Item archiveteam_archivebot_go_20200827070001

Filename	Size
archiv.emkk.hu-inf-20200827-013435-5vtu6-00000.warc.gz	1566859163	download job
archiv.emkk.hu-inf-20200827-013435-5vtu6-00000.warc.os.cdx.gz	543676	download
archiv.emkk.hu-inf-20200827-013435-5vtu6-meta.warc.gz	325089	download job
archiv.emkk.hu-inf-20200827-013435-5vtu6-meta.warc.os.cdx.gz	47	download
archiv.emkk.hu-inf-20200827-013435-5vtu6.json	244	download job
archiv.knykk.hu-inf-20200827-013715-1jtkd-00000.warc.gz	648810932	download job
archiv.knykk.hu-inf-20200827-013715-1jtkd-00000.warc.os.cdx.gz	548735	download
archiv.knykk.hu-inf-20200827-013715-1jtkd-meta.warc.gz	351482	download job
archiv.knykk.hu-inf-20200827-013715-1jtkd-meta.warc.os.cdx.gz	47	download
archiv.knykk.hu-inf-20200827-013715-1jtkd.json	245	download job
archiveteam_archivebot_go_20200827070001.cdx.gz	91153455	download
archiveteam_archivebot_go_20200827070001.cdx.idx	102592	download
archiveteam_archivebot_go_20200827070001_files.xml	0	download
archiveteam_archivebot_go_20200827070001_meta.sqlite	225280	download
archiveteam_archivebot_go_20200827070001_meta.xml	969	download
big5.xinhuanet.com-inf-20200804-144727-f0ved-00062.warc.gz	5368711540	download job
big5.xinhuanet.com-inf-20200804-144727-f0ved-00062.warc.os.cdx.gz	2155552	download
bobjinx.blogspot.com-inf-20200826-235426-ccopk-00000.warc.gz	2958556004	download job
bobjinx.blogspot.com-inf-20200826-235426-ccopk-00000.warc.os.cdx.gz	3656174	download
bobjinx.blogspot.com-inf-20200826-235426-ccopk-meta.warc.gz	2547394	download job
bobjinx.blogspot.com-inf-20200826-235426-ccopk-meta.warc.os.cdx.gz	47	download
bobjinx.blogspot.com-inf-20200826-235426-ccopk.json	245	download job
brontisorengo.blogspot.com-inf-20200827-054755-7titr-00000.warc.gz	14009922	download job
brontisorengo.blogspot.com-inf-20200827-054755-7titr-00000.warc.os.cdx.gz	44179	download
brontisorengo.blogspot.com-inf-20200827-054755-7titr-meta.warc.gz	32897	download job
brontisorengo.blogspot.com-inf-20200827-054755-7titr-meta.warc.os.cdx.gz	47	download
brontisorengo.blogspot.com-inf-20200827-054755-7titr.json	251	download job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00030.warc.gz	5842195856	download job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00030.warc.os.cdx.gz	4853897	download
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00031.warc.gz	5853097096	download job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00031.warc.os.cdx.gz	20232	download
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00032.warc.gz	5408397211	download job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00032.warc.os.cdx.gz	19318	download
classroommagic.blogspot.com-inf-20200826-220529-1a403-meta.warc.gz	15634566	download job
classroommagic.blogspot.com-inf-20200826-220529-1a403-meta.warc.os.cdx.gz	47	download
digi230project.blogspot.com-inf-20200827-031340-erdiw-00000.warc.gz	50425824	download job
digi230project.blogspot.com-inf-20200827-031340-erdiw-00000.warc.os.cdx.gz	109806	download
docs.microsoft.com-inf-20200719-173331-ex56m-00327.warc.gz	5687476925	download job
docs.microsoft.com-inf-20200719-173331-ex56m-00327.warc.os.cdx.gz	174125	download
earfulofemelia.blogspot.com-inf-20200827-031805-1nrtm.json	252	download job
flameslayer93.blogspot.com-inf-20200827-053930-1jsa4-00000.warc.gz	141937025	download job
flameslayer93.blogspot.com-inf-20200827-053930-1jsa4-00000.warc.os.cdx.gz	275984	download
flameslayer93.blogspot.com-inf-20200827-053930-1jsa4-meta.warc.gz	209425	download job
flameslayer93.blogspot.com-inf-20200827-053930-1jsa4-meta.warc.os.cdx.gz	47	download
flameslayer93.blogspot.com-inf-20200827-053930-1jsa4.json	251	download job
fyzika.borec.cz-inf-20200827-030808-994k6.json	245	download job
gadgetinsane2.blogspot.com-inf-20200827-052015-75yvg-00000.warc.gz	191005654	download job
gadgetinsane2.blogspot.com-inf-20200827-052015-75yvg-00000.warc.os.cdx.gz	330048	download
gadgetinsane2.blogspot.com-inf-20200827-052015-75yvg-meta.warc.gz	247954	download job
gadgetinsane2.blogspot.com-inf-20200827-052015-75yvg-meta.warc.os.cdx.gz	47	download
gadgetinsane2.blogspot.com-inf-20200827-052015-75yvg.json	251	download job
gingernibbles.blogspot.com-inf-20200827-052547-6o6pw-00000.warc.gz	96755722	download job
gingernibbles.blogspot.com-inf-20200827-052547-6o6pw-00000.warc.os.cdx.gz	219401	download
gingernibbles.blogspot.com-inf-20200827-052547-6o6pw-meta.warc.gz	153519	download job
gingernibbles.blogspot.com-inf-20200827-052547-6o6pw-meta.warc.os.cdx.gz	47	download
gingernibbles.blogspot.com-inf-20200827-052547-6o6pw.json	251	download job
github.com-inf-20200827-055449-dyg19-00000.warc.gz	133742920	download job
github.com-inf-20200827-055449-dyg19-00000.warc.os.cdx.gz	130139	download
github.com-inf-20200827-055449-dyg19-meta.warc.gz	109493	download job
github.com-inf-20200827-055449-dyg19-meta.warc.os.cdx.gz	47	download
gomel.gov.by-inf-20200823-035616-euc6j-00001.warc.gz	5368949524	download job
gomel.gov.by-inf-20200823-035616-euc6j-00001.warc.os.cdx.gz	6388821	download
horizonwebref.blogspot.com-inf-20200827-033527-4ueth-00000.warc.gz	9329448	download job
horizonwebref.blogspot.com-inf-20200827-033527-4ueth-00000.warc.os.cdx.gz	35675	download
index.hu-inf-20200725-012829-8goer-00082.warc.gz	5368845685	download job
index.hu-inf-20200725-012829-8goer-00082.warc.os.cdx.gz	2523271	download
klenthingungu.blogspot.com-inf-20200827-054228-7f3ie-00000.warc.gz	104183046	download job
klenthingungu.blogspot.com-inf-20200827-054228-7f3ie-00000.warc.os.cdx.gz	170767	download
klenthingungu.blogspot.com-inf-20200827-054228-7f3ie-meta.warc.gz	133624	download job
klenthingungu.blogspot.com-inf-20200827-054228-7f3ie-meta.warc.os.cdx.gz	47	download
klenthingungu.blogspot.com-inf-20200827-054228-7f3ie.json	251	download job
neptoonstudios.blogspot.com-inf-20200827-031924-b16kf-00000.warc.gz	911199455	download job
neptoonstudios.blogspot.com-inf-20200827-031924-b16kf-00000.warc.os.cdx.gz	1525822	download
neptoonstudios.blogspot.com-inf-20200827-031924-b16kf-meta.warc.gz	1118443	download job
neptoonstudios.blogspot.com-inf-20200827-031924-b16kf-meta.warc.os.cdx.gz	47	download
neptoonstudios.blogspot.com-inf-20200827-031924-b16kf.json	252	download job
pauloviveiros.blogspot.com-inf-20200827-052019-8068p-00000.warc.gz	145730878	download job
pauloviveiros.blogspot.com-inf-20200827-052019-8068p-00000.warc.os.cdx.gz	258879	download
pauloviveiros.blogspot.com-inf-20200827-052019-8068p-meta.warc.gz	196646	download job
pauloviveiros.blogspot.com-inf-20200827-052019-8068p-meta.warc.os.cdx.gz	47	download
pauloviveiros.blogspot.com-inf-20200827-052019-8068p.json	251	download job
phone.ceu.edu-inf-20200827-030008-eli5s-00000.warc.gz	2466	download job
phone.ceu.edu-inf-20200827-030008-eli5s-00000.warc.os.cdx.gz	47	download
roguedjackflash.blogspot.com-inf-20200827-055455-97vec-00000.warc.gz	13641389	download job
roguedjackflash.blogspot.com-inf-20200827-055455-97vec-00000.warc.os.cdx.gz	43619	download
roguedjackflash.blogspot.com-inf-20200827-055455-97vec-meta.warc.gz	33576	download job
roguedjackflash.blogspot.com-inf-20200827-055455-97vec-meta.warc.os.cdx.gz	47	download
roguedjackflash.blogspot.com-inf-20200827-055455-97vec.json	253	download job
roguesurvivor.clan.su-inf-20200827-055504-f0zpi-meta.warc.gz	142859	download job
roguesurvivor.clan.su-inf-20200827-055504-f0zpi-meta.warc.os.cdx.gz	47	download
seahunter2010.blogspot.com-inf-20200827-054801-e04vu-00000.warc.gz	26661374	download job
seahunter2010.blogspot.com-inf-20200827-054801-e04vu-00000.warc.os.cdx.gz	49356	download
seahunter2010.blogspot.com-inf-20200827-054801-e04vu-meta.warc.gz	43172	download job
seahunter2010.blogspot.com-inf-20200827-054801-e04vu-meta.warc.os.cdx.gz	47	download
seahunter2010.blogspot.com-inf-20200827-054801-e04vu.json	251	download job
shaunbebbington.blogspot.com-inf-20200827-052316-7ut0e-00000.warc.gz	664567768	download job
shaunbebbington.blogspot.com-inf-20200827-052316-7ut0e-00000.warc.os.cdx.gz	234961	download
shaunbebbington.blogspot.com-inf-20200827-052316-7ut0e-meta.warc.gz	188948	download job
shaunbebbington.blogspot.com-inf-20200827-052316-7ut0e-meta.warc.os.cdx.gz	47	download
shaunbebbington.blogspot.com-inf-20200827-052316-7ut0e.json	253	download job
springboardmedia.blogspot.com-inf-20200826-214639-8wqn9-00002.warc.gz	6045126115	download job
springboardmedia.blogspot.com-inf-20200826-214639-8wqn9-00002.warc.os.cdx.gz	1655476	download
springboardmedia.blogspot.com-inf-20200826-214639-8wqn9-00003.warc.gz	1154983755	download job
springboardmedia.blogspot.com-inf-20200826-214639-8wqn9-00003.warc.os.cdx.gz	3950	download
springboardmedia.blogspot.com-inf-20200826-214639-8wqn9-meta.warc.gz	3820329	download job
springboardmedia.blogspot.com-inf-20200826-214639-8wqn9-meta.warc.os.cdx.gz	47	download
springboardmedia.blogspot.com-inf-20200826-214639-8wqn9.json	254	download job
stevengoddard.wordpress.com-inf-20200821-072627-35jh0-00045.warc.gz	5368709499	download job
stevengoddard.wordpress.com-inf-20200821-072627-35jh0-00045.warc.os.cdx.gz	3265975	download
supportyourlocalwhiteboy.com-inf-20200827-031436-33mrq.json	258	download job
thebatshatters.blogspot.com-inf-20200827-033534-8bibm-00000.warc.gz	5369403911	download job
thebatshatters.blogspot.com-inf-20200827-033534-8bibm-00000.warc.os.cdx.gz	1474297	download
thebatshatters.blogspot.com-inf-20200827-033534-8bibm-00001.warc.gz	2020140747	download job
thebatshatters.blogspot.com-inf-20200827-033534-8bibm-00001.warc.os.cdx.gz	665130	download
thebatshatters.blogspot.com-inf-20200827-033534-8bibm-meta.warc.gz	1498461	download job
thebatshatters.blogspot.com-inf-20200827-033534-8bibm-meta.warc.os.cdx.gz	47	download
thebatshatters.blogspot.com-inf-20200827-033534-8bibm.json	252	download job
thetriangleoffense.blogspot.com-inf-20200826-215029-6yadf-00000.warc.gz	828949776	download job
thetriangleoffense.blogspot.com-inf-20200826-215029-6yadf-00000.warc.os.cdx.gz	760687	download
thetriangleoffense.blogspot.com-inf-20200826-215029-6yadf-meta.warc.gz	509392	download job
thetriangleoffense.blogspot.com-inf-20200826-215029-6yadf-meta.warc.os.cdx.gz	47	download
thetriangleoffense.blogspot.com-inf-20200826-215029-6yadf.json	256	download job
thetwilightjen.blogspot.com-inf-20200827-031314-e08ew-00000.warc.gz	1579461045	download job
thetwilightjen.blogspot.com-inf-20200827-031314-e08ew-00000.warc.os.cdx.gz	3584418	download
thetwilightjen.blogspot.com-inf-20200827-031314-e08ew-meta.warc.gz	2195147	download job
thetwilightjen.blogspot.com-inf-20200827-031314-e08ew-meta.warc.os.cdx.gz	47	download
thetwilightjen.blogspot.com-inf-20200827-031314-e08ew.json	252	download job
thevintageera.blogspot.com-inf-20200827-054222-5zi7i-00000.warc.gz	21962982	download job
thevintageera.blogspot.com-inf-20200827-054222-5zi7i-00000.warc.os.cdx.gz	41812	download
thevintageera.blogspot.com-inf-20200827-054222-5zi7i-meta.warc.gz	33689	download job
thevintageera.blogspot.com-inf-20200827-054222-5zi7i-meta.warc.os.cdx.gz	47	download
thevintageera.blogspot.com-inf-20200827-054222-5zi7i.json	251	download job
thewordnerds.wordpress.com-inf-20200826-231623-79qo8-00007.warc.gz	5369542925	download job
thewordnerds.wordpress.com-inf-20200826-231623-79qo8-00007.warc.os.cdx.gz	2223578	download
tododetuidolo.blogspot.com-inf-20200826-215627-3qm2b-00000.warc.gz	998153553	download job
tododetuidolo.blogspot.com-inf-20200826-215627-3qm2b-00000.warc.os.cdx.gz	1068374	download
tododetuidolo.blogspot.com-inf-20200826-215627-3qm2b-meta.warc.gz	831276	download job
tododetuidolo.blogspot.com-inf-20200826-215627-3qm2b-meta.warc.os.cdx.gz	47	download
tododetuidolo.blogspot.com-inf-20200826-215627-3qm2b.json	251	download job
transfer.notkiska.pw-shallow-20200827-055902-7n6a9-00000.warc.gz	533597	download job
transfer.notkiska.pw-shallow-20200827-055902-7n6a9-00000.warc.os.cdx.gz	242	download
transfer.notkiska.pw-shallow-20200827-055902-7n6a9-meta.warc.gz	3535	download job
transfer.notkiska.pw-shallow-20200827-055902-7n6a9-meta.warc.os.cdx.gz	47	download
transfer.notkiska.pw-shallow-20200827-055902-7n6a9.json	280	download job
transfer.notkiska.pw-shallow-20200827-055908-7mnjl-00000.warc.gz	525353	download job
transfer.notkiska.pw-shallow-20200827-055908-7mnjl-00000.warc.os.cdx.gz	239	download
transfer.notkiska.pw-shallow-20200827-055908-7mnjl-meta.warc.gz	3539	download job
transfer.notkiska.pw-shallow-20200827-055908-7mnjl-meta.warc.os.cdx.gz	47	download
transfer.notkiska.pw-shallow-20200827-055908-7mnjl.json	280	download job
urls-transfer.notkiska.pw-facebook-@PoliticalScienceDepartment-shallow-20200827-040415-b2kmq-meta.warc.gz	1704729	download job
urls-transfer.notkiska.pw-facebook-@PoliticalScienceDepartment-shallow-20200827-040415-b2kmq-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@PoliticalScienceDepartment-shallow-20200827-040415-b2kmq-urls.txt	208061	download
urls-transfer.notkiska.pw-facebook-@PoliticalScienceDepartment-shallow-20200827-040415-b2kmq.json	366	download job
urls-transfer.notkiska.pw-facebook-@jacindaardern-shallow-20200827-013621-f05xl-00000.warc.gz	1724310435	download job
urls-transfer.notkiska.pw-facebook-@jacindaardern-shallow-20200827-013621-f05xl-00000.warc.os.cdx.gz	1230434	download
urls-transfer.notkiska.pw-facebook-@polbergceu-shallow-20200827-030426-55qk5-urls.txt	22636	download
urls-transfer.notkiska.pw-github.com-servo-inf-20200813-042451-1cn5u-00007.warc.gz	5373579555	download job
urls-transfer.notkiska.pw-github.com-servo-inf-20200813-042451-1cn5u-00007.warc.os.cdx.gz	2552999	download
urls-transfer.notkiska.pw-rootsweb-lists-inf-20200109-032010-1m71j-00051.warc.gz	5384193973	download job
urls-transfer.notkiska.pw-rootsweb-lists-inf-20200109-032010-1m71j-00051.warc.os.cdx.gz	12973977	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00323.warc.gz	5391023169	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00323.warc.os.cdx.gz	286795	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00324.warc.gz	6019463290	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00324.warc.os.cdx.gz	250826	download
urls-transfer.notkiska.pw-twitter-%23DNCConvention-shallow-20200825-141621-10hd0-00023.warc.gz	5406168945	download job
urls-transfer.notkiska.pw-twitter-%23DNCConvention-shallow-20200825-141621-10hd0-00023.warc.os.cdx.gz	2418837	download
urls-transfer.notkiska.pw-twitter-%23istandwithceu-shallow-20200826-205856-9uz80-00000.warc.gz	5371074870	download job
urls-transfer.notkiska.pw-twitter-%23istandwithceu-shallow-20200826-205856-9uz80-00000.warc.os.cdx.gz	6079893	download
urls-transfer.notkiska.pw-twitter-%23istandwithceu-shallow-20200826-205856-9uz80-00001.warc.gz	5378985957	download job
urls-transfer.notkiska.pw-twitter-%23istandwithceu-shallow-20200826-205856-9uz80-00001.warc.os.cdx.gz	960445	download
urls-transfer.notkiska.pw-twitter-@CEUpolsci-shallow-20200827-040158-dn72f-00000.warc.gz	782497595	download job
urls-transfer.notkiska.pw-twitter-@CEUpolsci-shallow-20200827-040158-dn72f-00000.warc.os.cdx.gz	1452202	download
urls-transfer.notkiska.pw-twitter-@CEUpolsci-shallow-20200827-040158-dn72f-meta.warc.gz	882711	download job
urls-transfer.notkiska.pw-twitter-@CEUpolsci-shallow-20200827-040158-dn72f-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@CEUpolsci-shallow-20200827-040158-dn72f-urls.txt	81138	download
urls-transfer.notkiska.pw-twitter-@CEUpolsci-shallow-20200827-040158-dn72f.json	330	download job
urls-transfer.notkiska.pw-twitter-@CSSCGC2018-shallow-20200827-052325-a0ema-00000.warc.gz	61026939	download job
urls-transfer.notkiska.pw-twitter-@CSSCGC2018-shallow-20200827-052325-a0ema-00000.warc.os.cdx.gz	113647	download
urls-transfer.notkiska.pw-twitter-@CSSCGC2018-shallow-20200827-052325-a0ema-meta.warc.gz	72464	download job
urls-transfer.notkiska.pw-twitter-@CSSCGC2018-shallow-20200827-052325-a0ema-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@CSSCGC2018-shallow-20200827-052325-a0ema-urls.txt	24788	download
urls-transfer.notkiska.pw-twitter-@CSSCGC2018-shallow-20200827-052325-a0ema.json	332	download job
urls-transfer.notkiska.pw-twitter-@a_krueger-shallow-20200827-033601-a9izf-00000.warc.gz	5455532051	download job
urls-transfer.notkiska.pw-twitter-@a_krueger-shallow-20200827-033601-a9izf-00000.warc.os.cdx.gz	623551	download
urls-transfer.notkiska.pw-twitter-@a_krueger-shallow-20200827-033601-a9izf-urls.txt	183749	download
urls-transfer.notkiska.pw-twitter-@a_krueger-shallow-20200827-033601-a9izf.json	330	download job
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr-00018.warc.gz	5601683656	download job
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr-00018.warc.os.cdx.gz	4797908	download
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr-00019.warc.gz	2527	download job
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr-00019.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr-meta.warc.gz	16624155	download job
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr-urls.txt	2446737	download
urls-transfer.notkiska.pw-twitter-@shaunking-shallow-20200826-092757-sgssr.json	330	download job
urls-transfer.notkiska.pw-twitter-@thebatshatters-shallow-20200827-033705-87rmy-00000.warc.gz	5917222138	download job
urls-transfer.notkiska.pw-twitter-@thebatshatters-shallow-20200827-033705-87rmy-00000.warc.os.cdx.gz	1472838	download
urls-transfer.notkiska.pw-twitter-@tsm_26-shallow-20200827-033631-60cik-00000.warc.gz	5372543680	download job
urls-transfer.notkiska.pw-twitter-@tsm_26-shallow-20200827-033631-60cik-00000.warc.os.cdx.gz	1085262	download
urls-transfer.notkiska.pw-twitter-@tsm_26-shallow-20200827-033631-60cik-00001.warc.gz	5751883770	download job
urls-transfer.notkiska.pw-twitter-@tsm_26-shallow-20200827-033631-60cik-00001.warc.os.cdx.gz	512355	download
urls-transfer.notkiska.pw-twitter-@tsm_26-shallow-20200827-033631-60cik-00002.warc.gz	5436873584	download job
urls-transfer.notkiska.pw-twitter-@tsm_26-shallow-20200827-033631-60cik-00002.warc.os.cdx.gz	477035	download
www.crwflags.com-inf-20200822-154640-ig4vc-00005.warc.gz	5376645083	download job
www.crwflags.com-inf-20200822-154640-ig4vc-00005.warc.os.cdx.gz	2820861	download
www.mediafire.com-inf-20200827-055345-axmbh-00000.warc.gz	72472963	download job
www.mediafire.com-inf-20200827-055345-axmbh-00000.warc.os.cdx.gz	48367	download
www.mediafire.com-inf-20200827-055345-axmbh-meta.warc.gz	29851	download job
www.mediafire.com-inf-20200827-055345-axmbh-meta.warc.os.cdx.gz	47	download
www.mediafire.com-inf-20200827-055345-axmbh.json	261	download job
www.mediafire.com-inf-20200827-055413-8oqaz-00000.warc.gz	73620035	download job
www.mediafire.com-inf-20200827-055413-8oqaz-00000.warc.os.cdx.gz	48314	download
www.mediafire.com-inf-20200827-055413-8oqaz-meta.warc.gz	29963	download job
www.mediafire.com-inf-20200827-055413-8oqaz-meta.warc.os.cdx.gz	47	download
www.mediafire.com-inf-20200827-055413-8oqaz.json	261	download job
www.oocities.org-inf-20200827-031827-chrwu.json	267	download job
www.qiagen.com-inf-20200621-061202-1wax4-00102.warc.gz	5368732233	download job
www.qiagen.com-inf-20200621-061202-1wax4-00102.warc.os.cdx.gz	16206146	download