Item archiveteam_archivebot_go_20210204070002

Filename	Size
alphabetty.info-inf-20210204-051416-2tric.json	240	download job
archiveteam_archivebot_go_20210204070002.cdx.gz	69498328	download
archiveteam_archivebot_go_20210204070002.cdx.idx	65690	download
archiveteam_archivebot_go_20210204070002_files.xml	0	download
archiveteam_archivebot_go_20210204070002_meta.sqlite	227328	download
archiveteam_archivebot_go_20210204070002_meta.xml	969	download
cointr.ee-inf-20210204-045432-dfap6-00000.warc.gz	1102950	download job
cointr.ee-inf-20210204-045432-dfap6-00000.warc.os.cdx.gz	4028	download
cointr.ee-inf-20210204-045432-dfap6-meta.warc.gz	7214	download job
cointr.ee-inf-20210204-045432-dfap6-meta.warc.os.cdx.gz	47	download
cointr.ee-inf-20210204-045432-dfap6.json	244	download job
cqww.com-inf-20210203-010759-3upb4-00062.warc.gz	5369016503	download job
cqww.com-inf-20210203-010759-3upb4-00062.warc.os.cdx.gz	252608	download
cqww.com-inf-20210203-010759-3upb4-00063.warc.gz	5374547516	download job
cqww.com-inf-20210203-010759-3upb4-00063.warc.os.cdx.gz	239212	download
cqww.com-inf-20210203-010759-3upb4-00064.warc.gz	5373600182	download job
cqww.com-inf-20210203-010759-3upb4-00064.warc.os.cdx.gz	269868	download
cqww.com-inf-20210203-010759-3upb4-00065.warc.gz	5372684787	download job
cqww.com-inf-20210203-010759-3upb4-00065.warc.os.cdx.gz	262388	download
cqww.com-inf-20210203-010759-3upb4-00066.warc.gz	5374737900	download job
cqww.com-inf-20210203-010759-3upb4-00066.warc.os.cdx.gz	255410	download
cqww.com-inf-20210203-010759-3upb4-00067.warc.gz	5371027611	download job
cqww.com-inf-20210203-010759-3upb4-00067.warc.os.cdx.gz	246987	download
cqww.com-inf-20210203-010759-3upb4-00068.warc.gz	5370757673	download job
cqww.com-inf-20210203-010759-3upb4-00068.warc.os.cdx.gz	265977	download
cqww.com-inf-20210203-010759-3upb4-00070.warc.gz	5369275955	download job
cqww.com-inf-20210203-010759-3upb4-00070.warc.os.cdx.gz	260269	download
elderofziyon.blogspot.com-inf-20210201-130408-7tz0m-00031.warc.gz	5368827974	download job
elderofziyon.blogspot.com-inf-20210201-130408-7tz0m-00031.warc.os.cdx.gz	4738825	download
freedomguide.wordpress.com-inf-20210204-034118-55dy9-00000.warc.gz	974114202	download job
freedomguide.wordpress.com-inf-20210204-034118-55dy9-00000.warc.os.cdx.gz	1347025	download
freedomguide.wordpress.com-inf-20210204-034118-55dy9-meta.warc.gz	912865	download job
freedomguide.wordpress.com-inf-20210204-034118-55dy9-meta.warc.os.cdx.gz	47	download
freedomguide.wordpress.com-inf-20210204-034118-55dy9.json	256	download job
harrydent.com-inf-20210204-030907-8wehp.json	243	download job
hsdpublishing.wpengine.com-inf-20210204-024844-6idgq-00000.warc.gz	300104669	download job
hsdpublishing.wpengine.com-inf-20210204-024844-6idgq-00000.warc.os.cdx.gz	329364	download
hsdpublishing.wpengine.com-inf-20210204-024844-6idgq-meta.warc.gz	216703	download job
hsdpublishing.wpengine.com-inf-20210204-024844-6idgq-meta.warc.os.cdx.gz	47	download
hsdpublishing.wpengine.com-inf-20210204-024844-6idgq.json	256	download job
ips-dc.org-inf-20210130-204903-9rvn4-00057.warc.gz	5369005498	download job
ips-dc.org-inf-20210130-204903-9rvn4-00057.warc.os.cdx.gz	1645432	download
jonathanturley.org-inf-20210131-225656-6gjyk-00024.warc.gz	5382376834	download job
jonathanturley.org-inf-20210131-225656-6gjyk-00024.warc.os.cdx.gz	1341846	download
libertyunderattack.com-inf-20210204-050008-aip9v-00001.warc.gz	6272752933	download job
libertyunderattack.com-inf-20210204-050008-aip9v-00001.warc.os.cdx.gz	341627	download
maydaystudentorganization.com-inf-20210204-033426-7jrne-00000.warc.gz	5368794782	download job
maydaystudentorganization.com-inf-20210204-033426-7jrne-00000.warc.os.cdx.gz	629672	download
maydaystudentorganization.com-inf-20210204-033426-7jrne-00001.warc.gz	1037156923	download job
maydaystudentorganization.com-inf-20210204-033426-7jrne-00001.warc.os.cdx.gz	1105194	download
maydaystudentorganization.com-inf-20210204-033426-7jrne-meta.warc.gz	1140748	download job
maydaystudentorganization.com-inf-20210204-033426-7jrne-meta.warc.os.cdx.gz	47	download
maydaystudentorganization.com-inf-20210204-033426-7jrne.json	259	download job
maydaystudentshome.wordpress.com-inf-20210204-032703-akppx-meta.warc.gz	102003	download job
maydaystudentshome.wordpress.com-inf-20210204-032703-akppx-meta.warc.os.cdx.gz	47	download
mforum.ist-inf-20210131-100642-1v6ja-00006.warc.gz	5369269487	download job
mforum.ist-inf-20210131-100642-1v6ja-00006.warc.os.cdx.gz	17183100	download
paznia.com-inf-20210204-045137-6o7fy-00000.warc.gz	1406051103	download job
paznia.com-inf-20210204-045137-6o7fy-00000.warc.os.cdx.gz	228965	download
paznia.com-inf-20210204-045137-6o7fy-meta.warc.gz	145156	download job
paznia.com-inf-20210204-045137-6o7fy-meta.warc.os.cdx.gz	47	download
paznia.com-inf-20210204-045137-6o7fy.json	240	download job
plexus.techlore.tech-inf-20210204-051733-aea68-00000.warc.gz	36181486	download job
plexus.techlore.tech-inf-20210204-051733-aea68-00000.warc.os.cdx.gz	112028	download
plexus.techlore.tech-inf-20210204-051733-aea68-meta.warc.gz	64222	download job
plexus.techlore.tech-inf-20210204-051733-aea68-meta.warc.os.cdx.gz	47	download
plexus.techlore.tech-inf-20210204-051733-aea68.json	251	download job
radiostudent.si-inf-20210117-132940-a2ru7-00369.warc.gz	5442666644	download job
radiostudent.si-inf-20210117-132940-a2ru7-00369.warc.os.cdx.gz	94772	download
radiostudent.si-inf-20210117-132940-a2ru7-00370.warc.gz	5447707167	download job
radiostudent.si-inf-20210117-132940-a2ru7-00370.warc.os.cdx.gz	93945	download
seed-solutions.com-inf-20210204-041634-19j0e-meta.warc.gz	553447	download job
seed-solutions.com-inf-20210204-041634-19j0e-meta.warc.os.cdx.gz	47	download
upload.libertyunderattack.com-inf-20210204-045639-b7bfv-00000.warc.gz	6126	download job
upload.libertyunderattack.com-inf-20210204-045639-b7bfv-00000.warc.os.cdx.gz	274	download
upload.libertyunderattack.com-inf-20210204-045639-b7bfv-meta.warc.gz	3556	download job
upload.libertyunderattack.com-inf-20210204-045639-b7bfv-meta.warc.os.cdx.gz	47	download
upload.libertyunderattack.com-inf-20210204-045639-b7bfv.json	259	download job
urls-transfer.notkiska.pw-grist.org-cx3tj-remaining-shallow-20210125-023448-eg17n-00039.warc.gz	5369519015	download job
urls-transfer.notkiska.pw-grist.org-cx3tj-remaining-shallow-20210125-023448-eg17n-00039.warc.os.cdx.gz	3135326	download
urls-transfer.notkiska.pw-twitter-%23NotMyPresident-shallow-20210120-215332-3pwf0-00033.warc.gz	5368745839	download job
urls-transfer.notkiska.pw-twitter-%23NotMyPresident-shallow-20210120-215332-3pwf0-00033.warc.os.cdx.gz	5706703	download
urls-transfer.notkiska.pw-twitter-%23NotMyPresident-shallow-20210120-215332-3pwf0-00034.warc.gz	5368751093	download job
urls-transfer.notkiska.pw-twitter-%23NotMyPresident-shallow-20210120-215332-3pwf0-00034.warc.os.cdx.gz	463154	download
urls-transfer.notkiska.pw-twitter-@GearboxOfficial-shallow-20210203-165406-3t5y0-00001.warc.gz	5431229419	download job
urls-transfer.notkiska.pw-twitter-@GearboxOfficial-shallow-20210203-165406-3t5y0-00001.warc.os.cdx.gz	5357435	download
urls-transfer.notkiska.pw-twitter-@GearboxOfficial-shallow-20210203-165406-3t5y0-meta.warc.gz	5125286	download job
urls-transfer.notkiska.pw-twitter-@GearboxOfficial-shallow-20210203-165406-3t5y0-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@GearboxOfficial-shallow-20210203-165406-3t5y0.json	344	download job
urls-transfer.notkiska.pw-twitter-@HarryDentjr-shallow-20210204-024528-br1l4-00000.warc.gz	3540616344	download job
urls-transfer.notkiska.pw-twitter-@HarryDentjr-shallow-20210204-024528-br1l4-00000.warc.os.cdx.gz	1721678	download
urls-transfer.notkiska.pw-twitter-@HarryDentjr-shallow-20210204-024528-br1l4-meta.warc.gz	1097787	download job
urls-transfer.notkiska.pw-twitter-@HarryDentjr-shallow-20210204-024528-br1l4-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@HarryDentjr-shallow-20210204-024528-br1l4-urls.txt	259314	download
urls-transfer.notkiska.pw-twitter-@HarryDentjr-shallow-20210204-024528-br1l4.json	334	download job
urls-transfer.notkiska.pw-twitter-@I_came_to_game-shallow-20210204-022840-bt1co-00000.warc.gz	433397670	download job
urls-transfer.notkiska.pw-twitter-@I_came_to_game-shallow-20210204-022840-bt1co-00000.warc.os.cdx.gz	813898	download
urls-transfer.notkiska.pw-twitter-@I_came_to_game-shallow-20210204-022840-bt1co-meta.warc.gz	446910	download job
urls-transfer.notkiska.pw-twitter-@I_came_to_game-shallow-20210204-022840-bt1co-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@Kyoto_Esports-shallow-20210204-021250-1h06v-urls.txt	126670	download
urls-transfer.notkiska.pw-twitter-@LUAradio-shallow-20210204-045441-3d91b-00000.warc.gz	5389775536	download job
urls-transfer.notkiska.pw-twitter-@LUAradio-shallow-20210204-045441-3d91b-00000.warc.os.cdx.gz	1247179	download
urls-transfer.notkiska.pw-twitter-@LUAradio-shallow-20210204-045441-3d91b-00001.warc.gz	5424135136	download job
urls-transfer.notkiska.pw-twitter-@LUAradio-shallow-20210204-045441-3d91b-00001.warc.os.cdx.gz	218317	download
urls-transfer.notkiska.pw-twitter-@MDSO_NYC-shallow-20210204-031825-1sdf1-meta.warc.gz	403050	download job
urls-transfer.notkiska.pw-twitter-@MDSO_NYC-shallow-20210204-031825-1sdf1-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@RealMiniAOC-shallow-20210204-040407-9uuow-00000.warc.gz	924027284	download job
urls-transfer.notkiska.pw-twitter-@RealMiniAOC-shallow-20210204-040407-9uuow-00000.warc.os.cdx.gz	1415963	download
urls-transfer.notkiska.pw-twitter-@RealMiniAOC-shallow-20210204-040407-9uuow-meta.warc.gz	786808	download job
urls-transfer.notkiska.pw-twitter-@RealMiniAOC-shallow-20210204-040407-9uuow-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@RealMiniAOC-shallow-20210204-040407-9uuow-urls.txt	116420	download
urls-transfer.notkiska.pw-twitter-@RealMiniAOC-shallow-20210204-040407-9uuow.json	334	download job
urls-transfer.notkiska.pw-twitter-@SaltOPepper-shallow-20210204-021048-8dyen-00000.warc.gz	313557122	download job
urls-transfer.notkiska.pw-twitter-@SaltOPepper-shallow-20210204-021048-8dyen-00000.warc.os.cdx.gz	944883	download
urls-transfer.notkiska.pw-twitter-@SaltOPepper-shallow-20210204-021048-8dyen-meta.warc.gz	663986	download job
urls-transfer.notkiska.pw-twitter-@SaltOPepper-shallow-20210204-021048-8dyen-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@SoooDistracted-shallow-20210204-022611-b7yrl-meta.warc.gz	484039	download job
urls-transfer.notkiska.pw-twitter-@SoooDistracted-shallow-20210204-022611-b7yrl-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b-00000.warc.gz	5383814350	download job
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b-00000.warc.os.cdx.gz	1223945	download
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b-00001.warc.gz	43003226	download job
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b-00001.warc.os.cdx.gz	1963	download
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b-meta.warc.gz	723569	download job
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b-urls.txt	149973	download
urls-transfer.notkiska.pw-twitter-@VelensPodcast-shallow-20210204-021024-5j50b.json	340	download job
urls-transfer.notkiska.pw-twitter-@WatchmanHS-shallow-20210204-021018-emp1f.json	332	download job
urls-transfer.notkiska.pw-twitter-@coffee6727-shallow-20210204-021531-coet4-00000.warc.gz	2748493442	download job
urls-transfer.notkiska.pw-twitter-@coffee6727-shallow-20210204-021531-coet4-00000.warc.os.cdx.gz	5205123	download
urls-transfer.notkiska.pw-twitter-@crotana-shallow-20210204-021733-9agky.json	326	download job
urls-transfer.notkiska.pw-twitter-@cwol_glassjaw-shallow-20210204-024209-rgjdl-00000.warc.gz	1110706826	download job
urls-transfer.notkiska.pw-twitter-@cwol_glassjaw-shallow-20210204-024209-rgjdl-00000.warc.os.cdx.gz	1222877	download
urls-transfer.notkiska.pw-twitter-@cwol_glassjaw-shallow-20210204-024209-rgjdl-meta.warc.gz	683616	download job
urls-transfer.notkiska.pw-twitter-@cwol_glassjaw-shallow-20210204-024209-rgjdl-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@cwol_glassjaw-shallow-20210204-024209-rgjdl-urls.txt	429411	download
urls-transfer.notkiska.pw-twitter-@cwol_glassjaw-shallow-20210204-024209-rgjdl.json	338	download job
urls-transfer.notkiska.pw-twitter-@itinerantwizard-shallow-20210204-024249-5b0cc-00000.warc.gz	5414120023	download job
urls-transfer.notkiska.pw-twitter-@itinerantwizard-shallow-20210204-024249-5b0cc-00000.warc.os.cdx.gz	3250350	download
urls-transfer.notkiska.pw-twitter-@itinerantwizard-shallow-20210204-024249-5b0cc.json	342	download job
urls-transfer.notkiska.pw-twitter-@project_eversio-shallow-20210204-022649-955xn-00000.warc.gz	1272204313	download job
urls-transfer.notkiska.pw-twitter-@project_eversio-shallow-20210204-022649-955xn-00000.warc.os.cdx.gz	1703749	download
urls-transfer.notkiska.pw-twitter-@project_eversio-shallow-20210204-022649-955xn-meta.warc.gz	983725	download job
urls-transfer.notkiska.pw-twitter-@project_eversio-shallow-20210204-022649-955xn-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@project_eversio-shallow-20210204-022649-955xn-urls.txt	179654	download
urls-transfer.notkiska.pw-twitter-@project_eversio-shallow-20210204-022649-955xn.json	342	download job
us.zgamz.org-inf-20210104-204452-cye3n-00311.warc.gz	5368894152	download job
us.zgamz.org-inf-20210104-204452-cye3n-00311.warc.os.cdx.gz	808594	download
www.degiro.at-inf-20210204-042327-dc287-00000.warc.gz	100464097	download job
www.degiro.at-inf-20210204-042327-dc287-00000.warc.os.cdx.gz	46542	download
www.degiro.at-inf-20210204-042327-dc287-meta.warc.gz	32246	download job
www.degiro.at-inf-20210204-042327-dc287-meta.warc.os.cdx.gz	47	download
www.degiro.at-inf-20210204-042327-dc287.json	238	download job
www.degiro.ch-inf-20210204-041008-9gtgf-00000.warc.gz	151243779	download job
www.degiro.ch-inf-20210204-041008-9gtgf-00000.warc.os.cdx.gz	100156	download
www.degiro.ch-inf-20210204-041008-9gtgf-meta.warc.gz	63638	download job
www.degiro.ch-inf-20210204-041008-9gtgf-meta.warc.os.cdx.gz	47	download
www.degiro.ch-inf-20210204-041008-9gtgf.json	238	download job
www.degiro.dk-inf-20210204-040529-2y4lm-00000.warc.gz	88300934	download job
www.degiro.dk-inf-20210204-040529-2y4lm-00000.warc.os.cdx.gz	38896	download
www.degiro.dk-inf-20210204-040529-2y4lm-meta.warc.gz	27078	download job
www.degiro.dk-inf-20210204-040529-2y4lm-meta.warc.os.cdx.gz	47	download
www.degiro.dk-inf-20210204-040529-2y4lm.json	238	download job
www.degiro.fi-inf-20210204-050741-ba54o-00000.warc.gz	90019482	download job
www.degiro.fi-inf-20210204-050741-ba54o-00000.warc.os.cdx.gz	46998	download
www.degiro.fi-inf-20210204-050741-ba54o-meta.warc.gz	32060	download job
www.degiro.fi-inf-20210204-050741-ba54o-meta.warc.os.cdx.gz	47	download
www.degiro.fi-inf-20210204-050741-ba54o.json	238	download job
www.degiro.gr-inf-20210204-043431-7h6i2-00000.warc.gz	105694963	download job
www.degiro.gr-inf-20210204-043431-7h6i2-00000.warc.os.cdx.gz	48707	download
www.degiro.gr-inf-20210204-043431-7h6i2-meta.warc.gz	32044	download job
www.degiro.gr-inf-20210204-043431-7h6i2-meta.warc.os.cdx.gz	47	download
www.degiro.gr-inf-20210204-043431-7h6i2.json	238	download job
www.degiro.hu-inf-20210204-050433-7y2sw-00000.warc.gz	90465780	download job
www.degiro.hu-inf-20210204-050433-7y2sw-00000.warc.os.cdx.gz	37116	download
www.degiro.hu-inf-20210204-050433-7y2sw-meta.warc.gz	25627	download job
www.degiro.hu-inf-20210204-050433-7y2sw-meta.warc.os.cdx.gz	47	download
www.degiro.hu-inf-20210204-050433-7y2sw.json	238	download job
www.degiro.ie-inf-20210204-043722-67ur5-00000.warc.gz	167055657	download job
www.degiro.ie-inf-20210204-043722-67ur5-00000.warc.os.cdx.gz	60621	download
www.degiro.ie-inf-20210204-043722-67ur5-meta.warc.gz	39648	download job
www.degiro.ie-inf-20210204-043722-67ur5-meta.warc.os.cdx.gz	47	download
www.degiro.ie-inf-20210204-043722-67ur5.json	238	download job
www.degiro.nl-inf-20210204-045253-74y59-00000.warc.gz	266041713	download job
www.degiro.nl-inf-20210204-045253-74y59-00000.warc.os.cdx.gz	122348	download
www.degiro.nl-inf-20210204-045253-74y59-meta.warc.gz	73156	download job
www.degiro.nl-inf-20210204-045253-74y59-meta.warc.os.cdx.gz	47	download
www.degiro.nl-inf-20210204-045253-74y59.json	238	download job
www.degiro.pl-inf-20210204-041900-5hfjj-00000.warc.gz	101672053	download job
www.degiro.pl-inf-20210204-041900-5hfjj-00000.warc.os.cdx.gz	46573	download
www.degiro.pl-inf-20210204-041900-5hfjj-meta.warc.gz	32277	download job
www.degiro.pl-inf-20210204-041900-5hfjj-meta.warc.os.cdx.gz	47	download
www.degiro.pl-inf-20210204-041900-5hfjj.json	238	download job
www.degiro.pt-inf-20210204-042844-c72hl-00000.warc.gz	101069788	download job
www.degiro.pt-inf-20210204-042844-c72hl-00000.warc.os.cdx.gz	45121	download
www.degiro.pt-inf-20210204-042844-c72hl-meta.warc.gz	31292	download job
www.degiro.pt-inf-20210204-042844-c72hl-meta.warc.os.cdx.gz	47	download
www.degiro.pt-inf-20210204-042844-c72hl.json	238	download job
www.legacy.com-shallow-20210204-052327-mddye-00000.warc.gz	608249338	download job
www.legacy.com-shallow-20210204-052327-mddye-00000.warc.os.cdx.gz	66102	download
www.legacy.com-shallow-20210204-052327-mddye-meta.warc.gz	46266	download job
www.legacy.com-shallow-20210204-052327-mddye-meta.warc.os.cdx.gz	47	download
www.legacy.com-shallow-20210204-052327-mddye.json	301	download job
www.mcon-esports.com-inf-20210204-022307-6hlv4-00000.warc.gz	820890920	download job
www.mcon-esports.com-inf-20210204-022307-6hlv4-00000.warc.os.cdx.gz	948474	download
www.moi.gov.mm-inf-20210201-051200-6t0qt-00005.warc.gz	5371684493	download job
www.moi.gov.mm-inf-20210201-051200-6t0qt-00005.warc.os.cdx.gz	2538190	download
www.nytimes.com-shallow-20210204-051419-bjy82-00000.warc.gz	39572125	download job
www.nytimes.com-shallow-20210204-051419-bjy82-00000.warc.os.cdx.gz	43115	download
www.nytimes.com-shallow-20210204-051419-bjy82-meta.warc.gz	40352	download job
www.nytimes.com-shallow-20210204-051419-bjy82-meta.warc.os.cdx.gz	47	download
www.nytimes.com-shallow-20210204-051419-bjy82.json	309	download job
www.seed-solutions.com-inf-20210204-041401-69jwo-00000.warc.gz	12563	download job
www.seed-solutions.com-inf-20210204-041401-69jwo-00000.warc.os.cdx.gz	356	download
www.seed-solutions.com-inf-20210204-041401-69jwo-meta.warc.gz	3814	download job
www.seed-solutions.com-inf-20210204-041401-69jwo-meta.warc.os.cdx.gz	47	download
www.seed-solutions.com-inf-20210204-041401-69jwo.json	251	download job
www.seed-solutions.com-inf-20210204-043550-4kzqr-00000.warc.gz	1569329	download job
www.seed-solutions.com-inf-20210204-043550-4kzqr-00000.warc.os.cdx.gz	10841	download
www.seed-solutions.com-inf-20210204-043550-4kzqr-meta.warc.gz	9435	download job
www.seed-solutions.com-inf-20210204-043550-4kzqr-meta.warc.os.cdx.gz	47	download
www.seed-solutions.com-inf-20210204-043550-4kzqr.json	260	download job
www.uqac.ca-inf-20210203-100222-c3tlx-00001.warc.gz	5371513670	download job
www.uqac.ca-inf-20210203-100222-c3tlx-00001.warc.os.cdx.gz	3862874	download