Item archiveteam_archivebot_go_20210514020003

Filename	Size
archiveteam_archivebot_go_20210514020003.cdx.gz	82929157	download
archiveteam_archivebot_go_20210514020003.cdx.idx	83921	download
archiveteam_archivebot_go_20210514020003_files.xml	0	download
archiveteam_archivebot_go_20210514020003_meta.sqlite	471040	download
archiveteam_archivebot_go_20210514020003_meta.xml	969	download
barneteye.blogspot.com-inf-20210512-030355-9lmq2-00007.warc.gz	2328584953	download job
barneteye.blogspot.com-inf-20210512-030355-9lmq2-00007.warc.os.cdx.gz	3562757	download
barneteye.blogspot.com-inf-20210512-030355-9lmq2-meta.warc.gz	26731774	download job
barneteye.blogspot.com-inf-20210512-030355-9lmq2-meta.warc.os.cdx.gz	47	download
barneteye.blogspot.com-inf-20210512-030355-9lmq2.json	254	download job
buduaar.tv3.ee-inf-20210511-100827-4wydv-00005.warc.gz	5370675070	download job
buduaar.tv3.ee-inf-20210511-100827-4wydv-00005.warc.os.cdx.gz	5628563	download
chinese.cdc.gov-inf-20210513-194442-9jli0-00000.warc.gz	1991742172	download job
chinese.cdc.gov-inf-20210513-194442-9jli0-00000.warc.os.cdx.gz	2070273	download
chinese.cdc.gov-inf-20210513-194442-9jli0-meta.warc.gz	1559077	download job
chinese.cdc.gov-inf-20210513-194442-9jli0-meta.warc.os.cdx.gz	47	download
chinese.cdc.gov-inf-20210513-194442-9jli0.json	278	download job
cs50.tv-inf-20210508-211626-3b411-00141.warc.gz	19996973968	download job
cs50.tv-inf-20210508-211626-3b411-00141.warc.os.cdx.gz	1407	download
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234317-58kk5-00000.warc.gz	65939010	download job
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234317-58kk5-00000.warc.os.cdx.gz	261	download
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234317-58kk5-meta.warc.gz	3558	download job
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234317-58kk5-meta.warc.os.cdx.gz	47	download
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234317-58kk5.json	287	download job
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234321-dk21t-00000.warc.gz	62833976	download job
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234321-dk21t-00000.warc.os.cdx.gz	253	download
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234321-dk21t-meta.warc.gz	3536	download job
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234321-dk21t-meta.warc.os.cdx.gz	47	download
d250f2ux8pmbq4.cloudfront.net-shallow-20210513-234321-dk21t.json	283	download job
en.unesco.org-inf-20210510-031454-ei0k7-00023.warc.gz	5371709813	download job
en.unesco.org-inf-20210510-031454-ei0k7-00023.warc.os.cdx.gz	5178192	download
espanol.cdc.gov-inf-20210513-194340-bdgzu-00001.warc.gz	240173079	download job
espanol.cdc.gov-inf-20210513-194340-bdgzu-00001.warc.os.cdx.gz	578149	download
espanol.cdc.gov-inf-20210513-194340-bdgzu-meta.warc.gz	3217535	download job
espanol.cdc.gov-inf-20210513-194340-bdgzu-meta.warc.os.cdx.gz	47	download
espanol.cdc.gov-inf-20210513-194340-bdgzu.json	278	download job
files.elomatreb.eu-shallow-20210514-002952-dmap1-00000.warc.gz	51414	download job
files.elomatreb.eu-shallow-20210514-002952-dmap1-00000.warc.os.cdx.gz	242	download
files.elomatreb.eu-shallow-20210514-002952-dmap1-meta.warc.gz	3459	download job
files.elomatreb.eu-shallow-20210514-002952-dmap1-meta.warc.os.cdx.gz	47	download
files.elomatreb.eu-shallow-20210514-002952-dmap1.json	285	download job
github.com-inf-20210511-230212-c4io5-meta.warc.gz	4235340	download job
github.com-inf-20210511-230212-c4io5-meta.warc.os.cdx.gz	47	download
grimmlawdc.com-inf-20210514-001941-156q5-00000.warc.gz	1009328050	download job
grimmlawdc.com-inf-20210514-001941-156q5-00000.warc.os.cdx.gz	323236	download
grimmlawdc.com-inf-20210514-001941-156q5-meta.warc.gz	230287	download job
grimmlawdc.com-inf-20210514-001941-156q5-meta.warc.os.cdx.gz	47	download
grimmlawdc.com-inf-20210514-001941-156q5.json	243	download job
imeu.org-inf-20210513-010303-dfbph-meta.warc.gz	8546953	download job
imeu.org-inf-20210513-010303-dfbph-meta.warc.os.cdx.gz	47	download
imeu.org-inf-20210513-010303-dfbph.json	238	download job
northwiltslibdems.org.uk-inf-20210513-043643-5ccbw-aborted-00000.warc.gz	497407227	download job
northwiltslibdems.org.uk-inf-20210513-043643-5ccbw-aborted-00000.warc.os.cdx.gz	668272	download
northwiltslibdems.org.uk-inf-20210513-043643-5ccbw-aborted-wpull.log.gz	467654	download
northwiltslibdems.org.uk-inf-20210513-043643-5ccbw-aborted.json	256	download job
papersdev.nber.org-inf-20210311-024527-8v7hr-00082.warc.gz	5376657056	download job
papersdev.nber.org-inf-20210311-024527-8v7hr-00082.warc.os.cdx.gz	1298292	download
patriots.win-inf-20210220-015122-uuues-00779.warc.gz	5368745425	download job
patriots.win-inf-20210220-015122-uuues-00779.warc.os.cdx.gz	1149599	download
patriots.win-inf-20210220-015122-uuues-00780.warc.gz	5457960067	download job
patriots.win-inf-20210220-015122-uuues-00780.warc.os.cdx.gz	584633	download
patriots.win-inf-20210220-015122-uuues-00781.warc.gz	5421566956	download job
patriots.win-inf-20210220-015122-uuues-00781.warc.os.cdx.gz	8969	download
pefop.iiep.unesco.org-inf-20210513-221931-8edxr-00000.warc.gz	5374377173	download job
pefop.iiep.unesco.org-inf-20210513-221931-8edxr-00000.warc.os.cdx.gz	1774667	download
pefop.iiep.unesco.org-inf-20210513-221931-8edxr-00002.warc.gz	2470	download job
pefop.iiep.unesco.org-inf-20210513-221931-8edxr-00002.warc.os.cdx.gz	47	download
pefop.iiep.unesco.org-inf-20210513-221931-8edxr.json	251	download job
rinkworks.com-inf-20210504-181328-4eivl-00012.warc.gz	5368711562	download job
rinkworks.com-inf-20210504-181328-4eivl-00012.warc.os.cdx.gz	5829796	download
stallman.org-inf-20210505-021045-4xt4z-00036.warc.gz	5375724963	download job
stallman.org-inf-20210505-021045-4xt4z-00036.warc.os.cdx.gz	1340012	download
stirlinglibdems.org.uk-inf-20210513-072556-f0xlh-00000.warc.gz	1720565222	download job
stirlinglibdems.org.uk-inf-20210513-072556-f0xlh-00000.warc.os.cdx.gz	1130346	download
stirlinglibdems.org.uk-inf-20210513-072556-f0xlh-meta.warc.gz	793624	download job
stirlinglibdems.org.uk-inf-20210513-072556-f0xlh-meta.warc.os.cdx.gz	47	download
stirlinglibdems.org.uk-inf-20210513-072556-f0xlh.json	255	download job
stuartjeffery.blogspot.com-inf-20210513-101311-4ks8u-00002.warc.gz	1509027366	download job
stuartjeffery.blogspot.com-inf-20210513-101311-4ks8u-00002.warc.os.cdx.gz	1845117	download
stuartjeffery.blogspot.com-inf-20210513-101311-4ks8u-meta.warc.gz	5420284	download job
stuartjeffery.blogspot.com-inf-20210513-101311-4ks8u-meta.warc.os.cdx.gz	47	download
stuartjeffery.blogspot.com-inf-20210513-101311-4ks8u.json	258	download job
tilde.club-inf-20210505-030212-ckqhh-00024.warc.gz	5561258841	download job
tilde.club-inf-20210505-030212-ckqhh-00024.warc.os.cdx.gz	4547386	download
tilde.club-inf-20210505-030212-ckqhh-00025.warc.gz	5387638461	download job
tilde.club-inf-20210505-030212-ckqhh-00025.warc.os.cdx.gz	6049	download
tilde.club-inf-20210505-030212-ckqhh-00026.warc.gz	5383244079	download job
tilde.club-inf-20210505-030212-ckqhh-00026.warc.os.cdx.gz	7416	download
urls-transfer.archivete.am-twitter-%23GazaUnderAttack-shallow-20210512-195522-elkbw-00009.warc.gz	5368728215	download job
urls-transfer.archivete.am-twitter-%23GazaUnderAttack-shallow-20210512-195522-elkbw-00009.warc.os.cdx.gz	5263435	download
urls-transfer.archivete.am-twitter-%23freepalestine-shallow-20210512-205108-d55gc-00008.warc.gz	5368764663	download job
urls-transfer.archivete.am-twitter-%23freepalestine-shallow-20210512-205108-d55gc-00008.warc.os.cdx.gz	4139704	download
urls-transfer.archivete.am-twitter-@AJCGlobal-shallow-20210513-215611-1agr0-00000.warc.gz	5387921482	download job
urls-transfer.archivete.am-twitter-@AJCGlobal-shallow-20210513-215611-1agr0-00000.warc.os.cdx.gz	4298451	download
urls-transfer.archivete.am-twitter-@FDIonline-shallow-20210513-224017-4kdx0-00000.warc.gz	3864130604	download job
urls-transfer.archivete.am-twitter-@FDIonline-shallow-20210513-224017-4kdx0-00000.warc.os.cdx.gz	3383894	download
urls-transfer.archivete.am-twitter-@FDIonline-shallow-20210513-224017-4kdx0-meta.warc.gz	1888887	download job
urls-transfer.archivete.am-twitter-@FDIonline-shallow-20210513-224017-4kdx0-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@FDIonline-shallow-20210513-224017-4kdx0-urls.txt	819318	download
urls-transfer.archivete.am-twitter-@HanaSalahGaza-shallow-20210513-225152-4hiti-00000.warc.gz	1459479549	download job
urls-transfer.archivete.am-twitter-@HanaSalahGaza-shallow-20210513-225152-4hiti-00000.warc.os.cdx.gz	1248946	download
urls-transfer.archivete.am-twitter-@HanaSalahGaza-shallow-20210513-225152-4hiti-meta.warc.gz	800269	download job
urls-transfer.archivete.am-twitter-@HanaSalahGaza-shallow-20210513-225152-4hiti-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@HanaSalahGaza-shallow-20210513-225152-4hiti-urls.txt	93462	download
urls-transfer.archivete.am-twitter-@HanaSalahGaza-shallow-20210513-225152-4hiti.json	342	download job
urls-transfer.archivete.am-twitter-@idfonline-shallow-20210513-224106-aopfp-00000.warc.gz	5473601204	download job
urls-transfer.archivete.am-twitter-@idfonline-shallow-20210513-224106-aopfp-00000.warc.os.cdx.gz	1538119	download
urls-transfer.archivete.am-twitter-@idfonline-shallow-20210513-224106-aopfp-00001.warc.gz	5466997784	download job
urls-transfer.archivete.am-twitter-@idfonline-shallow-20210513-224106-aopfp-00001.warc.os.cdx.gz	302828	download
vietnamese.cdc.gov-inf-20210513-194458-39skb-00000.warc.gz	1634204740	download job
vietnamese.cdc.gov-inf-20210513-194458-39skb-00000.warc.os.cdx.gz	1977645	download
vietnamese.cdc.gov-inf-20210513-194458-39skb-meta.warc.gz	1426850	download job
vietnamese.cdc.gov-inf-20210513-194458-39skb-meta.warc.os.cdx.gz	47	download
vietnamese.cdc.gov-inf-20210513-194458-39skb.json	281	download job
ww5.swindon.gov.uk-inf-20210513-163259-7h2o7-00002.warc.gz	5371536587	download job
ww5.swindon.gov.uk-inf-20210513-163259-7h2o7-00002.warc.os.cdx.gz	1121034	download
www.darrylpreston.org.uk-inf-20210513-184150-84sbm-00000.warc.gz	253324237	download job
www.darrylpreston.org.uk-inf-20210513-184150-84sbm-00000.warc.os.cdx.gz	459236	download
www.darrylpreston.org.uk-inf-20210513-184150-84sbm-meta.warc.gz	338137	download job
www.darrylpreston.org.uk-inf-20210513-184150-84sbm-meta.warc.os.cdx.gz	47	download
www.darrylpreston.org.uk-inf-20210513-184150-84sbm.json	257	download job
www.dcbar.org-shallow-20210514-002035-dc58r-00000.warc.gz	172685	download job
www.dcbar.org-shallow-20210514-002035-dc58r-00000.warc.os.cdx.gz	284	download
www.dcbar.org-shallow-20210514-002035-dc58r-meta.warc.gz	3539	download job
www.dcbar.org-shallow-20210514-002035-dc58r-meta.warc.os.cdx.gz	47	download
www.dcbar.org-shallow-20210514-002035-dc58r.json	313	download job
www.enfield-libdems.org.uk-inf-20210513-191916-699p6-00000.warc.gz	1345841116	download job
www.enfield-libdems.org.uk-inf-20210513-191916-699p6-00000.warc.os.cdx.gz	526485	download
www.glasgowlibdems.org.uk-inf-20210513-202803-x5vmq-00000.warc.gz	598932334	download job
www.glasgowlibdems.org.uk-inf-20210513-202803-x5vmq-00000.warc.os.cdx.gz	476174	download
www.glasgowlibdems.org.uk-inf-20210513-202803-x5vmq-meta.warc.gz	296532	download job
www.glasgowlibdems.org.uk-inf-20210513-202803-x5vmq-meta.warc.os.cdx.gz	47	download
www.glasgowlibdems.org.uk-inf-20210513-202803-x5vmq.json	258	download job
www.jamesnewport.co.uk-inf-20210513-215434-y8yav-00000.warc.gz	4413275486	download job
www.jamesnewport.co.uk-inf-20210513-215434-y8yav-00000.warc.os.cdx.gz	2935858	download
www.jamesnewport.co.uk-inf-20210513-215434-y8yav-meta.warc.gz	2296225	download job
www.jamesnewport.co.uk-inf-20210513-215434-y8yav-meta.warc.os.cdx.gz	47	download
www.jamesnewport.co.uk-inf-20210513-215434-y8yav.json	255	download job
www.joycewatson.org.uk-inf-20210513-222301-e82ov-00000.warc.gz	1143410881	download job
www.joycewatson.org.uk-inf-20210513-222301-e82ov-00000.warc.os.cdx.gz	1575884	download
www.joycewatson.org.uk-inf-20210513-222301-e82ov.json	255	download job
www.ketteringgreenparty.org-inf-20210513-223337-39q6g-00000.warc.gz	762412358	download job
www.ketteringgreenparty.org-inf-20210513-223337-39q6g-00000.warc.os.cdx.gz	2102986	download
www.ketteringgreenparty.org-inf-20210513-223337-39q6g-meta.warc.gz	827485	download job
www.ketteringgreenparty.org-inf-20210513-223337-39q6g-meta.warc.os.cdx.gz	47	download
www.ketteringgreenparty.org-inf-20210513-223337-39q6g.json	260	download job
www.ketteringgreenparty.org-shallow-20210513-233948-3a2r4-00000.warc.gz	2008031	download job
www.ketteringgreenparty.org-shallow-20210513-233948-3a2r4-00000.warc.os.cdx.gz	4685	download
www.ketteringgreenparty.org-shallow-20210513-233948-3a2r4-meta.warc.gz	6161	download job
www.ketteringgreenparty.org-shallow-20210513-233948-3a2r4-meta.warc.os.cdx.gz	47	download
www.ketteringgreenparty.org-shallow-20210513-233948-3a2r4.json	293	download job
www.krisforpcc.org.uk-inf-20210513-223904-cbmql-00000.warc.gz	153292631	download job
www.krisforpcc.org.uk-inf-20210513-223904-cbmql-00000.warc.os.cdx.gz	233659	download
www.krisforpcc.org.uk-inf-20210513-223904-cbmql-meta.warc.gz	160612	download job
www.krisforpcc.org.uk-inf-20210513-223904-cbmql-meta.warc.os.cdx.gz	47	download
www.krisforpcc.org.uk-inf-20210513-223904-cbmql.json	254	download job
www.langley4mayor.co.uk-inf-20210513-225820-ejvn3-00000.warc.gz	430373198	download job
www.langley4mayor.co.uk-inf-20210513-225820-ejvn3-00000.warc.os.cdx.gz	123566	download
www.langley4mayor.co.uk-inf-20210513-225820-ejvn3.json	256	download job
www.laura-evans.org.uk-inf-20210513-230231-c0zjz-00000.warc.gz	563826835	download job
www.laura-evans.org.uk-inf-20210513-230231-c0zjz-00000.warc.os.cdx.gz	249759	download
www.laura-evans.org.uk-inf-20210513-230231-c0zjz-meta.warc.gz	169378	download job
www.laura-evans.org.uk-inf-20210513-230231-c0zjz-meta.warc.os.cdx.gz	47	download
www.laura-evans.org.uk-inf-20210513-230231-c0zjz.json	255	download job
www.leannerhondda.wales-inf-20210513-230337-72bi6-00000.warc.gz	1496687541	download job
www.leannerhondda.wales-inf-20210513-230337-72bi6-00000.warc.os.cdx.gz	6520587	download
www.lewiswhyte.scot-inf-20210513-232355-21jt2-00000.warc.gz	124763623	download job
www.lewiswhyte.scot-inf-20210513-232355-21jt2-00000.warc.os.cdx.gz	228395	download
www.lewiswhyte.scot-inf-20210513-232355-21jt2-meta.warc.gz	151006	download job
www.lewiswhyte.scot-inf-20210513-232355-21jt2-meta.warc.os.cdx.gz	47	download
www.lewiswhyte.scot-inf-20210513-232355-21jt2.json	252	download job
www.lisatownsend.org.uk-inf-20210514-001232-21zd5-00000.warc.gz	210625414	download job
www.lisatownsend.org.uk-inf-20210514-001232-21zd5-00000.warc.os.cdx.gz	141325	download
www.lisatownsend.org.uk-inf-20210514-001232-21zd5-meta.warc.gz	97586	download job
www.lisatownsend.org.uk-inf-20210514-001232-21zd5-meta.warc.os.cdx.gz	47	download
www.lisatownsend.org.uk-inf-20210514-001232-21zd5.json	256	download job
www.lizhilloshea.org.uk-inf-20210514-001540-4eb45-00000.warc.gz	67606764	download job
www.lizhilloshea.org.uk-inf-20210514-001540-4eb45-00000.warc.os.cdx.gz	122430	download
www.lizhilloshea.org.uk-inf-20210514-001540-4eb45-meta.warc.gz	88070	download job
www.lizhilloshea.org.uk-inf-20210514-001540-4eb45-meta.warc.os.cdx.gz	47	download
www.lizhilloshea.org.uk-inf-20210514-001540-4eb45.json	256	download job
www.lizwebster.org.uk-inf-20210514-002047-7wor2-00000.warc.gz	180515038	download job
www.lizwebster.org.uk-inf-20210514-002047-7wor2-00000.warc.os.cdx.gz	497826	download
www.lizwebster.org.uk-inf-20210514-002047-7wor2-meta.warc.gz	249951	download job
www.lizwebster.org.uk-inf-20210514-002047-7wor2-meta.warc.os.cdx.gz	47	download
www.lizwebster.org.uk-inf-20210514-002047-7wor2.json	254	download job
www.lizzicollinge.com-inf-20210514-002349-arvya-00000.warc.gz	17998299	download job
www.lizzicollinge.com-inf-20210514-002349-arvya-00000.warc.os.cdx.gz	41670	download
www.lizzicollinge.com-inf-20210514-002349-arvya-meta.warc.gz	30320	download job
www.lizzicollinge.com-inf-20210514-002349-arvya-meta.warc.os.cdx.gz	47	download
www.lizzicollinge.com-inf-20210514-002349-arvya.json	254	download job
www.louiscarserides.co.uk-inf-20210514-002703-ddape-00000.warc.gz	71808393	download job
www.louiscarserides.co.uk-inf-20210514-002703-ddape-00000.warc.os.cdx.gz	100661	download
www.louiscarserides.co.uk-inf-20210514-002703-ddape-meta.warc.gz	72580	download job
www.louiscarserides.co.uk-inf-20210514-002703-ddape-meta.warc.os.cdx.gz	47	download
www.louiscarserides.co.uk-inf-20210514-002703-ddape.json	258	download job
www.louisecalland.co.uk-inf-20210514-002818-a4pfe-00000.warc.gz	156047268	download job
www.louisecalland.co.uk-inf-20210514-002818-a4pfe-00000.warc.os.cdx.gz	157247	download
www.louisecalland.co.uk-inf-20210514-002818-a4pfe-meta.warc.gz	107858	download job
www.louisecalland.co.uk-inf-20210514-002818-a4pfe-meta.warc.os.cdx.gz	47	download
www.louisecalland.co.uk-inf-20210514-002818-a4pfe.json	256	download job
www.maddy-kirkman.uk-inf-20210514-002824-783r6-00000.warc.gz	47926810	download job
www.maddy-kirkman.uk-inf-20210514-002824-783r6-00000.warc.os.cdx.gz	54579	download
www.maddy-kirkman.uk-inf-20210514-002824-783r6-meta.warc.gz	77837	download job
www.maddy-kirkman.uk-inf-20210514-002824-783r6-meta.warc.os.cdx.gz	47	download
www.maddy-kirkman.uk-inf-20210514-002824-783r6.json	253	download job
www.mahaboobforwales.co.uk-inf-20210514-003125-31d3x-00000.warc.gz	96774029	download job
www.mahaboobforwales.co.uk-inf-20210514-003125-31d3x-00000.warc.os.cdx.gz	173680	download
www.mahaboobforwales.co.uk-inf-20210514-003125-31d3x-meta.warc.gz	110825	download job
www.mahaboobforwales.co.uk-inf-20210514-003125-31d3x-meta.warc.os.cdx.gz	47	download
www.mahaboobforwales.co.uk-inf-20210514-003125-31d3x.json	259	download job
www.maidstonelabour.com-inf-20210514-003246-cygvx-00000.warc.gz	32884031	download job
www.maidstonelabour.com-inf-20210514-003246-cygvx-00000.warc.os.cdx.gz	45907	download
www.maidstonelabour.com-inf-20210514-003246-cygvx-meta.warc.gz	34150	download job
www.maidstonelabour.com-inf-20210514-003246-cygvx-meta.warc.os.cdx.gz	47	download
www.maidstonelabour.com-inf-20210514-003246-cygvx.json	256	download job
www.marcus4bingley.co.uk-inf-20210514-003446-ekz5a-00000.warc.gz	14521356	download job
www.marcus4bingley.co.uk-inf-20210514-003446-ekz5a-00000.warc.os.cdx.gz	56007	download
www.marcus4bingley.co.uk-inf-20210514-003446-ekz5a-meta.warc.gz	36336	download job
www.marcus4bingley.co.uk-inf-20210514-003446-ekz5a-meta.warc.os.cdx.gz	47	download
www.marcus4bingley.co.uk-inf-20210514-003446-ekz5a.json	257	download job
www.marinaahmadlabour.com-inf-20210514-003546-1k54h-00000.warc.gz	100762214	download job
www.marinaahmadlabour.com-inf-20210514-003546-1k54h-00000.warc.os.cdx.gz	159955	download
www.marinaahmadlabour.com-inf-20210514-003546-1k54h-meta.warc.gz	107741	download job
www.marinaahmadlabour.com-inf-20210514-003546-1k54h-meta.warc.os.cdx.gz	47	download
www.marinaahmadlabour.com-inf-20210514-003546-1k54h.json	258	download job
www.markshelford.org.uk-inf-20210514-003901-d2khn-00000.warc.gz	126218313	download job
www.markshelford.org.uk-inf-20210514-003901-d2khn-00000.warc.os.cdx.gz	145909	download
www.markshelford.org.uk-inf-20210514-003901-d2khn-meta.warc.gz	99511	download job
www.markshelford.org.uk-inf-20210514-003901-d2khn-meta.warc.os.cdx.gz	47	download
www.markshelford.org.uk-inf-20210514-003901-d2khn.json	256	download job
www.martinbristow.wales-inf-20210514-004012-aemwb-00000.warc.gz	10445	download job
www.martinbristow.wales-inf-20210514-004012-aemwb-00000.warc.os.cdx.gz	302	download
www.martinbristow.wales-inf-20210514-004012-aemwb-meta.warc.gz	3481	download job
www.martinbristow.wales-inf-20210514-004012-aemwb-meta.warc.os.cdx.gz	47	download
www.martinbristow.wales-inf-20210514-004012-aemwb.json	256	download job
www.martyn4abbey.com-inf-20210514-004021-cgv0s-00000.warc.gz	2280490108	download job
www.martyn4abbey.com-inf-20210514-004021-cgv0s-00000.warc.os.cdx.gz	214766	download
www.martyn4abbey.com-inf-20210514-004021-cgv0s-meta.warc.gz	141347	download job
www.martyn4abbey.com-inf-20210514-004021-cgv0s-meta.warc.os.cdx.gz	47	download
www.martyn4abbey.com-inf-20210514-004021-cgv0s.json	253	download job
www.mattfarrell.co.uk-inf-20210514-004228-46cb4-00000.warc.gz	117053128	download job
www.mattfarrell.co.uk-inf-20210514-004228-46cb4-00000.warc.os.cdx.gz	197963	download
www.mattfarrell.co.uk-inf-20210514-004228-46cb4-meta.warc.gz	131750	download job
www.mattfarrell.co.uk-inf-20210514-004228-46cb4-meta.warc.os.cdx.gz	47	download
www.mattfarrell.co.uk-inf-20210514-004228-46cb4.json	254	download job
www.mauricegolden.com-inf-20210514-004253-bvxzh-00000.warc.gz	193640900	download job
www.mauricegolden.com-inf-20210514-004253-bvxzh-00000.warc.os.cdx.gz	341023	download
www.mauricegolden.com-inf-20210514-004253-bvxzh-meta.warc.gz	201907	download job
www.mauricegolden.com-inf-20210514-004253-bvxzh-meta.warc.os.cdx.gz	47	download
www.mauricegolden.com-inf-20210514-004253-bvxzh.json	254	download job
www.michaelmarra.net-inf-20210514-004011-60jvf-00000.warc.gz	103371297	download job
www.michaelmarra.net-inf-20210514-004011-60jvf-00000.warc.os.cdx.gz	172045	download
www.michaelmarra.net-inf-20210514-004011-60jvf-meta.warc.gz	114746	download job
www.michaelmarra.net-inf-20210514-004011-60jvf-meta.warc.os.cdx.gz	47	download
www.michaelmarra.net-inf-20210514-004011-60jvf.json	253	download job
www.mikeforcommissioner.co.uk-inf-20210514-004758-87jz2-00000.warc.gz	98068441	download job
www.mikeforcommissioner.co.uk-inf-20210514-004758-87jz2-00000.warc.os.cdx.gz	42439	download
www.mikeforcommissioner.co.uk-inf-20210514-004758-87jz2-meta.warc.gz	27593	download job
www.mikeforcommissioner.co.uk-inf-20210514-004758-87jz2-meta.warc.os.cdx.gz	47	download
www.mikeforcommissioner.co.uk-inf-20210514-004758-87jz2.json	262	download job
www.milesbriggs.scot-inf-20210514-005006-3u05w-00000.warc.gz	75534693	download job
www.milesbriggs.scot-inf-20210514-005006-3u05w-00000.warc.os.cdx.gz	184970	download
www.milesbriggs.scot-inf-20210514-005006-3u05w.json	253	download job
www.myleslangstone.org.uk-inf-20210514-005141-1d81l-00000.warc.gz	105881580	download job
www.myleslangstone.org.uk-inf-20210514-005141-1d81l-00000.warc.os.cdx.gz	113281	download
www.naglauramanston.com-inf-20210514-005442-de46q-00000.warc.gz	205325271	download job
www.naglauramanston.com-inf-20210514-005442-de46q-00000.warc.os.cdx.gz	445831	download
www.naglauramanston.com-inf-20210514-005442-de46q-meta.warc.gz	281692	download job
www.naglauramanston.com-inf-20210514-005442-de46q-meta.warc.os.cdx.gz	47	download
www.naglauramanston.com-inf-20210514-005442-de46q.json	256	download job
www.neilgarratt.com-inf-20210514-005447-2ttgm-00000.warc.gz	719652969	download job
www.neilgarratt.com-inf-20210514-005447-2ttgm-00000.warc.os.cdx.gz	602541	download
www.neilgarratt.com-inf-20210514-005447-2ttgm.json	252	download job
www.neilmcevoy.wales-inf-20210514-005852-dfpr1-00000.warc.gz	10808	download job
www.neilmcevoy.wales-inf-20210514-005852-dfpr1-00000.warc.os.cdx.gz	315	download
www.neilmcevoy.wales-inf-20210514-005852-dfpr1-meta.warc.gz	3595	download job
www.neilmcevoy.wales-inf-20210514-005852-dfpr1-meta.warc.os.cdx.gz	47	download
www.neilmcevoy.wales-inf-20210514-005852-dfpr1.json	253	download job
www.nicholasrogers.org-inf-20210514-010020-cn9g3-00000.warc.gz	150117216	download job
www.nicholasrogers.org-inf-20210514-010020-cn9g3-00000.warc.os.cdx.gz	189552	download
www.nicholasrogers.org-inf-20210514-010020-cn9g3-meta.warc.gz	121395	download job
www.nicholasrogers.org-inf-20210514-010020-cn9g3-meta.warc.os.cdx.gz	47	download
www.nimsforlondon.com-inf-20210514-010320-76vwq-meta.warc.gz	167803	download job
www.nimsforlondon.com-inf-20210514-010320-76vwq-meta.warc.os.cdx.gz	47	download
www.nimsforlondon.com-inf-20210514-010320-76vwq.json	254	download job
www.northdevonlabour.org-inf-20210514-010428-bkicg-00000.warc.gz	712536381	download job
www.northdevonlabour.org-inf-20210514-010428-bkicg-00000.warc.os.cdx.gz	471263	download
www.northdevonlabour.org-inf-20210514-010428-bkicg.json	257	download job
www.paul-hodgkinson.org.uk-inf-20210514-011701-f3eba-00000.warc.gz	553274661	download job
www.paul-hodgkinson.org.uk-inf-20210514-011701-f3eba-00000.warc.os.cdx.gz	681818	download
www.paul-hodgkinson.org.uk-inf-20210514-011701-f3eba.json	259	download job
www.paulokane.scot-inf-20210514-011709-6z6j4-00000.warc.gz	32185914	download job
www.paulokane.scot-inf-20210514-011709-6z6j4-00000.warc.os.cdx.gz	30209	download
www.peverell2021.co.uk-inf-20210514-011723-29n9j-00000.warc.gz	166262845	download job
www.peverell2021.co.uk-inf-20210514-011723-29n9j-00000.warc.os.cdx.gz	200213	download
www.populistparty.co.uk-inf-20210514-012031-bumfw-meta.warc.gz	30566	download job
www.populistparty.co.uk-inf-20210514-012031-bumfw-meta.warc.os.cdx.gz	47	download
www.rhodagrant.org.uk-inf-20210514-012804-1a4ea-00000.warc.gz	576125378	download job
www.rhodagrant.org.uk-inf-20210514-012804-1a4ea-00000.warc.os.cdx.gz	491919	download
www.rhodagrant.org.uk-inf-20210514-012804-1a4ea-meta.warc.gz	316774	download job
www.rhodagrant.org.uk-inf-20210514-012804-1a4ea-meta.warc.os.cdx.gz	47	download
www.rhodagrant.org.uk-inf-20210514-012804-1a4ea.json	254	download job
www.rhysabowen.cymru-inf-20210514-013010-20ijw-00000.warc.gz	39692380	download job
www.rhysabowen.cymru-inf-20210514-013010-20ijw-00000.warc.os.cdx.gz	57623	download
www.riazhassan.co.uk-inf-20210514-013223-vip81-00000.warc.gz	97033074	download job
www.riazhassan.co.uk-inf-20210514-013223-vip81-00000.warc.os.cdx.gz	160229	download
www.riazhassan.co.uk-inf-20210514-013223-vip81.json	253	download job
www.richardmurphy.news-inf-20210514-013326-es59u-00000.warc.gz	151044287	download job
www.richardmurphy.news-inf-20210514-013326-es59u-00000.warc.os.cdx.gz	173152	download
www.richardmurphy.news-inf-20210514-013326-es59u.json	255	download job
www.richardroyal.com-inf-20210514-013350-1ux5s-00000.warc.gz	172699567	download job
www.richardroyal.com-inf-20210514-013350-1ux5s-00000.warc.os.cdx.gz	293784	download
www.richardroyal.com-inf-20210514-013350-1ux5s.json	253	download job
www.risboroughindependents.uk-inf-20210514-013544-bugc9-meta.warc.gz	49857	download job
www.risboroughindependents.uk-inf-20210514-013544-bugc9-meta.warc.os.cdx.gz	47	download
www.ros4doncastermayor.org.uk-inf-20210514-013953-a5yyn-00000.warc.gz	18555876	download job
www.ros4doncastermayor.org.uk-inf-20210514-013953-a5yyn-00000.warc.os.cdx.gz	30324	download
www.ros4doncastermayor.org.uk-inf-20210514-013953-a5yyn-meta.warc.gz	23026	download job
www.ros4doncastermayor.org.uk-inf-20210514-013953-a5yyn-meta.warc.os.cdx.gz	47	download
www.ruth4lancaster.co.uk-inf-20210514-014431-39640-00000.warc.gz	20295411	download job
www.ruth4lancaster.co.uk-inf-20210514-014431-39640-00000.warc.os.cdx.gz	43916	download
www.ruth4lancaster.co.uk-inf-20210514-014431-39640.json	257	download job
www.ruthgripper.org.uk-inf-20210514-014738-dyhuo-meta.warc.gz	3686	download job
www.ruthgripper.org.uk-inf-20210514-014738-dyhuo-meta.warc.os.cdx.gz	47	download
www.ruthgripper.org.uk-inf-20210514-014738-dyhuo.json	255	download job
www.rwbygrimmeclipse.com-inf-20210513-234310-11gi1-00000.warc.gz	572735101	download job
www.rwbygrimmeclipse.com-inf-20210513-234310-11gi1-00000.warc.os.cdx.gz	486936	download
www.rwbygrimmeclipse.com-inf-20210513-234310-11gi1-meta.warc.gz	299225	download job
www.rwbygrimmeclipse.com-inf-20210513-234310-11gi1-meta.warc.os.cdx.gz	47	download
www.rwbygrimmeclipse.com-inf-20210513-234310-11gi1.json	253	download job
www.ryanscott.uk-inf-20210514-014852-dxepi-00000.warc.gz	94650033	download job
www.ryanscott.uk-inf-20210514-014852-dxepi-00000.warc.os.cdx.gz	72997	download
www.ryanscott.uk-inf-20210514-014852-dxepi-meta.warc.gz	52687	download job
www.ryanscott.uk-inf-20210514-014852-dxepi-meta.warc.os.cdx.gz	47	download
www.stopantisemitism.org-inf-20210513-001728-bykuq-00006.warc.gz	3980994161	download job
www.stopantisemitism.org-inf-20210513-001728-bykuq-00006.warc.os.cdx.gz	3003868	download
www.stopantisemitism.org-inf-20210513-001728-bykuq-meta.warc.gz	9693988	download job
www.stopantisemitism.org-inf-20210513-001728-bykuq-meta.warc.os.cdx.gz	47	download
www.stopantisemitism.org-inf-20210513-001728-bykuq.json	254	download job
www.stpauls.co.uk-inf-20210513-072226-1d8pm-00003.warc.gz	5110369943	download job
www.stpauls.co.uk-inf-20210513-072226-1d8pm-00003.warc.os.cdx.gz	2821593	download
www.stpauls.co.uk-inf-20210513-072226-1d8pm-meta.warc.gz	6222117	download job
www.stpauls.co.uk-inf-20210513-072226-1d8pm-meta.warc.os.cdx.gz	47	download
www.stpauls.co.uk-inf-20210513-072226-1d8pm.json	245	download job