Item archiveteam_archivebot_go_20200523070002

Filename	Size
andranaproject.com-inf-20200523-043332-69bcx-00000.warc.gz	344044892	download job
andranaproject.com-inf-20200523-043332-69bcx-00000.warc.os.cdx.gz	256142	download
andranaproject.com-inf-20200523-043332-69bcx-meta.warc.gz	166811	download job
andranaproject.com-inf-20200523-043332-69bcx-meta.warc.os.cdx.gz	47	download
andranaproject.com-inf-20200523-043332-69bcx.json	243	download job
archiveteam_archivebot_go_20200523070002.cdx.gz	69513328	download
archiveteam_archivebot_go_20200523070002.cdx.idx	74009	download
archiveteam_archivebot_go_20200523070002_files.xml	0	download
archiveteam_archivebot_go_20200523070002_meta.sqlite	233472	download
archiveteam_archivebot_go_20200523070002_meta.xml	969	download
blob7.wixsite.com-inf-20200523-042156-e4w3l.json	251	download job
blog.tresebrothers.com-inf-20200523-034432-dnzik-meta.warc.gz	1616807	download job
blog.tresebrothers.com-inf-20200523-034432-dnzik-meta.warc.os.cdx.gz	47	download
brosbeforegiraffes.com-inf-20200523-042351-1nigg-00000.warc.gz	444261381	download job
brosbeforegiraffes.com-inf-20200523-042351-1nigg-00000.warc.os.cdx.gz	226726	download
brosbeforegiraffes.com-inf-20200523-042351-1nigg-meta.warc.gz	134449	download job
brosbeforegiraffes.com-inf-20200523-042351-1nigg-meta.warc.os.cdx.gz	47	download
brosbeforegiraffes.com-inf-20200523-042351-1nigg.json	247	download job
cliqz.com-inf-20200501-194732-82yzf-00130.warc.gz	5369206203	download job
cliqz.com-inf-20200501-194732-82yzf-00130.warc.os.cdx.gz	4898495	download
committeetounleashprosperity.com-inf-20200522-022530-b41ul-00011.warc.gz	5371601156	download job
committeetounleashprosperity.com-inf-20200522-022530-b41ul-00011.warc.os.cdx.gz	641409	download
danganronpaxl.tumblr.com-inf-20200523-042035-2ylv4-00000.warc.gz	3085093542	download job
danganronpaxl.tumblr.com-inf-20200523-042035-2ylv4-00000.warc.os.cdx.gz	1124960	download
danganronpaxl.tumblr.com-inf-20200523-042035-2ylv4-meta.warc.gz	1007061	download job
danganronpaxl.tumblr.com-inf-20200523-042035-2ylv4-meta.warc.os.cdx.gz	47	download
danganronpaxl.tumblr.com-inf-20200523-042035-2ylv4.json	249	download job
enralis.co-inf-20200523-041543-4xjl1-00000.warc.gz	403656828	download job
enralis.co-inf-20200523-041543-4xjl1-00000.warc.os.cdx.gz	139187	download
enralis.tumblr.com-inf-20200523-041615-4tszu-meta.warc.gz	694205	download job
enralis.tumblr.com-inf-20200523-041615-4tszu-meta.warc.os.cdx.gz	47	download
enralis.tumblr.com-inf-20200523-041615-4tszu.json	243	download job
epicmeal.wixsite.com-inf-20200523-041500-af9gx-meta.warc.gz	226674	download job
epicmeal.wixsite.com-inf-20200523-041500-af9gx-meta.warc.os.cdx.gz	47	download
f-fman.wixsite.com-inf-20200523-040404-azyvd-00000.warc.gz	856859883	download job
f-fman.wixsite.com-inf-20200523-040404-azyvd-00000.warc.os.cdx.gz	1080322	download
f-fman.wixsite.com-inf-20200523-040404-azyvd-meta.warc.gz	1322255	download job
f-fman.wixsite.com-inf-20200523-040404-azyvd-meta.warc.os.cdx.gz	47	download
f-fman.wixsite.com-inf-20200523-040404-azyvd.json	259	download job
fightthehorror.com-inf-20200523-040338-b8rrg.json	243	download job
fluff-tough.tumblr.com-inf-20200523-041845-bvcga-00000.warc.gz	1090314721	download job
fluff-tough.tumblr.com-inf-20200523-041845-bvcga-00000.warc.os.cdx.gz	375382	download
fly.glitch.com-inf-20200523-042531-9dv7l-00000.warc.gz	5378526684	download job
fly.glitch.com-inf-20200523-042531-9dv7l-00000.warc.os.cdx.gz	900273	download
fly.glitch.com-inf-20200523-042531-9dv7l-00001.warc.gz	5390896806	download job
fly.glitch.com-inf-20200523-042531-9dv7l-00001.warc.os.cdx.gz	32538	download
fly.glitch.com-inf-20200523-042531-9dv7l-00006.warc.gz	766979371	download job
fly.glitch.com-inf-20200523-042531-9dv7l-00006.warc.os.cdx.gz	308379	download
github.com-inf-20200523-035805-7bcod-00000.warc.gz	92854238	download job
github.com-inf-20200523-035805-7bcod-00000.warc.os.cdx.gz	141281	download
glitch.com-inf-20200523-023055-cpqwr-00002.warc.gz	5371106706	download job
glitch.com-inf-20200523-023055-cpqwr-00002.warc.os.cdx.gz	1830583	download
hedgefield.blog-inf-20200523-033751-c0c48-00000.warc.gz	5456638140	download job
hedgefield.blog-inf-20200523-033751-c0c48-00000.warc.os.cdx.gz	1288402	download
herobeatstudios.com-inf-20200523-035138-7e4kr-00000.warc.gz	262116207	download job
herobeatstudios.com-inf-20200523-035138-7e4kr-00000.warc.os.cdx.gz	454935	download
herobeatstudios.com-inf-20200523-035138-7e4kr-meta.warc.gz	311191	download job
herobeatstudios.com-inf-20200523-035138-7e4kr-meta.warc.os.cdx.gz	47	download
herobeatstudios.com-inf-20200523-035138-7e4kr.json	244	download job
heycmdrcody.wordpress.com-inf-20200523-035041-11vj6-00000.warc.gz	598049083	download job
heycmdrcody.wordpress.com-inf-20200523-035041-11vj6-00000.warc.os.cdx.gz	518501	download
heycmdrcody.wordpress.com-inf-20200523-035041-11vj6.json	250	download job
imagoofficial.wixsite.com-inf-20200523-035326-9abg3-00000.warc.gz	343328950	download job
imagoofficial.wixsite.com-inf-20200523-035326-9abg3-00000.warc.os.cdx.gz	488230	download
imagoofficial.wixsite.com-inf-20200523-035326-9abg3-meta.warc.gz	385921	download job
imagoofficial.wixsite.com-inf-20200523-035326-9abg3-meta.warc.os.cdx.gz	47	download
imagoofficial.wixsite.com-inf-20200523-035326-9abg3.json	255	download job
pdl.warnerbros.com-shallow-20200523-041047-d7oc4-00000.warc.gz	440805	download job
pdl.warnerbros.com-shallow-20200523-041047-d7oc4-00000.warc.os.cdx.gz	252	download
pdl.warnerbros.com-shallow-20200523-041048-a3uh8-00000.warc.gz	440801	download job
pdl.warnerbros.com-shallow-20200523-041048-a3uh8-00000.warc.os.cdx.gz	252	download
pdl.warnerbros.com-shallow-20200523-041048-a3uh8-meta.warc.gz	3525	download job
pdl.warnerbros.com-shallow-20200523-041048-a3uh8-meta.warc.os.cdx.gz	47	download
pdl.warnerbros.com-shallow-20200523-041054-bzsz2-meta.warc.gz	3526	download job
pdl.warnerbros.com-shallow-20200523-041054-bzsz2-meta.warc.os.cdx.gz	47	download
pdl.warnerbros.com-shallow-20200523-041054-bzsz2.json	283	download job
pdl.warnerbros.com-shallow-20200523-041055-eizww.json	280	download job
pdl.warnerbros.com-shallow-20200523-041101-2ul1c-00000.warc.gz	111572	download job
pdl.warnerbros.com-shallow-20200523-041101-2ul1c-00000.warc.os.cdx.gz	254	download
pdl.warnerbros.com-shallow-20200523-041101-2ul1c.json	283	download job
pdl.warnerbros.com-shallow-20200523-041106-1bycl-meta.warc.gz	3528	download job
pdl.warnerbros.com-shallow-20200523-041106-1bycl-meta.warc.os.cdx.gz	47	download
pdl.warnerbros.com-shallow-20200523-041106-1bycl.json	282	download job
pdl.warnerbros.com-shallow-20200523-041107-f2gdn-00000.warc.gz	170963	download job
pdl.warnerbros.com-shallow-20200523-041107-f2gdn-00000.warc.os.cdx.gz	253	download
pdl.warnerbros.com-shallow-20200523-041107-f2gdn.json	283	download job
pdl.warnerbros.com-shallow-20200523-041114-2sc04-00000.warc.gz	320853	download job
pdl.warnerbros.com-shallow-20200523-041114-2sc04-00000.warc.os.cdx.gz	257	download
pdl.warnerbros.com-shallow-20200523-041114-2sc04-meta.warc.gz	3510	download job
pdl.warnerbros.com-shallow-20200523-041114-2sc04-meta.warc.os.cdx.gz	47	download
pdl.warnerbros.com-shallow-20200523-041120-55rf0-00000.warc.gz	385738	download job
pdl.warnerbros.com-shallow-20200523-041120-55rf0-00000.warc.os.cdx.gz	259	download
pdl.warnerbros.com-shallow-20200523-041120-55rf0-meta.warc.gz	3533	download job
pdl.warnerbros.com-shallow-20200523-041120-55rf0-meta.warc.os.cdx.gz	47	download
pdl.warnerbros.com-shallow-20200523-041120-55rf0.json	293	download job
player.fm-inf-20200501-233943-6recr-00444.warc.gz	5397893108	download job
player.fm-inf-20200501-233943-6recr-00444.warc.os.cdx.gz	683396	download
rawfury.com-inf-20200523-014544-8jjkj.json	236	download job
setiathome.berkeley.edu-inf-20200308-014735-d3oh4-00055.warc.gz	5368727740	download job
setiathome.berkeley.edu-inf-20200308-014735-d3oh4-00055.warc.os.cdx.gz	14922943	download
status.glitch.com-inf-20200523-043636-7gyf5-00000.warc.gz	80294140	download job
status.glitch.com-inf-20200523-043636-7gyf5-00000.warc.os.cdx.gz	103566	download
thegentlebros.com-inf-20200523-031150-df9mu-00000.warc.gz	283991262	download job
thegentlebros.com-inf-20200523-031150-df9mu-00000.warc.os.cdx.gz	350234	download
thegentlebros.com-inf-20200523-031150-df9mu-meta.warc.gz	211828	download job
thegentlebros.com-inf-20200523-031150-df9mu-meta.warc.os.cdx.gz	47	download
thegentlebros.com-inf-20200523-031150-df9mu.json	242	download job
thevitalounge.net-inf-20200520-181244-7hkd3-00009.warc.gz	4011589438	download job
thevitalounge.net-inf-20200520-181244-7hkd3-00009.warc.os.cdx.gz	5596335	download
thevitalounge.net-inf-20200520-181244-7hkd3-meta.warc.gz	29658380	download job
thevitalounge.net-inf-20200520-181244-7hkd3-meta.warc.os.cdx.gz	47	download
thevitalounge.net-inf-20200520-181244-7hkd3.json	241	download job
timhengeveld.com-inf-20200523-033719-7w6a5-00000.warc.gz	588768417	download job
timhengeveld.com-inf-20200523-033719-7w6a5-00000.warc.os.cdx.gz	197602	download
totalmayhemgames.com-inf-20200523-033614-eldd8-00000.warc.gz	2672008287	download job
totalmayhemgames.com-inf-20200523-033614-eldd8-00000.warc.os.cdx.gz	1316776	download
totalmayhemgames.com-inf-20200523-033614-eldd8-meta.warc.gz	963017	download job
totalmayhemgames.com-inf-20200523-033614-eldd8-meta.warc.os.cdx.gz	47	download
totalmayhemgames.com-inf-20200523-033614-eldd8.json	245	download job
traplabsgame.tumblr.com-inf-20200523-055346-1oun9-00000.warc.gz	62405345	download job
traplabsgame.tumblr.com-inf-20200523-055346-1oun9-00000.warc.os.cdx.gz	50048	download
traplabsgame.tumblr.com-inf-20200523-055346-1oun9-meta.warc.gz	62168	download job
traplabsgame.tumblr.com-inf-20200523-055346-1oun9-meta.warc.os.cdx.gz	47	download
traplabsgame.tumblr.com-inf-20200523-055346-1oun9.json	248	download job
trent-polack.com-inf-20200523-034143-cfn2l-00000.warc.gz	1211177008	download job
trent-polack.com-inf-20200523-034143-cfn2l-00000.warc.os.cdx.gz	169335	download
ultimateclassicrock.com-shallow-20200523-050744-70bts-00000.warc.gz	14811167	download job
ultimateclassicrock.com-shallow-20200523-050744-70bts-00000.warc.os.cdx.gz	22003	download
ultimateclassicrock.com-shallow-20200523-050744-70bts-meta.warc.gz	16063	download job
ultimateclassicrock.com-shallow-20200523-050744-70bts-meta.warc.os.cdx.gz	47	download
ultimateclassicrock.com-shallow-20200523-050744-70bts.json	279	download job
urls-transfer.notkiska.pw-facebook-@TogglegearGames-shallow-20200523-035725-di8fd-00000.warc.gz	112903962	download job
urls-transfer.notkiska.pw-facebook-@TogglegearGames-shallow-20200523-035725-di8fd-00000.warc.os.cdx.gz	106259	download
urls-transfer.notkiska.pw-facebook-@TogglegearGames-shallow-20200523-035725-di8fd-urls.txt	2427	download
urls-transfer.notkiska.pw-facebook-@hertz-shallow-20200523-025804-bi3nw-00000.warc.gz	5393162998	download job
urls-transfer.notkiska.pw-facebook-@hertz-shallow-20200523-025804-bi3nw-00000.warc.os.cdx.gz	1039251	download
urls-transfer.notkiska.pw-facebook-@hertz-shallow-20200523-025804-bi3nw-00001.warc.gz	5369014041	download job
urls-transfer.notkiska.pw-facebook-@hertz-shallow-20200523-025804-bi3nw-00001.warc.os.cdx.gz	34352	download
urls-transfer.notkiska.pw-twitter-%23AmateurRadio-shallow-20200522-011244-diazq-00006.warc.gz	5386579498	download job
urls-transfer.notkiska.pw-twitter-%23AmateurRadio-shallow-20200522-011244-diazq-00006.warc.os.cdx.gz	2316446	download
urls-transfer.notkiska.pw-twitter-%23FMDX-shallow-20200521-132313-cfpjn-00006.warc.gz	5377435994	download job
urls-transfer.notkiska.pw-twitter-%23FMDX-shallow-20200521-132313-cfpjn-00006.warc.os.cdx.gz	468673	download
urls-transfer.notkiska.pw-twitter-%23FMDX-shallow-20200521-132313-cfpjn-00007.warc.gz	5368845932	download job
urls-transfer.notkiska.pw-twitter-%23FMDX-shallow-20200521-132313-cfpjn-00007.warc.os.cdx.gz	599557	download
urls-transfer.notkiska.pw-twitter-%23WesternSahara-shallow-20200520-155232-fw0b7-00018.warc.gz	5386597437	download job
urls-transfer.notkiska.pw-twitter-%23WesternSahara-shallow-20200520-155232-fw0b7-00018.warc.os.cdx.gz	2548361	download
urls-transfer.notkiska.pw-twitter-%23futurism-shallow-20200521-145926-dif3r-00015.warc.gz	5561231278	download job
urls-transfer.notkiska.pw-twitter-%23futurism-shallow-20200521-145926-dif3r-00015.warc.os.cdx.gz	1783894	download
urls-transfer.notkiska.pw-twitter-%23futurism-shallow-20200521-145926-dif3r-00017.warc.gz	5536609865	download job
urls-transfer.notkiska.pw-twitter-%23futurism-shallow-20200521-145926-dif3r-00017.warc.os.cdx.gz	778376	download
urls-transfer.notkiska.pw-twitter-%23transhumanism-shallow-20200521-125431-4727v-00046.warc.gz	5368714051	download job
urls-transfer.notkiska.pw-twitter-%23transhumanism-shallow-20200521-125431-4727v-00046.warc.os.cdx.gz	2403422	download
urls-transfer.notkiska.pw-twitter-%23transhumanism-shallow-20200521-125431-4727v-00047.warc.gz	5393384361	download job
urls-transfer.notkiska.pw-twitter-%23transhumanism-shallow-20200521-125431-4727v-00047.warc.os.cdx.gz	671809	download
urls-transfer.notkiska.pw-twitter-@GlitchDevs-shallow-20200523-030824-3fzhq-meta.warc.gz	833474	download job
urls-transfer.notkiska.pw-twitter-@GlitchDevs-shallow-20200523-030824-3fzhq-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@GlitchDevs-shallow-20200523-030824-3fzhq.json	332	download job
urls-transfer.notkiska.pw-twitter-@NRA-shallow-20200522-173339-b7ppp-00001.warc.gz	5492068886	download job
urls-transfer.notkiska.pw-twitter-@NRA-shallow-20200522-173339-b7ppp-00001.warc.os.cdx.gz	2330661	download
urls-transfer.notkiska.pw-twitter-@glitch-shallow-20200523-030804-an4br-00003.warc.gz	1920967455	download job
urls-transfer.notkiska.pw-twitter-@glitch-shallow-20200523-030804-an4br-00003.warc.os.cdx.gz	1530802	download
urls-transfer.notkiska.pw-twitter-@glitch-shallow-20200523-030804-an4br-meta.warc.gz	1593664	download job
urls-transfer.notkiska.pw-twitter-@glitch-shallow-20200523-030804-an4br-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@glitch-shallow-20200523-030804-an4br-urls.txt	218891	download
urls-transfer.notkiska.pw-twitter-@glitch-shallow-20200523-030804-an4br.json	324	download job
urls-transfer.notkiska.pw-wikidata-twitter-217k.txt-shallow-20200522-204135-548p7-00000.warc.gz	5368759663	download job
urls-transfer.notkiska.pw-wikidata-twitter-217k.txt-shallow-20200522-204135-548p7-00000.warc.os.cdx.gz	3928609	download
useyouroutsidevoice.co-inf-20200522-224859-7f51r-00010.warc.gz	5368712228	download job
useyouroutsidevoice.co-inf-20200522-224859-7f51r-00010.warc.os.cdx.gz	912099	download
wnpv1440.com-inf-20200502-032515-7z25h-00021.warc.gz	5375753936	download job
wnpv1440.com-inf-20200502-032515-7z25h-00021.warc.os.cdx.gz	64615	download
www.blowfishstudios.com-inf-20200523-003127-6cved-00000.warc.gz	2109357139	download job
www.blowfishstudios.com-inf-20200523-003127-6cved-00000.warc.os.cdx.gz	1202685	download
www.devespressogames.com-inf-20200523-003610-78n71-00000.warc.gz	1984808110	download job
www.devespressogames.com-inf-20200523-003610-78n71-00000.warc.os.cdx.gz	3093733	download
www.devespressogames.com-inf-20200523-003610-78n71-meta.warc.gz	3586674	download job
www.devespressogames.com-inf-20200523-003610-78n71-meta.warc.os.cdx.gz	47	download
www.devespressogames.com-inf-20200523-003610-78n71.json	249	download job
www.hertz.co.uk-inf-20200523-050736-dqa3s-00000.warc.gz	31489	download job
www.hertz.co.uk-inf-20200523-050736-dqa3s-00000.warc.os.cdx.gz	416	download
www.hertz.co.uk-inf-20200523-050736-dqa3s-meta.warc.gz	3623	download job
www.hertz.co.uk-inf-20200523-050736-dqa3s-meta.warc.os.cdx.gz	47	download
www.hertz.co.uk-inf-20200523-050736-dqa3s.json	241	download job
www.hertz.com.au-inf-20200523-045354-8enii-00001.warc.gz	1454146257	download job
www.hertz.com.au-inf-20200523-045354-8enii-00001.warc.os.cdx.gz	363	download
www.hertz247.com-inf-20200523-050257-6zxho-00000.warc.gz	230201300	download job
www.hertz247.com-inf-20200523-050257-6zxho-00000.warc.os.cdx.gz	351311	download
www.hertz247.com-inf-20200523-050257-6zxho-meta.warc.gz	262219	download job
www.hertz247.com-inf-20200523-050257-6zxho-meta.warc.os.cdx.gz	47	download
www.hertz247.com-inf-20200523-050257-6zxho.json	242	download job
www.hertztrucks.com.au-inf-20200523-045907-78agv-00000.warc.gz	53068020	download job
www.hertztrucks.com.au-inf-20200523-045907-78agv-00000.warc.os.cdx.gz	134181	download
www.hertztrucks.com.au-inf-20200523-045907-78agv-meta.warc.gz	81707	download job
www.hertztrucks.com.au-inf-20200523-045907-78agv-meta.warc.os.cdx.gz	47	download
www.hertztrucks.com.au-inf-20200523-045907-78agv.json	248	download job
www.overlawyered.com-inf-20200523-023638-e9pcr-00000.warc.gz	5388581859	download job
www.overlawyered.com-inf-20200523-023638-e9pcr-00000.warc.os.cdx.gz	2251154	download
www.primordia-game.com-inf-20200523-044053-cgeg0.json	246	download job
www.thevoxelagents.com-inf-20200523-033041-2lb5a-00000.warc.gz	747858025	download job
www.thevoxelagents.com-inf-20200523-033041-2lb5a-00000.warc.os.cdx.gz	316930	download
www.thevoxelagents.com-inf-20200523-033041-2lb5a.json	246	download job
www.togglegear.com-inf-20200523-035037-q5wow-00000.warc.gz	478773680	download job
www.togglegear.com-inf-20200523-035037-q5wow-00000.warc.os.cdx.gz	605073	download
www.togglegear.com-inf-20200523-035037-q5wow.json	243	download job
www.trancefix.nl-inf-20200506-120341-f0i5k-00138.warc.gz	5368718411	download job
www.trancefix.nl-inf-20200506-120341-f0i5k-00138.warc.os.cdx.gz	5020293	download
www.traplabs.net-inf-20200523-055256-d58di-meta.warc.gz	111485	download job
www.traplabs.net-inf-20200523-055256-d58di-meta.warc.os.cdx.gz	47	download
www.tresebrothers.com-inf-20200523-034348-1l2la-00000.warc.gz	606741034	download job
www.tresebrothers.com-inf-20200523-034348-1l2la-00000.warc.os.cdx.gz	546286	download
www.tresebrothers.com-inf-20200523-034348-1l2la.json	245	download job
www.ultizerogames.com-inf-20200523-055219-7w58y-00000.warc.gz	32867816	download job
www.ultizerogames.com-inf-20200523-055219-7w58y-00000.warc.os.cdx.gz	61519	download
www.ultizerogames.com-inf-20200523-055219-7w58y-meta.warc.gz	39687	download job
www.ultizerogames.com-inf-20200523-055219-7w58y-meta.warc.os.cdx.gz	47	download
www.ultizerogames.com-inf-20200523-055219-7w58y.json	245	download job
www.winkingworks.com-inf-20200523-043922-fcdel-00000.warc.gz	55364708	download job
www.winkingworks.com-inf-20200523-043922-fcdel-00000.warc.os.cdx.gz	116468	download
www.wobbegonggames.com-inf-20200523-044659-djqmz-meta.warc.gz	123617	download job
www.wobbegonggames.com-inf-20200523-044659-djqmz-meta.warc.os.cdx.gz	47	download
www.wobbegonggames.com-inf-20200523-044659-djqmz.json	247	download job
www.wormwoodstudios.com-inf-20200523-043946-78g8b-00000.warc.gz	2683464950	download job
www.wormwoodstudios.com-inf-20200523-043946-78g8b-00000.warc.os.cdx.gz	948211	download
www.wormwoodstudios.com-inf-20200523-043946-78g8b-meta.warc.gz	611765	download job
www.wormwoodstudios.com-inf-20200523-043946-78g8b-meta.warc.os.cdx.gz	47	download
www.wormwoodstudios.com-inf-20200523-043946-78g8b.json	247	download job
www.yahoo.com-shallow-20200523-050843-98j9d-00000.warc.gz	5461929	download job
www.yahoo.com-shallow-20200523-050843-98j9d-00000.warc.os.cdx.gz	9046	download
www.yahoo.com-shallow-20200523-050843-98j9d-meta.warc.gz	8912	download job
www.yahoo.com-shallow-20200523-050843-98j9d-meta.warc.os.cdx.gz	47	download
www.yahoo.com-shallow-20200523-050843-98j9d.json	331	download job