Item archiveteam_archivebot_go_20200731210002

Filename	Size
archiveteam_archivebot_go_20200731210002.cdx.gz	51804266	download
archiveteam_archivebot_go_20200731210002.cdx.idx	48003	download
archiveteam_archivebot_go_20200731210002_files.xml	0	download
archiveteam_archivebot_go_20200731210002_meta.sqlite	229376	download
archiveteam_archivebot_go_20200731210002_meta.xml	968	download
big5.cri.cn-inf-20200719-230814-2nxf5-00092.warc.gz	5369236938	download job
big5.cri.cn-inf-20200719-230814-2nxf5-00092.warc.os.cdx.gz	4195508	download
c64.tin.at-inf-20200731-195615-9tagn-00000.warc.gz	81500695	download job
c64.tin.at-inf-20200731-195615-9tagn-00000.warc.os.cdx.gz	83520	download
c64.tin.at-inf-20200731-195615-9tagn.json	234	download job
claraschumann.de-inf-20200731-201841-13xlp-00000.warc.gz	9130387	download job
claraschumann.de-inf-20200731-201841-13xlp-00000.warc.os.cdx.gz	43623	download
claraschumann.de-inf-20200731-201841-13xlp-meta.warc.gz	30306	download job
claraschumann.de-inf-20200731-201841-13xlp-meta.warc.os.cdx.gz	47	download
claraschumann.de-inf-20200731-201841-13xlp.json	240	download job
hermancain.com-inf-20200730-152518-c0go0-00016.warc.gz	5372129193	download job
hermancain.com-inf-20200730-152518-c0go0-00016.warc.os.cdx.gz	1031574	download
investors.noblecorp.com-inf-20200731-174222-bgzjg-00000.warc.gz	575613500	download job
investors.noblecorp.com-inf-20200731-174222-bgzjg-00000.warc.os.cdx.gz	735643	download
investors.noblecorp.com-inf-20200731-174222-bgzjg-meta.warc.gz	427406	download job
investors.noblecorp.com-inf-20200731-174222-bgzjg-meta.warc.os.cdx.gz	47	download
korean.cri.cn-inf-20200730-001225-7iv4z-00020.warc.gz	5388124582	download job
korean.cri.cn-inf-20200730-001225-7iv4z-00020.warc.os.cdx.gz	25636	download
korean.cri.cn-inf-20200730-001225-7iv4z-00021.warc.gz	5382163548	download job
korean.cri.cn-inf-20200730-001225-7iv4z-00021.warc.os.cdx.gz	21450	download
korean.cri.cn-inf-20200730-001225-7iv4z-00022.warc.gz	5374179495	download job
korean.cri.cn-inf-20200730-001225-7iv4z-00022.warc.os.cdx.gz	12324	download
mleguludec.free.fr-inf-20200731-201003-9epx1-meta.warc.gz	301337	download job
mleguludec.free.fr-inf-20200731-201003-9epx1-meta.warc.os.cdx.gz	47	download
mleguludec.free.fr-inf-20200731-201003-9epx1.json	249	download job
news.cri.cn-inf-20200730-220446-994q6-00017.warc.gz	5383687430	download job
news.cri.cn-inf-20200730-220446-994q6-00017.warc.os.cdx.gz	1229081	download
news.cri.cn-inf-20200730-220446-994q6-00018.warc.gz	5368747611	download job
news.cri.cn-inf-20200730-220446-994q6-00018.warc.os.cdx.gz	1250965	download
newsradio.cri.cn-inf-20200731-024107-7umup-00010.warc.gz	5374745291	download job
newsradio.cri.cn-inf-20200731-024107-7umup-00010.warc.os.cdx.gz	47579	download
opcfg.kontek.net-inf-20200731-190556-a4k36-00000.warc.gz	1764402095	download job
opcfg.kontek.net-inf-20200731-190556-a4k36-00000.warc.os.cdx.gz	314119	download
opcfg.kontek.net-inf-20200731-190556-a4k36-meta.warc.gz	197847	download job
opcfg.kontek.net-inf-20200731-190556-a4k36-meta.warc.os.cdx.gz	47	download
opcfg.kontek.net-inf-20200731-190556-a4k36.json	247	download job
patiopizzastjames.com-inf-20200731-194642-59vfe-00000.warc.gz	97669815	download job
patiopizzastjames.com-inf-20200731-194642-59vfe-00000.warc.os.cdx.gz	185855	download
patiopizzastjames.com-inf-20200731-194642-59vfe-meta.warc.gz	119426	download job
patiopizzastjames.com-inf-20200731-194642-59vfe-meta.warc.os.cdx.gz	47	download
patiopizzastjames.com-inf-20200731-194642-59vfe.json	250	download job
persian.cri.cn-inf-20200731-163351-621lz-00001.warc.gz	5439215436	download job
persian.cri.cn-inf-20200731-163351-621lz-00001.warc.os.cdx.gz	642498	download
persian.cri.cn-inf-20200731-163351-621lz-00002.warc.gz	5450368258	download job
persian.cri.cn-inf-20200731-163351-621lz-00002.warc.os.cdx.gz	7629	download
persian.cri.cn-inf-20200731-163351-621lz-00003.warc.gz	5369614796	download job
persian.cri.cn-inf-20200731-163351-621lz-00003.warc.os.cdx.gz	1233198	download
persian.cri.cn-inf-20200731-163351-621lz-00004.warc.gz	3381322814	download job
persian.cri.cn-inf-20200731-163351-621lz-00004.warc.os.cdx.gz	2483945	download
persian.cri.cn-inf-20200731-163351-621lz-meta.warc.gz	2968139	download job
persian.cri.cn-inf-20200731-163351-621lz-meta.warc.os.cdx.gz	47	download
persian.cri.cn-inf-20200731-163351-621lz.json	243	download job
ratical.org-inf-20200731-183959-bfnol-00000.warc.gz	5382553460	download job
ratical.org-inf-20200731-183959-bfnol-00000.warc.os.cdx.gz	1147434	download
sdicks.free.fr-inf-20200731-200618-bxyaw-00000.warc.gz	54905678	download job
sdicks.free.fr-inf-20200731-200618-bxyaw-00000.warc.os.cdx.gz	154007	download
sdicks.free.fr-inf-20200731-200618-bxyaw-meta.warc.gz	85512	download job
sdicks.free.fr-inf-20200731-200618-bxyaw-meta.warc.os.cdx.gz	47	download
sdicks.free.fr-inf-20200731-200618-bxyaw.json	238	download job
thevirustracker.com-inf-20200620-170113-b912c-00044.warc.gz	5368957660	download job
thevirustracker.com-inf-20200620-170113-b912c-00044.warc.os.cdx.gz	6011526	download
urls-transfer.notkiska.pw-facebook-@PatioPizza-shallow-20200731-194832-ctdim-00000.warc.gz	67770323	download job
urls-transfer.notkiska.pw-facebook-@PatioPizza-shallow-20200731-194832-ctdim-00000.warc.os.cdx.gz	126249	download
urls-transfer.notkiska.pw-facebook-@PatioPizza-shallow-20200731-194832-ctdim-meta.warc.gz	72923	download job
urls-transfer.notkiska.pw-facebook-@PatioPizza-shallow-20200731-194832-ctdim-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@PatioPizza-shallow-20200731-194832-ctdim-urls.txt	32566	download
urls-transfer.notkiska.pw-facebook-@PatioPizza-shallow-20200731-194832-ctdim.json	334	download job
urls-transfer.notkiska.pw-facebook-@claraschumannmusician-shallow-20200731-201905-d638b-00000.warc.gz	73438227	download job
urls-transfer.notkiska.pw-facebook-@claraschumannmusician-shallow-20200731-201905-d638b-00000.warc.os.cdx.gz	109759	download
urls-transfer.notkiska.pw-facebook-@claraschumannmusician-shallow-20200731-201905-d638b-meta.warc.gz	67498	download job
urls-transfer.notkiska.pw-facebook-@claraschumannmusician-shallow-20200731-201905-d638b-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@claraschumannmusician-shallow-20200731-201905-d638b.json	356	download job
urls-transfer.notkiska.pw-facebook-@swvlapp-shallow-20200731-174720-24eny-00000.warc.gz	117543150	download job
urls-transfer.notkiska.pw-facebook-@swvlapp-shallow-20200731-174720-24eny-00000.warc.os.cdx.gz	190422	download
urls-transfer.notkiska.pw-facebook-@swvlapp-shallow-20200731-174720-24eny-meta.warc.gz	119781	download job
urls-transfer.notkiska.pw-facebook-@swvlapp-shallow-20200731-174720-24eny-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@swvlapp-shallow-20200731-174720-24eny.json	328	download job
urls-transfer.notkiska.pw-facebook-@timcastnews-shallow-20200731-140953-2enj0-00001.warc.gz	26384617	download job
urls-transfer.notkiska.pw-facebook-@timcastnews-shallow-20200731-140953-2enj0-00001.warc.os.cdx.gz	81109	download
urls-transfer.notkiska.pw-facebook-@timcastnews-shallow-20200731-140953-2enj0-urls.txt	235605	download
urls-transfer.notkiska.pw-facebook-@timcastnews-shallow-20200731-140953-2enj0.json	336	download job
urls-transfer.notkiska.pw-facebook-@virtualcaveman-shallow-20200731-190654-7jbzp-00000.warc.gz	807855978	download job
urls-transfer.notkiska.pw-facebook-@virtualcaveman-shallow-20200731-190654-7jbzp-00000.warc.os.cdx.gz	616477	download
urls-transfer.notkiska.pw-facebook-@virtualcaveman-shallow-20200731-190654-7jbzp-meta.warc.gz	385441	download job
urls-transfer.notkiska.pw-facebook-@virtualcaveman-shallow-20200731-190654-7jbzp-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@virtualcaveman-shallow-20200731-190654-7jbzp-urls.txt	40117	download
urls-transfer.notkiska.pw-facebook-@virtualcaveman-shallow-20200731-190654-7jbzp.json	342	download job
urls-transfer.notkiska.pw-rootsweb-lists-inf-20200109-032010-1m71j-00037.warc.gz	5385936615	download job
urls-transfer.notkiska.pw-rootsweb-lists-inf-20200109-032010-1m71j-00037.warc.os.cdx.gz	1591586	download
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00338.warc.gz	5391071605	download job
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00338.warc.os.cdx.gz	735194	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00135.warc.gz	5514614695	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00135.warc.os.cdx.gz	1003144	download
urls-transfer.notkiska.pw-twitter-%23notmypresident-shallow-20200530-220957-2c0z0-00282.warc.gz	5369648271	download job
urls-transfer.notkiska.pw-twitter-%23notmypresident-shallow-20200530-220957-2c0z0-00282.warc.os.cdx.gz	1480597	download
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00259.warc.gz	6456082629	download job
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00259.warc.os.cdx.gz	1207889	download
urls-transfer.notkiska.pw-twitter-@Arriolus-shallow-20200731-192945-4lrkn-00000.warc.gz	1226851141	download job
urls-transfer.notkiska.pw-twitter-@Arriolus-shallow-20200731-192945-4lrkn-00000.warc.os.cdx.gz	801625	download
urls-transfer.notkiska.pw-twitter-@Arriolus-shallow-20200731-192945-4lrkn-meta.warc.gz	462271	download job
urls-transfer.notkiska.pw-twitter-@Arriolus-shallow-20200731-192945-4lrkn-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@Arriolus-shallow-20200731-192945-4lrkn.json	328	download job
urls-transfer.notkiska.pw-twitter-@BytedanceTalk-shallow-20200731-181805-1xknm-00000.warc.gz	445083627	download job
urls-transfer.notkiska.pw-twitter-@BytedanceTalk-shallow-20200731-181805-1xknm-00000.warc.os.cdx.gz	301994	download
urls-transfer.notkiska.pw-twitter-@BytedanceTalk-shallow-20200731-181805-1xknm-meta.warc.gz	191926	download job
urls-transfer.notkiska.pw-twitter-@BytedanceTalk-shallow-20200731-181805-1xknm-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@BytedanceTalk-shallow-20200731-181805-1xknm-urls.txt	26528	download
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h-00006.warc.gz	5840690354	download job
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h-00006.warc.os.cdx.gz	329104	download
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h-00008.warc.gz	2733118137	download job
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h-00008.warc.os.cdx.gz	1115860	download
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h-meta.warc.gz	5720856	download job
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h-urls.txt	573179	download
urls-transfer.notkiska.pw-twitter-@Timcast-shallow-20200731-140248-18l6h.json	326	download job
urls-transfer.notkiska.pw-twitter-@VirtualCaveman-shallow-20200731-190610-avnc3-00000.warc.gz	213056027	download job
urls-transfer.notkiska.pw-twitter-@VirtualCaveman-shallow-20200731-190610-avnc3-00000.warc.os.cdx.gz	324191	download
urls-transfer.notkiska.pw-twitter-@VirtualCaveman-shallow-20200731-190610-avnc3-meta.warc.gz	194461	download job
urls-transfer.notkiska.pw-twitter-@VirtualCaveman-shallow-20200731-190610-avnc3-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@VirtualCaveman-shallow-20200731-190610-avnc3-urls.txt	49664	download
urls-transfer.notkiska.pw-twitter-@VirtualCaveman-shallow-20200731-190610-avnc3.json	340	download job
urls-transfer.notkiska.pw-twitter-@lanebryant-shallow-20200731-050148-d9cl7-00001.warc.gz	2765894061	download job
urls-transfer.notkiska.pw-twitter-@lanebryant-shallow-20200731-050148-d9cl7-00001.warc.os.cdx.gz	2401791	download
urls-transfer.notkiska.pw-twitter-@lanebryant-shallow-20200731-050148-d9cl7-meta.warc.gz	4930947	download job
urls-transfer.notkiska.pw-twitter-@lanebryant-shallow-20200731-050148-d9cl7-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00018.warc.gz	5431650180	download job
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00018.warc.os.cdx.gz	2208564	download
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00019.warc.gz	5436346141	download job
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00019.warc.os.cdx.gz	1688228	download
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00020.warc.gz	5368713605	download job
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00020.warc.os.cdx.gz	820746	download
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00021.warc.gz	5529628518	download job
urls-transfer.notkiska.pw-twitter-@the_moviebob-shallow-20200730-152334-9d4wz-00021.warc.os.cdx.gz	568173	download
urls-transfer.notkiska.pw-vkontakte-projectgenom-shallow-20200731-183809-25vz5-00000.warc.gz	212127568	download job
urls-transfer.notkiska.pw-vkontakte-projectgenom-shallow-20200731-183809-25vz5-00000.warc.os.cdx.gz	410126	download
urls-transfer.notkiska.pw-vkontakte-projectgenom-shallow-20200731-183809-25vz5-meta.warc.gz	238801	download job
urls-transfer.notkiska.pw-vkontakte-projectgenom-shallow-20200731-183809-25vz5-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-vkontakte-projectgenom-shallow-20200731-183809-25vz5-urls.txt	18584	download
urls-transfer.notkiska.pw-vkontakte-projectgenom-shallow-20200731-183809-25vz5.json	338	download job
urls-transfer.notkiska.pw-yandex-music-by-Nikchemny-1.txt-shallow-20200731-185432-105cz-00000.warc.gz	1279630	download job
urls-transfer.notkiska.pw-yandex-music-by-Nikchemny-1.txt-shallow-20200731-185432-105cz-00000.warc.os.cdx.gz	7072	download
urls-transfer.notkiska.pw-yandex-music-by-Nikchemny-1.txt-shallow-20200731-185432-105cz-meta.warc.gz	7917	download job
urls-transfer.notkiska.pw-yandex-music-by-Nikchemny-1.txt-shallow-20200731-185432-105cz-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-yandex-music-by-Nikchemny-1.txt-shallow-20200731-185432-105cz-urls.txt	157	download
urls-transfer.notkiska.pw-yandex-music-by-Nikchemny-1.txt-shallow-20200731-185432-105cz.json	356	download job
www.blackzeppelinstudio.com-inf-20200731-193109-cugyv-00000.warc.gz	38656154	download job
www.blackzeppelinstudio.com-inf-20200731-193109-cugyv-00000.warc.os.cdx.gz	49950	download
www.blackzeppelinstudio.com-inf-20200731-193109-cugyv-meta.warc.gz	32622	download job
www.blackzeppelinstudio.com-inf-20200731-193109-cugyv-meta.warc.os.cdx.gz	47	download
www.blackzeppelinstudio.com-inf-20200731-193109-cugyv.json	252	download job
www.cc65.org-inf-20200731-181437-56khj-meta.warc.gz	88590	download job
www.cc65.org-inf-20200731-181437-56khj-meta.warc.os.cdx.gz	47	download
www.foxbusiness.com-shallow-20200731-183545-7nygy-00000.warc.gz	10188421	download job
www.foxbusiness.com-shallow-20200731-183545-7nygy-00000.warc.os.cdx.gz	17410	download
www.foxbusiness.com-shallow-20200731-183545-7nygy-meta.warc.gz	12700	download job
www.foxbusiness.com-shallow-20200731-183545-7nygy-meta.warc.os.cdx.gz	47	download
www.freewebs.com-inf-20200731-205053-6izbq-00000.warc.gz	78078906	download job
www.freewebs.com-inf-20200731-205053-6izbq-00000.warc.os.cdx.gz	98462	download
www.freewebs.com-inf-20200731-205053-6izbq-meta.warc.gz	60860	download job
www.freewebs.com-inf-20200731-205053-6izbq-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20200731-193107-csamp-00000.warc.gz	10768744	download job
www.instagram.com-inf-20200731-193107-csamp-00000.warc.os.cdx.gz	24204	download
www.instagram.com-inf-20200731-193107-csamp-meta.warc.gz	20260	download job
www.instagram.com-inf-20200731-193107-csamp-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20200731-193107-csamp.json	262	download job
www.lonelyplanet.com-inf-20200414-172453-73pjj-00106.warc.gz	5371180356	download job
www.lonelyplanet.com-inf-20200414-172453-73pjj-00106.warc.os.cdx.gz	2679293	download
www.luna-art.com-inf-20200731-202910-d9xas-meta.warc.gz	133793	download job
www.luna-art.com-inf-20200731-202910-d9xas-meta.warc.os.cdx.gz	47	download
www.luna-art.com-inf-20200731-202910-d9xas.json	240	download job
www.lunchclock.com-inf-20200731-203148-80kid-00000.warc.gz	41732	download job
www.lunchclock.com-inf-20200731-203148-80kid-00000.warc.os.cdx.gz	678	download
www.lunchclock.com-inf-20200731-203148-80kid-meta.warc.gz	3791	download job
www.lunchclock.com-inf-20200731-203148-80kid-meta.warc.os.cdx.gz	47	download
www.lunchclock.com-inf-20200731-203148-80kid.json	242	download job
www.mystfanart.org-inf-20200731-202533-8jtd5-00000.warc.gz	536728982	download job
www.mystfanart.org-inf-20200731-202533-8jtd5-00000.warc.os.cdx.gz	43776	download
www.mystfanart.org-inf-20200731-202533-8jtd5-meta.warc.gz	29457	download job
www.mystfanart.org-inf-20200731-202533-8jtd5-meta.warc.os.cdx.gz	47	download
www.mystfanart.org-inf-20200731-202533-8jtd5.json	242	download job
www.raspberrypi.org-inf-20200707-192424-bv6p7-00077.warc.gz	5381739506	download job
www.raspberrypi.org-inf-20200707-192424-bv6p7-00077.warc.os.cdx.gz	5197927	download
www.retrorealities.com-inf-20200731-181250-4aeeo-meta.warc.gz	56876	download job
www.retrorealities.com-inf-20200731-181250-4aeeo-meta.warc.os.cdx.gz	47	download
www.retrorealities.com-inf-20200731-181250-4aeeo.json	247	download job
www.shattered-worlds.com-inf-20200731-192910-9ud6h-00000.warc.gz	8146	download job
www.shattered-worlds.com-inf-20200731-192910-9ud6h-00000.warc.os.cdx.gz	47	download
www.shattered-worlds.com-inf-20200731-192910-9ud6h-meta.warc.gz	3646	download job
www.shattered-worlds.com-inf-20200731-192910-9ud6h-meta.warc.os.cdx.gz	47	download
www.shattered-worlds.com-inf-20200731-192910-9ud6h.json	248	download job
www.shattered-worlds.com-inf-20200731-193235-9ud6h-aborted-00000.warc.gz	3536	download job
www.shattered-worlds.com-inf-20200731-193235-9ud6h-aborted-00000.warc.os.cdx.gz	47	download
www.shattered-worlds.com-inf-20200731-193235-9ud6h-aborted-wpull.log.gz	772	download
www.shattered-worlds.com-inf-20200731-193235-9ud6h-aborted.json	247	download job
www.southlakecarroll.edu-shallow-20200731-194952-876hw-00000.warc.gz	587379	download job
www.southlakecarroll.edu-shallow-20200731-194952-876hw-00000.warc.os.cdx.gz	326	download
www.southlakecarroll.edu-shallow-20200731-194952-876hw-meta.warc.gz	3635	download job
www.southlakecarroll.edu-shallow-20200731-194952-876hw-meta.warc.os.cdx.gz	47	download
www.southlakecarroll.edu-shallow-20200731-194952-876hw.json	369	download job
www.spywarewarrior.com-inf-20200731-042306-494ah-00002.warc.gz	5396125694	download job
www.spywarewarrior.com-inf-20200731-042306-494ah-00002.warc.os.cdx.gz	4834471	download
www.tabc.texas.gov-shallow-20200731-180345-willq-00000.warc.gz	114729	download job
www.tabc.texas.gov-shallow-20200731-180345-willq-00000.warc.os.cdx.gz	275	download
www.tabc.texas.gov-shallow-20200731-180345-willq-meta.warc.gz	3546	download job
www.tabc.texas.gov-shallow-20200731-180345-willq-meta.warc.os.cdx.gz	47	download
www.tabc.texas.gov-shallow-20200731-180345-willq.json	312	download job
www.tabc.texas.gov-shallow-20200731-180354-abcqw-00000.warc.gz	114497	download job
www.tabc.texas.gov-shallow-20200731-180354-abcqw-00000.warc.os.cdx.gz	273	download
www.tabc.texas.gov-shallow-20200731-180354-abcqw-meta.warc.gz	3561	download job
www.tabc.texas.gov-shallow-20200731-180354-abcqw-meta.warc.os.cdx.gz	47	download
www.tabc.texas.gov-shallow-20200731-180354-abcqw.json	307	download job
www.udic.org-inf-20200731-192711-c42e9-00000.warc.gz	7422792	download job
www.udic.org-inf-20200731-192711-c42e9-00000.warc.os.cdx.gz	22580	download
www.udic.org-inf-20200731-192711-c42e9-meta.warc.gz	18818	download job
www.udic.org-inf-20200731-192711-c42e9-meta.warc.os.cdx.gz	47	download
www.udic.org-inf-20200731-192711-c42e9.json	236	download job
zuperpunch.blogspot.com-inf-20200727-060426-ezvnv-00031.warc.gz	5379775234	download job
zuperpunch.blogspot.com-inf-20200727-060426-ezvnv-00031.warc.os.cdx.gz	2367623	download