Item archiveteam_archivebot_go_20201111160002

Filename	Size
album.ee-inf-20200928-223451-4nqsi-00269.warc.gz	5368786309	download job
album.ee-inf-20200928-223451-4nqsi-00269.warc.os.cdx.gz	2384351	download
archiveteam_archivebot_go_20201111160002.cdx.gz	20940108	download
archiveteam_archivebot_go_20201111160002.cdx.idx	21723	download
archiveteam_archivebot_go_20201111160002_files.xml	0	download
archiveteam_archivebot_go_20201111160002_meta.sqlite	229376	download
archiveteam_archivebot_go_20201111160002_meta.xml	968	download
commonslibrary.org-inf-20201111-022421-ezy1j-00018.warc.gz	5537380530	download job
commonslibrary.org-inf-20201111-022421-ezy1j-00018.warc.os.cdx.gz	4408923	download
disinformationartist.com-inf-20201111-155014-2017b-meta.warc.gz	14270	download job
disinformationartist.com-inf-20201111-155014-2017b-meta.warc.os.cdx.gz	47	download
graphika.com-inf-20201111-124317-90d76-00001.warc.gz	3180617237	download job
graphika.com-inf-20201111-124317-90d76-00001.warc.os.cdx.gz	1082420	download
graphika.com-inf-20201111-124317-90d76-meta.warc.gz	1075657	download job
graphika.com-inf-20201111-124317-90d76-meta.warc.os.cdx.gz	47	download
graphika.com-inf-20201111-124317-90d76.json	242	download job
groups.io-inf-20201111-023117-udsgk-00010.warc.gz	5376883640	download job
groups.io-inf-20201111-023117-udsgk-00010.warc.os.cdx.gz	32989	download
groups.io-inf-20201111-023117-udsgk-00011.warc.gz	5369210585	download job
groups.io-inf-20201111-023117-udsgk-00011.warc.os.cdx.gz	249692	download
hostmaster.donor.watch-shallow-20201111-144629-2s8ll-00000.warc.gz	2792117	download job
hostmaster.donor.watch-shallow-20201111-144629-2s8ll-00000.warc.os.cdx.gz	11790	download
hostmaster.donor.watch-shallow-20201111-144629-2s8ll-meta.warc.gz	9568	download job
hostmaster.donor.watch-shallow-20201111-144629-2s8ll-meta.warc.os.cdx.gz	47	download
hostmaster.donor.watch-shallow-20201111-144629-2s8ll.json	256	download job
hrf.org-inf-20201111-143746-b4bht-00000.warc.gz	5369897517	download job
hrf.org-inf-20201111-143746-b4bht-00000.warc.os.cdx.gz	137352	download
hrf.org-inf-20201111-143746-b4bht-00002.warc.gz	5400311018	download job
hrf.org-inf-20201111-143746-b4bht-00002.warc.os.cdx.gz	28736	download
hrp.urbanjustice.org-inf-20201111-124821-dw3kk-00000.warc.gz	3890472271	download job
hrp.urbanjustice.org-inf-20201111-124821-dw3kk-00000.warc.os.cdx.gz	1220936	download
hrp.urbanjustice.org-inf-20201111-124821-dw3kk-meta.warc.gz	755911	download job
hrp.urbanjustice.org-inf-20201111-124821-dw3kk-meta.warc.os.cdx.gz	47	download
hrp.urbanjustice.org-inf-20201111-124821-dw3kk.json	250	download job
imperiumadinfinitum.wordpress.com-inf-20201111-140432-9qrng-00000.warc.gz	5407614265	download job
imperiumadinfinitum.wordpress.com-inf-20201111-140432-9qrng-00000.warc.os.cdx.gz	814250	download
inpdum.bigcartel.com-inf-20201111-141925-4c0p2-00000.warc.gz	24357275	download job
inpdum.bigcartel.com-inf-20201111-141925-4c0p2-00000.warc.os.cdx.gz	32628	download
inpdum.bigcartel.com-inf-20201111-141925-4c0p2-meta.warc.gz	22360	download job
inpdum.bigcartel.com-inf-20201111-141925-4c0p2-meta.warc.os.cdx.gz	47	download
inpdum.bigcartel.com-inf-20201111-141925-4c0p2.json	250	download job
ischool.uw.edu-inf-20201111-155201-b07rn-00000.warc.gz	3767	download job
ischool.uw.edu-inf-20201111-155201-b07rn-00000.warc.os.cdx.gz	206	download
parler.com-shallow-20201111-145351-bew1g-00000.warc.gz	56373396	download job
parler.com-shallow-20201111-145351-bew1g-00000.warc.os.cdx.gz	10721	download
parler.com-shallow-20201111-145351-bew1g-meta.warc.gz	10030	download job
parler.com-shallow-20201111-145351-bew1g-meta.warc.os.cdx.gz	47	download
parler.com-shallow-20201111-145351-bew1g.json	277	download job
t.co-shallow-20201111-142454-ac87a-00000.warc.gz	3978	download job
t.co-shallow-20201111-142454-ac87a-00000.warc.os.cdx.gz	216	download
t.co-shallow-20201111-142454-ac87a-meta.warc.gz	3365	download job
t.co-shallow-20201111-142454-ac87a-meta.warc.os.cdx.gz	47	download
t.co-shallow-20201111-142454-ac87a.json	253	download job
t.me-inf-20201111-144055-643ci-00000.warc.gz	3598791	download job
t.me-inf-20201111-144055-643ci-00000.warc.os.cdx.gz	7194	download
t.me-inf-20201111-144055-643ci-meta.warc.gz	7569	download job
t.me-inf-20201111-144055-643ci-meta.warc.os.cdx.gz	47	download
t.me-inf-20201111-144055-643ci.json	244	download job
the-eye.eu-shallow-20201111-140331-b1xmj-00000.warc.gz	551228034	download job
the-eye.eu-shallow-20201111-140331-b1xmj-00000.warc.os.cdx.gz	251	download
the-eye.eu-shallow-20201111-140331-b1xmj-meta.warc.gz	3528	download job
the-eye.eu-shallow-20201111-140331-b1xmj-meta.warc.os.cdx.gz	47	download
the-eye.eu-shallow-20201111-140331-b1xmj.json	297	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00010.warc.gz	5433365027	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00010.warc.os.cdx.gz	33315	download
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00011.warc.gz	5391538220	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00011.warc.os.cdx.gz	35385	download
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00013.warc.gz	5383433020	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00013.warc.os.cdx.gz	31249	download
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00015.warc.gz	5373962536	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00015.warc.os.cdx.gz	29833	download
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00016.warc.gz	5375703293	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00016.warc.os.cdx.gz	32018	download
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00017.warc.gz	5377358484	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00017.warc.os.cdx.gz	540273	download
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00018.warc.gz	5477708676	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00018.warc.os.cdx.gz	567248	download
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00019.warc.gz	5391547664	download job
urls-archive.max.fan-twitter-@DrChristineMann-20201104T104920Z.txt-shallow-20201111-041124-6rxuf-00019.warc.os.cdx.gz	66493	download
urls-archive.max.fan-twitter-@DrInam4Congress-20201104T042519Z.txt-shallow-20201111-141555-ahp8t-00000.warc.gz	8439601	download job
urls-archive.max.fan-twitter-@DrInam4Congress-20201104T042519Z.txt-shallow-20201111-141555-ahp8t-00000.warc.os.cdx.gz	7120	download
urls-archive.max.fan-twitter-@DrInam4Congress-20201104T042519Z.txt-shallow-20201111-141555-ahp8t-meta.warc.gz	7914	download job
urls-archive.max.fan-twitter-@DrInam4Congress-20201104T042519Z.txt-shallow-20201111-141555-ahp8t-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrInam4Congress-20201104T042519Z.txt-shallow-20201111-141555-ahp8t-urls.txt	167	download
urls-archive.max.fan-twitter-@DrInam4Congress-20201104T042519Z.txt-shallow-20201111-141555-ahp8t.json	385	download job
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201103T211024Z.txt-shallow-20201111-141556-ce02l-00000.warc.gz	5382115225	download job
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201103T211024Z.txt-shallow-20201111-141556-ce02l-00000.warc.os.cdx.gz	112394	download
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201104T042200Z.txt-shallow-20201111-141556-e4pts-00000.warc.gz	2003393	download job
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201104T042200Z.txt-shallow-20201111-141556-e4pts-00000.warc.os.cdx.gz	5226	download
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201104T042200Z.txt-shallow-20201111-141556-e4pts-meta.warc.gz	6793	download job
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201104T042200Z.txt-shallow-20201111-141556-e4pts-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201104T042200Z.txt-shallow-20201111-141556-e4pts-urls.txt	230	download
urls-archive.max.fan-twitter-@DrJamesStGeorge-20201104T042200Z.txt-shallow-20201111-141556-e4pts.json	385	download job
urls-archive.max.fan-twitter-@DrJayKinzler-20201103T221705Z.txt-shallow-20201111-141624-1rf09-00000.warc.gz	5408553402	download job
urls-archive.max.fan-twitter-@DrJayKinzler-20201103T221705Z.txt-shallow-20201111-141624-1rf09-00000.warc.os.cdx.gz	632837	download
urls-archive.max.fan-twitter-@DrJoe4congress-20201104T041654Z.txt-shallow-20201111-141626-b8ki3-00000.warc.gz	98233268	download job
urls-archive.max.fan-twitter-@DrJoe4congress-20201104T041654Z.txt-shallow-20201111-141626-b8ki3-00000.warc.os.cdx.gz	81676	download
urls-archive.max.fan-twitter-@DrJoe4congress-20201104T041654Z.txt-shallow-20201111-141626-b8ki3-meta.warc.gz	54931	download job
urls-archive.max.fan-twitter-@DrJoe4congress-20201104T041654Z.txt-shallow-20201111-141626-b8ki3-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrJoe4congress-20201104T041654Z.txt-shallow-20201111-141626-b8ki3-urls.txt	230	download
urls-archive.max.fan-twitter-@DrJoe4congress-20201104T041654Z.txt-shallow-20201111-141626-b8ki3.json	383	download job
urls-archive.max.fan-twitter-@DrK4Congress-20201104T140943Z.txt-shallow-20201111-141626-1bpbo-00000.warc.gz	227830762	download job
urls-archive.max.fan-twitter-@DrK4Congress-20201104T140943Z.txt-shallow-20201111-141626-1bpbo-00000.warc.os.cdx.gz	293801	download
urls-archive.max.fan-twitter-@DrK4Congress-20201104T140943Z.txt-shallow-20201111-141626-1bpbo-meta.warc.gz	180663	download job
urls-archive.max.fan-twitter-@DrK4Congress-20201104T140943Z.txt-shallow-20201111-141626-1bpbo-meta.warc.os.cdx.gz	47	download
urls-archive.max.fan-twitter-@DrK4Congress-20201104T140943Z.txt-shallow-20201111-141626-1bpbo-urls.txt	32561	download
urls-archive.max.fan-twitter-@DrK4Congress-20201104T140943Z.txt-shallow-20201111-141626-1bpbo.json	379	download job
urls-archive.max.fan-twitter-@candacefor24-20201104T104845Z.txt-shallow-20201107-165805-2eh4r-urls.txt	382940	download
urls-archive.max.fan-twitter-@chiproytx-20201104T111530Z.txt-shallow-20201108-000312-5n6w8-00010.warc.gz	5499381201	download job
urls-archive.max.fan-twitter-@chiproytx-20201104T111530Z.txt-shallow-20201108-000312-5n6w8-00010.warc.os.cdx.gz	1207655	download
urls-archive.max.fan-twitter-@chiproytx-20201104T111530Z.txt-shallow-20201108-000312-5n6w8-00011.warc.gz	5685530430	download job
urls-archive.max.fan-twitter-@chiproytx-20201104T111530Z.txt-shallow-20201108-000312-5n6w8-00011.warc.os.cdx.gz	173880	download
urls-transfer.notkiska.pw-house.gov-representatives-a-inf-20201027-025500-8hpox-00094.warc.gz	5373138481	download job
urls-transfer.notkiska.pw-house.gov-representatives-a-inf-20201027-025500-8hpox-00094.warc.os.cdx.gz	2331951	download
urls-transfer.notkiska.pw-house.gov-representatives-d-inf-20201027-025523-dgqzt-00084.warc.gz	5377774618	download job
urls-transfer.notkiska.pw-house.gov-representatives-d-inf-20201027-025523-dgqzt-00084.warc.os.cdx.gz	390754	download
urls-transfer.notkiska.pw-twitter-%23Disenfranchised-shallow-20201111-024133-34gum-meta.warc.gz	6109466	download job
urls-transfer.notkiska.pw-twitter-%23Disenfranchised-shallow-20201111-024133-34gum-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-%23Disenfranchised-shallow-20201111-024133-34gum-urls.txt	751550	download
urls-transfer.notkiska.pw-twitter-@Baochoy-shallow-20201111-142129-5557r-00000.warc.gz	100813873	download job
urls-transfer.notkiska.pw-twitter-@Baochoy-shallow-20201111-142129-5557r-00000.warc.os.cdx.gz	219894	download
urls-transfer.notkiska.pw-twitter-@Baochoy-shallow-20201111-142129-5557r-meta.warc.gz	133417	download job
urls-transfer.notkiska.pw-twitter-@Baochoy-shallow-20201111-142129-5557r-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@Baochoy-shallow-20201111-142129-5557r-urls.txt	24274	download
urls-transfer.notkiska.pw-twitter-@Baochoy-shallow-20201111-142129-5557r.json	326	download job
urls-transfer.notkiska.pw-twitter-@CChinaScholars-shallow-20201111-143020-6eiuh-00000.warc.gz	8005065	download job
urls-transfer.notkiska.pw-twitter-@CChinaScholars-shallow-20201111-143020-6eiuh-00000.warc.os.cdx.gz	15514	download
urls-transfer.notkiska.pw-twitter-@CChinaScholars-shallow-20201111-143020-6eiuh-meta.warc.gz	12710	download job
urls-transfer.notkiska.pw-twitter-@CChinaScholars-shallow-20201111-143020-6eiuh-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@CChinaScholars-shallow-20201111-143020-6eiuh-urls.txt	528	download
urls-transfer.notkiska.pw-twitter-@CChinaScholars-shallow-20201111-143020-6eiuh.json	340	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00033.warc.gz	5404328345	download job
urls-transfer.notkiska.pw-twitter-@JeffreyGuterman-shallow-20201107-204309-28fif-00033.warc.os.cdx.gz	1649260	download
urls-transfer.notkiska.pw-twitter-@SophieMak1-shallow-20201111-142002-cgu6w-00000.warc.gz	1090641289	download job
urls-transfer.notkiska.pw-twitter-@SophieMak1-shallow-20201111-142002-cgu6w-00000.warc.os.cdx.gz	508662	download
urls-transfer.notkiska.pw-twitter-@StillLoudHK-shallow-20201111-143058-cisj9-00000.warc.gz	282152071	download job
urls-transfer.notkiska.pw-twitter-@StillLoudHK-shallow-20201111-143058-cisj9-00000.warc.os.cdx.gz	188560	download
urls-transfer.notkiska.pw-twitter-@StillLoudHK-shallow-20201111-143058-cisj9-meta.warc.gz	109789	download job
urls-transfer.notkiska.pw-twitter-@StillLoudHK-shallow-20201111-143058-cisj9-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@StillLoudHK-shallow-20201111-143058-cisj9-urls.txt	10419	download
urls-transfer.notkiska.pw-twitter-@StillLoudHK-shallow-20201111-143058-cisj9.json	334	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00025.warc.gz	5474556360	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00025.warc.os.cdx.gz	9832	download
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00026.warc.gz	5423995332	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00026.warc.os.cdx.gz	8238	download
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00027.warc.gz	5674846053	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00027.warc.os.cdx.gz	6509	download
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00029.warc.gz	5681341055	download job
urls-transfer.notkiska.pw-twitter-@TomBevanRCP-shallow-20201110-210919-ethp2-00029.warc.os.cdx.gz	1287819	download
urls-transfer.notkiska.pw-twitter-@Transition46-shallow-20201111-142935-5lpur-00000.warc.gz	9936677	download job
urls-transfer.notkiska.pw-twitter-@Transition46-shallow-20201111-142935-5lpur-00000.warc.os.cdx.gz	33232	download
urls-transfer.notkiska.pw-twitter-@Transition46-shallow-20201111-142935-5lpur-meta.warc.gz	22826	download job
urls-transfer.notkiska.pw-twitter-@Transition46-shallow-20201111-142935-5lpur-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@Transition46-shallow-20201111-142935-5lpur-urls.txt	1552	download
urls-transfer.notkiska.pw-twitter-@Transition46-shallow-20201111-142935-5lpur.json	336	download job
www.hmdb.org-inf-20201018-175958-aboei-00312.warc.gz	5370088440	download job
www.hmdb.org-inf-20201018-175958-aboei-00312.warc.os.cdx.gz	136527	download
www.instagram.com-inf-20201111-133758-2b81n-00000.warc.gz	37124348	download job
www.instagram.com-inf-20201111-133758-2b81n-00000.warc.os.cdx.gz	76589	download
www.instagram.com-inf-20201111-133758-2b81n-meta.warc.gz	52055	download job
www.instagram.com-inf-20201111-133758-2b81n-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-133758-2b81n.json	261	download job
www.instagram.com-inf-20201111-140045-a4lmw-00000.warc.gz	4476927	download job
www.instagram.com-inf-20201111-140045-a4lmw-00000.warc.os.cdx.gz	18309	download
www.instagram.com-inf-20201111-140045-a4lmw-meta.warc.gz	15575	download job
www.instagram.com-inf-20201111-140045-a4lmw-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-140045-a4lmw.json	262	download job
www.instagram.com-inf-20201111-140715-1lq0o-00000.warc.gz	19640079	download job
www.instagram.com-inf-20201111-140715-1lq0o-00000.warc.os.cdx.gz	33321	download
www.instagram.com-inf-20201111-140715-1lq0o-meta.warc.gz	25791	download job
www.instagram.com-inf-20201111-140715-1lq0o-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-140715-1lq0o.json	258	download job
www.instagram.com-inf-20201111-141738-ab6os-00000.warc.gz	28267333	download job
www.instagram.com-inf-20201111-141738-ab6os-00000.warc.os.cdx.gz	75743	download
www.instagram.com-inf-20201111-141738-ab6os-meta.warc.gz	50563	download job
www.instagram.com-inf-20201111-141738-ab6os-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-141738-ab6os.json	261	download job
www.instagram.com-inf-20201111-151139-a8ej0.json	262	download job
www.instagram.com-inf-20201111-152130-5tjkw-meta.warc.gz	34164	download job
www.instagram.com-inf-20201111-152130-5tjkw-meta.warc.os.cdx.gz	47	download
www.instagram.com-inf-20201111-153345-6p698-00000.warc.gz	28588026	download job
www.instagram.com-inf-20201111-153345-6p698-00000.warc.os.cdx.gz	75604	download
www.instagram.com-inf-20201111-153345-6p698.json	264	download job
www.jonesday.com-inf-20201110-183013-5ct9e-00003.warc.gz	5397161822	download job
www.jonesday.com-inf-20201110-183013-5ct9e-00003.warc.os.cdx.gz	582197	download
www.mythorntons.com-shallow-20201111-141614-2m8e9-00000.warc.gz	2479167	download job
www.mythorntons.com-shallow-20201111-141614-2m8e9-00000.warc.os.cdx.gz	6674	download
www.mythorntons.com-shallow-20201111-141614-2m8e9-meta.warc.gz	7363	download job
www.mythorntons.com-shallow-20201111-141614-2m8e9-meta.warc.os.cdx.gz	47	download
www.mythorntons.com-shallow-20201111-141614-2m8e9.json	270	download job
www.nytimes.com-shallow-20201111-143325-f2fqt-00000.warc.gz	41590312	download job
www.nytimes.com-shallow-20201111-143325-f2fqt-00000.warc.os.cdx.gz	41660	download
www.nytimes.com-shallow-20201111-143325-f2fqt-meta.warc.gz	38801	download job
www.nytimes.com-shallow-20201111-143325-f2fqt-meta.warc.os.cdx.gz	47	download
www.nytimes.com-shallow-20201111-143325-f2fqt.json	362	download job
www.snapchat.com-shallow-20201111-144031-f2s6d-00000.warc.gz	5153303	download job
www.snapchat.com-shallow-20201111-144031-f2s6d-00000.warc.os.cdx.gz	20062	download
www.snapchat.com-shallow-20201111-144031-f2s6d-meta.warc.gz	17150	download job
www.snapchat.com-shallow-20201111-144031-f2s6d-meta.warc.os.cdx.gz	47	download
www.snapchat.com-shallow-20201111-144031-f2s6d.json	264	download job
www.stopthestealcaravan.com-inf-20201111-150733-ee4bf-meta.warc.gz	99977	download job
www.stopthestealcaravan.com-inf-20201111-150733-ee4bf-meta.warc.os.cdx.gz	47	download
www.stopthestealcaravan.com-inf-20201111-150733-ee4bf.json	256	download job
www.thorntonsinc.com-shallow-20201111-141719-7p40x-00000.warc.gz	411817	download job
www.thorntonsinc.com-shallow-20201111-141719-7p40x-00000.warc.os.cdx.gz	283	download
www.thorntonsinc.com-shallow-20201111-141719-7p40x-meta.warc.gz	3568	download job
www.thorntonsinc.com-shallow-20201111-141719-7p40x-meta.warc.os.cdx.gz	47	download
www.thorntonsinc.com-shallow-20201111-141719-7p40x.json	319	download job
www.washingtonpost.com-shallow-20201111-143324-effey-00000.warc.gz	189679055	download job
www.washingtonpost.com-shallow-20201111-143324-effey-00000.warc.os.cdx.gz	12566	download
www.washingtonpost.com-shallow-20201111-143324-effey-meta.warc.gz	11484	download job
www.washingtonpost.com-shallow-20201111-143324-effey-meta.warc.os.cdx.gz	47	download
www.washingtonpost.com-shallow-20201111-143324-effey.json	373	download job