Item archiveteam_archivebot_go_20200201170002

Filename	Size
2003page.ga-inf-20200201-121348-cfwvd-00000.warc.gz	331158088	download job
2003page.ga-inf-20200201-121348-cfwvd-00000.warc.os.cdx.gz	244612	download
2003page.ga-inf-20200201-121348-cfwvd-meta.warc.gz	159028	download job
2003page.ga-inf-20200201-121348-cfwvd-meta.warc.os.cdx.gz	47	download
2003page.ga-inf-20200201-121348-cfwvd.json	235	download job
4kyws.ua.edu-inf-20200201-122013-dy8qe-00000.warc.gz	107530133	download job
4kyws.ua.edu-inf-20200201-122013-dy8qe-00000.warc.os.cdx.gz	230243	download
8tracks.com-inf-20191228-013657-daow6-00096.warc.gz	5368933439	download job
8tracks.com-inf-20191228-013657-daow6-00096.warc.os.cdx.gz	4217197	download
archiveteam_archivebot_go_20200201170002.cdx.gz	89801311	download
archiveteam_archivebot_go_20200201170002.cdx.idx	91372	download
archiveteam_archivebot_go_20200201170002_files.xml	0	download
archiveteam_archivebot_go_20200201170002_meta.sqlite	249856	download
archiveteam_archivebot_go_20200201170002_meta.xml	1018	download
blackvoices.donaldjtrump.com-inf-20200201-144250-8edl8-00000.warc.gz	118533389	download job
blackvoices.donaldjtrump.com-inf-20200201-144250-8edl8-00000.warc.os.cdx.gz	147138	download
blackvoices.donaldjtrump.com-inf-20200201-144250-8edl8-meta.warc.gz	97649	download job
blackvoices.donaldjtrump.com-inf-20200201-144250-8edl8-meta.warc.os.cdx.gz	47	download
blackvoices.donaldjtrump.com-inf-20200201-144250-8edl8.json	258	download job
boilerlink.purdue.edu-inf-20200201-162409-3mxd4-00000.warc.gz	23402731	download job
boilerlink.purdue.edu-inf-20200201-162409-3mxd4-00000.warc.os.cdx.gz	54092	download
boilerlink.purdue.edu-inf-20200201-162409-3mxd4.json	269	download job
campaignlegal.org-shallow-20200201-151148-5plm9-00000.warc.gz	1008241	download job
campaignlegal.org-shallow-20200201-151148-5plm9-00000.warc.os.cdx.gz	268	download
campaignlegal.org-shallow-20200201-151148-5plm9-meta.warc.gz	3545	download job
campaignlegal.org-shallow-20200201-151148-5plm9-meta.warc.os.cdx.gz	47	download
campaignlegal.org-shallow-20200201-151148-5plm9.json	308	download job
capnben0.tripod.com-inf-20200201-050410-74tpa-00000.warc.gz	174161768	download job
capnben0.tripod.com-inf-20200201-050410-74tpa-00000.warc.os.cdx.gz	334129	download
capnben0.tripod.com-inf-20200201-050410-74tpa.json	243	download job
cops.donaldjtrump.com-inf-20200201-144614-7b77u-00000.warc.gz	22706330	download job
cops.donaldjtrump.com-inf-20200201-144614-7b77u-00000.warc.os.cdx.gz	59488	download
cops.donaldjtrump.com-inf-20200201-144614-7b77u-meta.warc.gz	37917	download job
cops.donaldjtrump.com-inf-20200201-144614-7b77u-meta.warc.os.cdx.gz	47	download
cops.donaldjtrump.com-inf-20200201-144614-7b77u.json	251	download job
democrats.donaldjtrump.com-inf-20200201-144844-9djic-00000.warc.gz	18156647	download job
democrats.donaldjtrump.com-inf-20200201-144844-9djic-00000.warc.os.cdx.gz	52038	download
democrats.donaldjtrump.com-inf-20200201-144844-9djic-meta.warc.gz	33857	download job
democrats.donaldjtrump.com-inf-20200201-144844-9djic-meta.warc.os.cdx.gz	47	download
democrats.donaldjtrump.com-inf-20200201-144844-9djic.json	256	download job
entnemdept.ufl.edu-inf-20200201-154848-297o0-00000.warc.gz	22251896	download job
entnemdept.ufl.edu-inf-20200201-154848-297o0-00000.warc.os.cdx.gz	47272	download
entnemdept.ufl.edu-inf-20200201-154848-297o0-meta.warc.gz	31032	download job
entnemdept.ufl.edu-inf-20200201-154848-297o0-meta.warc.os.cdx.gz	47	download
entnemdept.ufl.edu-inf-20200201-154848-297o0.json	253	download job
es.donaldjtrump.com-inf-20200201-145108-1557z-00000.warc.gz	62795164	download job
es.donaldjtrump.com-inf-20200201-145108-1557z-00000.warc.os.cdx.gz	142603	download
es.donaldjtrump.com-inf-20200201-145108-1557z-meta.warc.gz	88121	download job
es.donaldjtrump.com-inf-20200201-145108-1557z-meta.warc.os.cdx.gz	47	download
es.donaldjtrump.com-inf-20200201-145108-1557z.json	249	download job
evangelicals.donaldjtrump.com-inf-20200201-145921-ba5w8-00000.warc.gz	34922027	download job
evangelicals.donaldjtrump.com-inf-20200201-145921-ba5w8-00000.warc.os.cdx.gz	79822	download
evangelicals.donaldjtrump.com-inf-20200201-145921-ba5w8-meta.warc.gz	50312	download job
evangelicals.donaldjtrump.com-inf-20200201-145921-ba5w8-meta.warc.os.cdx.gz	47	download
evangelicals.donaldjtrump.com-inf-20200201-145921-ba5w8.json	259	download job
flipboard.com-inf-20190530-021845-a9z36-01466.warc.gz	5385213510	download job
flipboard.com-inf-20190530-021845-a9z36-01466.warc.os.cdx.gz	17471	download
flipboard.com-inf-20190530-021845-a9z36-01467.warc.gz	5381397076	download job
flipboard.com-inf-20190530-021845-a9z36-01467.warc.os.cdx.gz	19417	download
flipboard.com-inf-20190530-021845-a9z36-01468.warc.gz	5370564549	download job
flipboard.com-inf-20190530-021845-a9z36-01468.warc.os.cdx.gz	21841	download
forms.donaldjtrump.com-inf-20200201-150234-5btzp-00000.warc.gz	2888282	download job
forms.donaldjtrump.com-inf-20200201-150234-5btzp-00000.warc.os.cdx.gz	11191	download
forms.donaldjtrump.com-inf-20200201-150234-5btzp-meta.warc.gz	10099	download job
forms.donaldjtrump.com-inf-20200201-150234-5btzp-meta.warc.os.cdx.gz	47	download
forms.donaldjtrump.com-inf-20200201-150234-5btzp.json	294	download job
insekten-evb.ch-inf-20200201-135651-4vm03-00000.warc.gz	1535920839	download job
insekten-evb.ch-inf-20200201-135651-4vm03-00000.warc.os.cdx.gz	1061354	download
insekten-evb.ch-inf-20200201-135651-4vm03-meta.warc.gz	682827	download job
insekten-evb.ch-inf-20200201-135651-4vm03-meta.warc.os.cdx.gz	47	download
insekten-evb.ch-inf-20200201-135651-4vm03.json	245	download job
latinos.donaldjtrump.com-inf-20200201-150421-f3nc3-00000.warc.gz	18221	download job
latinos.donaldjtrump.com-inf-20200201-150421-f3nc3-00000.warc.os.cdx.gz	326	download
latinos.donaldjtrump.com-inf-20200201-150421-f3nc3-meta.warc.gz	3572	download job
latinos.donaldjtrump.com-inf-20200201-150421-f3nc3-meta.warc.os.cdx.gz	47	download
latinos.donaldjtrump.com-inf-20200201-150421-f3nc3.json	254	download job
latinos.donaldjtrump.com-inf-20200201-150518-f3nc3-00000.warc.gz	17653	download job
latinos.donaldjtrump.com-inf-20200201-150518-f3nc3-00000.warc.os.cdx.gz	330	download
latinos.donaldjtrump.com-inf-20200201-150518-f3nc3-meta.warc.gz	3518	download job
latinos.donaldjtrump.com-inf-20200201-150518-f3nc3-meta.warc.os.cdx.gz	47	download
latinos.donaldjtrump.com-inf-20200201-150518-f3nc3.json	254	download job
latinos.donaldjtrump.com-inf-20200201-150601-f3nc3-00000.warc.gz	17979	download job
latinos.donaldjtrump.com-inf-20200201-150601-f3nc3-00000.warc.os.cdx.gz	332	download
latinos.donaldjtrump.com-inf-20200201-150601-f3nc3-meta.warc.gz	3522	download job
latinos.donaldjtrump.com-inf-20200201-150601-f3nc3-meta.warc.os.cdx.gz	47	download
latinos.donaldjtrump.com-inf-20200201-150601-f3nc3.json	254	download job
latinos.donaldjtrump.com-inf-20200201-160453-f3nc3-00000.warc.gz	112167821	download job
latinos.donaldjtrump.com-inf-20200201-160453-f3nc3-00000.warc.os.cdx.gz	187052	download
latinos.donaldjtrump.com-inf-20200201-160453-f3nc3.json	254	download job
linksunten.archive.indymedia.org-inf-20200116-165027-8oc1i-00069.warc.gz	5736482115	download job
linksunten.archive.indymedia.org-inf-20200116-165027-8oc1i-00069.warc.os.cdx.gz	1294366	download
mkt.com-inf-20200201-155521-1jb8w-00000.warc.gz	3208835	download job
mkt.com-inf-20200201-155521-1jb8w-00000.warc.os.cdx.gz	11962	download
mkt.com-inf-20200201-155521-1jb8w-meta.warc.gz	10874	download job
mkt.com-inf-20200201-155521-1jb8w-meta.warc.os.cdx.gz	47	download
mkt.com-inf-20200201-155521-1jb8w.json	241	download job
naturwissenschaften.ch-inf-20200201-125637-32vd0-00000.warc.gz	455255736	download job
naturwissenschaften.ch-inf-20200201-125637-32vd0-00000.warc.os.cdx.gz	1948618	download
naturwissenschaften.ch-inf-20200201-125637-32vd0-meta.warc.gz	3109938	download job
naturwissenschaften.ch-inf-20200201-125637-32vd0-meta.warc.os.cdx.gz	47	download
naturwissenschaften.ch-inf-20200201-125637-32vd0.json	278	download job
public.nudge.ai-inf-20200123-184904-43los-00037.warc.gz	5374712007	download job
public.nudge.ai-inf-20200123-184904-43los-00037.warc.os.cdx.gz	3550866	download
spyware.neocities.org-inf-20200201-010810-3bleh-00000.warc.gz	380468848	download job
spyware.neocities.org-inf-20200201-010810-3bleh-00000.warc.os.cdx.gz	955108	download
spyware.neocities.org-inf-20200201-010810-3bleh-meta.warc.gz	595952	download job
spyware.neocities.org-inf-20200201-010810-3bleh-meta.warc.os.cdx.gz	47	download
spyware.neocities.org-inf-20200201-010810-3bleh.json	246	download job
talk.donaldjtrump.com-inf-20200201-151228-54sw4-00000.warc.gz	18165	download job
talk.donaldjtrump.com-inf-20200201-151228-54sw4-00000.warc.os.cdx.gz	325	download
talk.donaldjtrump.com-inf-20200201-151228-54sw4-meta.warc.gz	3548	download job
talk.donaldjtrump.com-inf-20200201-151228-54sw4-meta.warc.os.cdx.gz	47	download
talk.donaldjtrump.com-inf-20200201-151228-54sw4.json	251	download job
talk.sonymobile.com-inf-20200108-034950-c0eu4-00024.warc.gz	5392424542	download job
talk.sonymobile.com-inf-20200108-034950-c0eu4-00024.warc.os.cdx.gz	5904290	download
talk.sonymobile.com-inf-20200108-034950-c0eu4-00025.warc.gz	5435571902	download job
talk.sonymobile.com-inf-20200108-034950-c0eu4-00025.warc.os.cdx.gz	32311	download
talk.sonymobile.com-inf-20200108-034950-c0eu4-00026.warc.gz	5386726703	download job
talk.sonymobile.com-inf-20200108-034950-c0eu4-00026.warc.os.cdx.gz	42490	download
tunes.org-inf-20200201-101759-3qk7r-00000.warc.gz	5539656842	download job
tunes.org-inf-20200201-101759-3qk7r-00000.warc.os.cdx.gz	3068701	download
tunes.org-inf-20200201-101759-3qk7r-00001.warc.gz	1140962	download job
tunes.org-inf-20200201-101759-3qk7r-00001.warc.os.cdx.gz	11022	download
tunes.org-inf-20200201-101759-3qk7r-meta.warc.gz	1926567	download job
tunes.org-inf-20200201-101759-3qk7r-meta.warc.os.cdx.gz	47	download
tunes.org-inf-20200201-101759-3qk7r.json	234	download job
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00131.warc.gz	5374701247	download job
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00131.warc.os.cdx.gz	14434	download
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00132.warc.gz	5399453932	download job
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00132.warc.os.cdx.gz	19734	download
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00133.warc.gz	5369754600	download job
urls-transfer.notkiska.pw-fs.net-film.ru-video-redirect-links-10-thru-104689-shallow-20200120-185005-6nodk-00133.warc.os.cdx.gz	30882	download
urls-transfer.notkiska.pw-house.gov-representatives-websites-inf-20200110-171507-ajhnt-00136.warc.gz	5369340379	download job
urls-transfer.notkiska.pw-house.gov-representatives-websites-inf-20200110-171507-ajhnt-00136.warc.os.cdx.gz	821396	download
urls-transfer.notkiska.pw-twitter-search-coronavirus-shallow-20200128-232058-afh1t-00034.warc.gz	5368711970	download job
urls-transfer.notkiska.pw-twitter-search-coronavirus-shallow-20200128-232058-afh1t-00034.warc.os.cdx.gz	9618981	download
urls-transfer.notkiska.pw-twitter-search-coronavirus-shallow-20200128-232058-afh1t-00035.warc.gz	5368769210	download job
urls-transfer.notkiska.pw-twitter-search-coronavirus-shallow-20200128-232058-afh1t-00035.warc.os.cdx.gz	10786820	download
urls-transfer.notkiska.pw-twitter-search-coronavirus-shallow-20200128-232058-afh1t-00036.warc.gz	5368725276	download job
urls-transfer.notkiska.pw-twitter-search-coronavirus-shallow-20200128-232058-afh1t-00036.warc.os.cdx.gz	10685971	download
veterans.donaldjtrump.com-inf-20200201-151435-8nl9n-00000.warc.gz	18235	download job
veterans.donaldjtrump.com-inf-20200201-151435-8nl9n-00000.warc.os.cdx.gz	332	download
veterans.donaldjtrump.com-inf-20200201-151435-8nl9n-meta.warc.gz	3558	download job
veterans.donaldjtrump.com-inf-20200201-151435-8nl9n-meta.warc.os.cdx.gz	47	download
veterans.donaldjtrump.com-inf-20200201-151435-8nl9n.json	255	download job
veterans.donaldjtrump.com-inf-20200201-151536-8nl9n-00000.warc.gz	61192226	download job
veterans.donaldjtrump.com-inf-20200201-151536-8nl9n-00000.warc.os.cdx.gz	132588	download
veterans.donaldjtrump.com-inf-20200201-151536-8nl9n-meta.warc.gz	86670	download job
veterans.donaldjtrump.com-inf-20200201-151536-8nl9n-meta.warc.os.cdx.gz	47	download
veterans.donaldjtrump.com-inf-20200201-151536-8nl9n.json	255	download job
waycoolclarissa.tripod.com-inf-20200201-053303-29f1d-00000.warc.gz	100373702	download job
waycoolclarissa.tripod.com-inf-20200201-053303-29f1d-00000.warc.os.cdx.gz	199568	download
waycoolclarissa.tripod.com-inf-20200201-053303-29f1d-meta.warc.gz	129823	download job
waycoolclarissa.tripod.com-inf-20200201-053303-29f1d-meta.warc.os.cdx.gz	47	download
waycoolclarissa.tripod.com-inf-20200201-053303-29f1d.json	250	download job
women.donaldjtrump.com-inf-20200201-151738-14hvr-00000.warc.gz	18189	download job
women.donaldjtrump.com-inf-20200201-151738-14hvr-00000.warc.os.cdx.gz	323	download
women.donaldjtrump.com-inf-20200201-151738-14hvr-meta.warc.gz	3567	download job
women.donaldjtrump.com-inf-20200201-151738-14hvr-meta.warc.os.cdx.gz	47	download
women.donaldjtrump.com-inf-20200201-151738-14hvr.json	252	download job
women.donaldjtrump.com-inf-20200201-151822-14hvr-00000.warc.gz	17592	download job
women.donaldjtrump.com-inf-20200201-151822-14hvr-00000.warc.os.cdx.gz	329	download
women.donaldjtrump.com-inf-20200201-151822-14hvr-meta.warc.gz	3507	download job
women.donaldjtrump.com-inf-20200201-151822-14hvr-meta.warc.os.cdx.gz	47	download
women.donaldjtrump.com-inf-20200201-151822-14hvr.json	252	download job
women.donaldjtrump.com-inf-20200201-153713-14hvr-00000.warc.gz	83564840	download job
women.donaldjtrump.com-inf-20200201-153713-14hvr-00000.warc.os.cdx.gz	142186	download
women.donaldjtrump.com-inf-20200201-153713-14hvr-meta.warc.gz	93061	download job
women.donaldjtrump.com-inf-20200201-153713-14hvr-meta.warc.os.cdx.gz	47	download
women.donaldjtrump.com-inf-20200201-153713-14hvr.json	252	download job
workers.donaldjtrump.com-inf-20200201-152008-easft-00000.warc.gz	18240	download job
workers.donaldjtrump.com-inf-20200201-152008-easft-00000.warc.os.cdx.gz	329	download
workers.donaldjtrump.com-inf-20200201-152008-easft-meta.warc.gz	3574	download job
workers.donaldjtrump.com-inf-20200201-152008-easft-meta.warc.os.cdx.gz	47	download
workers.donaldjtrump.com-inf-20200201-152008-easft.json	254	download job
workers.donaldjtrump.com-inf-20200201-153311-easft-00000.warc.gz	18323970	download job
workers.donaldjtrump.com-inf-20200201-153311-easft-00000.warc.os.cdx.gz	51474	download
workers.donaldjtrump.com-inf-20200201-153311-easft-meta.warc.gz	33649	download job
workers.donaldjtrump.com-inf-20200201-153311-easft-meta.warc.os.cdx.gz	47	download
workers.donaldjtrump.com-inf-20200201-153311-easft.json	254	download job
www.1960sailors.net-inf-20200201-120146-dhjhj-meta.warc.gz	838272	download job
www.1960sailors.net-inf-20200201-120146-dhjhj-meta.warc.os.cdx.gz	47	download
www.1960sailors.net-inf-20200201-120146-dhjhj.json	243	download job
www.altexxanet.org-inf-20200201-115332-vez7m-meta.warc.gz	30879	download job
www.altexxanet.org-inf-20200201-115332-vez7m-meta.warc.os.cdx.gz	47	download
www.altexxanet.org-inf-20200201-115332-vez7m.json	242	download job
www.bamlog.com-inf-20200201-114302-eiq11-00000.warc.gz	1549593008	download job
www.bamlog.com-inf-20200201-114302-eiq11-00000.warc.os.cdx.gz	927211	download
www.bamlog.com-inf-20200201-114302-eiq11-meta.warc.gz	587572	download job
www.bamlog.com-inf-20200201-114302-eiq11-meta.warc.os.cdx.gz	47	download
www.bamlog.com-inf-20200201-114302-eiq11.json	238	download job
www.baumfamily.org-inf-20200201-113957-at3fk-00000.warc.gz	141958887	download job
www.baumfamily.org-inf-20200201-113957-at3fk-00000.warc.os.cdx.gz	199789	download
www.baumfamily.org-inf-20200201-113957-at3fk-meta.warc.gz	126932	download job
www.baumfamily.org-inf-20200201-113957-at3fk-meta.warc.os.cdx.gz	47	download
www.baumfamily.org-inf-20200201-113957-at3fk.json	242	download job
www.bjnews.com.cn-inf-20200131-153934-dfgnl-00006.warc.gz	5369755317	download job
www.bjnews.com.cn-inf-20200131-153934-dfgnl-00006.warc.os.cdx.gz	554532	download
www.dispropaganda.com-inf-20200131-225213-4iqce-00001.warc.gz	5428313285	download job
www.dispropaganda.com-inf-20200131-225213-4iqce-00001.warc.os.cdx.gz	971890	download
www.drive-now.com-inf-20200201-143630-28h9m-00000.warc.gz	1342501859	download job
www.drive-now.com-inf-20200201-143630-28h9m-00000.warc.os.cdx.gz	1019970	download
www.drive-now.com-inf-20200201-143630-28h9m-meta.warc.gz	699162	download job
www.drive-now.com-inf-20200201-143630-28h9m-meta.warc.os.cdx.gz	47	download
www.drive-now.com-inf-20200201-143630-28h9m.json	258	download job
www.ecured.cu-inf-20200116-203025-4cxhd-00025.warc.gz	5446235486	download job
www.ecured.cu-inf-20200116-203025-4cxhd-00025.warc.os.cdx.gz	5665377	download
www.homebrewtalk.com-inf-20200106-144131-3gpa8-00069.warc.gz	5368848529	download job
www.homebrewtalk.com-inf-20200106-144131-3gpa8-00069.warc.os.cdx.gz	3354965	download
www.johnstonefitness.com-inf-20200201-034132-4dk5o.json	253	download job
www.lastampa.it-inf-20191204-092117-22y4l-00371.warc.gz	5375299409	download job
www.lastampa.it-inf-20191204-092117-22y4l-00371.warc.os.cdx.gz	3749250	download
www.lavasurfer.com-inf-20200131-233600-exfro-00004.warc.gz	949799910	download job
www.lavasurfer.com-inf-20200131-233600-exfro-00004.warc.os.cdx.gz	1254158	download
www.lavasurfer.com-inf-20200131-233600-exfro-meta.warc.gz	2303917	download job
www.lavasurfer.com-inf-20200131-233600-exfro-meta.warc.os.cdx.gz	47	download
www.lavasurfer.com-inf-20200131-233600-exfro.json	243	download job
www.lawofficer.com-shallow-20200201-154225-7gbuu-00000.warc.gz	3305558	download job
www.lawofficer.com-shallow-20200201-154225-7gbuu-00000.warc.os.cdx.gz	12121	download
www.lawofficer.com-shallow-20200201-154225-7gbuu-meta.warc.gz	10895	download job
www.lawofficer.com-shallow-20200201-154225-7gbuu-meta.warc.os.cdx.gz	47	download
www.lawofficer.com-shallow-20200201-154225-7gbuu.json	301	download job
www.repubblica.it-inf-20191204-092043-6wowf-00192.warc.gz	5374601718	download job
www.repubblica.it-inf-20191204-092043-6wowf-00192.warc.os.cdx.gz	4303160	download
www.rochellerailroadpark.org-shallow-20200201-061823-81arg-00000.warc.gz	3426781	download job
www.rochellerailroadpark.org-shallow-20200201-061823-81arg-00000.warc.os.cdx.gz	8917	download
www.rochellerailroadpark.org-shallow-20200201-061823-81arg-meta.warc.gz	8519	download job
www.rochellerailroadpark.org-shallow-20200201-061823-81arg-meta.warc.os.cdx.gz	47	download
www.rochellerailroadpark.org-shallow-20200201-061823-81arg.json	263	download job
www.spin.com-inf-20200126-235314-465ro-00109.warc.gz	5373871277	download job
www.spin.com-inf-20200126-235314-465ro-00109.warc.os.cdx.gz	2250074	download
www.spin.com-inf-20200126-235314-465ro-00110.warc.gz	5369047084	download job
www.spin.com-inf-20200126-235314-465ro-00110.warc.os.cdx.gz	2740285	download
www.spin.com-inf-20200126-235314-465ro-00111.warc.gz	5368722396	download job
www.spin.com-inf-20200126-235314-465ro-00111.warc.os.cdx.gz	2879663	download
www.spin.com-inf-20200126-235314-465ro-00112.warc.gz	5371852052	download job
www.spin.com-inf-20200126-235314-465ro-00112.warc.os.cdx.gz	1681327	download
www.taringa.net-inf-20190927-205127-2a0h7-00266.warc.gz	5368753284	download job
www.taringa.net-inf-20190927-205127-2a0h7-00266.warc.os.cdx.gz	4460343	download
www.theguardian.com-shallow-20200201-102503-67suz-00000.warc.gz	804335	download job
www.theguardian.com-shallow-20200201-102503-67suz-00000.warc.os.cdx.gz	4266	download
www.theguardian.com-shallow-20200201-102503-67suz-meta.warc.gz	6825	download job
www.theguardian.com-shallow-20200201-102503-67suz-meta.warc.os.cdx.gz	47	download
www.theguardian.com-shallow-20200201-102503-67suz.json	370	download job
www.vermontinsects.org-inf-20200201-163857-acyyy-meta.warc.gz	78544	download job
www.vermontinsects.org-inf-20200201-163857-acyyy-meta.warc.os.cdx.gz	47	download
www.vermontinsects.org-inf-20200201-163857-acyyy.json	252	download job