Item archiveteam_archivebot_go_20181219050001

View on Internet Archive

Filename	Size
archiveteam_archivebot_go_20181219050001.cdx.gz	91783332	download
archiveteam_archivebot_go_20181219050001.cdx.idx	92107	download
archiveteam_archivebot_go_20181219050001_archive.torrent	842376	download
archiveteam_archivebot_go_20181219050001_files.xml	0	download
archiveteam_archivebot_go_20181219050001_meta.sqlite	225280	download
archiveteam_archivebot_go_20181219050001_meta.xml	974	download
boston.cbslocal.com-shallow-20181219-040557-agyr6-00000.warc.gz	6421351	download   job
boston.cbslocal.com-shallow-20181219-040557-agyr6-00000.warc.os.cdx.gz	19660	download
boston.cbslocal.com-shallow-20181219-040557-agyr6.json	285	download   job
boston.cbslocal.com-shallow-20181219-042438-8yqjn-meta.warc.gz	16919	download   job
boston.cbslocal.com-shallow-20181219-042438-8yqjn-meta.warc.os.cdx.gz	47	download
boston.cbslocal.com-shallow-20181219-042438-8yqjn.json	318	download   job
businessbankruptcies.com-shallow-20181219-035931-7thpy-00000.warc.gz	1038943	download   job
businessbankruptcies.com-shallow-20181219-035931-7thpy-00000.warc.os.cdx.gz	4966	download
businessbankruptcies.com-shallow-20181219-035931-7thpy-meta.warc.gz	7108	download   job
businessbankruptcies.com-shallow-20181219-035931-7thpy-meta.warc.os.cdx.gz	47	download
businessbankruptcies.com-shallow-20181219-035931-7thpy.json	284	download   job
businessbankruptcies.com-shallow-20181219-040318-9nk9n.json	272	download   job
businessbankruptcies.com-shallow-20181219-040813-4hh37-00000.warc.gz	1037514	download   job
businessbankruptcies.com-shallow-20181219-040813-4hh37-00000.warc.os.cdx.gz	4989	download
businessbankruptcies.com-shallow-20181219-040813-4hh37-meta.warc.gz	7077	download   job
businessbankruptcies.com-shallow-20181219-040813-4hh37-meta.warc.os.cdx.gz	47	download
businessbankruptcies.com-shallow-20181219-040813-4hh37.json	286	download   job
cdn.pacermonitor.com-shallow-20181219-041802-2dps3.json	327	download   job
cloud.google.com-shallow-20181219-025804-4wuwk-00000.warc.gz	19887219	download   job
cloud.google.com-shallow-20181219-025804-4wuwk-00000.warc.os.cdx.gz	4766	download
cloud.google.com-shallow-20181219-025804-4wuwk-meta.warc.gz	6070	download   job
cloud.google.com-shallow-20181219-025804-4wuwk-meta.warc.os.cdx.gz	47	download
cloud.google.com-shallow-20181219-025804-4wuwk.json	340	download   job
cointelegraph.com-shallow-20181219-022345-b42fv-00000.warc.gz	15695550	download   job
cointelegraph.com-shallow-20181219-022345-b42fv-00000.warc.os.cdx.gz	16611	download
cointelegraph.com-shallow-20181219-022345-b42fv-meta.warc.gz	13934	download   job
cointelegraph.com-shallow-20181219-022345-b42fv-meta.warc.os.cdx.gz	47	download
cointelegraph.com-shallow-20181219-022345-b42fv.json	327	download   job
dailypost.wordpress.com-inf-20181210-210814-am3qj-00143.warc.gz	5382628484	download   job
dailypost.wordpress.com-inf-20181210-210814-am3qj-00143.warc.os.cdx.gz	1007638	download
dailypost.wordpress.com-inf-20181210-210814-am3qj-00144.warc.gz	5369909405	download   job
dailypost.wordpress.com-inf-20181210-210814-am3qj-00144.warc.os.cdx.gz	1123909	download
dailypost.wordpress.com-inf-20181210-210814-am3qj-00145.warc.gz	5368967019	download   job
dailypost.wordpress.com-inf-20181210-210814-am3qj-00145.warc.os.cdx.gz	1220321	download
dailypost.wordpress.com-inf-20181210-210814-am3qj-00146.warc.gz	5387604283	download   job
dailypost.wordpress.com-inf-20181210-210814-am3qj-00146.warc.os.cdx.gz	1368660	download
dailypost.wordpress.com-inf-20181210-210814-am3qj-00147.warc.gz	5372557465	download   job
dailypost.wordpress.com-inf-20181210-210814-am3qj-00147.warc.os.cdx.gz	439457	download
dailypost.wordpress.com-inf-20181210-210814-am3qj-00148.warc.gz	5368755237	download   job
dailypost.wordpress.com-inf-20181210-210814-am3qj-00148.warc.os.cdx.gz	1764678	download
drive.google.com-shallow-20181218-235004-6n2dw-00000.warc.gz	1128474	download   job
drive.google.com-shallow-20181218-235004-6n2dw-00000.warc.os.cdx.gz	4888	download
drive.google.com-shallow-20181218-235004-6n2dw.json	292	download   job
forums.zybez.net-inf-20181217-040543-fh2fl-00002.warc.gz	5405303871	download   job
forums.zybez.net-inf-20181217-040543-fh2fl-00002.warc.os.cdx.gz	9171303	download
forums.zybez.net-inf-20181217-040543-fh2fl-00003.warc.gz	5368738780	download   job
forums.zybez.net-inf-20181217-040543-fh2fl-00003.warc.os.cdx.gz	1080710	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00410.warc.gz	5375849603	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00410.warc.os.cdx.gz	98680	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00411.warc.gz	5435616490	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00411.warc.os.cdx.gz	78213	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00412.warc.gz	5396185721	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00412.warc.os.cdx.gz	101411	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00413.warc.gz	5372893753	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00413.warc.os.cdx.gz	60122	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00414.warc.gz	5376847397	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00414.warc.os.cdx.gz	86915	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00415.warc.gz	5374610554	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00415.warc.os.cdx.gz	88133	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00416.warc.gz	5397138174	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00416.warc.os.cdx.gz	85595	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00417.warc.gz	5496124076	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00417.warc.os.cdx.gz	76314	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00418.warc.gz	5374014242	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00418.warc.os.cdx.gz	97309	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00419.warc.gz	5405325396	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00419.warc.os.cdx.gz	100552	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00420.warc.gz	5372016817	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00420.warc.os.cdx.gz	116005	download
freemusicarchive.org-inf-20181106-114510-7lzw7-00421.warc.gz	5369224151	download   job
freemusicarchive.org-inf-20181106-114510-7lzw7-00421.warc.os.cdx.gz	108386	download
konatamoe.tistory.com-inf-20181218-041205-4hq4i-00002.warc.gz	3918433291	download   job
konatamoe.tistory.com-inf-20181218-041205-4hq4i-00002.warc.os.cdx.gz	7853032	download
konatamoe.tistory.com-inf-20181218-041205-4hq4i.json	246	download   job
motus-labs.com-shallow-20181219-005559-5gc1s-00000.warc.gz	6360215	download   job
motus-labs.com-shallow-20181219-005559-5gc1s-00000.warc.os.cdx.gz	9481	download
motus-labs.com-shallow-20181219-005559-5gc1s-meta.warc.gz	9040	download   job
motus-labs.com-shallow-20181219-005559-5gc1s-meta.warc.os.cdx.gz	47	download
motus-labs.com-shallow-20181219-005559-5gc1s.json	258	download   job
nbamania.com-inf-20181125-182058-48vwo-00059.warc.gz	5383187990	download   job
nbamania.com-inf-20181125-182058-48vwo-00059.warc.os.cdx.gz	722186	download
nmpolitics.net-shallow-20181219-023619-5cihm-00000.warc.gz	1511056	download   job
nmpolitics.net-shallow-20181219-023619-5cihm-00000.warc.os.cdx.gz	5638	download
nmpolitics.net-shallow-20181219-023619-5cihm-meta.warc.gz	7035	download   job
nmpolitics.net-shallow-20181219-023619-5cihm-meta.warc.os.cdx.gz	47	download
nmpolitics.net-shallow-20181219-023619-5cihm.json	331	download   job
orenstransitpage.com-inf-20181218-075039-ek9xp-00001.warc.gz	971390376	download   job
orenstransitpage.com-inf-20181218-075039-ek9xp-00001.warc.os.cdx.gz	1995145	download
orenstransitpage.com-inf-20181218-075039-ek9xp-meta.warc.gz	3296036	download   job
orenstransitpage.com-inf-20181218-075039-ek9xp-meta.warc.os.cdx.gz	47	download
orenstransitpage.com-inf-20181218-075039-ek9xp.json	251	download   job
ottawacitizen.com-shallow-20181219-020615-c8j5d-00000.warc.gz	4570253	download   job
ottawacitizen.com-shallow-20181219-020615-c8j5d-00000.warc.os.cdx.gz	18927	download
ottawacitizen.com-shallow-20181219-020615-c8j5d-meta.warc.gz	15486	download   job
ottawacitizen.com-shallow-20181219-020615-c8j5d-meta.warc.os.cdx.gz	47	download
ottawacitizen.com-shallow-20181219-020615-c8j5d.json	356	download   job
siliconangle.com-shallow-20181219-024430-cnwje-00000.warc.gz	10520790	download   job
siliconangle.com-shallow-20181219-024430-cnwje-00000.warc.os.cdx.gz	17344	download
siliconangle.com-shallow-20181219-024430-cnwje-meta.warc.gz	14448	download   job
siliconangle.com-shallow-20181219-024430-cnwje-meta.warc.os.cdx.gz	47	download
siliconangle.com-shallow-20181219-024430-cnwje.json	319	download   job
urls-etc.sanqui.net-geocities.jp_various.txt-inf-20181121-025110-cp5r3-00049.warc.gz	5368733265	download   job
urls-etc.sanqui.net-geocities.jp_various.txt-inf-20181121-025110-cp5r3-00049.warc.os.cdx.gz	8196286	download
urls-www.vatterott.edu-sitemap.xml-shallow-20181219-014155-7zi30-00000.warc.gz	5683	download   job
urls-www.vatterott.edu-sitemap.xml-shallow-20181219-014155-7zi30-00000.warc.os.cdx.gz	305	download
urls-www.vatterott.edu-sitemap.xml-shallow-20181219-014155-7zi30-meta.warc.gz	6632	download   job
urls-www.vatterott.edu-sitemap.xml-shallow-20181219-014155-7zi30-meta.warc.os.cdx.gz	47	download
urls-www.vatterott.edu-sitemap.xml-shallow-20181219-014155-7zi30-urls.txt	56624	download
urls-www.vatterott.edu-sitemap.xml-shallow-20181219-014155-7zi30.json	292	download   job
www.aapeli.com-inf-20181126-214204-2ulom-00021.warc.gz	5368757374	download   job
www.aapeli.com-inf-20181126-214204-2ulom-00021.warc.os.cdx.gz	5705041	download
www.allrecipes.com-inf-20181124-011238-anmtj-00013.warc.gz	1073751688	download   job
www.allrecipes.com-inf-20181124-011238-anmtj-00013.warc.os.cdx.gz	2165580	download
www.animenewsnetwork.com-inf-20181013-181755-8k7di-00046.warc.gz	5378809894	download   job
www.animenewsnetwork.com-inf-20181013-181755-8k7di-00046.warc.os.cdx.gz	4677765	download
www.aruworks.com-inf-20181219-105649-2fvhg-00000.warc.gz	57068668	download   job
www.aruworks.com-inf-20181219-105649-2fvhg-00000.warc.os.cdx.gz	371141	download
www.aruworks.com-inf-20181219-105649-2fvhg-meta.warc.gz	194991	download   job
www.aruworks.com-inf-20181219-105649-2fvhg-meta.warc.os.cdx.gz	47	download
www.aruworks.com-inf-20181219-105649-2fvhg.json	241	download   job
www.azcentral.com-shallow-20181219-015938-1zkql-00000.warc.gz	2248840	download   job
www.azcentral.com-shallow-20181219-015938-1zkql-00000.warc.os.cdx.gz	15053	download
www.azcentral.com-shallow-20181219-015938-1zkql-meta.warc.gz	13291	download   job
www.azcentral.com-shallow-20181219-015938-1zkql-meta.warc.os.cdx.gz	47	download
www.azcentral.com-shallow-20181219-015938-1zkql.json	364	download   job
www.azcentral.com-shallow-20181219-020028-2hhcn-00000.warc.gz	41600441	download   job
www.azcentral.com-shallow-20181219-020028-2hhcn-00000.warc.os.cdx.gz	43814	download
www.azcentral.com-shallow-20181219-020028-2hhcn-meta.warc.gz	30661	download   job
www.azcentral.com-shallow-20181219-020028-2hhcn-meta.warc.os.cdx.gz	47	download
www.azcentral.com-shallow-20181219-020028-2hhcn.json	362	download   job
www.bloomberg.com-shallow-20181219-041552-4facf.json	300	download   job
www.bloomberg.com-shallow-20181219-041802-f10vj-00000.warc.gz	3891	download   job
www.bloomberg.com-shallow-20181219-041802-f10vj-00000.warc.os.cdx.gz	250	download
www.bloomberg.com-shallow-20181219-041802-f10vj-meta.warc.gz	3463	download   job
www.bloomberg.com-shallow-20181219-041802-f10vj-meta.warc.os.cdx.gz	47	download
www.bloomberg.com-shallow-20181219-042852-9rqbo-00000.warc.gz	1136400	download   job
www.bloomberg.com-shallow-20181219-042852-9rqbo-00000.warc.os.cdx.gz	8209	download
www.bloomberg.com-shallow-20181219-042852-9rqbo-meta.warc.gz	9519	download   job
www.bloomberg.com-shallow-20181219-042852-9rqbo-meta.warc.os.cdx.gz	47	download
www.bloomberg.com-shallow-20181219-042852-9rqbo.json	301	download   job
www.bostonglobe.com-shallow-20181219-040545-8v5hw-meta.warc.gz	9102	download   job
www.bostonglobe.com-shallow-20181219-040545-8v5hw-meta.warc.os.cdx.gz	47	download
www.britishpathe.com-inf-20181127-020056-8w0dc-00056.warc.gz	5368709196	download   job
www.britishpathe.com-inf-20181127-020056-8w0dc-00056.warc.os.cdx.gz	6455768	download
www.cnbc.com-shallow-20181219-042020-4o33n-meta.warc.gz	22321	download   job
www.cnbc.com-shallow-20181219-042020-4o33n-meta.warc.os.cdx.gz	47	download
www.cnbc.com-shallow-20181219-042020-4o33n.json	295	download   job
www.cruisersforum.com-inf-20181008-021210-70wkr-00102.warc.gz	5368832912	download   job
www.cruisersforum.com-inf-20181008-021210-70wkr-00102.warc.os.cdx.gz	11151293	download
www.engadget.com-shallow-20181219-022759-2mmz8-00000.warc.gz	6770958	download   job
www.engadget.com-shallow-20181219-022759-2mmz8-00000.warc.os.cdx.gz	11436	download
www.engadget.com-shallow-20181219-022759-2mmz8-meta.warc.gz	10619	download   job
www.engadget.com-shallow-20181219-022759-2mmz8-meta.warc.os.cdx.gz	47	download
www.engadget.com-shallow-20181219-022759-2mmz8.json	266	download   job
www.globalbankingandfinance.com-shallow-20181219-041915-epnz9-00000.warc.gz	2304240	download   job
www.globalbankingandfinance.com-shallow-20181219-041915-epnz9-00000.warc.os.cdx.gz	6810	download
www.guidelive.com-shallow-20181219-042915-sevff-00000.warc.gz	4081802	download   job
www.guidelive.com-shallow-20181219-042915-sevff-00000.warc.os.cdx.gz	10167	download
www.guidelive.com-shallow-20181219-042915-sevff-meta.warc.gz	9641	download   job
www.guidelive.com-shallow-20181219-042915-sevff-meta.warc.os.cdx.gz	47	download
www.guidelive.com-shallow-20181219-042915-sevff.json	333	download   job
www.gurufocus.com-shallow-20181219-042638-8uypu-meta.warc.gz	10298	download   job
www.gurufocus.com-shallow-20181219-042638-8uypu-meta.warc.os.cdx.gz	47	download
www.gurufocus.com-shallow-20181219-042638-8uypu.json	419	download   job
www.heykuri.com-shallow-20181218-235446-15j1x-00000.warc.gz	1790957	download   job
www.heykuri.com-shallow-20181218-235446-15j1x-00000.warc.os.cdx.gz	2865	download
www.heykuri.com-shallow-20181218-235446-15j1x-meta.warc.gz	5464	download   job
www.heykuri.com-shallow-20181218-235446-15j1x-meta.warc.os.cdx.gz	47	download
www.heykuri.com-shallow-20181218-235446-15j1x.json	299	download   job
www.joplinglobe.com-shallow-20181219-021238-1lrfl-00000.warc.gz	13678	download   job
www.joplinglobe.com-shallow-20181219-021238-1lrfl-00000.warc.os.cdx.gz	318	download
www.joplinglobe.com-shallow-20181219-021238-1lrfl-meta.warc.gz	3674	download   job
www.joplinglobe.com-shallow-20181219-021238-1lrfl-meta.warc.os.cdx.gz	47	download
www.joplinglobe.com-shallow-20181219-021238-1lrfl.json	365	download   job
www.kivitv.com-shallow-20181219-015506-9w2ry-00000.warc.gz	63556269	download   job
www.kivitv.com-shallow-20181219-015506-9w2ry-00000.warc.os.cdx.gz	5253	download
www.kivitv.com-shallow-20181219-015506-9w2ry-meta.warc.gz	7013	download   job
www.kivitv.com-shallow-20181219-015506-9w2ry-meta.warc.os.cdx.gz	47	download
www.kivitv.com-shallow-20181219-015506-9w2ry.json	302	download   job
www.lifesitenews.com-inf-20181215-120114-etqrv-00008.warc.gz	5422279458	download   job
www.lifesitenews.com-inf-20181215-120114-etqrv-00008.warc.os.cdx.gz	3029625	download
www.marketwatch.com-shallow-20181219-024021-2h9g3-00000.warc.gz	7901046	download   job
www.marketwatch.com-shallow-20181219-024021-2h9g3-00000.warc.os.cdx.gz	9834	download
www.marketwatch.com-shallow-20181219-024021-2h9g3-meta.warc.gz	9241	download   job
www.marketwatch.com-shallow-20181219-024021-2h9g3-meta.warc.os.cdx.gz	47	download
www.marketwatch.com-shallow-20181219-024021-2h9g3.json	325	download   job
www.nrn.com-shallow-20181219-042408-8c3ub-meta.warc.gz	11072	download   job
www.nrn.com-shallow-20181219-042408-8c3ub-meta.warc.os.cdx.gz	47	download
www.nrn.com-shallow-20181219-042408-8c3ub.json	333	download   job
www.purple-robotics.com-shallow-20181219-003616-29s6k-00000.warc.gz	267821	download   job
www.purple-robotics.com-shallow-20181219-003616-29s6k-00000.warc.os.cdx.gz	943	download
www.purple-robotics.com-shallow-20181219-003616-29s6k-meta.warc.gz	3933	download   job
www.purple-robotics.com-shallow-20181219-003616-29s6k-meta.warc.os.cdx.gz	47	download
www.purple-robotics.com-shallow-20181219-003616-29s6k.json	254	download   job
www.reuters.com-shallow-20181219-042617-542ih-00000.warc.gz	4945580	download   job
www.reuters.com-shallow-20181219-042617-542ih-00000.warc.os.cdx.gz	40537	download
www.reuters.com-shallow-20181219-042617-542ih-meta.warc.gz	25747	download   job
www.reuters.com-shallow-20181219-042617-542ih-meta.warc.os.cdx.gz	47	download
www.reuters.com-shallow-20181219-042617-542ih.json	291	download   job
www.sears.com-inf-20181011-182140-ckwxj-00116.warc.gz	5368714569	download   job
www.sears.com-inf-20181011-182140-ckwxj-00116.warc.os.cdx.gz	20017745	download
www.slashgear.com-shallow-20181219-023334-4mn6l-00000.warc.gz	2234071	download   job
www.slashgear.com-shallow-20181219-023334-4mn6l-00000.warc.os.cdx.gz	8395	download
www.slashgear.com-shallow-20181219-023334-4mn6l-meta.warc.gz	8566	download   job
www.slashgear.com-shallow-20181219-023334-4mn6l-meta.warc.os.cdx.gz	47	download
www.slashgear.com-shallow-20181219-023334-4mn6l.json	321	download   job
www.teamfortress.com-inf-20181219-111137-ccdvf-00000.warc.gz	4330312221	download   job
www.teamfortress.com-inf-20181219-111137-ccdvf-00000.warc.os.cdx.gz	3646841	download
www.teamfortress.com-inf-20181219-111137-ccdvf-meta.warc.gz	2489956	download   job
www.teamfortress.com-inf-20181219-111137-ccdvf-meta.warc.os.cdx.gz	47	download
www.teamfortress.com-inf-20181219-111137-ccdvf.json	250	download   job
www.techdirt.com-shallow-20181219-002707-6tj2y-00000.warc.gz	2041315	download   job
www.techdirt.com-shallow-20181219-002707-6tj2y-00000.warc.os.cdx.gz	13611	download
www.techdirt.com-shallow-20181219-002707-6tj2y-meta.warc.gz	11552	download   job
www.techdirt.com-shallow-20181219-002707-6tj2y-meta.warc.os.cdx.gz	47	download
www.techdirt.com-shallow-20181219-002707-6tj2y.json	349	download   job
www.therobotreport.com-shallow-20181218-234936-8cx0b-00000.warc.gz	1565592	download   job
www.therobotreport.com-shallow-20181218-234936-8cx0b-00000.warc.os.cdx.gz	6583	download
www.therobotreport.com-shallow-20181218-234936-8cx0b-meta.warc.gz	7739	download   job
www.therobotreport.com-shallow-20181218-234936-8cx0b-meta.warc.os.cdx.gz	47	download
www.therobotreport.com-shallow-20181218-234936-8cx0b.json	278	download   job
www.therobotreport.com-shallow-20181218-235227-bvwun-00000.warc.gz	4286557	download   job
www.therobotreport.com-shallow-20181218-235227-bvwun-00000.warc.os.cdx.gz	7603	download
www.therobotreport.com-shallow-20181218-235227-bvwun-meta.warc.gz	8309	download   job
www.therobotreport.com-shallow-20181218-235227-bvwun-meta.warc.os.cdx.gz	47	download
www.therobotreport.com-shallow-20181218-235227-bvwun.json	279	download   job
www.therobotreport.com-shallow-20181218-235401-dm0hq-00000.warc.gz	1615737	download   job
www.therobotreport.com-shallow-20181218-235401-dm0hq-00000.warc.os.cdx.gz	6030	download
www.therobotreport.com-shallow-20181218-235401-dm0hq-meta.warc.gz	7240	download   job
www.therobotreport.com-shallow-20181218-235401-dm0hq-meta.warc.os.cdx.gz	47	download
www.therobotreport.com-shallow-20181218-235401-dm0hq.json	290	download   job
www.theverge.com-shallow-20181219-013428-3rghd-00000.warc.gz	33166189	download   job
www.theverge.com-shallow-20181219-013428-3rghd-00000.warc.os.cdx.gz	36031	download
www.theverge.com-shallow-20181219-013428-3rghd-meta.warc.gz	26874	download   job
www.theverge.com-shallow-20181219-013428-3rghd-meta.warc.os.cdx.gz	47	download
www.theverge.com-shallow-20181219-013428-3rghd.json	328	download   job