.flickr.com-inf-20201108-180643-9137d-00003.warc.os.cdx.gz	384109	download
www.glaad.org-inf-20201108-150253-1xg5n-00000.warc.gz	136209855	download job
www.glaad.org-inf-20201108-150253-1xg5n-00000.warc.os.cdx.gz	83855	download
www.hmdb.org-inf-20201018-175958-aboei-00277.warc.gz	5373289593	download job
www.hmdb.org-inf-20201018-175958-aboei-00277.warc.os.cdx.gz	138605	download
www.hmdb.org-inf-20201018-175958-aboei-00278.warc.gz	5378439014	download job
www.hmdb.org-inf-20201018-175958-aboei-00278.warc.os.cdx.gz	196554	download
www.hmdb.org-inf-20201018-175958-aboei-00279.warc.gz	5384989289	download job
www.hmdb.org-inf-20201018-175958-aboei-00279.warc.os.cdx.gz	234836	download
www.imfromnewmexico.com-inf-20201108-095244-emjv3-00000.warc.gz	27938862	download job
www.imfromnewmexico.com-inf-20201108-095244-emjv3-00000.warc.os.cdx.gz	79601	download
www.imfromnewmexico.com-inf-20201108-095244-emjv3-meta.warc.gz	50227	download job
www.imfromnewmexico.com-inf-20201108-095244-emjv3-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-080533-cnjv7-meta.warc.gz	48504	download job
www.instagram.com-inf-20201108-080533-cnjv7-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-082817-5zm4c-meta.warc.gz	27083	download job
www.instagram.com-inf-20201108-082817-5zm4c-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-091003-e74af-meta.warc.gz	54633	download job
www.instagram.com-inf-20201108-091003-e74af-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-091003-e74af.json	263	download job
www.instagram.com-inf-20201108-093535-31y99-00000.warc.gz	36047338	download job
www.instagram.com-inf-20201108-093535-31y99-00000.warc.os.cdx.gz	31212	download
www.instagram.com-inf-20201108-093535-31y99-meta.warc.gz	24426	download job
www.instagram.com-inf-20201108-093535-31y99-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-094531-4votk-meta.warc.gz	26046	download job
www.instagram.com-inf-20201108-094531-4votk-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-094531-4votk.json	259	download job
www.instagram.com-inf-20201108-095610-8z1x1-00000.warc.gz	51294648	download job
www.instagram.com-inf-20201108-095610-8z1x1-00000.warc.os.cdx.gz	43499	download
www.instagram.com-inf-20201108-095610-8z1x1-meta.warc.gz	33316	download job
www.instagram.com-inf-20201108-095610-8z1x1-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-095610-8z1x1.json	262	download job
www.instagram.com-inf-20201108-100904-ehoi4-meta.warc.gz	26302	download job
www.instagram.com-inf-20201108-100904-ehoi4-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-100904-ehoi4.json	266	download job
www.instagram.com-inf-20201108-101939-f17u7.json	263	download job
www.instagram.com-inf-20201108-103704-3q9j5-00000.warc.gz	8774973	download job
www.instagram.com-inf-20201108-103704-3q9j5-00000.warc.os.cdx.gz	27153	download
www.instagram.com-inf-20201108-103704-3q9j5-meta.warc.gz	22072	download job
www.instagram.com-inf-20201108-103704-3q9j5-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-103704-3q9j5.json	262	download job
www.instagram.com-inf-20201108-104530-n8gcj-00000.warc.gz	16146808	download job
www.instagram.com-inf-20201108-104530-n8gcj-00000.warc.os.cdx.gz	34153	download
www.instagram.com-inf-20201108-104530-n8gcj-meta.warc.gz	25861	download job
www.instagram.com-inf-20201108-104530-n8gcj-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-104530-n8gcj.json	268	download job
www.instagram.com-inf-20201108-111617-eyx9g-meta.warc.gz	29986	download job
www.instagram.com-inf-20201108-111617-eyx9g-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-112753-a78df-00000.warc.gz	20901406	download job
www.instagram.com-inf-20201108-112753-a78df-00000.warc.os.cdx.gz	28583	download
www.instagram.com-inf-20201108-112753-a78df-meta.warc.gz	23216	download job
www.instagram.com-inf-20201108-112753-a78df-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-112753-a78df.json	263	download job
www.instagram.com-inf-20201108-113644-1bunx-00000.warc.gz	16703248	download job
www.instagram.com-inf-20201108-113644-1bunx-00000.warc.os.cdx.gz	58205	download
www.instagram.com-inf-20201108-113644-1bunx-meta.warc.gz	40456	download job
www.instagram.com-inf-20201108-113644-1bunx-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-113644-1bunx.json	273	download job
www.instagram.com-inf-20201108-115228-9cmvn-00000.warc.gz	12297147	download job
www.instagram.com-inf-20201108-115228-9cmvn-00000.warc.os.cdx.gz	34602	download
www.instagram.com-inf-20201108-115228-9cmvn-meta.warc.gz	26545	download job
www.instagram.com-inf-20201108-115228-9cmvn-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201108-115228-9cmvn.json	265	download job
www.irenearmendarizjackson.com-inf-20201108-080636-5dz74-00000.warc.gz	107222405	download job
www.irenearmendarizjackson.com-inf-20201108-080636-5dz74-00000.warc.os.cdx.gz	25453	download
www.irenearmendarizjackson.com-inf-20201108-080636-5dz74-meta.warc.gz	18301	download job
www.irenearmendarizjackson.com-inf-20201108-080636-5dz74-meta.warc.os.cdx.gz	47	download
www.irenearmendarizjackson.com-inf-20201108-080636-5dz74.json	255	download job
www.jennalowenstein.com-inf-20201108-161620-e9xts-00000.warc.gz	159544482	download job
www.jennalowenstein.com-inf-20201108-161620-e9xts-00000.warc.os.cdx.gz	165452	download
www.jennalowenstein.com-inf-20201108-161620-e9xts-meta.warc.gz	160591	download job
www.jennalowenstein.com-inf-20201108-161620-e9xts-meta.warc.os.cdx.gz	47	download
www.jennalowenstein.com-inf-20201108-161620-e9xts.json	253	download job
www.kulkarniforcongress.com-inf-20201108-184534-8lc96-meta.warc.gz	56819	download job
www.kulkarniforcongress.com-inf-20201108-184534-8lc96-meta.warc.os.cdx.gz	47	download
www.mclendonforcongress.com-inf-20201108-081126-3woek-00000.warc.gz	198192965	download job
www.mclendonforcongress.com-inf-20201108-081126-3woek-00000.warc.os.cdx.gz	311818	download
www.mclendonforcongress.com-inf-20201108-081126-3woek.json	252	download job
www.nytimes.com-inf-20201108-175124-e1t6z-aborted-00000.warc.gz	108768136	download job
www.nytimes.com-inf-20201108-175124-e1t6z-aborted-00000.warc.os.cdx.gz	114554	download
www.nytimes.com-inf-20201108-175124-e1t6z-aborted-wpull.log.gz	70572	download
www.nytimes.com-inf-20201108-175124-e1t6z-aborted.json	296	download job
www.nytimes.com-shallow-20201108-120655-188nk.json	304	download job
www.nytimes.com-shallow-20201108-175717-e1t6z-00000.warc.gz	39529090	download job
www.nytimes.com-shallow-20201108-175717-e1t6z-00000.warc.os.cdx.gz	41634	download
www.nytimes.com-shallow-20201108-175717-e1t6z-meta.warc.gz	39230	download job
www.nytimes.com-shallow-20201108-175717-e1t6z-meta.warc.os.cdx.gz	47	download
www.nytimes.com-shallow-20201108-175717-e1t6z.json	301	download job
www.putnamfortexas.com-inf-20201108-083025-64uck.json	247	download job
www.redstate.com-inf-20201002-220930-4bjxa-00207.warc.gz	5368749013	download job
www.redstate.com-inf-20201002-220930-4bjxa-00207.warc.os.cdx.gz	1199894	download
www.rollingstone.com-shallow-20201108-121131-8m8o1-meta.warc.gz	30419	download job
www.rollingstone.com-shallow-20201108-121131-8m8o1-meta.warc.os.cdx.gz	47	download
www.rollingstone.com-shallow-20201108-121131-8m8o1.json	341	download job
www.socialistpartyofamerica.us-inf-20201108-173135-28kac-00000.warc.gz	6059058	download job
www.socialistpartyofamerica.us-inf-20201108-173135-28kac-00000.warc.os.cdx.gz	7128	download
www.socialistpartyofamerica.us-inf-20201108-173135-28kac.json	259	download job
www.taap2020.com-inf-20201108-151009-37gyd-00001.warc.gz	5605849970	download job
www.taap2020.com-inf-20201108-151009-37gyd-00001.warc.os.cdx.gz	46666	download
www.taap2020.com-inf-20201108-151009-37gyd-00003.warc.gz	880311621	download job
www.taap2020.com-inf-20201108-151009-37gyd-00003.warc.os.cdx.gz	704818	download
www.taap2020.com-inf-20201108-151009-37gyd.json	246	download job