Item archiveteam_archivebot_go_20181124100002

Filename	Size
accounts.wmflabs.org-shallow-20181124-073814-78tdd-00000.warc.gz	102519	download job
accounts.wmflabs.org-shallow-20181124-073814-78tdd-00000.warc.os.cdx.gz	652	download
accounts.wmflabs.org-shallow-20181124-073814-78tdd-meta.warc.gz	3755	download job
accounts.wmflabs.org-shallow-20181124-073814-78tdd-meta.warc.os.cdx.gz	47	download
accounts.wmflabs.org-shallow-20181124-073814-78tdd.json	250	download job
archiveteam_archivebot_go_20181124100002.cdx.gz	56464882	download
archiveteam_archivebot_go_20181124100002.cdx.idx	52051	download
archiveteam_archivebot_go_20181124100002_archive.torrent	843083	download
archiveteam_archivebot_go_20181124100002_files.xml	0	download
archiveteam_archivebot_go_20181124100002_meta.sqlite	224256	download
archiveteam_archivebot_go_20181124100002_meta.xml	974	download
ballotpedia.org-inf-20181107-064223-7xeuu-00035.warc.gz	5370704198	download job
ballotpedia.org-inf-20181107-064223-7xeuu-00035.warc.os.cdx.gz	3039857	download
boazarad.net-inf-20181124-171929-6pvmz-00000.warc.gz	40852447	download job
boazarad.net-inf-20181124-171929-6pvmz-00000.warc.os.cdx.gz	66999	download
boazarad.net-inf-20181124-171929-6pvmz-meta.warc.gz	43068	download job
boazarad.net-inf-20181124-171929-6pvmz-meta.warc.os.cdx.gz	47	download
boazarad.net-inf-20181124-171929-6pvmz.json	236	download job
digibutter.nerr.biz-inf-20181030-171632-btw0w-00088.warc.gz	5368819103	download job
digibutter.nerr.biz-inf-20181030-171632-btw0w-00088.warc.os.cdx.gz	2339265	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00003.warc.gz	5473039758	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00003.warc.os.cdx.gz	308636	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00004.warc.gz	5381286178	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00004.warc.os.cdx.gz	8778	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00005.warc.gz	5473546951	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00005.warc.os.cdx.gz	4745	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00006.warc.gz	5435789068	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00006.warc.os.cdx.gz	7206	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00007.warc.gz	5577624996	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00007.warc.os.cdx.gz	1741	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00008.warc.gz	5481848998	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00008.warc.os.cdx.gz	4341	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00009.warc.gz	5387675888	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00009.warc.os.cdx.gz	2099	download
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00010.warc.gz	5482800956	download job
ebooks.bharathuniv.ac.in-inf-20181124-102704-8fdk5-00010.warc.os.cdx.gz	2275	download
fairybreadday.com-inf-20181124-175949-3hcpt-00000.warc.gz	559045067	download job
fairybreadday.com-inf-20181124-175949-3hcpt-00000.warc.os.cdx.gz	1507693	download
fairybreadday.com-inf-20181124-175949-3hcpt-meta.warc.gz	962567	download job
fairybreadday.com-inf-20181124-175949-3hcpt-meta.warc.os.cdx.gz	47	download
fairybreadday.com-inf-20181124-175949-3hcpt.json	248	download job
flog.tw-inf-20181021-120143-4abaj-00077.warc.gz	2147506390	download job
flog.tw-inf-20181021-120143-4abaj-00077.warc.os.cdx.gz	4626186	download
foresthillspost.com-shallow-20181124-092929-1v4mm-00000.warc.gz	8045587	download job
foresthillspost.com-shallow-20181124-092929-1v4mm-00000.warc.os.cdx.gz	16314	download
foresthillspost.com-shallow-20181124-092929-1v4mm-meta.warc.gz	13257	download job
foresthillspost.com-shallow-20181124-092929-1v4mm-meta.warc.os.cdx.gz	47	download
foresthillspost.com-shallow-20181124-092929-1v4mm.json	324	download job
forums.cpanel.net-inf-20181118-145653-7tafd-00008.warc.gz	5369974791	download job
forums.cpanel.net-inf-20181118-145653-7tafd-00008.warc.os.cdx.gz	10005686	download
ivansmirnov.com-inf-20181124-171712-5h9fu-00000.warc.gz	66948265	download job
ivansmirnov.com-inf-20181124-171712-5h9fu-00000.warc.os.cdx.gz	112011	download
ivansmirnov.com-inf-20181124-171712-5h9fu-meta.warc.gz	73141	download job
ivansmirnov.com-inf-20181124-171712-5h9fu-meta.warc.os.cdx.gz	47	download
ivansmirnov.com-inf-20181124-171712-5h9fu.json	239	download job
kmkeen.com-inf-20181124-063414-984ca-00000.warc.gz	273022662	download job
kmkeen.com-inf-20181124-063414-984ca-00000.warc.os.cdx.gz	698435	download
kmkeen.com-inf-20181124-063414-984ca-meta.warc.gz	433625	download job
kmkeen.com-inf-20181124-063414-984ca-meta.warc.os.cdx.gz	47	download
kmkeen.com-inf-20181124-063414-984ca.json	237	download job
kmkeen.com-inf-20181124-173345-8sb3k-aborted.json	251	download job
la.eater.com-shallow-20181124-092548-8mke4-00000.warc.gz	9003411	download job
la.eater.com-shallow-20181124-092548-8mke4-00000.warc.os.cdx.gz	9396	download
la.eater.com-shallow-20181124-092548-8mke4-meta.warc.gz	9733	download job
la.eater.com-shallow-20181124-092548-8mke4-meta.warc.os.cdx.gz	47	download
la.eater.com-shallow-20181124-092548-8mke4.json	325	download job
lonerandfriends.blogspot.com-inf-20181124-094653-7h480-00000.warc.gz	49033562	download job
lonerandfriends.blogspot.com-inf-20181124-094653-7h480-00000.warc.os.cdx.gz	89160	download
lonerandfriends.blogspot.com-inf-20181124-094653-7h480-meta.warc.gz	56057	download job
lonerandfriends.blogspot.com-inf-20181124-094653-7h480-meta.warc.os.cdx.gz	47	download
lonerandfriends.blogspot.com-inf-20181124-094653-7h480.json	305	download job
m.kakaobank.com-inf-20181124-080716-aqfvf-00000.warc.gz	25587272	download job
m.kakaobank.com-inf-20181124-080716-aqfvf-00000.warc.os.cdx.gz	7377	download
m.kakaobank.com-inf-20181124-080716-aqfvf-meta.warc.gz	8170	download job
m.kakaobank.com-inf-20181124-080716-aqfvf-meta.warc.os.cdx.gz	47	download
m.kakaobank.com-inf-20181124-080716-aqfvf.json	241	download job
m.kbanknow.com-inf-20181124-082407-8jxb9-00000.warc.gz	9551744	download job
m.kbanknow.com-inf-20181124-082407-8jxb9-00000.warc.os.cdx.gz	60765	download
m.kbanknow.com-inf-20181124-082407-8jxb9-meta.warc.gz	34525	download job
m.kbanknow.com-inf-20181124-082407-8jxb9-meta.warc.os.cdx.gz	47	download
m.kbanknow.com-inf-20181124-082407-8jxb9.json	240	download job
nypost.com-shallow-20181124-092800-62gax-00000.warc.gz	4228187	download job
nypost.com-shallow-20181124-092800-62gax-00000.warc.os.cdx.gz	17831	download
nypost.com-shallow-20181124-092800-62gax-meta.warc.gz	15645	download job
nypost.com-shallow-20181124-092800-62gax-meta.warc.os.cdx.gz	47	download
nypost.com-shallow-20181124-092800-62gax.json	304	download job
phabricator.wikimedia.org-inf-20181124-083437-anpwq-00000.warc.gz	15066202	download job
phabricator.wikimedia.org-inf-20181124-083437-anpwq-00000.warc.os.cdx.gz	25230	download
phabricator.wikimedia.org-inf-20181124-083437-anpwq-meta.warc.gz	19427	download job
phabricator.wikimedia.org-inf-20181124-083437-anpwq-meta.warc.os.cdx.gz	47	download
phabricator.wikimedia.org-inf-20181124-083437-anpwq.json	270	download job
phabricator.wikimedia.org-inf-20181124-084825-1cse9-00000.warc.gz	10188283	download job
phabricator.wikimedia.org-inf-20181124-084825-1cse9-00000.warc.os.cdx.gz	32309	download
phabricator.wikimedia.org-inf-20181124-084825-1cse9-meta.warc.gz	23716	download job
phabricator.wikimedia.org-inf-20181124-084825-1cse9-meta.warc.os.cdx.gz	47	download
phabricator.wikimedia.org-inf-20181124-084825-1cse9.json	270	download job
phabricator.wikimedia.org-inf-20181124-090843-6lv7e-aborted-00000.warc.gz	4298	download job
phabricator.wikimedia.org-inf-20181124-090843-6lv7e-aborted-00000.warc.os.cdx.gz	237	download
phabricator.wikimedia.org-inf-20181124-090843-6lv7e-aborted.json	269	download job
phabricator.wikimedia.org-inf-20181124-090845-84w40-meta.warc.gz	19149	download job
phabricator.wikimedia.org-inf-20181124-090845-84w40-meta.warc.os.cdx.gz	47	download
phabricator.wikimedia.org-inf-20181124-090845-84w40.json	269	download job
phabricator.wikimedia.org-inf-20181124-092314-4ep7e-00000.warc.gz	22892320	download job
phabricator.wikimedia.org-inf-20181124-092314-4ep7e-00000.warc.os.cdx.gz	43088	download
phabricator.wikimedia.org-inf-20181124-092314-4ep7e-meta.warc.gz	29888	download job
phabricator.wikimedia.org-inf-20181124-092314-4ep7e-meta.warc.os.cdx.gz	47	download
phabricator.wikimedia.org-inf-20181124-092314-4ep7e.json	268	download job
rankingamerica.wordpress.com-inf-20181124-115019-amhoh-00000.warc.gz	3377107606	download job
rankingamerica.wordpress.com-inf-20181124-115019-amhoh-00000.warc.os.cdx.gz	5022828	download
rankingamerica.wordpress.com-inf-20181124-115019-amhoh-meta.warc.gz	3407214	download job
rankingamerica.wordpress.com-inf-20181124-115019-amhoh-meta.warc.os.cdx.gz	47	download
satwcomic.com-shallow-20181124-175726-bojlh-00000.warc.gz	1403015	download job
satwcomic.com-shallow-20181124-175726-bojlh-00000.warc.os.cdx.gz	6072	download
satwcomic.com-shallow-20181124-175726-bojlh-meta.warc.gz	7111	download job
satwcomic.com-shallow-20181124-175726-bojlh-meta.warc.os.cdx.gz	47	download
satwcomic.com-shallow-20181124-175726-bojlh.json	259	download job
thisiswesthollywood.com-shallow-20181124-092124-9wpvf-meta.warc.gz	8988	download job
thisiswesthollywood.com-shallow-20181124-092124-9wpvf-meta.warc.os.cdx.gz	47	download
thisiswesthollywood.com-shallow-20181124-092124-9wpvf.json	295	download job
totalwararena.com-shallow-20181124-093405-a5dzg-00000.warc.gz	2488122	download job
totalwararena.com-shallow-20181124-093405-a5dzg-00000.warc.os.cdx.gz	6181	download
totalwararena.com-shallow-20181124-093405-a5dzg-meta.warc.gz	6935	download job
totalwararena.com-shallow-20181124-093405-a5dzg-meta.warc.os.cdx.gz	47	download
totalwararena.com-shallow-20181124-093405-a5dzg.json	291	download job
twitter.com-shallow-20181124-092214-1m7z6-00000.warc.gz	992234	download job
twitter.com-shallow-20181124-092214-1m7z6-00000.warc.os.cdx.gz	4147	download
twitter.com-shallow-20181124-092214-1m7z6-meta.warc.gz	6092	download job
twitter.com-shallow-20181124-092214-1m7z6-meta.warc.os.cdx.gz	47	download
twitter.com-shallow-20181124-092214-1m7z6.json	283	download job
twitter.com-shallow-20181124-171131-1w77m-00000.warc.gz	1168216	download job
twitter.com-shallow-20181124-171131-1w77m-00000.warc.os.cdx.gz	4564	download
twitter.com-shallow-20181124-171131-1w77m-meta.warc.gz	6310	download job
twitter.com-shallow-20181124-171131-1w77m-meta.warc.os.cdx.gz	47	download
urls-archive.org-urls-transfer.sh-geocities-misssp.txt-inf-20181007-102152-3ntkw-urls.txt-inf-20181031-231650-e8ynr-00071.warc.gz	5370796880	download job
urls-archive.org-urls-transfer.sh-geocities-misssp.txt-inf-20181007-102152-3ntkw-urls.txt-inf-20181031-231650-e8ynr-00071.warc.os.cdx.gz	3548449	download
urls-my.mixtape.moe-scfere.txt-shallow-20181122-095243-1pua9-00001.warc.gz	5368711693	download job
urls-my.mixtape.moe-scfere.txt-shallow-20181122-095243-1pua9-00001.warc.os.cdx.gz	5272760	download
urls-transfer.sh-irvsburgers-insta-shallow-20181124-092338-axi2y-00000.warc.gz	29196362	download job
urls-transfer.sh-irvsburgers-insta-shallow-20181124-092338-axi2y-00000.warc.os.cdx.gz	27389	download
urls-transfer.sh-irvsburgers-insta-shallow-20181124-092338-axi2y-urls.txt	2976	download
urls-transfer.sh-irvsburgers-insta-shallow-20181124-092338-axi2y.json	310	download job
utrs.wmflabs.org-shallow-20181124-073848-dml2l-00000.warc.gz	108473	download job
utrs.wmflabs.org-shallow-20181124-073848-dml2l-00000.warc.os.cdx.gz	671	download
utrs.wmflabs.org-shallow-20181124-073848-dml2l-meta.warc.gz	3931	download job
utrs.wmflabs.org-shallow-20181124-073848-dml2l-meta.warc.os.cdx.gz	47	download
utrs.wmflabs.org-shallow-20181124-073848-dml2l.json	246	download job
whytaxes.blogspot.com-inf-20181124-191939-46b2x-00000.warc.gz	83650817	download job
whytaxes.blogspot.com-inf-20181124-191939-46b2x-00000.warc.os.cdx.gz	229602	download
whytaxes.blogspot.com-inf-20181124-191939-46b2x-meta.warc.gz	143372	download job
whytaxes.blogspot.com-inf-20181124-191939-46b2x-meta.warc.os.cdx.gz	47	download
whytaxes.blogspot.com-inf-20181124-191939-46b2x.json	295	download job
writerswrite.co.za-inf-20181124-072340-2pywa-00000.warc.gz	401711503	download job
writerswrite.co.za-inf-20181124-072340-2pywa-00000.warc.os.cdx.gz	1048949	download
writerswrite.co.za-inf-20181124-072340-2pywa-meta.warc.gz	645434	download job
writerswrite.co.za-inf-20181124-072340-2pywa-meta.warc.os.cdx.gz	47	download
writerswrite.co.za-inf-20181124-072340-2pywa.json	289	download job
www.allmenus.com-shallow-20181124-093120-34z5m-00000.warc.gz	4016989	download job
www.allmenus.com-shallow-20181124-093120-34z5m-00000.warc.os.cdx.gz	6491	download
www.allmenus.com-shallow-20181124-093120-34z5m-meta.warc.gz	7610	download job
www.allmenus.com-shallow-20181124-093120-34z5m-meta.warc.os.cdx.gz	47	download
www.allmenus.com-shallow-20181124-093120-34z5m.json	290	download job
www.bkhwang.com-inf-20181124-062100-b5dp0-00000.warc.gz	34920809	download job
www.bkhwang.com-inf-20181124-062100-b5dp0-00000.warc.os.cdx.gz	120005	download
www.bkhwang.com-inf-20181124-062100-b5dp0-meta.warc.gz	57736	download job
www.bkhwang.com-inf-20181124-062100-b5dp0-meta.warc.os.cdx.gz	47	download
www.fanfiction.net-inf-20181026-181604-1bkfa-00053.warc.gz	2147813163	download job
www.fanfiction.net-inf-20181026-181604-1bkfa-00053.warc.os.cdx.gz	10705072	download
www.ihearthollywood.com-shallow-20181124-092716-5rm92-00000.warc.gz	3548754	download job
www.ihearthollywood.com-shallow-20181124-092716-5rm92-00000.warc.os.cdx.gz	7768	download
www.ihearthollywood.com-shallow-20181124-092716-5rm92-meta.warc.gz	7957	download job
www.ihearthollywood.com-shallow-20181124-092716-5rm92-meta.warc.os.cdx.gz	47	download
www.instagram.com-shallow-20181124-092044-3a193-00000.warc.gz	1439037	download job
www.instagram.com-shallow-20181124-092044-3a193-00000.warc.os.cdx.gz	2774	download
www.instagram.com-shallow-20181124-092044-3a193-meta.warc.gz	5340	download job
www.instagram.com-shallow-20181124-092044-3a193-meta.warc.os.cdx.gz	47	download
www.instagram.com-shallow-20181124-092044-3a193.json	266	download job
www.kakabank.com-inf-20181124-080932-7yeem-00000.warc.gz	2474	download job
www.kakabank.com-inf-20181124-080932-7yeem-00000.warc.os.cdx.gz	47	download
www.kakabank.com-inf-20181124-080932-7yeem-meta.warc.gz	3616	download job
www.kakabank.com-inf-20181124-080932-7yeem-meta.warc.os.cdx.gz	47	download
www.kakabank.com-inf-20181124-080932-7yeem.json	242	download job
www.lataco.com-shallow-20181124-092005-cdm7y-00000.warc.gz	26280642	download job
www.lataco.com-shallow-20181124-092005-cdm7y-00000.warc.os.cdx.gz	12232	download
www.lataco.com-shallow-20181124-092005-cdm7y.json	305	download job
www.launchgrowjoy.com-inf-20181124-081112-q1pzp-00000.warc.gz	155656454	download job
www.launchgrowjoy.com-inf-20181124-081112-q1pzp-00000.warc.os.cdx.gz	280246	download
www.launchgrowjoy.com-inf-20181124-081112-q1pzp-meta.warc.gz	336768	download job
www.launchgrowjoy.com-inf-20181124-081112-q1pzp-meta.warc.os.cdx.gz	47	download
www.launchgrowjoy.com-inf-20181124-081112-q1pzp.json	287	download job
www.lds.org-inf-20180925-030149-5t6yn-00811.warc.gz	8164763691	download job
www.lds.org-inf-20180925-030149-5t6yn-00811.warc.os.cdx.gz	1419	download
www.lds.org-inf-20180925-205550-e9g84-01709.warc.gz	5597836024	download job
www.lds.org-inf-20180925-205550-e9g84-01709.warc.os.cdx.gz	3593	download
www.lds.org-inf-20180925-205550-e9g84-01710.warc.gz	5695646276	download job
www.lds.org-inf-20180925-205550-e9g84-01710.warc.os.cdx.gz	4003	download
www.lds.org-inf-20180925-205550-e9g84-01711.warc.gz	5376625075	download job
www.lds.org-inf-20180925-205550-e9g84-01711.warc.os.cdx.gz	3365	download
www.lds.org-inf-20180925-205550-e9g84-01712.warc.gz	5671033405	download job
www.lds.org-inf-20180925-205550-e9g84-01712.warc.os.cdx.gz	3553	download
www.lds.org-inf-20180925-205550-e9g84-01713.warc.gz	5400103638	download job
www.lds.org-inf-20180925-205550-e9g84-01713.warc.os.cdx.gz	4588	download
www.lds.org-inf-20180925-205550-e9g84-01714.warc.gz	5836967770	download job
www.lds.org-inf-20180925-205550-e9g84-01714.warc.os.cdx.gz	3431	download
www.lds.org-inf-20180925-205550-e9g84-01715.warc.gz	5541924146	download job
www.lds.org-inf-20180925-205550-e9g84-01715.warc.os.cdx.gz	3081	download
www.lds.org-inf-20180929-013437-s21ic-01213.warc.gz	5391622900	download job
www.lds.org-inf-20180929-013437-s21ic-01213.warc.os.cdx.gz	117168	download
www.lds.org-inf-20180929-013437-s21ic-01214.warc.gz	5402096050	download job
www.lds.org-inf-20180929-013437-s21ic-01214.warc.os.cdx.gz	97315	download
www.lds.org-inf-20180929-013437-s21ic-01215.warc.gz	5369209373	download job
www.lds.org-inf-20180929-013437-s21ic-01215.warc.os.cdx.gz	72417	download
www.mapquest.com-shallow-20181124-093312-eile6-00000.warc.gz	4370373	download job
www.mapquest.com-shallow-20181124-093312-eile6-00000.warc.os.cdx.gz	17906	download
www.mapquest.com-shallow-20181124-093312-eile6-meta.warc.gz	17262	download job
www.mapquest.com-shallow-20181124-093312-eile6-meta.warc.os.cdx.gz	47	download
www.mapquest.com-shallow-20181124-093312-eile6.json	286	download job
www.rappler.com-inf-20181122-055324-878b0-00001.warc.gz	5368768896	download job
www.rappler.com-inf-20181122-055324-878b0-00001.warc.os.cdx.gz	10200129	download
www.technologyreview.com-inf-20181109-011503-6q1he-00077.warc.gz	6247711462	download job
www.technologyreview.com-inf-20181109-011503-6q1he-00077.warc.os.cdx.gz	128311	download
www.technologyreview.com-inf-20181109-011503-6q1he-00078.warc.gz	5443004720	download job
www.technologyreview.com-inf-20181109-011503-6q1he-00078.warc.os.cdx.gz	440090	download
www.timesledger.com-shallow-20181124-092846-7g8m0-00000.warc.gz	1536510	download job
www.timesledger.com-shallow-20181124-092846-7g8m0-00000.warc.os.cdx.gz	10503	download
www.timesledger.com-shallow-20181124-092846-7g8m0-meta.warc.gz	9707	download job
www.timesledger.com-shallow-20181124-092846-7g8m0-meta.warc.os.cdx.gz	47	download
www.timesledger.com-shallow-20181124-092846-7g8m0.json	300	download job
www.tradera.com-shallow-20181124-095440-6k0c7.json	347	download job
www.tripadvisor.com-shallow-20181124-093211-omobr-00000.warc.gz	31369527	download job
www.tripadvisor.com-shallow-20181124-093211-omobr-00000.warc.os.cdx.gz	56018	download
www.tripadvisor.com-shallow-20181124-093211-omobr-meta.warc.gz	35609	download job
www.tripadvisor.com-shallow-20181124-093211-omobr-meta.warc.os.cdx.gz	47	download
www.tripadvisor.com-shallow-20181124-093211-omobr.json	341	download job
www.wehoville.com-shallow-20181124-092630-2d6ko-00000.warc.gz	3228583	download job
www.wehoville.com-shallow-20181124-092630-2d6ko-00000.warc.os.cdx.gz	3472	download
www.wehoville.com-shallow-20181124-092630-2d6ko-meta.warc.gz	5699	download job
www.wehoville.com-shallow-20181124-092630-2d6ko-meta.warc.os.cdx.gz	47	download
www.wehoville.com-shallow-20181124-092630-2d6ko.json	269	download job
www.yelp.com-shallow-20181124-093025-7qlak-00000.warc.gz	8695198	download job
www.yelp.com-shallow-20181124-093025-7qlak-00000.warc.os.cdx.gz	39145	download
www.yelp.com-shallow-20181124-093025-7qlak-meta.warc.gz	24573	download job
www.yelp.com-shallow-20181124-093025-7qlak-meta.warc.os.cdx.gz	47	download
www.yelp.com-shallow-20181124-093025-7qlak.json	275	download job
yah.ac-inf-20181124-082944-5uvgd-00000.warc.gz	715500999	download job
yah.ac-inf-20181124-082944-5uvgd-00000.warc.os.cdx.gz	63756	download
yah.ac-inf-20181124-082944-5uvgd-meta.warc.gz	48623	download job
yah.ac-inf-20181124-082944-5uvgd-meta.warc.os.cdx.gz	47	download
yah.ac-inf-20181124-082944-5uvgd.json	232	download job