Item archiveteam_archivebot_go_20201109160003

Filename	Size
archiveteam_archivebot_go_20201109160003.cdx.gz	37178700	download
archiveteam_archivebot_go_20201109160003.cdx.idx	34655	download
archiveteam_archivebot_go_20201109160003_files.xml	0	download
archiveteam_archivebot_go_20201109160003_meta.sqlite	239616	download
archiveteam_archivebot_go_20201109160003_meta.xml	968	download
burningspearmarketplace.com-inf-20201109-135510-8yggk-00000.warc.gz	106024810	download job
burningspearmarketplace.com-inf-20201109-135510-8yggk-00000.warc.os.cdx.gz	80313	download
burningspearmarketplace.com-inf-20201109-135510-8yggk-meta.warc.gz	60804	download job
burningspearmarketplace.com-inf-20201109-135510-8yggk-meta.warc.os.cdx.gz	47	download
burningspearmarketplace.com-inf-20201109-135510-8yggk.json	256	download job
cap.urbanjustice.org-inf-20201109-135706-a6j6x-00000.warc.gz	118576855	download job
cap.urbanjustice.org-inf-20201109-135706-a6j6x-00000.warc.os.cdx.gz	266022	download
cap.urbanjustice.org-inf-20201109-135706-a6j6x-meta.warc.gz	198591	download job
cap.urbanjustice.org-inf-20201109-135706-a6j6x-meta.warc.os.cdx.gz	47	download
cap.urbanjustice.org-inf-20201109-135706-a6j6x.json	249	download job
cdn.afacwa.org-inf-20201109-154100-8xgkd-00000.warc.gz	7399	download job
cdn.afacwa.org-inf-20201109-154100-8xgkd-00000.warc.os.cdx.gz	295	download
cdn.afacwa.org-inf-20201109-154100-8xgkd-meta.warc.gz	3532	download job
cdn.afacwa.org-inf-20201109-154100-8xgkd-meta.warc.os.cdx.gz	47	download
cdn.afacwa.org-inf-20201109-154100-8xgkd.json	244	download job
cdp.urbanjustice.org-inf-20201109-141006-cg1jc-00000.warc.gz	108333654	download job
cdp.urbanjustice.org-inf-20201109-141006-cg1jc-00000.warc.os.cdx.gz	234213	download
cdp.urbanjustice.org-inf-20201109-141006-cg1jc-meta.warc.gz	137166	download job
cdp.urbanjustice.org-inf-20201109-141006-cg1jc-meta.warc.os.cdx.gz	47	download
cdp.urbanjustice.org-inf-20201109-141006-cg1jc.json	249	download job
dev.freespeech.org-inf-20201109-140300-b23cy-00000.warc.gz	179378701	download job
dev.freespeech.org-inf-20201109-140300-b23cy-00000.warc.os.cdx.gz	137232	download
dev.freespeech.org-inf-20201109-140300-b23cy-meta.warc.gz	115864	download job
dev.freespeech.org-inf-20201109-140300-b23cy-meta.warc.os.cdx.gz	47	download
dev.freespeech.org-inf-20201109-140300-b23cy.json	247	download job
events.urbanjustice.org-inf-20201109-140544-d3ryi-00000.warc.gz	268127184	download job
events.urbanjustice.org-inf-20201109-140544-d3ryi-00000.warc.os.cdx.gz	155972	download
events.urbanjustice.org-inf-20201109-140544-d3ryi-meta.warc.gz	162994	download job
events.urbanjustice.org-inf-20201109-140544-d3ryi-meta.warc.os.cdx.gz	47	download
events.urbanjustice.org-inf-20201109-140544-d3ryi.json	252	download job
history/files/urls-transfer.notkiska.pw-twitter-@IlhanMN-shallow-20201107-171800-eklwo-00001.warc.gz.~1~	5749052614	download
hoodcommunist.org-inf-20201109-141518-626lz-00000.warc.gz	5371272851	download job
hoodcommunist.org-inf-20201109-141518-626lz-00000.warc.os.cdx.gz	1331407	download
hoodcommunist.org-inf-20201109-141518-626lz-00001.warc.gz	5404595823	download job
hoodcommunist.org-inf-20201109-141518-626lz-00001.warc.os.cdx.gz	33512	download
humphreysrealestate.democracyinstitute.org-inf-20201109-142230-851eq-00000.warc.gz	16116233	download job
humphreysrealestate.democracyinstitute.org-inf-20201109-142230-851eq-00000.warc.os.cdx.gz	34268	download
humphreysrealestate.democracyinstitute.org-inf-20201109-142230-851eq-meta.warc.gz	25102	download job
humphreysrealestate.democracyinstitute.org-inf-20201109-142230-851eq-meta.warc.os.cdx.gz	47	download
humphreysrealestate.democracyinstitute.org-inf-20201109-142230-851eq.json	271	download job
irap.urbanjustice.org-inf-20201109-143351-3lquf-meta.warc.gz	346062	download job
irap.urbanjustice.org-inf-20201109-143351-3lquf-meta.warc.os.cdx.gz	47	download
irap.urbanjustice.org-inf-20201109-143351-3lquf.json	250	download job
medium.com-shallow-20201109-143653-5zekb-00000.warc.gz	3095573	download job
medium.com-shallow-20201109-143653-5zekb-00000.warc.os.cdx.gz	10096	download
medium.com-shallow-20201109-143653-5zekb-meta.warc.gz	9169	download job
medium.com-shallow-20201109-143653-5zekb-meta.warc.os.cdx.gz	47	download
medium.com-shallow-20201109-143653-5zekb.json	279	download job
new.apspuhuru.org-inf-20201109-143526-6f9zh-00000.warc.gz	400316504	download job
new.apspuhuru.org-inf-20201109-143526-6f9zh-00000.warc.os.cdx.gz	454790	download
new.apspuhuru.org-inf-20201109-143526-6f9zh-meta.warc.gz	292648	download job
new.apspuhuru.org-inf-20201109-143526-6f9zh-meta.warc.os.cdx.gz	47	download
new.apspuhuru.org-inf-20201109-143526-6f9zh.json	246	download job
oldbridgemilitia.org-inf-20201109-134511-1jf4j-00000.warc.gz	293151963	download job
oldbridgemilitia.org-inf-20201109-134511-1jf4j-00000.warc.os.cdx.gz	161877	download
one.gaslandthemovie.com-inf-20201109-144111-7l4cq-00000.warc.gz	15948	download job
one.gaslandthemovie.com-inf-20201109-144111-7l4cq-00000.warc.os.cdx.gz	323	download
one.gaslandthemovie.com-inf-20201109-144111-7l4cq-meta.warc.gz	3551	download job
one.gaslandthemovie.com-inf-20201109-144111-7l4cq-meta.warc.os.cdx.gz	47	download
one.gaslandthemovie.com-inf-20201109-144111-7l4cq.json	252	download job
one.gaslandthemovie.com-inf-20201109-144156-7l4cq-00000.warc.gz	15673	download job
one.gaslandthemovie.com-inf-20201109-144156-7l4cq-00000.warc.os.cdx.gz	328	download
one.gaslandthemovie.com-inf-20201109-144156-7l4cq-meta.warc.gz	3491	download job
one.gaslandthemovie.com-inf-20201109-144156-7l4cq-meta.warc.os.cdx.gz	47	download
one.gaslandthemovie.com-inf-20201109-144156-7l4cq.json	252	download job
one.gaslandthemovie.com-inf-20201109-144421-7l4cq-00000.warc.gz	15653	download job
one.gaslandthemovie.com-inf-20201109-144421-7l4cq-00000.warc.os.cdx.gz	331	download
one.gaslandthemovie.com-inf-20201109-144421-7l4cq.json	252	download job
poker.urbanjustice.org-inf-20201109-145620-dggp9-00000.warc.gz	94561527	download job
poker.urbanjustice.org-inf-20201109-145620-dggp9-00000.warc.os.cdx.gz	104655	download
purplestore.seasol.net-inf-20201109-145652-x0nck-00000.warc.gz	11327285	download job
purplestore.seasol.net-inf-20201109-145652-x0nck-00000.warc.os.cdx.gz	33166	download
purplestore.seasol.net-inf-20201109-145652-x0nck-meta.warc.gz	24327	download job
purplestore.seasol.net-inf-20201109-145652-x0nck-meta.warc.os.cdx.gz	47	download
purplestore.seasol.net-inf-20201109-145652-x0nck.json	251	download job
seasol.net-inf-20201109-145855-f0ayp-00000.warc.gz	174221084	download job
seasol.net-inf-20201109-145855-f0ayp-00000.warc.os.cdx.gz	267286	download
seasol.net-inf-20201109-145855-f0ayp-meta.warc.gz	188900	download job
seasol.net-inf-20201109-145855-f0ayp-meta.warc.os.cdx.gz	47	download
seattlesolidarity.net-inf-20201109-151648-910up-meta.warc.gz	11167	download job
seattlesolidarity.net-inf-20201109-151648-910up-meta.warc.os.cdx.gz	47	download
seattlesolidarity.net-inf-20201109-151648-910up.json	250	download job
secondchances.peoplepower.org-inf-20201109-150035-73mgh-00000.warc.gz	32361226	download job
secondchances.peoplepower.org-inf-20201109-150035-73mgh-00000.warc.os.cdx.gz	17705	download
secondchances.peoplepower.org-inf-20201109-150035-73mgh-meta.warc.gz	14346	download job
secondchances.peoplepower.org-inf-20201109-150035-73mgh-meta.warc.os.cdx.gz	47	download
uhurusolidarity.podbean.com-inf-20201109-150225-a4ef0-00000.warc.gz	5380878352	download job
uhurusolidarity.podbean.com-inf-20201109-150225-a4ef0-00000.warc.os.cdx.gz	162104	download
uhurusolidarity.podbean.com-inf-20201109-150225-a4ef0-00001.warc.gz	2893888976	download job
uhurusolidarity.podbean.com-inf-20201109-150225-a4ef0-00001.warc.os.cdx.gz	30215	download
uhurusolidarity.podbean.com-inf-20201109-150225-a4ef0-meta.warc.gz	135339	download job
uhurusolidarity.podbean.com-inf-20201109-150225-a4ef0-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@CarolynBMaloney-20201104T075649Z.txt-shallow-20201107-170446-cx0ql-00004.warc.gz	5408135574	download job
urls-archive.max.fan-twitter-@CarolynBMaloney-20201104T075649Z.txt-shallow-20201107-170446-cx0ql-00004.warc.os.cdx.gz	1266219	download
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00007.warc.gz	5369509176	download job
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00007.warc.os.cdx.gz	43799	download
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00009.warc.gz	5485611809	download job
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00009.warc.os.cdx.gz	30217	download
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00010.warc.gz	5382388232	download job
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00010.warc.os.cdx.gz	30325	download
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00011.warc.gz	5451194507	download job
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00011.warc.os.cdx.gz	34695	download
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00012.warc.gz	5376264974	download job
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00012.warc.os.cdx.gz	30906	download
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00013.warc.gz	5374622378	download job
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00013.warc.os.cdx.gz	34646	download
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00016.warc.gz	5423295466	download job
urls-archive.max.fan-twitter-@ColMorrisDavis-20201104T085822Z.txt-shallow-20201108-144045-6z8b1-00016.warc.os.cdx.gz	169524	download
urls-archive.max.fan-twitter-@CongressmanRaja-20201103T221040Z.txt-shallow-20201108-183914-dcv1e-00026.warc.gz	5369055009	download job
urls-archive.max.fan-twitter-@CongressmanRaja-20201103T221040Z.txt-shallow-20201108-183914-dcv1e-00026.warc.os.cdx.gz	2435392	download
urls-archive.max.fan-twitter-@CongressmanRaja-20201103T221040Z.txt-shallow-20201108-183914-dcv1e-00027.warc.gz	5063160120	download job
urls-archive.max.fan-twitter-@CongressmanRaja-20201103T221040Z.txt-shallow-20201108-183914-dcv1e-00027.warc.os.cdx.gz	2811163	download
urls-archive.max.fan-twitter-@CongressmanRaja-20201103T221040Z.txt-shallow-20201108-183914-dcv1e-urls.txt	1190577	download
urls-archive.max.fan-twitter-@CoraforMT-20201104T135914Z.txt-shallow-20201108-194036-6sasy-00005.warc.gz	1191611839	download job
urls-archive.max.fan-twitter-@CoraforMT-20201104T135914Z.txt-shallow-20201108-194036-6sasy-00005.warc.os.cdx.gz	778230	download
urls-transfer.notkiska.pw-house.gov-representatives-d-inf-20201027-025523-dgqzt-00072.warc.gz	5368752139	download job
urls-transfer.notkiska.pw-house.gov-representatives-d-inf-20201027-025523-dgqzt-00072.warc.os.cdx.gz	3331989	download
urls-transfer.notkiska.pw-house.gov-representatives-e-inf-20201027-025529-5nh3t-00108.warc.gz	5381636048	download job
urls-transfer.notkiska.pw-house.gov-representatives-e-inf-20201027-025529-5nh3t-00108.warc.os.cdx.gz	901842	download
urls-transfer.notkiska.pw-twitter-@DonaldJTrumpJr-shallow-20201108-232234-6oe3j-00010.warc.gz	5370221592	download job
urls-transfer.notkiska.pw-twitter-@DonaldJTrumpJr-shallow-20201108-232234-6oe3j-00010.warc.os.cdx.gz	35151	download
urls-transfer.notkiska.pw-twitter-@DonaldJTrumpJr-shallow-20201108-232234-6oe3j-00011.warc.gz	5371246462	download job
urls-transfer.notkiska.pw-twitter-@DonaldJTrumpJr-shallow-20201108-232234-6oe3j-00011.warc.os.cdx.gz	2261842	download
urls-transfer.notkiska.pw-twitter-@IRAP-shallow-20201109-005455-er6i2-meta.warc.gz	4424133	download job
urls-transfer.notkiska.pw-twitter-@IRAP-shallow-20201109-005455-er6i2-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@IlhanMN-shallow-20201107-171800-eklwo-00000.warc.gz	5411868601	download job
urls-transfer.notkiska.pw-twitter-@IlhanMN-shallow-20201107-171800-eklwo-00000.warc.os.cdx.gz	3672216	download
urls-transfer.notkiska.pw-twitter-@IlhanMN-shallow-20201107-171800-eklwo-00001.warc.gz	5749052614	download job
urls-transfer.notkiska.pw-twitter-@IlhanMN-shallow-20201107-171800-eklwo-00001.warc.os.cdx.gz	1813430	download
urls-transfer.notkiska.pw-twitter-@JRubinBlogger-shallow-20201108-151130-6u7ez-00009.warc.gz	5392078267	download job
urls-transfer.notkiska.pw-twitter-@JRubinBlogger-shallow-20201108-151130-6u7ez-00009.warc.os.cdx.gz	310976	download
urls-transfer.notkiska.pw-twitter-@JRubinBlogger-shallow-20201108-151130-6u7ez-00012.warc.gz	5379104197	download job
urls-transfer.notkiska.pw-twitter-@JRubinBlogger-shallow-20201108-151130-6u7ez-00012.warc.os.cdx.gz	483799	download
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00007.warc.gz	5423304530	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00007.warc.os.cdx.gz	1912695	download
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00008.warc.gz	6135783489	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00008.warc.os.cdx.gz	13522	download
urls-transfer.notkiska.pw-twitter-@StanfordCyber-shallow-20201109-143648-dgjws-00000.warc.gz	5372837510	download job
urls-transfer.notkiska.pw-twitter-@StanfordCyber-shallow-20201109-143648-dgjws-00000.warc.os.cdx.gz	884220	download
urls-transfer.notkiska.pw-twitter-@freespeechtv-shallow-20201109-003527-9hupm-00000.warc.gz	5368748913	download job
urls-transfer.notkiska.pw-twitter-@freespeechtv-shallow-20201109-003527-9hupm-00000.warc.os.cdx.gz	8973289	download
www.daiduetaqueria.com-inf-20201109-142821-es41y-00000.warc.gz	23926702	download job
www.daiduetaqueria.com-inf-20201109-142821-es41y-00000.warc.os.cdx.gz	80553	download
www.daiduetaqueria.com-inf-20201109-142821-es41y-meta.warc.gz	83773	download job
www.daiduetaqueria.com-inf-20201109-142821-es41y-meta.warc.os.cdx.gz	47	download
www.daiduetaqueria.com-inf-20201109-142821-es41y.json	252	download job
www.hmdb.org-inf-20201018-175958-aboei-00288.warc.gz	5370487246	download job
www.hmdb.org-inf-20201018-175958-aboei-00288.warc.os.cdx.gz	161661	download
www.instagram.com-inf-20201109-122529-592n5-meta.warc.gz	81505	download job
www.instagram.com-inf-20201109-122529-592n5-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-122529-592n5.json	261	download job
www.instagram.com-inf-20201109-131338-2sl7x-meta.warc.gz	33515	download job
www.instagram.com-inf-20201109-131338-2sl7x-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-132724-dmcbl.json	260	download job
www.instagram.com-inf-20201109-134435-c0r4s-meta.warc.gz	32936	download job
www.instagram.com-inf-20201109-134435-c0r4s-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-134435-c0r4s.json	261	download job
www.instagram.com-inf-20201109-135817-8xlft-00000.warc.gz	9158694	download job
www.instagram.com-inf-20201109-135817-8xlft-00000.warc.os.cdx.gz	30368	download
www.instagram.com-inf-20201109-135817-8xlft-meta.warc.gz	24892	download job
www.instagram.com-inf-20201109-135817-8xlft-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-135817-8xlft.json	266	download job
www.instagram.com-inf-20201109-140812-d5l4t-00000.warc.gz	76401938	download job
www.instagram.com-inf-20201109-140812-d5l4t-00000.warc.os.cdx.gz	49822	download
www.instagram.com-inf-20201109-140812-d5l4t-meta.warc.gz	34923	download job
www.instagram.com-inf-20201109-140812-d5l4t-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-140812-d5l4t.json	276	download job
www.instagram.com-inf-20201109-142528-3b5e0-00000.warc.gz	137608277	download job
www.instagram.com-inf-20201109-142528-3b5e0-00000.warc.os.cdx.gz	46300	download
www.instagram.com-inf-20201109-142528-3b5e0-meta.warc.gz	36859	download job
www.instagram.com-inf-20201109-142528-3b5e0-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-142528-3b5e0.json	265	download job
www.instagram.com-inf-20201109-143701-72kdf-00000.warc.gz	7278805	download job
www.instagram.com-inf-20201109-143701-72kdf-00000.warc.os.cdx.gz	22978	download
www.instagram.com-inf-20201109-143701-72kdf-meta.warc.gz	18878	download job
www.instagram.com-inf-20201109-143701-72kdf-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-143701-72kdf.json	271	download job
www.instagram.com-inf-20201109-144439-cwqed-00000.warc.gz	12729937	download job
www.instagram.com-inf-20201109-144439-cwqed-00000.warc.os.cdx.gz	34127	download
www.instagram.com-inf-20201109-144439-cwqed-meta.warc.gz	26661	download job
www.instagram.com-inf-20201109-144439-cwqed-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-144439-cwqed.json	259	download job
www.instagram.com-inf-20201109-145503-br7zj.json	266	download job
www.instagram.com-inf-20201109-150628-ermbo-00000.warc.gz	19124597	download job
www.instagram.com-inf-20201109-150628-ermbo-00000.warc.os.cdx.gz	76300	download
www.instagram.com-inf-20201109-150628-ermbo-meta.warc.gz	83389	download job
www.instagram.com-inf-20201109-150628-ermbo-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201109-150628-ermbo.json	257	download job
www.instagram.com-inf-20201109-154716-1cqkg.json	261	download job
www.julieoliver.org-inf-20201108-211405-aspch.json	244	download job
www.markgreentn.com-inf-20201109-034912-2t48c-00000.warc.gz	30489503	download job
www.markgreentn.com-inf-20201109-034912-2t48c-00000.warc.os.cdx.gz	33754	download
www.markgreentn.com-inf-20201109-034912-2t48c-meta.warc.gz	23367	download job
www.markgreentn.com-inf-20201109-034912-2t48c-meta.warc.os.cdx.gz	47	download
www.markgreentn.com-inf-20201109-034912-2t48c.json	244	download job
www.marquitabradshaw.com-inf-20201109-054502-1vdzx-meta.warc.gz	164565	download job
www.marquitabradshaw.com-inf-20201109-054502-1vdzx-meta.warc.os.cdx.gz	47	download
www.marsicanoforcongress.com-inf-20201109-064641-95sof-00000.warc.gz	248224616	download job
www.marsicanoforcongress.com-inf-20201109-064641-95sof-00000.warc.os.cdx.gz	220169	download
www.meg2020.com-inf-20201109-040112-bykdf-00000.warc.gz	66564504	download job
www.meg2020.com-inf-20201109-040112-bykdf-00000.warc.os.cdx.gz	132325	download
www.meg2020.com-inf-20201109-040112-bykdf.json	240	download job
www.noelle4tn.com-inf-20201109-040103-8zc6z-00000.warc.gz	8560	download job
www.noelle4tn.com-inf-20201109-040103-8zc6z-00000.warc.os.cdx.gz	259	download
www.oldbridgemilitia.org-inf-20201109-135156-obmse-meta.warc.gz	38156	download job
www.oldbridgemilitia.org-inf-20201109-135156-obmse-meta.warc.os.cdx.gz	47	download
www.phil4house.com-inf-20201109-034851-61zbw-meta.warc.gz	187314	download job
www.phil4house.com-inf-20201109-034851-61zbw-meta.warc.os.cdx.gz	47	download
www.phil4house.com-inf-20201109-034851-61zbw.json	243	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00330.warc.gz	5370786670	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00330.warc.os.cdx.gz	496610	download
www.tripadvisor.com-shallow-20201109-142921-cgw24-00000.warc.gz	34146802	download job
www.tripadvisor.com-shallow-20201109-142921-cgw24-00000.warc.os.cdx.gz	81489	download
www.tripadvisor.com-shallow-20201109-142921-cgw24-meta.warc.gz	46600	download job
www.tripadvisor.com-shallow-20201109-142921-cgw24-meta.warc.os.cdx.gz	47	download
www.tripadvisor.com-shallow-20201109-142921-cgw24.json	330	download job
www.votepachuta.com-inf-20201108-212533-8hfzh-meta.warc.gz	74341	download job
www.votepachuta.com-inf-20201108-212533-8hfzh-meta.warc.os.cdx.gz	47	download
www.yelp.com-shallow-20201109-142844-31d5f-00000.warc.gz	15403116	download job
www.yelp.com-shallow-20201109-142844-31d5f-00000.warc.os.cdx.gz	54775	download
www.yelp.com-shallow-20201109-142844-31d5f-meta.warc.gz	37356	download job
www.yelp.com-shallow-20201109-142844-31d5f-meta.warc.os.cdx.gz	47	download
www.yelp.com-shallow-20201109-142844-31d5f.json	275	download job
www.zerohedge.com-inf-20201002-220843-12m04-00201.warc.gz	5368855816	download job
www.zerohedge.com-inf-20201002-220843-12m04-00201.warc.os.cdx.gz	1715133	download
www.zinaforcongress.com-inf-20201108-234705-akvuy-meta.warc.gz	430710	download job
www.zinaforcongress.com-inf-20201108-234705-akvuy-meta.warc.os.cdx.gz	47	download