Item archiveteam_archivebot_go_20200714230004

Filename	Size
2019-ncov.jp-inf-20200714-201430-efyq0-00000.warc.gz	113963524	download job
2019-ncov.jp-inf-20200714-201430-efyq0-00000.warc.os.cdx.gz	94836	download
2019-ncov.jp-inf-20200714-201430-efyq0-meta.warc.gz	71782	download job
2019-ncov.jp-inf-20200714-201430-efyq0-meta.warc.os.cdx.gz	47	download
2019-ncov.sogiecn.com-inf-20200714-201431-ezsq8-meta.warc.gz	3574	download job
2019-ncov.sogiecn.com-inf-20200714-201431-ezsq8-meta.warc.os.cdx.gz	47	download
2019-ncov.sogiecn.com-inf-20200714-201431-ezsq8.json	252	download job
2019ncov.ga-inf-20200714-201435-c2fmw-00000.warc.gz	6545677	download job
2019ncov.ga-inf-20200714-201435-c2fmw-00000.warc.os.cdx.gz	17193	download
2019ncov.ga-inf-20200714-201435-c2fmw.json	242	download job
aaqr.org-shallow-20200714-223612-aazyl-00000.warc.gz	370542	download job
aaqr.org-shallow-20200714-223612-aazyl-00000.warc.os.cdx.gz	226	download
aaqr.org-shallow-20200714-223612-aazyl-meta.warc.gz	3391	download job
aaqr.org-shallow-20200714-223612-aazyl-meta.warc.os.cdx.gz	47	download
aaqr.org-shallow-20200714-223612-aazyl.json	273	download job
anti-corona.kz-inf-20200714-201437-ahg3m-00000.warc.gz	1866101458	download job
anti-corona.kz-inf-20200714-201437-ahg3m-00000.warc.os.cdx.gz	1418136	download
anti-corona.kz-inf-20200714-201437-ahg3m-meta.warc.gz	888360	download job
anti-corona.kz-inf-20200714-201437-ahg3m-meta.warc.os.cdx.gz	47	download
anti-corona.kz-inf-20200714-201437-ahg3m.json	245	download job
apiekorona.lt-inf-20200714-201435-btrg1-00000.warc.gz	1639088368	download job
apiekorona.lt-inf-20200714-201435-btrg1-00000.warc.os.cdx.gz	1069334	download
apiekorona.lt-inf-20200714-201435-btrg1-meta.warc.gz	651417	download job
apiekorona.lt-inf-20200714-201435-btrg1-meta.warc.os.cdx.gz	47	download
apiekorona.lt-inf-20200714-201435-btrg1.json	244	download job
archiveteam_archivebot_go_20200714230004.cdx.gz	85768190	download
archiveteam_archivebot_go_20200714230004.cdx.idx	82776	download
archiveteam_archivebot_go_20200714230004_files.xml	0	download
archiveteam_archivebot_go_20200714230004_meta.sqlite	268288	download
archiveteam_archivebot_go_20200714230004_meta.xml	969	download
atlasofsurveillance.org-inf-20200714-085512-awlbv-meta.warc.gz	4780065	download job
atlasofsurveillance.org-inf-20200714-085512-awlbv-meta.warc.os.cdx.gz	47	download
bag-coronavirus.ch-inf-20200714-201437-bttxz-00000.warc.gz	1221472258	download job
bag-coronavirus.ch-inf-20200714-201437-bttxz-00000.warc.os.cdx.gz	308338	download
bag-coronavirus.ch-inf-20200714-201437-bttxz-meta.warc.gz	190666	download job
bag-coronavirus.ch-inf-20200714-201437-bttxz-meta.warc.os.cdx.gz	47	download
bag-coronavirus.ch-inf-20200714-201437-bttxz.json	249	download job
beatcovid19.ai-inf-20200714-201437-e51sc-00000.warc.gz	400794658	download job
beatcovid19.ai-inf-20200714-201437-e51sc-00000.warc.os.cdx.gz	393426	download
beatcovid19.ai-inf-20200714-201437-e51sc-meta.warc.gz	232560	download job
beatcovid19.ai-inf-20200714-201437-e51sc-meta.warc.os.cdx.gz	47	download
beatcovid19.ai-inf-20200714-201437-e51sc.json	245	download job
bhagcorona.com-inf-20200714-201437-9uivr-00000.warc.gz	15471653	download job
bhagcorona.com-inf-20200714-201437-9uivr-00000.warc.os.cdx.gz	42852	download
brakofcorona.nl-inf-20200714-201442-34khc-00000.warc.gz	1176885	download job
brakofcorona.nl-inf-20200714-201442-34khc-00000.warc.os.cdx.gz	1542	download
brakofcorona.nl-inf-20200714-201442-34khc-meta.warc.gz	4512	download job
brakofcorona.nl-inf-20200714-201442-34khc-meta.warc.os.cdx.gz	47	download
cmcovid19.com-inf-20200714-201449-1qhcx-meta.warc.gz	25634	download job
cmcovid19.com-inf-20200714-201449-1qhcx-meta.warc.os.cdx.gz	47	download
cmcovid19.com-inf-20200714-201449-1qhcx.json	244	download job
connect.vk.com-shallow-20200714-213035-b273x-00000.warc.gz	360471	download job
connect.vk.com-shallow-20200714-213035-b273x-00000.warc.os.cdx.gz	1991	download
connect.vk.com-shallow-20200714-213035-b273x-meta.warc.gz	4588	download job
connect.vk.com-shallow-20200714-213035-b273x-meta.warc.os.cdx.gz	47	download
connect.vk.com-shallow-20200714-213035-b273x.json	252	download job
corona-dz.live-inf-20200714-201518-258n0-00000.warc.gz	69049511	download job
corona-dz.live-inf-20200714-201518-258n0-00000.warc.os.cdx.gz	91639	download
corona-dz.live-inf-20200714-201518-258n0.json	245	download job
corona-scanner.com-inf-20200714-201531-35srm-00000.warc.gz	92029196	download job
corona-scanner.com-inf-20200714-201531-35srm-00000.warc.os.cdx.gz	118170	download
corona-scanner.com-inf-20200714-201531-35srm-meta.warc.gz	71747	download job
corona-scanner.com-inf-20200714-201531-35srm-meta.warc.os.cdx.gz	47	download
corona-scanner.com-inf-20200714-201531-35srm.json	249	download job
corona-stats.mobi-inf-20200714-201534-efin0-meta.warc.gz	157602	download job
corona-stats.mobi-inf-20200714-201534-efin0-meta.warc.os.cdx.gz	47	download
corona-stats.online-inf-20200714-201545-ezu0f-meta.warc.gz	3581	download job
corona-stats.online-inf-20200714-201545-ezu0f-meta.warc.os.cdx.gz	47	download
corona-stats.online-inf-20200714-201545-ezu0f.json	250	download job
corona-sunsets.jp-inf-20200714-201556-b76uj-00000.warc.gz	649902402	download job
corona-sunsets.jp-inf-20200714-201556-b76uj-00000.warc.os.cdx.gz	576376	download
corona-sunsets.jp-inf-20200714-201556-b76uj-meta.warc.gz	363901	download job
corona-sunsets.jp-inf-20200714-201556-b76uj-meta.warc.os.cdx.gz	47	download
corona-sunsets.jp-inf-20200714-201556-b76uj.json	248	download job
corona-tracker-2020.netlify.com-inf-20200714-201607-464nk-00000.warc.gz	438725	download job
corona-tracker-2020.netlify.com-inf-20200714-201607-464nk-00000.warc.os.cdx.gz	2119	download
corona-tracker-2020.netlify.com-inf-20200714-201607-464nk-meta.warc.gz	4880	download job
corona-tracker-2020.netlify.com-inf-20200714-201607-464nk-meta.warc.os.cdx.gz	47	download
corona-tracker-2020.netlify.com-inf-20200714-201607-464nk.json	262	download job
corona.arrangy.com-inf-20200714-201622-6avko-00000.warc.gz	232991806	download job
corona.arrangy.com-inf-20200714-201622-6avko-00000.warc.os.cdx.gz	336367	download
corona.arrangy.com-inf-20200714-201622-6avko-meta.warc.gz	231287	download job
corona.arrangy.com-inf-20200714-201622-6avko-meta.warc.os.cdx.gz	47	download
corona.cbddo.gov.tr-inf-20200714-201624-4nj3k-00000.warc.gz	72130568	download job
corona.cbddo.gov.tr-inf-20200714-201624-4nj3k-00000.warc.os.cdx.gz	83585	download
corona.cbddo.gov.tr-inf-20200714-201624-4nj3k.json	250	download job
corona.e.gov.kw-inf-20200714-150252-cyob7-00000.warc.gz	17144283	download job
corona.e.gov.kw-inf-20200714-150252-cyob7-00000.warc.os.cdx.gz	47870	download
corona.e.gov.kw-inf-20200714-150252-cyob7-meta.warc.gz	36293	download job
corona.e.gov.kw-inf-20200714-150252-cyob7-meta.warc.os.cdx.gz	47	download
corona.e.gov.kw-inf-20200714-150252-cyob7.json	245	download job
corona.e.gov.kw-inf-20200714-201628-bvrqr-meta.warc.gz	34042	download job
corona.e.gov.kw-inf-20200714-201628-bvrqr-meta.warc.os.cdx.gz	47	download
corona.fo-inf-20200714-201633-5rtfn-00000.warc.gz	479253425	download job
corona.fo-inf-20200714-201633-5rtfn-00000.warc.os.cdx.gz	285479	download
corona.fo-inf-20200714-201633-5rtfn-meta.warc.gz	175539	download job
corona.fo-inf-20200714-201633-5rtfn-meta.warc.os.cdx.gz	47	download
corona.gov.bd-inf-20200714-150252-3jz1f-00000.warc.gz	4060225310	download job
corona.gov.bd-inf-20200714-150252-3jz1f-00000.warc.os.cdx.gz	3085201	download
corona.gov.bd-inf-20200714-150252-3jz1f-meta.warc.gz	1922213	download job
corona.gov.bd-inf-20200714-150252-3jz1f-meta.warc.os.cdx.gz	47	download
corona.gov.bd-inf-20200714-150252-3jz1f.json	243	download job
corona.jakarta.go.id-inf-20200714-201653-dy1g3-meta.warc.gz	807555	download job
corona.jakarta.go.id-inf-20200714-201653-dy1g3-meta.warc.os.cdx.gz	47	download
corona.jakarta.go.id-inf-20200714-201653-dy1g3.json	251	download job
corona.matsu.fi-inf-20200714-201859-5x5m5-00000.warc.gz	6305	download job
corona.matsu.fi-inf-20200714-201859-5x5m5-00000.warc.os.cdx.gz	289	download
corona.ministryinfo.gov.lb-inf-20200714-201717-6omzz-00000.warc.gz	365647770	download job
corona.ministryinfo.gov.lb-inf-20200714-201717-6omzz-00000.warc.os.cdx.gz	612563	download
corona.ministryinfo.gov.lb-inf-20200714-201717-6omzz-meta.warc.gz	359975	download job
corona.ministryinfo.gov.lb-inf-20200714-201717-6omzz-meta.warc.os.cdx.gz	47	download
corona.moh.gov.jo-inf-20200714-201907-9d2qu.json	248	download job
corona.ps-inf-20200714-202059-burl1-00000.warc.gz	42497444	download job
corona.ps-inf-20200714-202059-burl1-00000.warc.os.cdx.gz	117969	download
corona.ps-inf-20200714-202059-burl1-meta.warc.gz	75015	download job
corona.ps-inf-20200714-202059-burl1-meta.warc.os.cdx.gz	47	download
corona.ps-inf-20200714-202059-burl1.json	240	download job
corona.thueringen.de-inf-20200714-202250-c69nr-00000.warc.gz	6394168942	download job
corona.thueringen.de-inf-20200714-202250-c69nr-00000.warc.os.cdx.gz	2050887	download
corona.thueringen.de-inf-20200714-202250-c69nr-00001.warc.gz	2760573243	download job
corona.thueringen.de-inf-20200714-202250-c69nr-00001.warc.os.cdx.gz	2102	download
corona.thueringen.de-inf-20200714-202250-c69nr.json	251	download job
coronabeds.jantasamvad.org-inf-20200714-202505-eziao-00000.warc.gz	174494606	download job
coronabeds.jantasamvad.org-inf-20200714-202505-eziao-00000.warc.os.cdx.gz	95463	download
coronabeds.jantasamvad.org-inf-20200714-202505-eziao.json	257	download job
coronaboard.com-inf-20200714-202637-74b9t-00000.warc.gz	393575344	download job
coronaboard.com-inf-20200714-202637-74b9t-00000.warc.os.cdx.gz	522466	download
coronaboard.com-inf-20200714-202637-74b9t.json	246	download job
coronaboard.kr-inf-20200714-202813-om1wi-00000.warc.gz	518688762	download job
coronaboard.kr-inf-20200714-202813-om1wi-00000.warc.os.cdx.gz	650294	download
coronaboard.kr-inf-20200714-202813-om1wi-meta.warc.gz	383269	download job
coronaboard.kr-inf-20200714-202813-om1wi-meta.warc.os.cdx.gz	47	download
coronaboard.kr-inf-20200714-202813-om1wi.json	245	download job
coronavirus.bernews.com-inf-20200714-150354-9fvih-00002.warc.gz	1450858409	download job
coronavirus.bernews.com-inf-20200714-150354-9fvih-00002.warc.os.cdx.gz	1284409	download
coronavirus.bernews.com-inf-20200714-150354-9fvih-meta.warc.gz	2198101	download job
coronavirus.bernews.com-inf-20200714-150354-9fvih-meta.warc.os.cdx.gz	47	download
coronavirus.bernews.com-inf-20200714-150354-9fvih.json	253	download job
coronavirus.uz-inf-20200714-150405-79ce9-00005.warc.gz	1016868964	download job
coronavirus.uz-inf-20200714-150405-79ce9-00005.warc.os.cdx.gz	668	download
coronavirus.uz-inf-20200714-150405-79ce9-meta.warc.gz	202890	download job
coronavirus.uz-inf-20200714-150405-79ce9-meta.warc.os.cdx.gz	47	download
ektoplazm.com-inf-20200704-233408-66i1h-00036.warc.gz	5381758533	download job
ektoplazm.com-inf-20200704-233408-66i1h-00036.warc.os.cdx.gz	13750	download
europepmc.org-shallow-20200714-223937-2fw0i-00000.warc.gz	4473917	download job
europepmc.org-shallow-20200714-223937-2fw0i-00000.warc.os.cdx.gz	8278	download
europepmc.org-shallow-20200714-223937-2fw0i-meta.warc.gz	8355	download job
europepmc.org-shallow-20200714-223937-2fw0i-meta.warc.os.cdx.gz	47	download
europepmc.org-shallow-20200714-223937-2fw0i.json	266	download job
getsatisfaction.com-inf-20200708-234031-epnla-00025.warc.gz	5368744608	download job
getsatisfaction.com-inf-20200708-234031-epnla-00025.warc.os.cdx.gz	7339653	download
globalhealth.georgetown.edu-shallow-20200714-204914-6jsgu-00000.warc.gz	11307168	download job
globalhealth.georgetown.edu-shallow-20200714-204914-6jsgu-00000.warc.os.cdx.gz	11538	download
globalhealth.georgetown.edu-shallow-20200714-204914-6jsgu-meta.warc.gz	11074	download job
globalhealth.georgetown.edu-shallow-20200714-204914-6jsgu-meta.warc.os.cdx.gz	47	download
globalhealth.georgetown.edu-shallow-20200714-204914-6jsgu.json	302	download job
luc.devroye.org-inf-20200629-195003-6kmq5-00059.warc.gz	5369545774	download job
luc.devroye.org-inf-20200629-195003-6kmq5-00059.warc.os.cdx.gz	3661229	download
ogrecave.com-inf-20200714-071554-9zzxl-00007.warc.gz	4371379693	download job
ogrecave.com-inf-20200714-071554-9zzxl-00007.warc.os.cdx.gz	3432225	download
ogrecave.com-inf-20200714-071554-9zzxl-meta.warc.gz	5812398	download job
ogrecave.com-inf-20200714-071554-9zzxl-meta.warc.os.cdx.gz	47	download
theweek.com-shallow-20200714-223022-4l03c-00000.warc.gz	6640105	download job
theweek.com-shallow-20200714-223022-4l03c-00000.warc.os.cdx.gz	17124	download
theweek.com-shallow-20200714-223022-4l03c-meta.warc.gz	13604	download job
theweek.com-shallow-20200714-223022-4l03c-meta.warc.os.cdx.gz	47	download
theweek.com-shallow-20200714-223022-4l03c.json	285	download job
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00226.warc.gz	5489382031	download job
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00226.warc.os.cdx.gz	1844360	download
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00227.warc.gz	5393108246	download job
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00227.warc.os.cdx.gz	107651	download
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00228.warc.gz	5369559162	download job
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00228.warc.os.cdx.gz	744080	download
urls-transfer.notkiska.pw-twitter-%23CoronaDon-shallow-20200714-205411-casnd-00000.warc.gz	5369171420	download job
urls-transfer.notkiska.pw-twitter-%23CoronaDon-shallow-20200714-205411-casnd-00000.warc.os.cdx.gz	1795109	download
urls-transfer.notkiska.pw-twitter-%23CoronaDon-shallow-20200714-205411-casnd-00001.warc.gz	5383145633	download job
urls-transfer.notkiska.pw-twitter-%23CoronaDon-shallow-20200714-205411-casnd-00001.warc.os.cdx.gz	3297499	download
urls-transfer.notkiska.pw-twitter-%23EpsteinFlightLogs-shallow-20200714-205346-er1h2-00000.warc.gz	5425368324	download job
urls-transfer.notkiska.pw-twitter-%23EpsteinFlightLogs-shallow-20200714-205346-er1h2-00000.warc.os.cdx.gz	2348232	download
urls-transfer.notkiska.pw-twitter-%23IStandWithFauci-shallow-20200714-210410-9gjuh-00000.warc.gz	5368723380	download job
urls-transfer.notkiska.pw-twitter-%23IStandWithFauci-shallow-20200714-210410-9gjuh-00000.warc.os.cdx.gz	2277936	download
urls-transfer.notkiska.pw-twitter-%23MasksOnOhio-shallow-20200714-192542-8wphf-00000.warc.gz	1850959151	download job
urls-transfer.notkiska.pw-twitter-%23MasksOnOhio-shallow-20200714-192542-8wphf-00000.warc.os.cdx.gz	1471083	download
urls-transfer.notkiska.pw-twitter-%23WeReopenSchoolsWhen-shallow-20200714-193431-a7tzv-urls.txt	208475	download
urls-transfer.notkiska.pw-twitter-%23WeReopenSchoolsWhen-shallow-20200714-193431-a7tzv.json	354	download job
urls-transfer.notkiska.pw-twitter-%23notmypresident-shallow-20200530-220957-2c0z0-00154.warc.gz	5371361938	download job
urls-transfer.notkiska.pw-twitter-%23notmypresident-shallow-20200530-220957-2c0z0-00154.warc.os.cdx.gz	2143054	download
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00095.warc.gz	5381504596	download job
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00095.warc.os.cdx.gz	887595	download
urls-transfer.notkiska.pw-twitter-@MichaelRCaputo-shallow-20200714-204352-27777-00000.warc.gz	335576004	download job
urls-transfer.notkiska.pw-twitter-@MichaelRCaputo-shallow-20200714-204352-27777-00000.warc.os.cdx.gz	709144	download
urls-transfer.notkiska.pw-twitter-@MichaelRCaputo-shallow-20200714-204352-27777-meta.warc.gz	400067	download job
urls-transfer.notkiska.pw-twitter-@MichaelRCaputo-shallow-20200714-204352-27777-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@MichaelRCaputo-shallow-20200714-204352-27777-urls.txt	36958	download
urls-transfer.notkiska.pw-twitter-@MichaelRCaputo-shallow-20200714-204352-27777.json	340	download job
urls-transfer.notkiska.pw-twitter-@bug_gwen-shallow-20200714-042653-9wnzv-00010.warc.gz	5368804317	download job
urls-transfer.notkiska.pw-twitter-@bug_gwen-shallow-20200714-042653-9wnzv-00010.warc.os.cdx.gz	2157401	download
urls-transfer.notkiska.pw-twitter-@bug_gwen-shallow-20200714-042653-9wnzv-00011.warc.gz	5441444453	download job
urls-transfer.notkiska.pw-twitter-@bug_gwen-shallow-20200714-042653-9wnzv-00011.warc.os.cdx.gz	366312	download
urls-transfer.notkiska.pw-twitter-@grantimahara-shallow-20200714-184957-bqos9-00000.warc.gz	5368709571	download job
urls-transfer.notkiska.pw-twitter-@grantimahara-shallow-20200714-184957-bqos9-00000.warc.os.cdx.gz	5196694	download
wowbrandmanagement.com-inf-20200713-071817-sizcm-00000.warc.gz	5422713930	download job
wowbrandmanagement.com-inf-20200713-071817-sizcm-00000.warc.os.cdx.gz	8008974	download
www.covid19.gov.ph-inf-20200714-165953-5stj4-00000.warc.gz	3962254092	download job
www.covid19.gov.ph-inf-20200714-165953-5stj4-00000.warc.os.cdx.gz	1976424	download
www.covid19.gov.ph-inf-20200714-165953-5stj4-meta.warc.gz	1326791	download job
www.covid19.gov.ph-inf-20200714-165953-5stj4-meta.warc.os.cdx.gz	47	download
www.covid19.gov.ph-inf-20200714-165953-5stj4.json	248	download job
www.gametactics.com-inf-20200713-181500-ckdem-00005.warc.gz	705323897	download job
www.gametactics.com-inf-20200713-181500-ckdem-00005.warc.os.cdx.gz	108241	download
www.gametactics.com-inf-20200713-181500-ckdem-meta.warc.gz	6552278	download job
www.gametactics.com-inf-20200713-181500-ckdem-meta.warc.os.cdx.gz	47	download
www.gametactics.com-inf-20200713-181500-ckdem.json	247	download job
www.graspingforthewind.com-inf-20200714-053628-8sb7c-00000.warc.gz	5391128035	download job
www.graspingforthewind.com-inf-20200714-053628-8sb7c-00000.warc.os.cdx.gz	7067454	download
www.journalofhospitalinfection.com-shallow-20200714-223821-ehkbs-00000.warc.gz	12858	download job
www.journalofhospitalinfection.com-shallow-20200714-223821-ehkbs-00000.warc.os.cdx.gz	946	download
www.journalofhospitalinfection.com-shallow-20200714-223821-ehkbs-meta.warc.gz	4042	download job
www.journalofhospitalinfection.com-shallow-20200714-223821-ehkbs-meta.warc.os.cdx.gz	47	download
www.journalofhospitalinfection.com-shallow-20200714-223821-ehkbs.json	300	download job
www.journalofhospitalinfection.com-shallow-20200714-224247-ehkbs-meta.warc.gz	3979	download job
www.journalofhospitalinfection.com-shallow-20200714-224247-ehkbs-meta.warc.os.cdx.gz	47	download
www.journalofhospitalinfection.com-shallow-20200714-224247-ehkbs.json	300	download job
www.jstage.jst.go.jp-shallow-20200714-223718-5m7tf-00000.warc.gz	3115257	download job
www.jstage.jst.go.jp-shallow-20200714-223718-5m7tf-00000.warc.os.cdx.gz	246	download
www.jstage.jst.go.jp-shallow-20200714-223718-5m7tf-meta.warc.gz	3544	download job
www.jstage.jst.go.jp-shallow-20200714-223718-5m7tf-meta.warc.os.cdx.gz	47	download
www.jstage.jst.go.jp-shallow-20200714-223718-5m7tf.json	290	download job
www.mudcrutch.com-inf-20200710-231811-ablr0-00015.warc.gz	4826460917	download job
www.mudcrutch.com-inf-20200710-231811-ablr0-00015.warc.os.cdx.gz	6443853	download
www.mudcrutch.com-inf-20200710-231811-ablr0-meta.warc.gz	65636561	download job
www.mudcrutch.com-inf-20200710-231811-ablr0-meta.warc.os.cdx.gz	47	download
www.mudcrutch.com-inf-20200710-231811-ablr0.json	242	download job
www.ncbi.nlm.nih.gov-shallow-20200714-223800-66np4-00000.warc.gz	340905	download job
www.ncbi.nlm.nih.gov-shallow-20200714-223800-66np4-00000.warc.os.cdx.gz	263	download
www.ncbi.nlm.nih.gov-shallow-20200714-223800-66np4-meta.warc.gz	3551	download job
www.ncbi.nlm.nih.gov-shallow-20200714-223800-66np4-meta.warc.os.cdx.gz	47	download
www.ncbi.nlm.nih.gov-shallow-20200714-223800-66np4.json	303	download job
www.ncbi.nlm.nih.gov-shallow-20200714-223844-clvoc-00000.warc.gz	3599789	download job
www.ncbi.nlm.nih.gov-shallow-20200714-223844-clvoc-00000.warc.os.cdx.gz	6412	download
www.ncbi.nlm.nih.gov-shallow-20200714-223844-clvoc-meta.warc.gz	7293	download job
www.ncbi.nlm.nih.gov-shallow-20200714-223844-clvoc-meta.warc.os.cdx.gz	47	download
www.ncbi.nlm.nih.gov-shallow-20200714-223844-clvoc.json	278	download job
www.qiagen.com-inf-20200621-061202-1wax4-00037.warc.gz	5369071284	download job
www.qiagen.com-inf-20200621-061202-1wax4-00037.warc.os.cdx.gz	3102528	download
www.raspberrypi.org-inf-20200707-192424-bv6p7-00037.warc.gz	6534897235	download job
www.raspberrypi.org-inf-20200707-192424-bv6p7-00037.warc.os.cdx.gz	3328015	download
www.refinery29.com-inf-20191002-211042-3symg-00668.warc.gz	5372538595	download job
www.refinery29.com-inf-20191002-211042-3symg-00668.warc.os.cdx.gz	1500487	download
www.roughtype.com-inf-20200714-070746-dak3c-00007.warc.gz	5371013588	download job
www.roughtype.com-inf-20200714-070746-dak3c-00007.warc.os.cdx.gz	1583238	download
www.technocracy.news-shallow-20200714-223404-7o0zy-00000.warc.gz	9672511	download job
www.technocracy.news-shallow-20200714-223404-7o0zy-00000.warc.os.cdx.gz	16730	download
www.technocracy.news-shallow-20200714-223404-7o0zy-meta.warc.gz	13766	download job
www.technocracy.news-shallow-20200714-223404-7o0zy-meta.warc.os.cdx.gz	47	download
www.technocracy.news-shallow-20200714-223404-7o0zy.json	316	download job
www.technocracy.news-shallow-20200714-223420-b97zb-00000.warc.gz	98325	download job
www.technocracy.news-shallow-20200714-223420-b97zb-00000.warc.os.cdx.gz	273	download
www.technocracy.news-shallow-20200714-223420-b97zb-meta.warc.gz	3579	download job
www.technocracy.news-shallow-20200714-223420-b97zb-meta.warc.os.cdx.gz	47	download
www.technocracy.news-shallow-20200714-223420-b97zb.json	326	download job
www.technocracy.news-shallow-20200714-223440-79skp-00000.warc.gz	1457644	download job
www.technocracy.news-shallow-20200714-223440-79skp-00000.warc.os.cdx.gz	4123	download
www.technocracy.news-shallow-20200714-223440-79skp-meta.warc.gz	5868	download job
www.technocracy.news-shallow-20200714-223440-79skp-meta.warc.os.cdx.gz	47	download
www.technocracy.news-shallow-20200714-223440-79skp.json	328	download job
www.turiver.com-inf-20200629-212723-6d3re-00036.warc.gz	5368810264	download job
www.turiver.com-inf-20200629-212723-6d3re-00036.warc.os.cdx.gz	3507583	download