Item archiveteam_archivebot_go_20190521220001

View on Internet Archive

Filename	Size
allanfaulds.scot-inf-20190521-153344-5fk54-00000.warc.gz	1233299125	download   job
allanfaulds.scot-inf-20190521-153344-5fk54-00000.warc.os.cdx.gz	2373460	download
allanfaulds.scot-inf-20190521-153344-5fk54.json	240	download   job
archiveteam_archivebot_go_20190521220001.cdx.gz	73042933	download
archiveteam_archivebot_go_20190521220001.cdx.idx	75938	download
archiveteam_archivebot_go_20190521220001_archive.torrent	1582538	download
archiveteam_archivebot_go_20190521220001_files.xml	0	download
archiveteam_archivebot_go_20190521220001_meta.sqlite	241664	download
archiveteam_archivebot_go_20190521220001_meta.xml	974	download
bosworthlibdems.org.uk-inf-20190521-182808-e8qn4-meta.warc.gz	1926894	download   job
bosworthlibdems.org.uk-inf-20190521-182808-e8qn4-meta.warc.os.cdx.gz	47	download
bosworthlibdems.org.uk-inf-20190521-182808-e8qn4.json	247	download   job
chrisgalley.com-inf-20190521-194548-784tn-00000.warc.gz	441031101	download   job
chrisgalley.com-inf-20190521-194548-784tn-00000.warc.os.cdx.gz	727272	download
chrisgalley.com-inf-20190521-194548-784tn-meta.warc.gz	520425	download   job
chrisgalley.com-inf-20190521-194548-784tn-meta.warc.os.cdx.gz	47	download
chrisgalley.com-inf-20190521-194548-784tn.json	239	download   job
cllreleanorrylance.focusteam.org.uk-inf-20190521-222521-aoduk-00000.warc.gz	399570399	download   job
cllreleanorrylance.focusteam.org.uk-inf-20190521-222521-aoduk-00000.warc.os.cdx.gz	216286	download
cllreleanorrylance.focusteam.org.uk-inf-20190521-222521-aoduk-meta.warc.gz	134073	download   job
cllreleanorrylance.focusteam.org.uk-inf-20190521-222521-aoduk-meta.warc.os.cdx.gz	47	download
cllreleanorrylance.focusteam.org.uk-inf-20190521-222521-aoduk.json	260	download   job
croydon.greenparty.org.uk-inf-20190521-223649-dz5y8-meta.warc.gz	776240	download   job
croydon.greenparty.org.uk-inf-20190521-223649-dz5y8-meta.warc.os.cdx.gz	47	download
danieldaltonblog.blogspot.co.uk-shallow-20190521-205233-gfhq5-00000.warc.gz	685847	download   job
danieldaltonblog.blogspot.co.uk-shallow-20190521-205233-gfhq5-00000.warc.os.cdx.gz	3718	download
danieldaltonblog.blogspot.co.uk-shallow-20190521-205233-gfhq5-meta.warc.gz	5629	download   job
danieldaltonblog.blogspot.co.uk-shallow-20190521-205233-gfhq5-meta.warc.os.cdx.gz	47	download
danieldaltonblog.blogspot.co.uk-shallow-20190521-205233-gfhq5.json	259	download   job
danieldaltonblog.blogspot.com-inf-20190521-205925-3ohkv-00000.warc.gz	10191748	download   job
danieldaltonblog.blogspot.com-inf-20190521-205925-3ohkv-00000.warc.os.cdx.gz	43600	download
danielsimpson.org.uk-inf-20190521-210213-1wgjr-00000.warc.gz	19302	download   job
danielsimpson.org.uk-inf-20190521-210213-1wgjr-00000.warc.os.cdx.gz	605	download
dianawallis.wordpress.com-inf-20190521-210248-7d3k8.json	250	download   job
fyldelibdems.org.uk-shallow-20190521-215418-88yhs.json	247	download   job
hayarigami.com-inf-20190521-155628-538g9-00000.warc.gz	640967348	download   job
hayarigami.com-inf-20190521-155628-538g9-00000.warc.os.cdx.gz	844658	download
hayarigami.com-inf-20190521-155628-538g9-meta.warc.gz	587891	download   job
hayarigami.com-inf-20190521-155628-538g9-meta.warc.os.cdx.gz	47	download
hayarigami.com-inf-20190521-155628-538g9.json	238	download   job
history/files/twitter.com-shallow-20190521-190331-d1gls-00000.warc.gz.~1~	2490702	download
isdb.pw-inf-20190513-161528-e2ymx-00486.warc.gz	5414637948	download   job
isdb.pw-inf-20190513-161528-e2ymx-00486.warc.os.cdx.gz	635047	download
isdb.pw-inf-20190513-161528-e2ymx-00487.warc.gz	5370548961	download   job
isdb.pw-inf-20190513-161528-e2ymx-00487.warc.os.cdx.gz	508667	download
isdb.pw-inf-20190513-161528-e2ymx-00488.warc.gz	5384166773	download   job
isdb.pw-inf-20190513-161528-e2ymx-00488.warc.os.cdx.gz	342790	download
isdb.pw-inf-20190513-161528-e2ymx-00489.warc.gz	5420287071	download   job
isdb.pw-inf-20190513-161528-e2ymx-00489.warc.os.cdx.gz	675917	download
isdb.pw-inf-20190513-161528-e2ymx-00490.warc.gz	5444028761	download   job
isdb.pw-inf-20190513-161528-e2ymx-00490.warc.os.cdx.gz	621688	download
isdb.pw-inf-20190513-161528-e2ymx-00491.warc.gz	5370467890	download   job
isdb.pw-inf-20190513-161528-e2ymx-00491.warc.os.cdx.gz	845303	download
isdb.pw-inf-20190513-161528-e2ymx-00492.warc.gz	5368859727	download   job
isdb.pw-inf-20190513-161528-e2ymx-00492.warc.os.cdx.gz	552953	download
isdb.pw-inf-20190513-161528-e2ymx-00493.warc.gz	5369055718	download   job
isdb.pw-inf-20190513-161528-e2ymx-00493.warc.os.cdx.gz	381787	download
isdb.pw-inf-20190513-161528-e2ymx-00496.warc.gz	5452227140	download   job
isdb.pw-inf-20190513-161528-e2ymx-00496.warc.os.cdx.gz	434749	download
mini.johnbeak.cz-inf-20190521-195042-a6jyn-00000.warc.gz	2323514334	download   job
mini.johnbeak.cz-inf-20190521-195042-a6jyn-00000.warc.os.cdx.gz	2264173	download
mini.johnbeak.cz-inf-20190521-195042-a6jyn-meta.warc.gz	1307853	download   job
mini.johnbeak.cz-inf-20190521-195042-a6jyn-meta.warc.os.cdx.gz	47	download
mini.johnbeak.cz-inf-20190521-195042-a6jyn.json	243	download   job
nikeinsights.famguardian.org-inf-20190515-114122-7olb1-00002.warc.gz	5372003802	download   job
nikeinsights.famguardian.org-inf-20190515-114122-7olb1-00002.warc.os.cdx.gz	3291571	download
pplware.sapo.pt-inf-20190413-145521-2bmau-00125.warc.gz	5368719415	download   job
pplware.sapo.pt-inf-20190413-145521-2bmau-00125.warc.os.cdx.gz	7127670	download
sputniknews.com-inf-20190505-084431-an2l7-00180.warc.gz	5373946700	download   job
sputniknews.com-inf-20190505-084431-an2l7-00180.warc.os.cdx.gz	1469004	download
sputniknews.com-inf-20190505-084431-an2l7-00181.warc.gz	5497815145	download   job
sputniknews.com-inf-20190505-084431-an2l7-00181.warc.os.cdx.gz	1908600	download
tgftp.nws.noaa.gov-inf-20190516-192400-bwzo5-00022.warc.gz	5368734381	download   job
tgftp.nws.noaa.gov-inf-20190516-192400-bwzo5-00022.warc.os.cdx.gz	8418974	download
twitter.com-shallow-20190521-180236-2m84t-meta.warc.gz	6727	download   job
twitter.com-shallow-20190521-180236-2m84t-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-180236-2m84t.json	258	download   job
twitter.com-shallow-20190521-182845-5qgvk-00000.warc.gz	1400082	download   job
twitter.com-shallow-20190521-182845-5qgvk-00000.warc.os.cdx.gz	4935	download
twitter.com-shallow-20190521-182845-5qgvk-meta.warc.gz	6496	download   job
twitter.com-shallow-20190521-182845-5qgvk-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-185717-1x6gj-00000.warc.gz	956551	download   job
twitter.com-shallow-20190521-185717-1x6gj-00000.warc.os.cdx.gz	4084	download
twitter.com-shallow-20190521-185717-1x6gj-meta.warc.gz	6057	download   job
twitter.com-shallow-20190521-185717-1x6gj-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-190331-d1gls-00000.warc.gz	2490702	download   job
twitter.com-shallow-20190521-190331-d1gls-00000.warc.os.cdx.gz	6132	download
twitter.com-shallow-20190521-190331-d1gls-meta.warc.gz	7287	download   job
twitter.com-shallow-20190521-190331-d1gls-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-190331-d1gls.json	260	download   job
twitter.com-shallow-20190521-193014-3g5ch-00000.warc.gz	2681157	download   job
twitter.com-shallow-20190521-193014-3g5ch-00000.warc.os.cdx.gz	6148	download
twitter.com-shallow-20190521-193014-3g5ch-meta.warc.gz	7238	download   job
twitter.com-shallow-20190521-193014-3g5ch-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-193014-3g5ch.json	261	download   job
twitter.com-shallow-20190521-195721-5452l-00000.warc.gz	1388555	download   job
twitter.com-shallow-20190521-195721-5452l-00000.warc.os.cdx.gz	5358	download
twitter.com-shallow-20190521-195721-5452l-meta.warc.gz	6757	download   job
twitter.com-shallow-20190521-195721-5452l-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-195721-5452l.json	259	download   job
twitter.com-shallow-20190521-200744-8a5qq-00000.warc.gz	2368171	download   job
twitter.com-shallow-20190521-200744-8a5qq-00000.warc.os.cdx.gz	6985	download
twitter.com-shallow-20190521-200744-8a5qq-meta.warc.gz	7776	download   job
twitter.com-shallow-20190521-200744-8a5qq-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-200744-8a5qq.json	257	download   job
twitter.com-shallow-20190521-202040-4rzc8-00000.warc.gz	1055069	download   job
twitter.com-shallow-20190521-202040-4rzc8-00000.warc.os.cdx.gz	4085	download
twitter.com-shallow-20190521-202040-4rzc8-meta.warc.gz	6030	download   job
twitter.com-shallow-20190521-202040-4rzc8-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-202040-4rzc8.json	255	download   job
twitter.com-shallow-20190521-203141-efnat-00000.warc.gz	2997757	download   job
twitter.com-shallow-20190521-203141-efnat-00000.warc.os.cdx.gz	5995	download
twitter.com-shallow-20190521-203141-efnat-meta.warc.gz	7153	download   job
twitter.com-shallow-20190521-203141-efnat-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20190521-203141-efnat.json	257	download   job
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7-00004.warc.gz	2173402400	download   job
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7-00004.warc.os.cdx.gz	2302900	download
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7-00005.warc.gz	15676472	download   job
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7-00005.warc.os.cdx.gz	156736	download
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7-meta.warc.gz	4721843	download   job
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7-urls.txt	341295	download
urls-transfer.notkiska.pw-twitter-%23STAF-shallow-20190521-234408-bsqn7.json	320	download   job
urls-transfer.notkiska.pw-twitter-%23abst19-shallow-20190520-215424-3a3pt-meta.warc.gz	11600915	download   job
urls-transfer.notkiska.pw-twitter-%23abst19-shallow-20190520-215424-3a3pt-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-%23abst19-shallow-20190520-215424-3a3pt.json	322	download   job
urls-transfer.notkiska.pw-twitter-%23chvote-shallow-20190520-222446-e54ak-00003.warc.gz	5368770178	download   job
urls-transfer.notkiska.pw-twitter-%23chvote-shallow-20190520-222446-e54ak-00003.warc.os.cdx.gz	2525197	download
urls-transfer.notkiska.pw-twitter-@LatuffCartoons-shallow-20190521-172947-33269-00000.warc.gz	3456306710	download   job
urls-transfer.notkiska.pw-twitter-@LatuffCartoons-shallow-20190521-172947-33269-00000.warc.os.cdx.gz	5539891	download
urls-transfer.notkiska.pw-twitter-@LatuffCartoons-shallow-20190521-172947-33269-meta.warc.gz	2947210	download   job
urls-transfer.notkiska.pw-twitter-@LatuffCartoons-shallow-20190521-172947-33269-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@LatuffCartoons-shallow-20190521-172947-33269-urls.txt	1290443	download
urls-transfer.notkiska.pw-twitter-@LatuffCartoons-shallow-20190521-172947-33269.json	340	download   job
urls-transfer.notkiska.pw-twitter-@anyaparampil-shallow-20190521-174508-rk9ga-00000.warc.gz	1021937014	download   job
urls-transfer.notkiska.pw-twitter-@anyaparampil-shallow-20190521-174508-rk9ga-00000.warc.os.cdx.gz	1889652	download
urls-transfer.notkiska.pw-twitter-@anyaparampil-shallow-20190521-174508-rk9ga-meta.warc.gz	1009096	download   job
urls-transfer.notkiska.pw-twitter-@anyaparampil-shallow-20190521-174508-rk9ga-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@anyaparampil-shallow-20190521-174508-rk9ga.json	336	download   job
urls-transfer.notkiska.pw-twitter-user-DigitalSevilla-shallow-20190521-185718-al5r8-00000.warc.gz	1034763505	download   job
urls-transfer.notkiska.pw-twitter-user-DigitalSevilla-shallow-20190521-185718-al5r8-00000.warc.os.cdx.gz	2646302	download
urls-transfer.notkiska.pw-twitter-user-DigitalSevilla-shallow-20190521-185718-al5r8-meta.warc.gz	1429309	download   job
urls-transfer.notkiska.pw-twitter-user-DigitalSevilla-shallow-20190521-185718-al5r8-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-user-DigitalSevilla-shallow-20190521-185718-al5r8-urls.txt	516750	download
urls-transfer.notkiska.pw-twitter-user-DigitalSevilla-shallow-20190521-185718-al5r8.json	348	download   job
urls-transfer.notkiska.pw-twitter-user-Globoterror-shallow-20190521-182904-qhy67-00000.warc.gz	1573532509	download   job
urls-transfer.notkiska.pw-twitter-user-Globoterror-shallow-20190521-182904-qhy67-00000.warc.os.cdx.gz	3302374	download
urls-transfer.notkiska.pw-twitter-user-Globoterror-shallow-20190521-182904-qhy67-meta.warc.gz	1807270	download   job
urls-transfer.notkiska.pw-twitter-user-Globoterror-shallow-20190521-182904-qhy67-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-user-Globoterror-shallow-20190521-182904-qhy67-urls.txt	840724	download
urls-transfer.notkiska.pw-twitter-user-Globoterror-shallow-20190521-182904-qhy67.json	342	download   job
urls-transfer.notkiska.pw-twitter-user-MESA_MH_LATINA-shallow-20190521-190333-esyby-00000.warc.gz	246885719	download   job
urls-transfer.notkiska.pw-twitter-user-MESA_MH_LATINA-shallow-20190521-190333-esyby-00000.warc.os.cdx.gz	373526	download
urls-transfer.notkiska.pw-twitter-user-MESA_MH_LATINA-shallow-20190521-190333-esyby-meta.warc.gz	203055	download   job
urls-transfer.notkiska.pw-twitter-user-MESA_MH_LATINA-shallow-20190521-190333-esyby-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-user-MESA_MH_LATINA-shallow-20190521-190333-esyby-urls.txt	152651	download
urls-transfer.notkiska.pw-twitter-user-MESA_MH_LATINA-shallow-20190521-190333-esyby.json	348	download   job
urls-transfer.notkiska.pw-twitter-user-culpaderusia-shallow-20190521-180256-8gyrb-urls.txt	99594	download
urls-transfer.sh-blog.lemonde.fr-urls.txt-inf-20190409-111201-63hsy-00088.warc.gz	5369072860	download   job
urls-transfer.sh-blog.lemonde.fr-urls.txt-inf-20190409-111201-63hsy-00088.warc.os.cdx.gz	1259086	download
vgpavilion.com-inf-20190521-223752-5rpc4-00000.warc.gz	5371845188	download   job
vgpavilion.com-inf-20190521-223752-5rpc4-00000.warc.os.cdx.gz	169007	download
www.alynsmith.eu-inf-20190521-174431-bfceu-00000.warc.gz	5432047379	download   job
www.alynsmith.eu-inf-20190521-174431-bfceu-00000.warc.os.cdx.gz	3349117	download
www.alynsmith.eu-inf-20190521-174431-bfceu-00001.warc.gz	5693752882	download   job
www.alynsmith.eu-inf-20190521-174431-bfceu-00001.warc.os.cdx.gz	1064975	download
www.barbgibson.com-inf-20190521-175755-2otmx.json	243	download   job
www.bearder.eu-inf-20190521-135812-94h6q-00000.warc.gz	1076646842	download   job
www.bearder.eu-inf-20190521-135812-94h6q-00000.warc.os.cdx.gz	552333	download
www.bearder.eu-inf-20190521-135812-94h6q-00001.warc.gz	1073758408	download   job
www.bearder.eu-inf-20190521-135812-94h6q-00001.warc.os.cdx.gz	1212689	download
www.bearder.eu-inf-20190521-135812-94h6q-00002.warc.gz	581736373	download   job
www.bearder.eu-inf-20190521-135812-94h6q-00002.warc.os.cdx.gz	1166067	download
www.bearder.eu-inf-20190521-135812-94h6q.json	238	download   job
www.beverleynielsen.co.uk-inf-20190521-175828-4heq9.json	249	download   job
www.bhog.al-inf-20190521-195737-6sx8q-00000.warc.gz	19563509	download   job
www.bhog.al-inf-20190521-195737-6sx8q-00000.warc.os.cdx.gz	55556	download
www.bhog.al-inf-20190521-195737-6sx8q.json	235	download   job
www.brightonhovegreens.org-inf-20190521-200118-e14d2-00000.warc.gz	2123425116	download   job
www.brightonhovegreens.org-inf-20190521-200118-e14d2-00000.warc.os.cdx.gz	2277123	download
www.brightonhovegreens.org-inf-20190521-200118-e14d2-meta.warc.gz	1555214	download   job
www.brightonhovegreens.org-inf-20190521-200118-e14d2-meta.warc.os.cdx.gz	47	download
www.brightonhovegreens.org-inf-20190521-200118-e14d2.json	251	download   job
www.cambridgelabour.org.uk-inf-20190521-183235-4ryso-00000.warc.gz	706891668	download   job
www.cambridgelabour.org.uk-inf-20190521-183235-4ryso-00000.warc.os.cdx.gz	1296320	download
www.cambridgelabour.org.uk-inf-20190521-183235-4ryso-meta.warc.gz	1019398	download   job
www.cambridgelabour.org.uk-inf-20190521-183235-4ryso-meta.warc.os.cdx.gz	47	download
www.cambridgelabour.org.uk-inf-20190521-183235-4ryso.json	251	download   job
www.carolinevoaden.info-inf-20190521-185333-7leke-00000.warc.gz	7664052	download   job
www.carolinevoaden.info-inf-20190521-185333-7leke-00000.warc.os.cdx.gz	40455	download
www.carolinevoaden.info-inf-20190521-185333-7leke-meta.warc.gz	27973	download   job
www.carolinevoaden.info-inf-20190521-185333-7leke-meta.warc.os.cdx.gz	47	download
www.catherinemayer.co.uk-inf-20190521-185705-blsip-00000.warc.gz	342077034	download   job
www.catherinemayer.co.uk-inf-20190521-185705-blsip-00000.warc.os.cdx.gz	268189	download
www.catherinemayer.co.uk-inf-20190521-185705-blsip-meta.warc.gz	184032	download   job
www.catherinemayer.co.uk-inf-20190521-185705-blsip-meta.warc.os.cdx.gz	47	download
www.catherinemayer.co.uk-inf-20190521-185705-blsip.json	249	download   job
www.charlestannock.com-inf-20190521-191441-92js8-00000.warc.gz	293023538	download   job
www.charlestannock.com-inf-20190521-191441-92js8-00000.warc.os.cdx.gz	832977	download
www.charlestannock.com-inf-20190521-191441-92js8-meta.warc.gz	571923	download   job
www.charlestannock.com-inf-20190521-191441-92js8-meta.warc.os.cdx.gz	47	download
www.charlestannock.com-inf-20190521-191441-92js8.json	246	download   job
www.chrisbowers.org-inf-20190521-214032-6mrkx-00000.warc.gz	177476611	download   job
www.chrisbowers.org-inf-20190521-214032-6mrkx-00000.warc.os.cdx.gz	135081	download
www.chrisbowers.org-inf-20190521-214032-6mrkx-meta.warc.gz	82015	download   job
www.chrisbowers.org-inf-20190521-214032-6mrkx-meta.warc.os.cdx.gz	47	download
www.chrisbowers.org-inf-20190521-214032-6mrkx.json	244	download   job
www.claremoodymep.com-inf-20190521-214728-99l71-00000.warc.gz	455722599	download   job
www.claremoodymep.com-inf-20190521-214728-99l71-00000.warc.os.cdx.gz	1084176	download
www.claremoodymep.com-inf-20190521-214728-99l71-meta.warc.gz	788600	download   job
www.claremoodymep.com-inf-20190521-214728-99l71-meta.warc.os.cdx.gz	47	download
www.claremoodymep.com-inf-20190521-214728-99l71.json	246	download   job
www.clarence4pavilion.com-inf-20190521-215354-bjttf-00000.warc.gz	252847349	download   job
www.clarence4pavilion.com-inf-20190521-215354-bjttf-00000.warc.os.cdx.gz	656265	download
www.clarence4pavilion.com-inf-20190521-215354-bjttf-meta.warc.gz	467858	download   job
www.clarence4pavilion.com-inf-20190521-215354-bjttf-meta.warc.os.cdx.gz	47	download
www.clarence4pavilion.com-inf-20190521-215354-bjttf.json	250	download   job
www.claudemoraes.com-inf-20190521-195631-9fbw9-00000.warc.gz	651404730	download   job
www.claudemoraes.com-inf-20190521-195631-9fbw9-00000.warc.os.cdx.gz	949758	download
www.claudemoraes.com-inf-20190521-195631-9fbw9-meta.warc.gz	627516	download   job
www.claudemoraes.com-inf-20190521-195631-9fbw9-meta.warc.os.cdx.gz	47	download
www.claudemoraes.com-inf-20190521-195631-9fbw9.json	244	download   job
www.craiglawton.co.uk-shallow-20190521-195719-cg8yt-00000.warc.gz	31561782	download   job
www.craiglawton.co.uk-shallow-20190521-195719-cg8yt-00000.warc.os.cdx.gz	79863	download
www.craiglawton.co.uk-shallow-20190521-195719-cg8yt-meta.warc.gz	65310	download   job
www.craiglawton.co.uk-shallow-20190521-195719-cg8yt-meta.warc.os.cdx.gz	47	download
www.craiglawton.co.uk-shallow-20190521-195719-cg8yt.json	249	download   job
www.duncanenright.com-shallow-20190521-202500-5wp2g-00000.warc.gz	1288860	download   job
www.duncanenright.com-shallow-20190521-202500-5wp2g-00000.warc.os.cdx.gz	8385	download
www.duncanenright.com-shallow-20190521-202500-5wp2g-meta.warc.gz	8556	download   job
www.duncanenright.com-shallow-20190521-202500-5wp2g-meta.warc.os.cdx.gz	47	download
www.duncanenright.com-shallow-20190521-202500-5wp2g.json	249	download   job
www.europarl.europa.eu-inf-20190521-024131-4y8e5-00003.warc.gz	5377927347	download   job
www.europarl.europa.eu-inf-20190521-024131-4y8e5-00003.warc.os.cdx.gz	3635779	download
www.hannan.co.uk-shallow-20190521-215632-2bcjl-meta.warc.gz	7270	download   job
www.hannan.co.uk-shallow-20190521-215632-2bcjl-meta.warc.os.cdx.gz	47	download
www.hannan.co.uk-shallow-20190521-215632-2bcjl.json	244	download   job
www.iainmcgill.co.uk-shallow-20190521-215738-2layk-meta.warc.gz	6097	download   job
www.iainmcgill.co.uk-shallow-20190521-215738-2layk-meta.warc.os.cdx.gz	47	download
www.rebelion.org-inf-20190507-200655-7kc3l-00079.warc.gz	5368967005	download   job
www.rebelion.org-inf-20190507-200655-7kc3l-00079.warc.os.cdx.gz	2486307	download
www.supertopo.com-inf-20190520-063344-ew0hh-00012.warc.gz	5509631821	download   job
www.supertopo.com-inf-20190520-063344-ew0hh-00012.warc.os.cdx.gz	3558898	download
www.supertopo.com-inf-20190520-063344-ew0hh-00015.warc.gz	5390740324	download   job
www.supertopo.com-inf-20190520-063344-ew0hh-00015.warc.os.cdx.gz	32527	download
www.supertopo.com-inf-20190520-063344-ew0hh-00016.warc.gz	5405334934	download   job
www.supertopo.com-inf-20190520-063344-ew0hh-00016.warc.os.cdx.gz	36921	download
www.supertopo.com-inf-20190520-063344-ew0hh-00017.warc.gz	5511000564	download   job
www.supertopo.com-inf-20190520-063344-ew0hh-00017.warc.os.cdx.gz	34654	download
www.swanseaconservatives.org-inf-20190521-202813-2c9a8-meta.warc.gz	592453	download   job
www.swanseaconservatives.org-inf-20190521-202813-2c9a8-meta.warc.os.cdx.gz	47	download
www.usatoday.com-shallow-20190521-185338-2bxca-00000.warc.gz	2133622	download   job
www.usatoday.com-shallow-20190521-185338-2bxca-00000.warc.os.cdx.gz	8184	download
www.usatoday.com-shallow-20190521-185338-2bxca-meta.warc.gz	8536	download   job
www.usatoday.com-shallow-20190521-185338-2bxca-meta.warc.os.cdx.gz	47	download