Item archiveteam_archivebot_go_20200927200001

Filename	Size
2017.clintonfoundation.org-inf-20200927-173531-8i5v7-00000.warc.gz	27891	download job
2017.clintonfoundation.org-inf-20200927-173531-8i5v7-00000.warc.os.cdx.gz	274	download
2017.clintonfoundation.org-inf-20200927-173531-8i5v7-meta.warc.gz	3565	download job
2017.clintonfoundation.org-inf-20200927-173531-8i5v7-meta.warc.os.cdx.gz	47	download
2017.clintonfoundation.org-inf-20200927-173531-8i5v7.json	256	download job
2018.clintonfoundation.org-inf-20200927-173417-3eccs-00000.warc.gz	5379395	download job
2018.clintonfoundation.org-inf-20200927-173417-3eccs-00000.warc.os.cdx.gz	14524	download
2018.clintonfoundation.org-inf-20200927-173417-3eccs-meta.warc.gz	12616	download job
2018.clintonfoundation.org-inf-20200927-173417-3eccs-meta.warc.os.cdx.gz	47	download
2018.clintonfoundation.org-inf-20200927-173417-3eccs.json	256	download job
2019.clintonfoundation.org-inf-20200927-172524-5ik6y-00000.warc.gz	1596933112	download job
2019.clintonfoundation.org-inf-20200927-172524-5ik6y-00000.warc.os.cdx.gz	821124	download
2019.clintonfoundation.org-inf-20200927-172524-5ik6y-meta.warc.gz	551175	download job
2019.clintonfoundation.org-inf-20200927-172524-5ik6y-meta.warc.os.cdx.gz	47	download
2019.clintonfoundation.org-inf-20200927-172524-5ik6y.json	256	download job
42barandtable.org-inf-20200927-183759-1pzy5-00000.warc.gz	1614991120	download job
42barandtable.org-inf-20200927-183759-1pzy5-00000.warc.os.cdx.gz	811908	download
agriculture.clintonfoundation.org-inf-20200927-172515-dfp6c-00000.warc.gz	14772186	download job
agriculture.clintonfoundation.org-inf-20200927-172515-dfp6c-00000.warc.os.cdx.gz	11437	download
agriculture.clintonfoundation.org-inf-20200927-172515-dfp6c-meta.warc.gz	10205	download job
agriculture.clintonfoundation.org-inf-20200927-172515-dfp6c-meta.warc.os.cdx.gz	47	download
agriculture.clintonfoundation.org-inf-20200927-172515-dfp6c.json	263	download job
archiveteam_archivebot_go_20200927200001.cdx.gz	70478100	download
archiveteam_archivebot_go_20200927200001.cdx.idx	77361	download
archiveteam_archivebot_go_20200927200001_files.xml	0	download
archiveteam_archivebot_go_20200927200001_meta.sqlite	268288	download
archiveteam_archivebot_go_20200927200001_meta.xml	969	download
bbis.clintonfoundation.org-inf-20200927-172350-2vg61-meta.warc.gz	4726	download job
bbis.clintonfoundation.org-inf-20200927-172350-2vg61-meta.warc.os.cdx.gz	47	download
bbis.clintonfoundation.org-inf-20200927-172350-2vg61.json	256	download job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00363.warc.gz	5369614080	download job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00363.warc.os.cdx.gz	1139262	download
cgi-globe.herokuapp.com-inf-20200927-170720-rrs83-00000.warc.gz	72849121	download job
cgi-globe.herokuapp.com-inf-20200927-170720-rrs83-00000.warc.os.cdx.gz	57262	download
cgi-globe.herokuapp.com-inf-20200927-170720-rrs83-meta.warc.gz	36554	download job
cgi-globe.herokuapp.com-inf-20200927-170720-rrs83-meta.warc.os.cdx.gz	47	download
cgi-globe.herokuapp.com-inf-20200927-170720-rrs83.json	252	download job
cgievents.clintonfoundation.org-inf-20200927-171347-1uxl3-00000.warc.gz	112367099	download job
cgievents.clintonfoundation.org-inf-20200927-171347-1uxl3-00000.warc.os.cdx.gz	146767	download
cgievents.clintonfoundation.org-inf-20200927-171347-1uxl3-meta.warc.gz	92626	download job
cgievents.clintonfoundation.org-inf-20200927-171347-1uxl3-meta.warc.os.cdx.gz	47	download
cgievents.clintonfoundation.org-inf-20200927-171347-1uxl3.json	261	download job
cgiu.org-inf-20200927-183340-do1km-00000.warc.gz	84585943	download job
cgiu.org-inf-20200927-183340-do1km-00000.warc.os.cdx.gz	167223	download
cgiu.org-inf-20200927-183340-do1km-meta.warc.gz	103889	download job
cgiu.org-inf-20200927-183340-do1km-meta.warc.os.cdx.gz	47	download
cgiu.org-inf-20200927-183340-do1km.json	238	download job
cgiucommitments.clintonfoundation.org-inf-20200927-172341-9sfuo-00000.warc.gz	10591095	download job
cgiucommitments.clintonfoundation.org-inf-20200927-172341-9sfuo-00000.warc.os.cdx.gz	11109	download
cgiucommitments.clintonfoundation.org-inf-20200927-172341-9sfuo-meta.warc.gz	9533	download job
cgiucommitments.clintonfoundation.org-inf-20200927-172341-9sfuo-meta.warc.os.cdx.gz	47	download
cgiucommitments.clintonfoundation.org-inf-20200927-172341-9sfuo.json	267	download job
chatlogs.linuxoid.in-inf-20200922-201445-9jlyy-00008.warc.gz	5368805232	download job
chatlogs.linuxoid.in-inf-20200922-201445-9jlyy-00008.warc.os.cdx.gz	5431731	download
clinton-foundation.org-inf-20200927-175216-1w2ow-00000.warc.gz	1039138245	download job
clinton-foundation.org-inf-20200927-175216-1w2ow-00000.warc.os.cdx.gz	337115	download
clinton-foundation.org-inf-20200927-175216-1w2ow-meta.warc.gz	247494	download job
clinton-foundation.org-inf-20200927-175216-1w2ow-meta.warc.os.cdx.gz	47	download
clinton-foundation.org-inf-20200927-175216-1w2ow.json	256	download job
clinton-foundation.org-inf-20200927-175751-6ujzk-00000.warc.gz	65902	download job
clinton-foundation.org-inf-20200927-175751-6ujzk-00000.warc.os.cdx.gz	613	download
clinton-foundation.org-inf-20200927-175751-6ujzk-meta.warc.gz	3822	download job
clinton-foundation.org-inf-20200927-175751-6ujzk-meta.warc.os.cdx.gz	47	download
clinton-foundation.org-inf-20200927-175751-6ujzk.json	262	download job
clinton-foundation.org-inf-20200927-180551-z5vtt-00000.warc.gz	2004477080	download job
clinton-foundation.org-inf-20200927-180551-z5vtt-00000.warc.os.cdx.gz	805830	download
clinton-foundation.org-inf-20200927-180551-z5vtt-meta.warc.gz	529979	download job
clinton-foundation.org-inf-20200927-180551-z5vtt-meta.warc.os.cdx.gz	47	download
clinton-foundation.org-inf-20200927-180551-z5vtt.json	256	download job
clinton-foundation.org-inf-20200927-181449-2sq82-00000.warc.gz	1140242078	download job
clinton-foundation.org-inf-20200927-181449-2sq82-00000.warc.os.cdx.gz	423820	download
clinton-foundation.org-inf-20200927-181449-2sq82-meta.warc.gz	300143	download job
clinton-foundation.org-inf-20200927-181449-2sq82-meta.warc.os.cdx.gz	47	download
clinton-foundation.org-inf-20200927-181449-2sq82.json	252	download job
dc-400f706f56f1.higherpower2.com-inf-20200926-202141-7ttos-00000.warc.gz	3310417130	download job
dc-400f706f56f1.higherpower2.com-inf-20200926-202141-7ttos-00000.warc.os.cdx.gz	4173056	download
departments.kings.edu-inf-20200927-173008-avqdi-00000.warc.gz	30080706	download job
departments.kings.edu-inf-20200927-173008-avqdi-00000.warc.os.cdx.gz	24657	download
douro_kofc.tripod.com-inf-20200927-173046-4tt87-00000.warc.gz	91760479	download job
douro_kofc.tripod.com-inf-20200927-173046-4tt87-00000.warc.os.cdx.gz	127905	download
douro_kofc.tripod.com-inf-20200927-173046-4tt87.json	249	download job
ektoplazm.com-inf-20200704-233408-66i1h-00282.warc.gz	6174447795	download job
ektoplazm.com-inf-20200704-233408-66i1h-00282.warc.os.cdx.gz	5522	download
events.clinton-foundation.org-inf-20200927-171918-6d8o3-00000.warc.gz	1692876827	download job
events.clinton-foundation.org-inf-20200927-171918-6d8o3-00000.warc.os.cdx.gz	901872	download
events.clinton-foundation.org-inf-20200927-171918-6d8o3-meta.warc.gz	596844	download job
events.clinton-foundation.org-inf-20200927-171918-6d8o3-meta.warc.os.cdx.gz	47	download
events.clinton-foundation.org-inf-20200927-171918-6d8o3.json	267	download job
events.clintonfoundation.org-inf-20200927-170324-8cp38-meta.warc.gz	92259	download job
events.clintonfoundation.org-inf-20200927-170324-8cp38-meta.warc.os.cdx.gz	47	download
events.clintonfoundation.org-inf-20200927-170324-8cp38.json	258	download job
facts.clintonfoundation.org-inf-20200927-165849-awsg1-00000.warc.gz	756720448	download job
facts.clintonfoundation.org-inf-20200927-165849-awsg1-00000.warc.os.cdx.gz	302043	download
facts.clintonfoundation.org-inf-20200927-165849-awsg1-meta.warc.gz	212728	download job
facts.clintonfoundation.org-inf-20200927-165849-awsg1-meta.warc.os.cdx.gz	47	download
facts.clintonfoundation.org-inf-20200927-165849-awsg1.json	257	download job
forms.clintonfoundation.org-inf-20200927-165514-2tkk8-00000.warc.gz	112326401	download job
forms.clintonfoundation.org-inf-20200927-165514-2tkk8-00000.warc.os.cdx.gz	145684	download
forms.clintonfoundation.org-inf-20200927-165514-2tkk8.json	257	download job
fortytwobarandtable.alohaorderonline.com-inf-20200927-184034-4pq0n-00000.warc.gz	4121140	download job
fortytwobarandtable.alohaorderonline.com-inf-20200927-184034-4pq0n-00000.warc.os.cdx.gz	20127	download
fortytwobarandtable.alohaorderonline.com-inf-20200927-184034-4pq0n-meta.warc.gz	14870	download job
fortytwobarandtable.alohaorderonline.com-inf-20200927-184034-4pq0n-meta.warc.os.cdx.gz	47	download
fortytwobarandtable.alohaorderonline.com-inf-20200927-184034-4pq0n.json	270	download job
grayslakekofc.com-inf-20200927-173241-dh237-00000.warc.gz	18547254	download job
grayslakekofc.com-inf-20200927-173241-dh237-00000.warc.os.cdx.gz	36481	download
grayslakekofc.com-inf-20200927-173241-dh237-meta.warc.gz	26731	download job
grayslakekofc.com-inf-20200927-173241-dh237-meta.warc.os.cdx.gz	47	download
groups.google.com-inf-20200927-173337-6au6k-00000.warc.gz	48333841	download job
groups.google.com-inf-20200927-173337-6au6k-00000.warc.os.cdx.gz	41062	download
groups.google.com-inf-20200927-173337-6au6k-meta.warc.gz	27751	download job
groups.google.com-inf-20200927-173337-6au6k-meta.warc.os.cdx.gz	47	download
groups.google.com-inf-20200927-173337-6au6k.json	261	download job
groupspaces.com-inf-20200927-173804-f00vg-00000.warc.gz	66267675	download job
groupspaces.com-inf-20200927-173804-f00vg-00000.warc.os.cdx.gz	120163	download
groupspaces.com-inf-20200927-173804-f00vg-meta.warc.gz	75842	download job
groupspaces.com-inf-20200927-173804-f00vg-meta.warc.os.cdx.gz	47	download
gsz.gov.by-inf-20200927-050823-5h3r9-00000.warc.gz	3106355667	download job
gsz.gov.by-inf-20200927-050823-5h3r9-00000.warc.os.cdx.gz	5967194	download
gsz.gov.by-inf-20200927-050823-5h3r9-meta.warc.gz	3221259	download job
gsz.gov.by-inf-20200927-050823-5h3r9-meta.warc.os.cdx.gz	47	download
gsz.gov.by-inf-20200927-050823-5h3r9.json	239	download job
holyrosary10238.tripod.com-inf-20200927-173606-e7dd1-00000.warc.gz	70237673	download job
holyrosary10238.tripod.com-inf-20200927-173606-e7dd1-00000.warc.os.cdx.gz	197979	download
holyrosary10238.tripod.com-inf-20200927-173606-e7dd1-meta.warc.gz	122371	download job
holyrosary10238.tripod.com-inf-20200927-173606-e7dd1-meta.warc.os.cdx.gz	47	download
holyrosary10238.tripod.com-inf-20200927-173606-e7dd1.json	254	download job
ivacevichi.brest-region.gov.by-inf-20200927-051905-cm2m8-00000.warc.gz	4644274809	download job
ivacevichi.brest-region.gov.by-inf-20200927-051905-cm2m8-00000.warc.os.cdx.gz	6472537	download
ivacevichi.brest-region.gov.by-inf-20200927-051905-cm2m8-meta.warc.gz	4619110	download job
ivacevichi.brest-region.gov.by-inf-20200927-051905-cm2m8-meta.warc.os.cdx.gz	47	download
la.curbed.com-inf-20200923-164455-c92wk-00055.warc.gz	5369709935	download job
la.curbed.com-inf-20200923-164455-c92wk-00055.warc.os.cdx.gz	1843429	download
link.cgiu.org-inf-20200927-183139-boh8a-00000.warc.gz	48317654	download job
link.cgiu.org-inf-20200927-183139-boh8a-00000.warc.os.cdx.gz	102232	download
link.cgiu.org-inf-20200927-183139-boh8a-meta.warc.gz	63992	download job
link.cgiu.org-inf-20200927-183139-boh8a-meta.warc.os.cdx.gz	47	download
link.cgiu.org-inf-20200927-183139-boh8a.json	243	download job
live.cgiu.org-inf-20200927-174335-4nhje-00000.warc.gz	78341146	download job
live.cgiu.org-inf-20200927-174335-4nhje-00000.warc.os.cdx.gz	117894	download
live.cgiu.org-inf-20200927-174335-4nhje-meta.warc.gz	72732	download job
live.cgiu.org-inf-20200927-174335-4nhje-meta.warc.os.cdx.gz	47	download
live.cgiu.org-inf-20200927-174335-4nhje.json	243	download job
lyncdiscover.clintonfoundation.org-inf-20200927-164014-crggh-00000.warc.gz	7050	download job
lyncdiscover.clintonfoundation.org-inf-20200927-164014-crggh-00000.warc.os.cdx.gz	279	download
lyncdiscover.clintonfoundation.org-inf-20200927-164014-crggh-meta.warc.gz	3527	download job
lyncdiscover.clintonfoundation.org-inf-20200927-164014-crggh-meta.warc.os.cdx.gz	47	download
lyncdiscover.clintonfoundation.org-inf-20200927-164014-crggh.json	264	download job
mayday4mckinnondaymay3rd2010.blogspot.com-inf-20200924-030533-99j44-00032.warc.gz	5370141688	download job
mayday4mckinnondaymay3rd2010.blogspot.com-inf-20200924-030533-99j44-00032.warc.os.cdx.gz	3448456	download
medium.com-shallow-20200927-181238-2lo9u-00000.warc.gz	8778545	download job
medium.com-shallow-20200927-181238-2lo9u-00000.warc.os.cdx.gz	50364	download
medium.com-shallow-20200927-181238-2lo9u-meta.warc.gz	29311	download job
medium.com-shallow-20200927-181238-2lo9u-meta.warc.os.cdx.gz	47	download
medium.com-shallow-20200927-181238-2lo9u.json	255	download job
phoenix.maemo.org-inf-20200926-232644-ektr9-00003.warc.gz	5485506873	download job
phoenix.maemo.org-inf-20200926-232644-ektr9-00003.warc.os.cdx.gz	703711	download
podcasts.apple.com-shallow-20200927-182043-4th2b-00000.warc.gz	1971674596	download job
podcasts.apple.com-shallow-20200927-182043-4th2b-00000.warc.os.cdx.gz	53378	download
podcasts.apple.com-shallow-20200927-182043-4th2b-meta.warc.gz	37158	download job
podcasts.apple.com-shallow-20200927-182043-4th2b-meta.warc.os.cdx.gz	47	download
podcasts.apple.com-shallow-20200927-182043-4th2b.json	301	download job
repository.maemo.org-inf-20200926-234427-4q1c4-00007.warc.gz	5376046753	download job
repository.maemo.org-inf-20200926-234427-4q1c4-00007.warc.os.cdx.gz	245231	download
sites.google.com-inf-20200927-172909-evx43-00000.warc.gz	3915997689	download job
sites.google.com-inf-20200927-172909-evx43-00000.warc.os.cdx.gz	567499	download
sites.google.com-inf-20200927-172909-evx43-meta.warc.gz	339477	download job
sites.google.com-inf-20200927-172909-evx43-meta.warc.os.cdx.gz	47	download
sites.google.com-inf-20200927-172909-evx43.json	266	download job
stedwardonthelake.org-inf-20200927-175251-5f42c-00000.warc.gz	254985227	download job
stedwardonthelake.org-inf-20200927-175251-5f42c-00000.warc.os.cdx.gz	255806	download
stedwardonthelake.org-inf-20200927-175251-5f42c-meta.warc.gz	157576	download job
stedwardonthelake.org-inf-20200927-175251-5f42c-meta.warc.os.cdx.gz	47	download
stedwardonthelake.org-inf-20200927-175251-5f42c.json	250	download job
stillnessinthestorm.com-inf-20200925-175203-1g35m-00032.warc.gz	5378487015	download job
stillnessinthestorm.com-inf-20200925-175203-1g35m-00032.warc.os.cdx.gz	2885424	download
stillnessinthestorm.com-inf-20200925-175203-1g35m-00033.warc.gz	5483571129	download job
stillnessinthestorm.com-inf-20200925-175203-1g35m-00033.warc.os.cdx.gz	1521785	download
stsebastiancatholicchurch.org-inf-20200927-174927-clpq3-00000.warc.gz	151892557	download job
stsebastiancatholicchurch.org-inf-20200927-174927-clpq3-00000.warc.os.cdx.gz	215659	download
stsebastiancatholicchurch.org-inf-20200927-174927-clpq3-meta.warc.gz	135691	download job
stsebastiancatholicchurch.org-inf-20200927-174927-clpq3-meta.warc.os.cdx.gz	47	download
stsebastiancatholicchurch.org-inf-20200927-174927-clpq3.json	257	download job
techcamp.america.gov-inf-20200927-151848-50teo.json	250	download job
theclintonfoundation.org-inf-20200927-174008-811jg-00000.warc.gz	5954514622	download job
theclintonfoundation.org-inf-20200927-174008-811jg-00000.warc.os.cdx.gz	377999	download
theclintonfoundation.org-inf-20200927-174008-811jg-00001.warc.gz	1468020848	download job
theclintonfoundation.org-inf-20200927-174008-811jg-00001.warc.os.cdx.gz	671577	download
theclintonfoundation.org-inf-20200927-174008-811jg-meta.warc.gz	684047	download job
theclintonfoundation.org-inf-20200927-174008-811jg-meta.warc.os.cdx.gz	47	download
theclintonfoundation.org-inf-20200927-174008-811jg.json	254	download job
urls-transfer.notkiska.pw-docs.microsoft.com-duspk-remaining-offsite-shallow-20200920-040417-7e2ub-00105.warc.gz	5587246038	download job
urls-transfer.notkiska.pw-docs.microsoft.com-duspk-remaining-offsite-shallow-20200920-040417-7e2ub-00105.warc.os.cdx.gz	1331881	download
urls-transfer.notkiska.pw-facebook-@ClintonFoundation-shallow-20200927-162252-8jxt7-00001.warc.gz	5422655073	download job
urls-transfer.notkiska.pw-facebook-@ClintonFoundation-shallow-20200927-162252-8jxt7-00001.warc.os.cdx.gz	827949	download
urls-transfer.notkiska.pw-facebook-@clintonglobalinitiative-shallow-20200927-183916-b2jv9-00001.warc.gz	5371578111	download job
urls-transfer.notkiska.pw-facebook-@clintonglobalinitiative-shallow-20200927-183916-b2jv9-00001.warc.os.cdx.gz	32993	download
urls-transfer.notkiska.pw-garage.maemo.org-project-subdomains-inf-20200927-034900-aaqns-00000.warc.gz	4489178711	download job
urls-transfer.notkiska.pw-garage.maemo.org-project-subdomains-inf-20200927-034900-aaqns-00000.warc.os.cdx.gz	3723242	download
urls-transfer.notkiska.pw-garage.maemo.org-project-subdomains-inf-20200927-034900-aaqns-meta.warc.gz	2247814	download job
urls-transfer.notkiska.pw-garage.maemo.org-project-subdomains-inf-20200927-034900-aaqns-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-garage.maemo.org-project-subdomains-inf-20200927-034900-aaqns-urls.txt	66952	download
urls-transfer.notkiska.pw-github.com-treasure-data-inf-20200922-065021-8mjnu-00003.warc.gz	1190858264	download job
urls-transfer.notkiska.pw-github.com-treasure-data-inf-20200922-065021-8mjnu-00003.warc.os.cdx.gz	1059303	download
urls-transfer.notkiska.pw-github.com-treasure-data-inf-20200922-065021-8mjnu-urls.txt	161	download
urls-transfer.notkiska.pw-github.com-treasure-data-inf-20200922-065021-8mjnu.json	332	download job
urls-transfer.notkiska.pw-twitter-%23Fallout4-shallow-20200925-205114-ep4ps-00022.warc.gz	5368709669	download job
urls-transfer.notkiska.pw-twitter-%23Fallout4-shallow-20200925-205114-ep4ps-00022.warc.os.cdx.gz	6318849	download
urls-transfer.notkiska.pw-twitter-@ClintonFdn-shallow-20200927-161225-9hytu-00000.warc.gz	5370497867	download job
urls-transfer.notkiska.pw-twitter-@ClintonFdn-shallow-20200927-161225-9hytu-00000.warc.os.cdx.gz	1933260	download
urls-transfer.notkiska.pw-twitter-@milesSI-shallow-20200927-081537-atats-00001.warc.gz	5368761399	download job
urls-transfer.notkiska.pw-twitter-@milesSI-shallow-20200927-081537-atats-00001.warc.os.cdx.gz	3776660	download
urls-transfer.notkiska.pw-www.bigrigs.com.au-52odw-remaining-d-shallow-20200927-005643-1ilnt-00011.warc.gz	5394980141	download job
urls-transfer.notkiska.pw-www.bigrigs.com.au-52odw-remaining-d-shallow-20200927-005643-1ilnt-00011.warc.os.cdx.gz	1219326	download
urls-transfer.notkiska.pw-www.bigrigs.com.au-52odw-remaining-d-shallow-20200927-005643-1ilnt-00013.warc.gz	5539723324	download job
urls-transfer.notkiska.pw-www.bigrigs.com.au-52odw-remaining-d-shallow-20200927-005643-1ilnt-00013.warc.os.cdx.gz	1916115	download
visitstpetersgraveyard.org-inf-20200927-174616-77y01-00000.warc.gz	684157212	download job
visitstpetersgraveyard.org-inf-20200927-174616-77y01-00000.warc.os.cdx.gz	817549	download
visitstpetersgraveyard.org-inf-20200927-174616-77y01-meta.warc.gz	610678	download job
visitstpetersgraveyard.org-inf-20200927-174616-77y01-meta.warc.os.cdx.gz	47	download
visitstpetersgraveyard.org-inf-20200927-174616-77y01.json	255	download job
vitebsk.gov.by-inf-20200927-052937-4oi9r-00001.warc.gz	2780545796	download job
vitebsk.gov.by-inf-20200927-052937-4oi9r-00001.warc.os.cdx.gz	2398258	download
vitebsk.gov.by-inf-20200927-052937-4oi9r-meta.warc.gz	3439777	download job
vitebsk.gov.by-inf-20200927-052937-4oi9r-meta.warc.os.cdx.gz	47	download
vitebsk.gov.by-inf-20200927-052937-4oi9r.json	244	download job
whyamitellingyouthis.org-inf-20200927-181828-5a24w-00000.warc.gz	2319547870	download job
whyamitellingyouthis.org-inf-20200927-181828-5a24w-00000.warc.os.cdx.gz	98355	download
whyamitellingyouthis.org-inf-20200927-181828-5a24w-meta.warc.gz	96402	download job
whyamitellingyouthis.org-inf-20200927-181828-5a24w-meta.warc.os.cdx.gz	47	download
whyamitellingyouthis.org-inf-20200927-181828-5a24w.json	253	download job
wikileaks.org-shallow-20200927-175421-6h0jf-00000.warc.gz	1914780	download job
wikileaks.org-shallow-20200927-175421-6h0jf-00000.warc.os.cdx.gz	240	download
wikileaks.org-shallow-20200927-175421-6h0jf-meta.warc.gz	3500	download job
wikileaks.org-shallow-20200927-175421-6h0jf-meta.warc.os.cdx.gz	47	download
www.allsaintslakewylie.com-inf-20200927-174232-3th6j-00000.warc.gz	961052350	download job
www.allsaintslakewylie.com-inf-20200927-174232-3th6j-00000.warc.os.cdx.gz	514976	download
www.allsaintslakewylie.com-inf-20200927-174232-3th6j-meta.warc.gz	294390	download job
www.allsaintslakewylie.com-inf-20200927-174232-3th6j-meta.warc.os.cdx.gz	47	download
www.allsaintslakewylie.com-inf-20200927-174232-3th6j.json	255	download job
www.catholicmil.org-inf-20200927-175633-7yhoj-00000.warc.gz	6358	download job
www.catholicmil.org-inf-20200927-175633-7yhoj-00000.warc.os.cdx.gz	314	download
www.catholicmil.org-inf-20200927-175633-7yhoj-meta.warc.gz	3575	download job
www.catholicmil.org-inf-20200927-175633-7yhoj-meta.warc.os.cdx.gz	47	download
www.catholicmil.org-inf-20200927-175633-7yhoj.json	248	download job
www.catholicmil.org-inf-20200927-180818-7yhoj-00000.warc.gz	2510120753	download job
www.catholicmil.org-inf-20200927-180818-7yhoj-00000.warc.os.cdx.gz	582966	download
www.catholicmil.org-inf-20200927-180818-7yhoj-meta.warc.gz	367120	download job
www.catholicmil.org-inf-20200927-180818-7yhoj-meta.warc.os.cdx.gz	47	download
www.catholicmil.org-inf-20200927-180818-7yhoj.json	248	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00583.warc.gz	1074332638	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00583.warc.os.cdx.gz	986091	download
www.greanvillepost.com-inf-20200920-183741-4t3u5-00121.warc.gz	5392933777	download job
www.greanvillepost.com-inf-20200920-183741-4t3u5-00121.warc.os.cdx.gz	948241	download
www.scborromeo.org-shallow-20200927-180309-ct7n5-00000.warc.gz	143654	download job
www.scborromeo.org-shallow-20200927-180309-ct7n5-00000.warc.os.cdx.gz	229	download
www.scborromeo.org-shallow-20200927-180309-ct7n5-meta.warc.gz	3497	download job
www.scborromeo.org-shallow-20200927-180309-ct7n5-meta.warc.os.cdx.gz	47	download
www.scborromeo.org-shallow-20200927-180309-ct7n5.json	268	download job
www.smmcc.org-inf-20200927-174739-7e3wt-00000.warc.gz	5380889975	download job
www.smmcc.org-inf-20200927-174739-7e3wt-00000.warc.os.cdx.gz	743332	download
www.taringa.net-inf-20190927-205127-2a0h7-00870.warc.gz	5370018034	download job
www.taringa.net-inf-20190927-205127-2a0h7-00870.warc.os.cdx.gz	4900872	download
www.transfigsfld.org-inf-20200927-175349-6crjt-meta.warc.gz	550973	download job
www.transfigsfld.org-inf-20200927-175349-6crjt-meta.warc.os.cdx.gz	47	download