Item archiveteam_archivebot_go_20200128080002

Filename	Size
8tracks.com-inf-20191228-013657-daow6-00081.warc.gz	5369596932	download job
8tracks.com-inf-20191228-013657-daow6-00081.warc.os.cdx.gz	3674763	download
archiveteam_archivebot_go_20200128080002.cdx.gz	53226203	download
archiveteam_archivebot_go_20200128080002.cdx.idx	50328	download
archiveteam_archivebot_go_20200128080002_files.xml	0	download
archiveteam_archivebot_go_20200128080002_meta.sqlite	261120	download
archiveteam_archivebot_go_20200128080002_meta.xml	1016	download
books.discogs.com-shallow-20200128-063700-b58z8-00000.warc.gz	639231	download job
books.discogs.com-shallow-20200128-063700-b58z8-00000.warc.os.cdx.gz	1623	download
books.discogs.com-shallow-20200128-063700-b58z8-meta.warc.gz	4441	download job
books.discogs.com-shallow-20200128-063700-b58z8-meta.warc.os.cdx.gz	47	download
books.discogs.com-shallow-20200128-063700-b58z8.json	275	download job
chconservancy.pastperfectonline.com-shallow-20200128-062037-3k9c7-00000.warc.gz	475995	download job
chconservancy.pastperfectonline.com-shallow-20200128-062037-3k9c7-00000.warc.os.cdx.gz	3435	download
chconservancy.pastperfectonline.com-shallow-20200128-062037-3k9c7-meta.warc.gz	5623	download job
chconservancy.pastperfectonline.com-shallow-20200128-062037-3k9c7-meta.warc.os.cdx.gz	47	download
chconservancy.pastperfectonline.com-shallow-20200128-062037-3k9c7.json	312	download job
comptroller.texas.gov-shallow-20200128-041422-ep5yg-00000.warc.gz	3713801	download job
comptroller.texas.gov-shallow-20200128-041422-ep5yg-00000.warc.os.cdx.gz	257	download
comptroller.texas.gov-shallow-20200128-041422-ep5yg-meta.warc.gz	3533	download job
comptroller.texas.gov-shallow-20200128-041422-ep5yg-meta.warc.os.cdx.gz	47	download
comptroller.texas.gov-shallow-20200128-041422-ep5yg.json	292	download job
en.wikipedia.org-shallow-20200128-062849-d5og9-00000.warc.gz	326195	download job
en.wikipedia.org-shallow-20200128-062849-d5og9-00000.warc.os.cdx.gz	4564	download
en.wikipedia.org-shallow-20200128-062849-d5og9-meta.warc.gz	6272	download job
en.wikipedia.org-shallow-20200128-062849-d5og9-meta.warc.os.cdx.gz	47	download
en.wikipedia.org-shallow-20200128-062849-d5og9.json	275	download job
fedsoc.org-inf-20200126-043026-3oh49-00005.warc.gz	5443225610	download job
fedsoc.org-inf-20200126-043026-3oh49-00005.warc.os.cdx.gz	56032	download
fedsoc.org-inf-20200126-043026-3oh49-00006.warc.gz	47523479	download job
fedsoc.org-inf-20200126-043026-3oh49-00006.warc.os.cdx.gz	17434	download
fedsoc.org-inf-20200126-043026-3oh49-meta.warc.gz	594639	download job
fedsoc.org-inf-20200126-043026-3oh49-meta.warc.os.cdx.gz	47	download
fedsoc.org-inf-20200126-043026-3oh49.json	235	download job
flipboard.com-inf-20190530-021845-a9z36-01457.warc.gz	5368796255	download job
flipboard.com-inf-20190530-021845-a9z36-01457.warc.os.cdx.gz	615198	download
groups.yahoo.com-shallow-20200128-051615-ejjc0-00000.warc.gz	12241	download job
groups.yahoo.com-shallow-20200128-051615-ejjc0-00000.warc.os.cdx.gz	329	download
groups.yahoo.com-shallow-20200128-051615-ejjc0-meta.warc.gz	3557	download job
groups.yahoo.com-shallow-20200128-051615-ejjc0-meta.warc.os.cdx.gz	47	download
groups.yahoo.com-shallow-20200128-051615-ejjc0.json	279	download job
letterboxd.com-shallow-20200128-063746-8u8du-00000.warc.gz	3753121	download job
letterboxd.com-shallow-20200128-063746-8u8du-00000.warc.os.cdx.gz	9735	download
letterboxd.com-shallow-20200128-063746-8u8du-meta.warc.gz	10203	download job
letterboxd.com-shallow-20200128-063746-8u8du-meta.warc.os.cdx.gz	47	download
letterboxd.com-shallow-20200128-063746-8u8du.json	282	download job
linksunten.archive.indymedia.org-inf-20200116-165027-8oc1i-00046.warc.gz	5410397654	download job
linksunten.archive.indymedia.org-inf-20200116-165027-8oc1i-00046.warc.os.cdx.gz	1334324	download
lnks.gd-shallow-20200128-041353-9r2aa-00000.warc.gz	4780	download job
lnks.gd-shallow-20200128-041353-9r2aa-00000.warc.os.cdx.gz	581	download
lnks.gd-shallow-20200128-041353-9r2aa-meta.warc.gz	3956	download job
lnks.gd-shallow-20200128-041353-9r2aa-meta.warc.os.cdx.gz	47	download
lnks.gd-shallow-20200128-041353-9r2aa.json	528	download job
memorials.pennsylvaniaburialcompany.com-shallow-20200128-062114-d4s1a-00000.warc.gz	17507492	download job
memorials.pennsylvaniaburialcompany.com-shallow-20200128-062114-d4s1a-00000.warc.os.cdx.gz	37711	download
memorials.pennsylvaniaburialcompany.com-shallow-20200128-062114-d4s1a-meta.warc.gz	23727	download job
memorials.pennsylvaniaburialcompany.com-shallow-20200128-062114-d4s1a-meta.warc.os.cdx.gz	47	download
memorials.pennsylvaniaburialcompany.com-shallow-20200128-062114-d4s1a.json	299	download job
news.abs-cbn.com-inf-20200123-190204-awyod-00011.warc.gz	5371232503	download job
news.abs-cbn.com-inf-20200123-190204-awyod-00011.warc.os.cdx.gz	3765535	download
nhccunm.unm.edu-inf-20200128-043615-7lkns-00000.warc.gz	131588317	download job
nhccunm.unm.edu-inf-20200128-043615-7lkns-00000.warc.os.cdx.gz	150518	download
nhccunm.unm.edu-inf-20200128-043615-7lkns-meta.warc.gz	95441	download job
nhccunm.unm.edu-inf-20200128-043615-7lkns-meta.warc.os.cdx.gz	47	download
nhccunm.unm.edu-inf-20200128-043615-7lkns.json	244	download job
nl.wikipedia.org-shallow-20200128-062841-1bmp4-00000.warc.gz	2057461	download job
nl.wikipedia.org-shallow-20200128-062841-1bmp4-00000.warc.os.cdx.gz	4360	download
nl.wikipedia.org-shallow-20200128-062841-1bmp4-meta.warc.gz	6197	download job
nl.wikipedia.org-shallow-20200128-062841-1bmp4-meta.warc.os.cdx.gz	47	download
nl.wikipedia.org-shallow-20200128-062841-1bmp4.json	266	download job
spotlight.nudge.ai-inf-20200123-185237-d8fjm-00020.warc.gz	5383777308	download job
spotlight.nudge.ai-inf-20200123-185237-d8fjm-00020.warc.os.cdx.gz	5249690	download
thenhccn.wixsite.com-inf-20200128-042557-17zo9-meta.warc.gz	263460	download job
thenhccn.wixsite.com-inf-20200128-042557-17zo9-meta.warc.os.cdx.gz	47	download
thenhccn.wixsite.com-inf-20200128-042557-17zo9.json	255	download job
urls-transfer.notkiska.pw-facebook-@GardenMothScheme-shallow-20200128-051844-e899f-00000.warc.gz	61817011	download job
urls-transfer.notkiska.pw-facebook-@GardenMothScheme-shallow-20200128-051844-e899f-00000.warc.os.cdx.gz	140431	download
urls-transfer.notkiska.pw-facebook-@GardenMothScheme-shallow-20200128-051844-e899f-meta.warc.gz	143590	download job
urls-transfer.notkiska.pw-facebook-@GardenMothScheme-shallow-20200128-051844-e899f-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@GardenMothScheme-shallow-20200128-051844-e899f-urls.txt	20127	download
urls-transfer.notkiska.pw-facebook-@GardenMothScheme-shallow-20200128-051844-e899f.json	346	download job
urls-transfer.notkiska.pw-facebook-@MothsIreland-shallow-20200128-044537-3yhjd-00000.warc.gz	36655342	download job
urls-transfer.notkiska.pw-facebook-@MothsIreland-shallow-20200128-044537-3yhjd-00000.warc.os.cdx.gz	96837	download
urls-transfer.notkiska.pw-facebook-@MothsIreland-shallow-20200128-044537-3yhjd-meta.warc.gz	59272	download job
urls-transfer.notkiska.pw-facebook-@MothsIreland-shallow-20200128-044537-3yhjd-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@MothsIreland-shallow-20200128-044537-3yhjd-urls.txt	7468	download
urls-transfer.notkiska.pw-facebook-@MothsIreland-shallow-20200128-044537-3yhjd.json	338	download job
urls-transfer.notkiska.pw-facebook-@theNHCCN-shallow-20200128-042648-5wvoa-00000.warc.gz	119275424	download job
urls-transfer.notkiska.pw-facebook-@theNHCCN-shallow-20200128-042648-5wvoa-00000.warc.os.cdx.gz	152148	download
urls-transfer.notkiska.pw-facebook-@theNHCCN-shallow-20200128-042648-5wvoa-meta.warc.gz	100799	download job
urls-transfer.notkiska.pw-facebook-@theNHCCN-shallow-20200128-042648-5wvoa-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@theNHCCN-shallow-20200128-042648-5wvoa.json	330	download job
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00084.warc.gz	5401276673	download job
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00084.warc.os.cdx.gz	30672	download
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00085.warc.gz	5623667196	download job
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00085.warc.os.cdx.gz	28512	download
urls-transfer.notkiska.pw-house.gov-representatives-websites-inf-20200110-171507-ajhnt-00104.warc.gz	5389433721	download job
urls-transfer.notkiska.pw-house.gov-representatives-websites-inf-20200110-171507-ajhnt-00104.warc.os.cdx.gz	1324525	download
urls-transfer.notkiska.pw-house.gov-representatives-websites-inf-20200110-171507-ajhnt-00105.warc.gz	5371089967	download job
urls-transfer.notkiska.pw-house.gov-representatives-websites-inf-20200110-171507-ajhnt-00105.warc.os.cdx.gz	1591212	download
urls-transfer.notkiska.pw-instagram-@nhccunm-inf-20200128-043432-1hnwa-00000.warc.gz	8454290	download job
urls-transfer.notkiska.pw-instagram-@nhccunm-inf-20200128-043432-1hnwa-00000.warc.os.cdx.gz	20547	download
urls-transfer.notkiska.pw-instagram-@nhccunm-inf-20200128-043432-1hnwa-urls.txt	267	download
urls-transfer.notkiska.pw-instagram-@nhccunm-inf-20200128-043432-1hnwa.json	326	download job
urls-transfer.notkiska.pw-senate.gov-senators-websites-inf-20200110-173327-5e2rb-00156.warc.gz	5378498026	download job
urls-transfer.notkiska.pw-senate.gov-senators-websites-inf-20200110-173327-5e2rb-00156.warc.os.cdx.gz	2134751	download
urls-transfer.notkiska.pw-twitter-%23Wuhan-shallow-20200125-223027-2ialm-00026.warc.gz	2352012398	download job
urls-transfer.notkiska.pw-twitter-%23Wuhan-shallow-20200125-223027-2ialm-00026.warc.os.cdx.gz	8910	download
urls-transfer.notkiska.pw-twitter-%23Wuhan-shallow-20200125-223027-2ialm-meta.warc.gz	37195338	download job
urls-transfer.notkiska.pw-twitter-%23Wuhan-shallow-20200125-223027-2ialm-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-%23Wuhan-shallow-20200125-223027-2ialm-urls.txt	7617420	download
urls-transfer.notkiska.pw-twitter-%23goldenglobes-shallow-20200108-102809-8zzp6-00126.warc.gz	5368717114	download job
urls-transfer.notkiska.pw-twitter-%23goldenglobes-shallow-20200108-102809-8zzp6-00126.warc.os.cdx.gz	2313467	download
urls-transfer.notkiska.pw-twitter-@StaffsEcology-shallow-20200128-052713-eto5v-00000.warc.gz	5262312	download job
urls-transfer.notkiska.pw-twitter-@StaffsEcology-shallow-20200128-052713-eto5v-00000.warc.os.cdx.gz	6175	download
urls-transfer.notkiska.pw-twitter-@StaffsEcology-shallow-20200128-052713-eto5v-meta.warc.gz	7334	download job
urls-transfer.notkiska.pw-twitter-@StaffsEcology-shallow-20200128-052713-eto5v-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@StaffsEcology-shallow-20200128-052713-eto5v-urls.txt	34	download
urls-transfer.notkiska.pw-twitter-@StaffsEcology-shallow-20200128-052713-eto5v.json	338	download job
urls-transfer.notkiska.pw-twitter-@VTVcanal8-shallow-20200113-154111-1f4mt-00009.warc.gz	5369211016	download job
urls-transfer.notkiska.pw-twitter-@VTVcanal8-shallow-20200113-154111-1f4mt-00009.warc.os.cdx.gz	4364878	download
wiki.postgresql.org-shallow-20200128-044932-41vgt-meta.warc.gz	3551	download job
wiki.postgresql.org-shallow-20200128-044932-41vgt-meta.warc.os.cdx.gz	47	download
wiki.postgresql.org-shallow-20200128-044932-41vgt.json	310	download job
winkel.vpro.nl-shallow-20200128-063823-95o4i-00000.warc.gz	2942077	download job
winkel.vpro.nl-shallow-20200128-063823-95o4i-00000.warc.os.cdx.gz	11421	download
winkel.vpro.nl-shallow-20200128-063823-95o4i-meta.warc.gz	9689	download job
winkel.vpro.nl-shallow-20200128-063823-95o4i-meta.warc.os.cdx.gz	47	download
winkel.vpro.nl-shallow-20200128-063823-95o4i.json	280	download job
www.amazon.fr-shallow-20200128-063808-ctxtn-00000.warc.gz	4140424	download job
www.amazon.fr-shallow-20200128-063808-ctxtn-00000.warc.os.cdx.gz	14337	download
www.amazon.fr-shallow-20200128-063808-ctxtn-meta.warc.gz	12597	download job
www.amazon.fr-shallow-20200128-063808-ctxtn-meta.warc.os.cdx.gz	47	download
www.amazon.fr-shallow-20200128-063808-ctxtn.json	303	download job
www.bibliotheek.nl-shallow-20200128-064008-bwe2w-00000.warc.gz	1394430	download job
www.bibliotheek.nl-shallow-20200128-064008-bwe2w-00000.warc.os.cdx.gz	9548	download
www.bibliotheek.nl-shallow-20200128-064008-bwe2w-meta.warc.gz	9526	download job
www.bibliotheek.nl-shallow-20200128-064008-bwe2w-meta.warc.os.cdx.gz	47	download
www.bibliotheek.nl-shallow-20200128-064008-bwe2w.json	350	download job
www.change.org-shallow-20200128-051621-56l9x-00000.warc.gz	7724999	download job
www.change.org-shallow-20200128-051621-56l9x-00000.warc.os.cdx.gz	45611	download
www.change.org-shallow-20200128-051621-56l9x-meta.warc.gz	28467	download job
www.change.org-shallow-20200128-051621-56l9x-meta.warc.os.cdx.gz	47	download
www.change.org-shallow-20200128-051621-56l9x.json	304	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00144.warc.gz	1073854723	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00144.warc.os.cdx.gz	989667	download
www.duckworksmagazine.com-inf-20200127-055941-97gp1-00004.warc.gz	5368810934	download job
www.duckworksmagazine.com-inf-20200127-055941-97gp1-00004.warc.os.cdx.gz	6365497	download
www.earthstation9.com-inf-20200118-024902-ekvui-00037.warc.gz	5434068979	download job
www.earthstation9.com-inf-20200118-024902-ekvui-00037.warc.os.cdx.gz	2827471	download
www.earthstation9.com-inf-20200118-024902-ekvui-00038.warc.gz	5439700570	download job
www.earthstation9.com-inf-20200118-024902-ekvui-00038.warc.os.cdx.gz	183668	download
www.fantasyflightgames.com-shallow-20200128-074837-dh8t5-00000.warc.gz	1946795	download job
www.fantasyflightgames.com-shallow-20200128-074837-dh8t5-00000.warc.os.cdx.gz	5697	download
www.fantasyflightgames.com-shallow-20200128-074837-dh8t5-meta.warc.gz	6948	download job
www.fantasyflightgames.com-shallow-20200128-074837-dh8t5-meta.warc.os.cdx.gz	47	download
www.fantasyflightgames.com-shallow-20200128-074837-dh8t5.json	275	download job
www.gardenmoths.org.uk-inf-20200128-052053-f2hqd-00000.warc.gz	726292	download job
www.gardenmoths.org.uk-inf-20200128-052053-f2hqd-00000.warc.os.cdx.gz	2613	download
www.gardenmoths.org.uk-inf-20200128-052053-f2hqd-meta.warc.gz	5080	download job
www.gardenmoths.org.uk-inf-20200128-052053-f2hqd-meta.warc.os.cdx.gz	47	download
www.gardenmoths.org.uk-inf-20200128-052053-f2hqd.json	251	download job
www.gelechiid.co.uk-inf-20200128-034854-bnc8x-00000.warc.gz	535527065	download job
www.gelechiid.co.uk-inf-20200128-034854-bnc8x-00000.warc.os.cdx.gz	539814	download
www.gelechiid.co.uk-inf-20200128-034854-bnc8x-meta.warc.gz	298296	download job
www.gelechiid.co.uk-inf-20200128-034854-bnc8x-meta.warc.os.cdx.gz	47	download
www.gelechiid.co.uk-inf-20200128-034854-bnc8x.json	249	download job
www.gettyimages.com-shallow-20200128-062122-7cdu8-00000.warc.gz	3384809	download job
www.gettyimages.com-shallow-20200128-062122-7cdu8-00000.warc.os.cdx.gz	32468	download
www.gettyimages.com-shallow-20200128-062122-7cdu8-meta.warc.gz	31907	download job
www.gettyimages.com-shallow-20200128-062122-7cdu8-meta.warc.os.cdx.gz	47	download
www.gettyimages.com-shallow-20200128-062122-7cdu8.json	349	download job
www.gettyimages.com-shallow-20200128-062134-8tpxb-00000.warc.gz	3276175	download job
www.gettyimages.com-shallow-20200128-062134-8tpxb-00000.warc.os.cdx.gz	32404	download
www.gettyimages.com-shallow-20200128-062134-8tpxb-meta.warc.gz	32029	download job
www.gettyimages.com-shallow-20200128-062134-8tpxb-meta.warc.os.cdx.gz	47	download
www.gettyimages.com-shallow-20200128-062134-8tpxb.json	344	download job
www.idfa.nl-shallow-20200128-062933-74ync-00000.warc.gz	3536498	download job
www.idfa.nl-shallow-20200128-062933-74ync-00000.warc.os.cdx.gz	7155	download
www.idfa.nl-shallow-20200128-062933-74ync-meta.warc.gz	8379	download job
www.idfa.nl-shallow-20200128-062933-74ync-meta.warc.os.cdx.gz	47	download
www.idfa.nl-shallow-20200128-062933-74ync.json	335	download job
www.imdb.com-shallow-20200128-062856-epe5c-00000.warc.gz	2267225	download job
www.imdb.com-shallow-20200128-062856-epe5c-00000.warc.os.cdx.gz	14435	download
www.imdb.com-shallow-20200128-062856-epe5c-meta.warc.gz	14108	download job
www.imdb.com-shallow-20200128-062856-epe5c-meta.warc.os.cdx.gz	47	download
www.imdb.com-shallow-20200128-062856-epe5c.json	262	download job
www.lastampa.it-inf-20191204-092117-22y4l-00361.warc.gz	5368758579	download job
www.lastampa.it-inf-20191204-092117-22y4l-00361.warc.os.cdx.gz	3875772	download
www.npostart.nl-shallow-20200128-062646-bc3ag-00000.warc.gz	3381670	download job
www.npostart.nl-shallow-20200128-062646-bc3ag-00000.warc.os.cdx.gz	12445	download
www.npostart.nl-shallow-20200128-062646-bc3ag-meta.warc.gz	9597	download job
www.npostart.nl-shallow-20200128-062646-bc3ag-meta.warc.os.cdx.gz	47	download
www.npostart.nl-shallow-20200128-062646-bc3ag.json	281	download job
www.qt.io-inf-20200128-023405-alt3o-00000.warc.gz	5487819614	download job
www.qt.io-inf-20200128-023405-alt3o-00000.warc.os.cdx.gz	573976	download
www.qt.io-inf-20200128-023405-alt3o-00001.warc.gz	5692187563	download job
www.qt.io-inf-20200128-023405-alt3o-00001.warc.os.cdx.gz	2302	download
www.repubblica.it-inf-20191204-092043-6wowf-00165.warc.gz	5373352468	download job
www.repubblica.it-inf-20191204-092043-6wowf-00165.warc.os.cdx.gz	2528654	download
www.sbap.org.uk-inf-20200128-053133-3pk8p-00000.warc.gz	540010525	download job
www.sbap.org.uk-inf-20200128-053133-3pk8p-00000.warc.os.cdx.gz	690527	download
www.sbap.org.uk-inf-20200128-053133-3pk8p-meta.warc.gz	532910	download job
www.sbap.org.uk-inf-20200128-053133-3pk8p-meta.warc.os.cdx.gz	47	download
www.sbap.org.uk-inf-20200128-053133-3pk8p.json	244	download job
www.smithsonianmag.com-shallow-20200128-062709-4hl4t-00000.warc.gz	2091037666	download job
www.smithsonianmag.com-shallow-20200128-062709-4hl4t-00000.warc.os.cdx.gz	18565	download
www.smithsonianmag.com-shallow-20200128-062709-4hl4t-meta.warc.gz	17630	download job
www.smithsonianmag.com-shallow-20200128-062709-4hl4t-meta.warc.os.cdx.gz	47	download
www.smithsonianmag.com-shallow-20200128-062709-4hl4t.json	351	download job
www.spin.com-inf-20200126-235314-465ro-00030.warc.gz	5374089471	download job
www.spin.com-inf-20200126-235314-465ro-00030.warc.os.cdx.gz	2681592	download
www.staffs-ecology.org.uk-inf-20200128-052639-a0ql1-aborted-00000.warc.gz	96998597	download job
www.staffs-ecology.org.uk-inf-20200128-052639-a0ql1-aborted-00000.warc.os.cdx.gz	51248	download
www.staffs-ecology.org.uk-inf-20200128-052639-a0ql1-aborted-wpull.log.gz	33957	download
www.staffs-ecology.org.uk-inf-20200128-052639-a0ql1-aborted.json	253	download job
www.studiodaily.com-inf-20200126-092845-djwqb-00015.warc.gz	5556090034	download job
www.studiodaily.com-inf-20200126-092845-djwqb-00015.warc.os.cdx.gz	1559599	download
www.studiodaily.com-inf-20200126-092845-djwqb-00016.warc.gz	5834624762	download job
www.studiodaily.com-inf-20200126-092845-djwqb-00016.warc.os.cdx.gz	4600	download
www.studiodaily.com-inf-20200126-092845-djwqb-00017.warc.gz	5422152888	download job
www.studiodaily.com-inf-20200126-092845-djwqb-00017.warc.os.cdx.gz	464080	download
www.studiodaily.com-inf-20200126-092845-djwqb-00018.warc.gz	5407811640	download job
www.studiodaily.com-inf-20200126-092845-djwqb-00018.warc.os.cdx.gz	38660	download
www.studiodaily.com-inf-20200126-092845-djwqb-00019.warc.gz	5375714280	download job
www.studiodaily.com-inf-20200126-092845-djwqb-00019.warc.os.cdx.gz	37316	download
www.studiodaily.com-inf-20200126-092845-djwqb-00020.warc.gz	5394489706	download job
www.studiodaily.com-inf-20200126-092845-djwqb-00020.warc.os.cdx.gz	32687	download
www.taringa.net-inf-20190927-205127-2a0h7-00249.warc.gz	5372300443	download job
www.taringa.net-inf-20190927-205127-2a0h7-00249.warc.os.cdx.gz	3389693	download
www.thestranger.com-inf-20190827-222815-3hodl-00415.warc.gz	265602984	download job
www.thestranger.com-inf-20190827-222815-3hodl-00415.warc.os.cdx.gz	361856	download
www.thestranger.com-inf-20190827-222815-3hodl-meta.warc.gz	503927487	download job
www.thestranger.com-inf-20190827-222815-3hodl-meta.warc.os.cdx.gz	47	download
www.thestranger.com-inf-20190827-222815-3hodl.json	250	download job
www.uitgeverijbalans.nl-shallow-20200128-063940-5comu-00000.warc.gz	3149927	download job
www.uitgeverijbalans.nl-shallow-20200128-063940-5comu-00000.warc.os.cdx.gz	5881	download
www.uitgeverijbalans.nl-shallow-20200128-063940-5comu-meta.warc.gz	7082	download job
www.uitgeverijbalans.nl-shallow-20200128-063940-5comu-meta.warc.os.cdx.gz	47	download
www.uitgeverijbalans.nl-shallow-20200128-063940-5comu.json	289	download job
www.uitzendinggemist.net-shallow-20200128-062519-5n7o7-00000.warc.gz	732796	download job
www.uitzendinggemist.net-shallow-20200128-062519-5n7o7-00000.warc.os.cdx.gz	3078	download
www.uitzendinggemist.net-shallow-20200128-062519-5n7o7-meta.warc.gz	5641	download job
www.uitzendinggemist.net-shallow-20200128-062519-5n7o7-meta.warc.os.cdx.gz	47	download
www.uitzendinggemist.net-shallow-20200128-062519-5n7o7.json	293	download job
www.vice.com-shallow-20200128-034444-8tgp8-00000.warc.gz	19466903	download job
www.vice.com-shallow-20200128-034444-8tgp8-00000.warc.os.cdx.gz	15149	download
www.vice.com-shallow-20200128-034444-8tgp8-meta.warc.gz	11826	download job
www.vice.com-shallow-20200128-034444-8tgp8-meta.warc.os.cdx.gz	47	download
www.vice.com-shallow-20200128-034444-8tgp8.json	327	download job
www.worldcat.org-shallow-20200128-062918-ao87t-00000.warc.gz	136976	download job
www.worldcat.org-shallow-20200128-062918-ao87t-00000.warc.os.cdx.gz	1354	download
www.worldcat.org-shallow-20200128-062918-ao87t-meta.warc.gz	4390	download job
www.worldcat.org-shallow-20200128-062918-ao87t-meta.warc.os.cdx.gz	47	download
www.worldcat.org-shallow-20200128-062918-ao87t.json	277	download job