Item archiveteam_archivebot_go_20201110000002

Filename	Size
archiveteam_archivebot_go_20201110000002.cdx.gz	47558451	download
archiveteam_archivebot_go_20201110000002.cdx.idx	51638	download
archiveteam_archivebot_go_20201110000002_files.xml	0	download
archiveteam_archivebot_go_20201110000002_meta.sqlite	305152	download
archiveteam_archivebot_go_20201110000002_meta.xml	969	download
dandriscoll.com-inf-20201109-213235-bs0ku-meta.warc.gz	5531	download job
dandriscoll.com-inf-20201109-213235-bs0ku-meta.warc.os.cdx.gz	47	download
debeshsarkar2020.com-inf-20201109-213125-8urb8-meta.warc.gz	66848	download job
debeshsarkar2020.com-inf-20201109-213125-8urb8-meta.warc.os.cdx.gz	47	download
ethanpbaca.com-inf-20201109-213047-5viwt.json	238	download job
history/files/stevechabot.com-inf-20201109-193129-60l5h-00000.warc.gz.~1~	5320464710	download
jeffmatemu.com-inf-20201109-203941-bjsbn-meta.warc.gz	144571	download job
jeffmatemu.com-inf-20201109-203941-bjsbn-meta.warc.os.cdx.gz	47	download
jeffmatemu.com-inf-20201109-203941-bjsbn.json	239	download job
jennybell2020.us-inf-20201109-202544-4ie1t-00000.warc.gz	488080020	download job
jennybell2020.us-inf-20201109-202544-4ie1t-00000.warc.os.cdx.gz	565125	download
jennybell2020.us-inf-20201109-202544-4ie1t-meta.warc.gz	413202	download job
jennybell2020.us-inf-20201109-202544-4ie1t-meta.warc.os.cdx.gz	47	download
jennybell2020.us-inf-20201109-202544-4ie1t.json	241	download job
lyndaforcongress.com-inf-20201109-212903-4chpo-00000.warc.gz	1434487	download job
lyndaforcongress.com-inf-20201109-212903-4chpo-00000.warc.os.cdx.gz	4774	download
lyndaforcongress.com-inf-20201109-212903-4chpo-meta.warc.gz	6034	download job
lyndaforcongress.com-inf-20201109-212903-4chpo-meta.warc.os.cdx.gz	47	download
mchenryforcongress.com-inf-20201109-212551-aey0j-00000.warc.gz	4745013498	download job
mchenryforcongress.com-inf-20201109-212551-aey0j-00000.warc.os.cdx.gz	311063	download
michelenix.com-inf-20201109-212609-ebt1m-00000.warc.gz	2469	download job
michelenix.com-inf-20201109-212609-ebt1m-00000.warc.os.cdx.gz	47	download
michelenix.com-inf-20201109-212609-ebt1m-meta.warc.gz	3673	download job
michelenix.com-inf-20201109-212609-ebt1m-meta.warc.os.cdx.gz	47	download
morckel4congress.com-inf-20201109-195555-dsn1f-00000.warc.gz	336552285	download job
morckel4congress.com-inf-20201109-195555-dsn1f-00000.warc.os.cdx.gz	1760269	download
morckel4congress.com-inf-20201109-195555-dsn1f-meta.warc.gz	3368077	download job
morckel4congress.com-inf-20201109-195555-dsn1f-meta.warc.os.cdx.gz	47	download
morckel4congress.com-inf-20201109-195555-dsn1f.json	244	download job
murphy4congress.com-inf-20201109-213012-1zzni-00000.warc.gz	92520278	download job
murphy4congress.com-inf-20201109-213012-1zzni-00000.warc.os.cdx.gz	84316	download
nickrubando.com-inf-20201109-201440-9udoi-00000.warc.gz	5606521056	download job
nickrubando.com-inf-20201109-201440-9udoi-00000.warc.os.cdx.gz	351658	download
nickrubando.com-inf-20201109-201440-9udoi-00001.warc.gz	142076	download job
nickrubando.com-inf-20201109-201440-9udoi-00001.warc.os.cdx.gz	1901	download
nickrubando.com-inf-20201109-201440-9udoi.json	240	download job
oldpcgaming.net-inf-20201025-110611-2tc7b-00008.warc.gz	5368776202	download job
oldpcgaming.net-inf-20201025-110611-2tc7b-00008.warc.os.cdx.gz	14239471	download
osborneforcongress.com-inf-20201109-212920-a3dni-00000.warc.gz	868115	download job
osborneforcongress.com-inf-20201109-212920-a3dni-00000.warc.os.cdx.gz	3636	download
osborneforcongress.com-inf-20201109-212920-a3dni.json	246	download job
richardhudson.org-inf-20201109-212518-9zaoy-meta.warc.gz	3565	download job
richardhudson.org-inf-20201109-212518-9zaoy-meta.warc.os.cdx.gz	47	download
robertthomasforcongress.com-inf-20201109-212326-cu60t-00000.warc.gz	161414297	download job
robertthomasforcongress.com-inf-20201109-212326-cu60t-00000.warc.os.cdx.gz	113270	download
robertthomasforcongress.com-inf-20201109-212326-cu60t-meta.warc.gz	78092	download job
robertthomasforcongress.com-inf-20201109-212326-cu60t-meta.warc.os.cdx.gz	47	download
sandysmithnc.com-inf-20201109-212248-dk42k-00000.warc.gz	463830285	download job
sandysmithnc.com-inf-20201109-212248-dk42k-00000.warc.os.cdx.gz	504583	download
sandysmithnc.com-inf-20201109-212248-dk42k-meta.warc.gz	312932	download job
sandysmithnc.com-inf-20201109-212248-dk42k-meta.warc.os.cdx.gz	47	download
sandysmithnc.com-inf-20201109-212248-dk42k.json	241	download job
sitesforcongress.com-inf-20201109-202626-ecwdc-00000.warc.gz	700532889	download job
sitesforcongress.com-inf-20201109-202626-ecwdc-00000.warc.os.cdx.gz	815187	download
sitesforcongress.com-inf-20201109-202626-ecwdc-meta.warc.gz	570010	download job
sitesforcongress.com-inf-20201109-202626-ecwdc-meta.warc.os.cdx.gz	47	download
sitesforcongress.com-inf-20201109-202626-ecwdc.json	245	download job
stevechabot.com-inf-20201109-193129-60l5h-00000.warc.gz	5320464710	download job
stevechabot.com-inf-20201109-193129-60l5h-00000.warc.os.cdx.gz	1574750	download
stevechabot.com-inf-20201109-193129-60l5h-meta.warc.gz	995496	download job
stevechabot.com-inf-20201109-193129-60l5h-meta.warc.os.cdx.gz	47	download
stevechabot.com-inf-20201109-193129-60l5h.json	240	download job
timryanforcongress.com-inf-20201109-201253-5luqj-00001.warc.gz	3104793650	download job
timryanforcongress.com-inf-20201109-201253-5luqj-00001.warc.os.cdx.gz	608684	download
timryanforcongress.com-inf-20201109-201253-5luqj-meta.warc.gz	696727	download job
timryanforcongress.com-inf-20201109-201253-5luqj-meta.warc.os.cdx.gz	47	download
timryanforcongress.com-inf-20201109-201253-5luqj.json	247	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00181.warc.gz	9354610469	download job
tv.us-west-1c.infowars.com-inf-20201028-220548-f4zam-00181.warc.os.cdx.gz	982	download
urls-archive.max.fan-twitter-@Cano4NC-20201104T142914Z.txt-shallow-20201107-165807-52omg-urls.txt	425846	download
urls-archive.max.fan-twitter-@DanCrenshawTX-20201104T111841Z.txt-shallow-20201109-165044-blqv5-00004.warc.gz	5786864699	download job
urls-archive.max.fan-twitter-@DanCrenshawTX-20201104T111841Z.txt-shallow-20201109-165044-blqv5-00004.warc.os.cdx.gz	359405	download
urls-archive.max.fan-twitter-@DanJan4Congress-20201104T105115Z.txt-shallow-20201109-232919-eqr9p-urls.txt	969	download
urls-archive.max.fan-twitter-@DaniForCongress-20201104T042514Z.txt-shallow-20201109-232900-4uzrm-meta.warc.gz	61361	download job
urls-archive.max.fan-twitter-@DaniForCongress-20201104T042514Z.txt-shallow-20201109-232900-4uzrm-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DarrellIssa-20201104T041822Z.txt-shallow-20201109-233057-4d9om-meta.warc.gz	9123	download job
urls-archive.max.fan-twitter-@DarrellIssa-20201104T041822Z.txt-shallow-20201109-233057-4d9om-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DarrenSoto-20201104T042054Z.txt-shallow-20201109-233207-bngm1-00000.warc.gz	8932083	download job
urls-archive.max.fan-twitter-@DarrenSoto-20201104T042054Z.txt-shallow-20201109-233207-bngm1-00000.warc.os.cdx.gz	52199	download
urls-archive.max.fan-twitter-@DarrenSoto-20201104T042054Z.txt-shallow-20201109-233207-bngm1-meta.warc.gz	63471	download job
urls-archive.max.fan-twitter-@DarrenSoto-20201104T042054Z.txt-shallow-20201109-233207-bngm1-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DashaPruett-20201104T100458Z.txt-shallow-20201109-233348-acila-meta.warc.gz	65120	download job
urls-archive.max.fan-twitter-@DashaPruett-20201104T100458Z.txt-shallow-20201109-233348-acila-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DashaPruett-20201104T100458Z.txt-shallow-20201109-233348-acila.json	377	download job
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf-00008.warc.gz	5405475036	download job
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf-00008.warc.os.cdx.gz	1510330	download
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf-00009.warc.gz	5055150751	download job
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf-00009.warc.os.cdx.gz	1045942	download
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf-meta.warc.gz	3956141	download job
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf-urls.txt	514470	download
urls-archive.max.fan-twitter-@dana_balter-20201104T075810Z.txt-shallow-20201109-165014-6ompf.json	377	download job
urls-archive.max.fan-twitter-@danielfeehan-20201104T063304Z.txt-shallow-20201109-165130-9yqvl-00004.warc.gz	3841203930	download job
urls-archive.max.fan-twitter-@danielfeehan-20201104T063304Z.txt-shallow-20201109-165130-9yqvl-00004.warc.os.cdx.gz	1660269	download
urls-archive.max.fan-twitter-@danielfeehan-20201104T063304Z.txt-shallow-20201109-165130-9yqvl-meta.warc.gz	2482866	download job
urls-archive.max.fan-twitter-@danielfeehan-20201104T063304Z.txt-shallow-20201109-165130-9yqvl-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@danielfeehan-20201104T063304Z.txt-shallow-20201109-165130-9yqvl-urls.txt	352127	download
urls-archive.max.fan-twitter-@danielfeehan-20201104T063304Z.txt-shallow-20201109-165130-9yqvl.json	379	download job
urls-transfer.notkiska.pw-house.gov-officers-and-organizations-inf-20201026-025214-dxvfo-00051.warc.gz	5368875680	download job
urls-transfer.notkiska.pw-house.gov-officers-and-organizations-inf-20201026-025214-dxvfo-00051.warc.os.cdx.gz	226534	download
urls-transfer.notkiska.pw-house.gov-representatives-e-inf-20201027-025529-5nh3t-00110.warc.gz	5369067896	download job
urls-transfer.notkiska.pw-house.gov-representatives-e-inf-20201027-025529-5nh3t-00110.warc.os.cdx.gz	2248345	download
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00093.warc.gz	5388003544	download job
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00093.warc.os.cdx.gz	15546	download
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00094.warc.gz	5389279366	download job
urls-transfer.notkiska.pw-senate.gov-senator-sites-inf-20201026-013306-3m680-00094.warc.os.cdx.gz	16264	download
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr-00000.warc.gz	5504525315	download job
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr-00000.warc.os.cdx.gz	951759	download
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr-00002.warc.gz	2118784671	download job
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr-00002.warc.os.cdx.gz	179707	download
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr-meta.warc.gz	1010957	download job
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr-urls.txt	111260	download
urls-transfer.notkiska.pw-twitter-@EsperDoD-shallow-20201109-220802-cr9yr.json	328	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00013.warc.gz	5459680176	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00013.warc.os.cdx.gz	609020	download
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00014.warc.gz	5669756175	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00014.warc.os.cdx.gz	33692	download
urls-transfer.notkiska.pw-twitter-@freespeechtv-shallow-20201109-003527-9hupm-00010.warc.gz	5420858299	download job
urls-transfer.notkiska.pw-twitter-@freespeechtv-shallow-20201109-003527-9hupm-00010.warc.os.cdx.gz	33473	download
urls-transfer.notkiska.pw-twitter-@scientificrealm-shallow-20201107-203125-6tvv7-00001.warc.gz	5368809075	download job
urls-transfer.notkiska.pw-twitter-@scientificrealm-shallow-20201107-203125-6tvv7-00001.warc.os.cdx.gz	6821180	download
urls-transfer.notkiska.pw-twitter-@supremenewyork-shallow-20201109-213532-br368-00000.warc.gz	1119385	download job
urls-transfer.notkiska.pw-twitter-@supremenewyork-shallow-20201109-213532-br368-00000.warc.os.cdx.gz	5515	download
urls-transfer.notkiska.pw-twitter-@supremenewyork-shallow-20201109-213532-br368-meta.warc.gz	7001	download job
urls-transfer.notkiska.pw-twitter-@supremenewyork-shallow-20201109-213532-br368-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@supremenewyork-shallow-20201109-213532-br368.json	342	download job
ushouserace2020.blogspot.com-inf-20201109-203920-6ghr0-meta.warc.gz	22931	download job
ushouserace2020.blogspot.com-inf-20201109-203920-6ghr0-meta.warc.os.cdx.gz	47	download
votedanbishop.com-inf-20201109-213247-ezgyh-00000.warc.gz	267272686	download job
votedanbishop.com-inf-20201109-213247-ezgyh-00000.warc.os.cdx.gz	343726	download
votedanbishop.com-inf-20201109-213247-ezgyh-meta.warc.gz	228208	download job
votedanbishop.com-inf-20201109-213247-ezgyh-meta.warc.os.cdx.gz	47	download
votedanbishop.com-inf-20201109-213247-ezgyh.json	242	download job
waynekingforcongress.com-inf-20201109-204037-7mdnp-00000.warc.gz	868007	download job
waynekingforcongress.com-inf-20201109-204037-7mdnp-00000.warc.os.cdx.gz	3657	download
waynekingforcongress.com-inf-20201109-204037-7mdnp-meta.warc.gz	5554	download job
waynekingforcongress.com-inf-20201109-204037-7mdnp-meta.warc.os.cdx.gz	47	download
weibo.cn-shallow-20201109-213743-ccpsm-00000.warc.gz	90868	download job
weibo.cn-shallow-20201109-213743-ccpsm-00000.warc.os.cdx.gz	1157	download
weibo.cn-shallow-20201109-213743-ccpsm.json	253	download job
wildforcongress.com-inf-20201109-190045-by3i5-00000.warc.gz	5426983540	download job
wildforcongress.com-inf-20201109-190045-by3i5-00000.warc.os.cdx.gz	396976	download
wildforcongress.com-inf-20201109-190045-by3i5-00001.warc.gz	2837508593	download job
wildforcongress.com-inf-20201109-190045-by3i5-00001.warc.os.cdx.gz	191590	download
wildforcongress.com-inf-20201109-190045-by3i5-meta.warc.gz	363402	download job
wildforcongress.com-inf-20201109-190045-by3i5-meta.warc.os.cdx.gz	47	download
woodsmall4nc.com-inf-20201109-213518-5asyd-00000.warc.gz	867099	download job
woodsmall4nc.com-inf-20201109-213518-5asyd-00000.warc.os.cdx.gz	3650	download
www.360haven.com-inf-20201031-180433-1l7vz-00019.warc.gz	7526084151	download job
www.360haven.com-inf-20201031-180433-1l7vz-00019.warc.os.cdx.gz	208021	download
www.360haven.com-inf-20201031-180433-1l7vz-00020.warc.gz	118424913	download job
www.360haven.com-inf-20201031-180433-1l7vz-00020.warc.os.cdx.gz	437754	download
www.360haven.com-inf-20201031-180433-1l7vz-meta.warc.gz	73307458	download job
www.360haven.com-inf-20201031-180433-1l7vz-meta.warc.os.cdx.gz	47	download
www.alaina2020.com-inf-20201109-203035-a29u8-meta.warc.gz	1013208	download job
www.alaina2020.com-inf-20201109-203035-a29u8-meta.warc.os.cdx.gz	47	download
www.bestgore.com-inf-20200908-124434-e9cla-00031.warc.gz	5368718017	download job
www.bestgore.com-inf-20200908-124434-e9cla-00031.warc.os.cdx.gz	4239023	download
www.bigganforcongress.com-inf-20201108-211447-egeq0-00000.warc.gz	9223	download job
www.bigganforcongress.com-inf-20201108-211447-egeq0-00000.warc.os.cdx.gz	271	download
www.bigganforcongress.com-inf-20201108-211447-egeq0-meta.warc.gz	3579	download job
www.bigganforcongress.com-inf-20201108-211447-egeq0-meta.warc.os.cdx.gz	47	download
www.boblanciaforcongress.com-inf-20201109-062908-9s7c5-00000.warc.gz	567797361	download job
www.boblanciaforcongress.com-inf-20201109-062908-9s7c5-00000.warc.os.cdx.gz	160566	download
www.boblanciaforcongress.com-inf-20201109-062908-9s7c5-meta.warc.gz	104133	download job
www.boblanciaforcongress.com-inf-20201109-062908-9s7c5-meta.warc.os.cdx.gz	47	download
www.brianfitzpatrick.com-inf-20201109-185931-d1gxo-meta.warc.gz	457368	download job
www.brianfitzpatrick.com-inf-20201109-185931-d1gxo-meta.warc.os.cdx.gz	47	download
www.castroforcongress.com-inf-20201108-211527-e11p4-00000.warc.gz	8482520	download job
www.castroforcongress.com-inf-20201108-211527-e11p4-00000.warc.os.cdx.gz	22298	download
www.castroforcongress.com-inf-20201108-211527-e11p4-meta.warc.gz	16647	download job
www.castroforcongress.com-inf-20201108-211527-e11p4-meta.warc.os.cdx.gz	47	download
www.chanceforcongress.com-inf-20201109-041446-b4l4f-00000.warc.gz	18276786	download job
www.chanceforcongress.com-inf-20201109-041446-b4l4f-00000.warc.os.cdx.gz	45507	download
www.chanceforcongress.com-inf-20201109-041446-b4l4f-meta.warc.gz	32550	download job
www.chanceforcongress.com-inf-20201109-041446-b4l4f-meta.warc.os.cdx.gz	47	download
www.charliejacksonforcongress.com-inf-20201108-225933-3q5qq-00000.warc.gz	55987375	download job
www.charliejacksonforcongress.com-inf-20201108-225933-3q5qq-00000.warc.os.cdx.gz	144643	download
www.charliejacksonforcongress.com-inf-20201108-225933-3q5qq-meta.warc.gz	144719	download job
www.charliejacksonforcongress.com-inf-20201108-225933-3q5qq-meta.warc.os.cdx.gz	47	download
www.chuckforcongress.com-inf-20201109-035504-auc65-00000.warc.gz	83700344	download job
www.chuckforcongress.com-inf-20201109-035504-auc65-00000.warc.os.cdx.gz	169561	download
www.chuckforcongress.com-inf-20201109-035504-auc65-meta.warc.gz	123900	download job
www.chuckforcongress.com-inf-20201109-035504-auc65-meta.warc.os.cdx.gz	47	download
www.cidob.org-inf-20201030-011402-1ftxx-00015.warc.gz	1898403670	download job
www.cidob.org-inf-20201030-011402-1ftxx-00015.warc.os.cdx.gz	3334098	download
www.cidob.org-inf-20201030-011402-1ftxx-meta.warc.gz	33197007	download job
www.cidob.org-inf-20201030-011402-1ftxx-meta.warc.os.cdx.gz	47	download
www.danahlers.com-inf-20201109-054753-37qus-00000.warc.gz	166321729	download job
www.danahlers.com-inf-20201109-054753-37qus-00000.warc.os.cdx.gz	181924	download
www.danahlers.com-inf-20201109-054753-37qus-meta.warc.gz	128405	download job
www.danahlers.com-inf-20201109-054753-37qus-meta.warc.os.cdx.gz	47	download
www.danielkilgoreforohio.com-inf-20201109-203006-6cuxc-00000.warc.gz	20292275	download job
www.danielkilgoreforohio.com-inf-20201109-203006-6cuxc-00000.warc.os.cdx.gz	45425	download
www.danielkilgoreforohio.com-inf-20201109-203006-6cuxc-meta.warc.gz	30703	download job
www.danielkilgoreforohio.com-inf-20201109-203006-6cuxc-meta.warc.os.cdx.gz	47	download
www.danyellforcongress.com-inf-20201109-192100-7ak5n-00000.warc.gz	5369283809	download job
www.danyellforcongress.com-inf-20201109-192100-7ak5n-00000.warc.os.cdx.gz	422621	download
www.danyellforcongress.com-inf-20201109-192100-7ak5n-00001.warc.gz	5369202008	download job
www.danyellforcongress.com-inf-20201109-192100-7ak5n-00001.warc.os.cdx.gz	185684	download
www.danyellforcongress.com-inf-20201109-192100-7ak5n-00002.warc.gz	1154122760	download job
www.danyellforcongress.com-inf-20201109-192100-7ak5n-00002.warc.os.cdx.gz	269259	download
www.davidrouzer.com-inf-20201109-213158-prtfp-meta.warc.gz	37024	download job
www.davidrouzer.com-inf-20201109-213158-prtfp-meta.warc.os.cdx.gz	47	download
www.defense.gov-shallow-20201109-220857-8282j-00000.warc.gz	9180551	download job
www.defense.gov-shallow-20201109-220857-8282j-00000.warc.os.cdx.gz	8464	download
www.defense.gov-shallow-20201109-220857-8282j-meta.warc.gz	8664	download job
www.defense.gov-shallow-20201109-220857-8282j-meta.warc.os.cdx.gz	47	download
www.defense.gov-shallow-20201109-220857-8282j.json	294	download job
www.efrainvaldezforcongress.com-inf-20201108-222702-yx19r-00000.warc.gz	55306047	download job
www.efrainvaldezforcongress.com-inf-20201108-222702-yx19r-00000.warc.os.cdx.gz	126058	download
www.efrainvaldezforcongress.com-inf-20201108-222702-yx19r-meta.warc.gz	80091	download job
www.efrainvaldezforcongress.com-inf-20201108-222702-yx19r-meta.warc.os.cdx.gz	47	download
www.electchrisbell.com-inf-20201108-231042-a8ocw-meta.warc.gz	4128	download job
www.electchrisbell.com-inf-20201108-231042-a8ocw-meta.warc.os.cdx.gz	47	download
www.gandhifortexas.com-inf-20201108-205839-4vvic-00000.warc.gz	2030514955	download job
www.gandhifortexas.com-inf-20201108-205839-4vvic-00000.warc.os.cdx.gz	697791	download
www.godfreyforcongress.com-inf-20201109-203052-8jg6s.json	250	download job
www.hankefortexas.com-inf-20201108-222521-dme0v-meta.warc.gz	13256	download job
www.hankefortexas.com-inf-20201108-222521-dme0v-meta.warc.os.cdx.gz	47	download
www.hmdb.org-inf-20201018-175958-aboei-00292.warc.gz	5372570724	download job
www.hmdb.org-inf-20201018-175958-aboei-00292.warc.os.cdx.gz	164540	download
www.instagram.com-inf-20201109-205925-16ri7.json	262	download job
www.instagram.com-inf-20201109-212354-apbs3-meta.warc.gz	33739	download job
www.instagram.com-inf-20201109-212354-apbs3-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-212354-apbs3.json	264	download job
www.instagram.com-inf-20201109-213654-emree.json	274	download job
www.instagram.com-inf-20201109-214557-42hxd-meta.warc.gz	17862	download job
www.instagram.com-inf-20201109-214557-42hxd-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-215335-6eb2s-00000.warc.gz	9965818	download job
www.instagram.com-inf-20201109-215335-6eb2s-00000.warc.os.cdx.gz	50000	download
www.instagram.com-inf-20201109-215335-6eb2s-meta.warc.gz	33595	download job
www.instagram.com-inf-20201109-215335-6eb2s-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-215335-6eb2s.json	264	download job
www.instagram.com-inf-20201109-221150-393l6-00000.warc.gz	10274384	download job
www.instagram.com-inf-20201109-221150-393l6-00000.warc.os.cdx.gz	46773	download
www.instagram.com-inf-20201109-221150-393l6-meta.warc.gz	36723	download job
www.instagram.com-inf-20201109-221150-393l6-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-221150-393l6.json	268	download job
www.instagram.com-inf-20201109-222304-6nglk-00000.warc.gz	12545143	download job
www.instagram.com-inf-20201109-222304-6nglk-00000.warc.os.cdx.gz	36894	download
www.instagram.com-inf-20201109-222304-6nglk-meta.warc.gz	28516	download job
www.instagram.com-inf-20201109-222304-6nglk-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-222304-6nglk.json	269	download job
www.instagram.com-inf-20201109-223423-efj7f-00000.warc.gz	278857152	download job
www.instagram.com-inf-20201109-223423-efj7f-00000.warc.os.cdx.gz	59913	download
www.instagram.com-inf-20201109-223423-efj7f-meta.warc.gz	45246	download job
www.instagram.com-inf-20201109-223423-efj7f-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-223423-efj7f.json	266	download job
www.instagram.com-inf-20201109-224905-27sjo-00000.warc.gz	10401386	download job
www.instagram.com-inf-20201109-224905-27sjo-00000.warc.os.cdx.gz	30229	download
www.instagram.com-inf-20201109-224905-27sjo-meta.warc.gz	24020	download job
www.instagram.com-inf-20201109-224905-27sjo-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-224905-27sjo.json	262	download job
www.instagram.com-inf-20201109-225653-72khx.json	273	download job
www.leehaywood.com-inf-20201109-212941-3kuex-00000.warc.gz	44534563	download job
www.leehaywood.com-inf-20201109-212941-3kuex-00000.warc.os.cdx.gz	53775	download
www.leehaywood.com-inf-20201109-212941-3kuex-meta.warc.gz	34886	download job
www.leehaywood.com-inf-20201109-212941-3kuex-meta.warc.os.cdx.gz	47	download
www.leehaywood.com-inf-20201109-212941-3kuex.json	243	download job
www.moyer2020.org-inf-20201109-202931-eev75-meta.warc.gz	246670	download job
www.moyer2020.org-inf-20201109-202931-eev75-meta.warc.os.cdx.gz	47	download
www.moyer2020.org-inf-20201109-202931-eev75.json	242	download job
www.redstate.com-inf-20201002-220930-4bjxa-00214.warc.gz	5369087441	download job
www.redstate.com-inf-20201002-220930-4bjxa-00214.warc.os.cdx.gz	1081722	download
www.richardsonforcongress.com-inf-20201109-200534-7cf02.json	254	download job
www.scotthuffman.com-inf-20201109-213530-8v2xm-00000.warc.gz	59783505	download job
www.scotthuffman.com-inf-20201109-213530-8v2xm-00000.warc.os.cdx.gz	88434	download
www.scotthuffman.com-inf-20201109-213530-8v2xm.json	245	download job
www.steveavonloor.com-inf-20201109-212234-2jnzz-00000.warc.gz	135853007	download job
www.steveavonloor.com-inf-20201109-212234-2jnzz-00000.warc.os.cdx.gz	90697	download
www.steveavonloor.com-inf-20201109-212234-2jnzz-meta.warc.gz	62085	download job
www.steveavonloor.com-inf-20201109-212234-2jnzz-meta.warc.os.cdx.gz	47	download
www.swainforcongress.com-inf-20201109-213443-5yqij-meta.warc.gz	60778	download job
www.swainforcongress.com-inf-20201109-213443-5yqij-meta.warc.os.cdx.gz	47	download
www.swainforcongress.com-inf-20201109-213443-5yqij.json	249	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00334.warc.gz	5427568070	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00334.warc.os.cdx.gz	640235	download
www.vancenc.com-inf-20201109-212153-cpki2-00000.warc.gz	192418715	download job
www.vancenc.com-inf-20201109-212153-cpki2-00000.warc.os.cdx.gz	60998	download
www.vancenc.com-inf-20201109-212153-cpki2-meta.warc.gz	43075	download job
www.vancenc.com-inf-20201109-212153-cpki2-meta.warc.os.cdx.gz	47	download
www.vancenc.com-inf-20201109-212153-cpki2.json	240	download job
www.wuxiaworld.com-inf-20201109-210033-br4qg-00000.warc.gz	4080	download job
www.wuxiaworld.com-inf-20201109-210033-br4qg-00000.warc.os.cdx.gz	234	download
www.wuxiaworld.com-inf-20201109-210033-br4qg.json	276	download job
www.wuxiaworld.com-inf-20201109-211454-br4qg-00000.warc.gz	182286586	download job
www.wuxiaworld.com-inf-20201109-211454-br4qg-00000.warc.os.cdx.gz	250641	download
www.wuxiaworld.com-inf-20201109-211454-br4qg-meta.warc.gz	156143	download job
www.wuxiaworld.com-inf-20201109-211454-br4qg-meta.warc.os.cdx.gz	47	download
www.wuxiaworld.com-inf-20201109-211454-br4qg.json	276	download job
www.wuxiaworld.com-inf-20201109-212543-e8a1y-00000.warc.gz	95699883	download job
www.wuxiaworld.com-inf-20201109-212543-e8a1y-00000.warc.os.cdx.gz	212532	download
www.wuxiaworld.com-inf-20201109-212543-e8a1y-meta.warc.gz	138632	download job
www.wuxiaworld.com-inf-20201109-212543-e8a1y-meta.warc.os.cdx.gz	47	download
www.wuxiaworld.com-inf-20201109-212543-e8a1y.json	276	download job
www.zachfornorthdakota.com-inf-20201109-203906-2s98y-meta.warc.gz	486880	download job
www.zachfornorthdakota.com-inf-20201109-203906-2s98y-meta.warc.os.cdx.gz	47	download
www.zachfornorthdakota.com-inf-20201109-203906-2s98y.json	251	download job