Item archiveteam_archivebot_go_20200902020003

View on Internet Archive

Filename	Size
2013.edmarkey.com-inf-20200901-200518-ebw4e-meta.warc.gz	1439540	download   job
2013.edmarkey.com-inf-20200901-200518-ebw4e-meta.warc.os.cdx.gz	47	download
4rtgallery.blogspot.com-inf-20200901-162501-dbsk9-00001.warc.gz	5371777198	download   job
4rtgallery.blogspot.com-inf-20200901-162501-dbsk9-00001.warc.os.cdx.gz	3971786	download
aday.29mayis.edu.tr-inf-20200902-002522-dqvm7.json	250	download   job
akademik.29mayis.edu.tr-inf-20200901-235715-2mqjo-00000.warc.gz	9253693	download   job
akademik.29mayis.edu.tr-inf-20200901-235715-2mqjo-00000.warc.os.cdx.gz	42986	download
akademik.29mayis.edu.tr-inf-20200901-235715-2mqjo-meta.warc.gz	27930	download   job
akademik.29mayis.edu.tr-inf-20200901-235715-2mqjo-meta.warc.os.cdx.gz	47	download
alexmorseforcongress.com-inf-20200902-004625-a8wea-00000.warc.gz	1839376199	download   job
alexmorseforcongress.com-inf-20200902-004625-a8wea-00000.warc.os.cdx.gz	793055	download
alexmorseforcongress.com-inf-20200902-004625-a8wea-meta.warc.gz	571952	download   job
alexmorseforcongress.com-inf-20200902-004625-a8wea-meta.warc.os.cdx.gz	47	download
alexmorseforcongress.com-inf-20200902-004625-a8wea.json	254	download   job
archive.savetheinternet.eu-inf-20200901-225209-ab1ba.json	257	download   job
archiveteam_archivebot_go_20200902020003.cdx.gz	86240781	download
archiveteam_archivebot_go_20200902020003.cdx.idx	175913	download
archiveteam_archivebot_go_20200902020003_files.xml	0	download
archiveteam_archivebot_go_20200902020003_meta.sqlite	300032	download
archiveteam_archivebot_go_20200902020003_meta.xml	969	download
aromer.29mayis.edu.tr-inf-20200902-001636-dp1l7-00000.warc.gz	480037971	download   job
aromer.29mayis.edu.tr-inf-20200902-001636-dp1l7-00000.warc.os.cdx.gz	354987	download
aromer.29mayis.edu.tr-inf-20200902-001636-dp1l7-meta.warc.gz	230062	download   job
aromer.29mayis.edu.tr-inf-20200902-001636-dp1l7-meta.warc.os.cdx.gz	47	download
aromer.29mayis.edu.tr-inf-20200902-001636-dp1l7.json	252	download   job
big-data.29mayis.edu.tr-inf-20200901-231620-80qou.json	254	download   job
big5.xinhuanet.com-inf-20200804-144727-f0ved-00069.warc.gz	5598462390	download   job
big5.xinhuanet.com-inf-20200804-144727-f0ved-00069.warc.os.cdx.gz	1943457	download
big5.xinhuanet.com-inf-20200804-144727-f0ved-00070.warc.gz	5424814186	download   job
big5.xinhuanet.com-inf-20200804-144727-f0ved-00070.warc.os.cdx.gz	1037933	download
box.nyu.tokyo-inf-20200901-234818-dg4g0-00000.warc.gz	5081596	download   job
box.nyu.tokyo-inf-20200901-234818-dg4g0-00000.warc.os.cdx.gz	12979	download
box.nyu.tokyo-inf-20200901-234818-dg4g0-meta.warc.gz	12307	download   job
box.nyu.tokyo-inf-20200901-234818-dg4g0-meta.warc.os.cdx.gz	47	download
box.nyu.tokyo-inf-20200901-234818-dg4g0.json	243	download   job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00079.warc.gz	5369009011	download   job
catalog.osaarchivum.org-inf-20200825-010137-40ig1-00079.warc.os.cdx.gz	717116	download
community.arm.com-inf-20200619-035248-6egsi-00038.warc.gz	5368711249	download   job
community.arm.com-inf-20200619-035248-6egsi-00038.warc.os.cdx.gz	34231177	download
cpanel.ipv6.songexploder.net-inf-20200902-015223-53eth-00000.warc.gz	14233868	download   job
cpanel.ipv6.songexploder.net-inf-20200902-015223-53eth-00000.warc.os.cdx.gz	44496	download
cpanel.ipv6.songexploder.net-inf-20200902-015223-53eth-meta.warc.gz	41622	download   job
cpanel.ipv6.songexploder.net-inf-20200902-015223-53eth-meta.warc.os.cdx.gz	47	download
cpanel.ipv6.songexploder.net-inf-20200902-015223-53eth-wpull.log.gz	38878	download
cpanel.ipv6.songexploder.net-inf-20200902-015223-53eth.json	259	download   job
creole.kennedyforma.com-inf-20200901-232100-4b5vs-meta.warc.gz	26261	download   job
creole.kennedyforma.com-inf-20200901-232100-4b5vs-meta.warc.os.cdx.gz	47	download
docs.microsoft.com-inf-20200719-173331-ex56m-00353.warc.gz	5610686742	download   job
docs.microsoft.com-inf-20200719-173331-ex56m-00353.warc.os.cdx.gz	1273671	download
docs.microsoft.com-inf-20200719-173331-ex56m-00355.warc.gz	5505497894	download   job
docs.microsoft.com-inf-20200719-173331-ex56m-00355.warc.os.cdx.gz	69910	download
donate.sunshinegardens.org-inf-20200902-012221-edg6h.json	256	download   job
ebys.29mayis.edu.tr-inf-20200901-235955-c3eyr-00000.warc.gz	78138690	download   job
ebys.29mayis.edu.tr-inf-20200901-235955-c3eyr-00000.warc.os.cdx.gz	49588	download
ebys.29mayis.edu.tr-inf-20200901-235955-c3eyr-meta.warc.gz	31516	download   job
ebys.29mayis.edu.tr-inf-20200901-235955-c3eyr-meta.warc.os.cdx.gz	47	download
ebys.29mayis.edu.tr-inf-20200901-235955-c3eyr.json	250	download   job
economics.29mayis.edu.tr-inf-20200901-230422-1bo69-00000.warc.gz	200437319	download   job
economics.29mayis.edu.tr-inf-20200901-230422-1bo69-00000.warc.os.cdx.gz	216308	download
economics.29mayis.edu.tr-inf-20200901-230422-1bo69-meta.warc.gz	139582	download   job
economics.29mayis.edu.tr-inf-20200901-230422-1bo69-meta.warc.os.cdx.gz	47	download
english.29mayis.edu.tr-inf-20200902-000300-bh284.json	253	download   job
espanol.kennedyforma.com-inf-20200901-232138-s00kc.json	254	download   job
felsefe.29mayis.edu.tr-inf-20200901-231221-d4qqr-00000.warc.gz	1714310551	download   job
felsefe.29mayis.edu.tr-inf-20200901-231221-d4qqr-00000.warc.os.cdx.gz	869500	download
felsefe.29mayis.edu.tr-inf-20200901-231221-d4qqr-meta.warc.gz	740085	download   job
felsefe.29mayis.edu.tr-inf-20200901-231221-d4qqr-meta.warc.os.cdx.gz	47	download
felsefe.29mayis.edu.tr-inf-20200901-231221-d4qqr.json	253	download   job
git.sunshinegardens.org-inf-20200902-002514-cqmqz-00000.warc.gz	102030	download   job
git.sunshinegardens.org-inf-20200902-002514-cqmqz-00000.warc.os.cdx.gz	1157	download
git.sunshinegardens.org-inf-20200902-002514-cqmqz-meta.warc.gz	4227	download   job
git.sunshinegardens.org-inf-20200902-002514-cqmqz-meta.warc.os.cdx.gz	47	download
git.sunshinegardens.org-inf-20200902-002514-cqmqz.json	253	download   job
hg.sunshinegardens.org-inf-20200902-002638-28y2q-00000.warc.gz	101617	download   job
hg.sunshinegardens.org-inf-20200902-002638-28y2q-00000.warc.os.cdx.gz	1154	download
hg.sunshinegardens.org-inf-20200902-002638-28y2q-meta.warc.gz	4221	download   job
hg.sunshinegardens.org-inf-20200902-002638-28y2q-meta.warc.os.cdx.gz	47	download
hg.sunshinegardens.org-inf-20200902-002638-28y2q.json	252	download   job
idari.29mayis.edu.tr-inf-20200901-230554-cufd1-00000.warc.gz	3183950	download   job
idari.29mayis.edu.tr-inf-20200901-230554-cufd1-00000.warc.os.cdx.gz	19008	download
ilahiyat.29mayis.edu.tr-inf-20200901-231543-9zv87-meta.warc.gz	497831	download   job
ilahiyat.29mayis.edu.tr-inf-20200901-231543-9zv87-meta.warc.os.cdx.gz	47	download
index.hu-inf-20200725-012829-8goer-00098.warc.gz	5368894616	download   job
index.hu-inf-20200725-012829-8goer-00098.warc.os.cdx.gz	2168106	download
international.29mayis.edu.tr-inf-20200902-000702-a2fai-00000.warc.gz	932808930	download   job
international.29mayis.edu.tr-inf-20200902-000702-a2fai-00000.warc.os.cdx.gz	776141	download
international.29mayis.edu.tr-inf-20200902-000702-a2fai-meta.warc.gz	519175	download   job
international.29mayis.edu.tr-inf-20200902-000702-a2fai-meta.warc.os.cdx.gz	47	download
international.29mayis.edu.tr-inf-20200902-000702-a2fai.json	259	download   job
kariyer.29mayis.edu.tr-inf-20200901-230434-53nve-00000.warc.gz	646504990	download   job
kariyer.29mayis.edu.tr-inf-20200901-230434-53nve-00000.warc.os.cdx.gz	75923	download
kennedy.house.gov-inf-20200901-200827-dcbfz-00000.warc.gz	5432664837	download   job
kennedy.house.gov-inf-20200901-200827-dcbfz-00000.warc.os.cdx.gz	1640312	download
kennedyforma.com-inf-20200901-200941-ce036-00003.warc.gz	5414371927	download   job
kennedyforma.com-inf-20200901-200941-ce036-00003.warc.os.cdx.gz	59483	download
kennedyforma.com-inf-20200901-200941-ce036-00004.warc.gz	5368834233	download   job
kennedyforma.com-inf-20200901-200941-ce036-00004.warc.os.cdx.gz	484022	download
kennedyforma.com-inf-20200901-200941-ce036-00005.warc.gz	5867124368	download   job
kennedyforma.com-inf-20200901-200941-ce036-00005.warc.os.cdx.gz	454748	download
kennedyforma.com-inf-20200901-200941-ce036-00006.warc.gz	6462412219	download   job
kennedyforma.com-inf-20200901-200941-ce036-00006.warc.os.cdx.gz	3393	download
kutuphane.29mayis.edu.tr-inf-20200901-231019-75fmt-00000.warc.gz	278676865	download   job
kutuphane.29mayis.edu.tr-inf-20200901-231019-75fmt-00000.warc.os.cdx.gz	471505	download
kutuphane.29mayis.edu.tr-inf-20200901-231019-75fmt-meta.warc.gz	282701	download   job
kutuphane.29mayis.edu.tr-inf-20200901-231019-75fmt-meta.warc.os.cdx.gz	47	download
mail.29mayis.edu.tr-inf-20200902-002303-5vlm9-00000.warc.gz	348672	download   job
mail.29mayis.edu.tr-inf-20200902-002303-5vlm9-00000.warc.os.cdx.gz	1967	download
mail.29mayis.edu.tr-inf-20200902-002303-5vlm9-meta.warc.gz	4745	download   job
mail.29mayis.edu.tr-inf-20200902-002303-5vlm9-meta.warc.os.cdx.gz	47	download
mail.29mayis.edu.tr-inf-20200902-002303-5vlm9.json	250	download   job
mail.soundlazer.com-inf-20200902-002655-ah7jh-00000.warc.gz	89267538	download   job
mail.soundlazer.com-inf-20200902-002655-ah7jh-00000.warc.os.cdx.gz	73485	download
mail.soundlazer.com-inf-20200902-002655-ah7jh-meta.warc.gz	45130	download   job
mail.soundlazer.com-inf-20200902-002655-ah7jh-meta.warc.os.cdx.gz	47	download
mail.soundlazer.com-inf-20200902-002655-ah7jh.json	250	download   job
majide2ch.blogspot.com-inf-20200901-162205-coi8a-00000.warc.gz	5371487190	download   job
majide2ch.blogspot.com-inf-20200901-162205-coi8a-00000.warc.os.cdx.gz	5842892	download
meta.sunshinegardens.org-inf-20200902-002558-3fsg4-00000.warc.gz	53928	download   job
meta.sunshinegardens.org-inf-20200902-002558-3fsg4-00000.warc.os.cdx.gz	693	download
meta.sunshinegardens.org-inf-20200902-002558-3fsg4-meta.warc.gz	3895	download   job
meta.sunshinegardens.org-inf-20200902-002558-3fsg4-meta.warc.os.cdx.gz	47	download
meta.sunshinegardens.org-inf-20200902-002558-3fsg4.json	254	download   job
muhmhs.com-inf-20200901-234916-9a4g4-meta.warc.gz	39583	download   job
muhmhs.com-inf-20200901-234916-9a4g4-meta.warc.os.cdx.gz	47	download
muhmhs.com-inf-20200901-234916-9a4g4.json	241	download   job
narrationroom.blogspot.com-inf-20200901-170119-c5c8e-00000.warc.gz	5368739799	download   job
narrationroom.blogspot.com-inf-20200901-170119-c5c8e-00000.warc.os.cdx.gz	8557124	download
nyu.tokyo-inf-20200901-235155-98jol-00000.warc.gz	2830079	download   job
nyu.tokyo-inf-20200901-235155-98jol-00000.warc.os.cdx.gz	6458	download
nyu.tokyo-inf-20200901-235155-98jol-meta.warc.gz	8430	download   job
nyu.tokyo-inf-20200901-235155-98jol-meta.warc.os.cdx.gz	47	download
obs.29mayis.edu.tr-inf-20200902-002421-edfy0.json	249	download   job
odeme.29mayis.edu.tr-inf-20200901-234756-3u2ff-meta.warc.gz	6364	download   job
odeme.29mayis.edu.tr-inf-20200901-234756-3u2ff-meta.warc.os.cdx.gz	47	download
odeme.29mayis.edu.tr-inf-20200901-234756-3u2ff.json	251	download   job
ogrenci.29mayis.edu.tr-inf-20200901-235049-8ppiy-00000.warc.gz	445922947	download   job
ogrenci.29mayis.edu.tr-inf-20200901-235049-8ppiy-00000.warc.os.cdx.gz	60550	download
ogrenci.29mayis.edu.tr-inf-20200901-235049-8ppiy-meta.warc.gz	38869	download   job
ogrenci.29mayis.edu.tr-inf-20200901-235049-8ppiy-meta.warc.os.cdx.gz	47	download
ogrenci.29mayis.edu.tr-inf-20200901-235049-8ppiy.json	253	download   job
politics.29mayis.edu.tr-inf-20200901-234557-3hrax-00000.warc.gz	253105395	download   job
politics.29mayis.edu.tr-inf-20200901-234557-3hrax-00000.warc.os.cdx.gz	292792	download
politics.29mayis.edu.tr-inf-20200901-234557-3hrax-meta.warc.gz	184433	download   job
politics.29mayis.edu.tr-inf-20200901-234557-3hrax-meta.warc.os.cdx.gz	47	download
politics.29mayis.edu.tr-inf-20200901-234557-3hrax.json	254	download   job
portal.29mayis.edu.tr-inf-20200901-230525-dciwu-meta.warc.gz	60967	download   job
portal.29mayis.edu.tr-inf-20200901-230525-dciwu-meta.warc.os.cdx.gz	47	download
portugues.kennedyforma.com-inf-20200901-232320-88mry-00000.warc.gz	398233179	download   job
portugues.kennedyforma.com-inf-20200901-232320-88mry-00000.warc.os.cdx.gz	375545	download
portugues.kennedyforma.com-inf-20200901-232320-88mry-meta.warc.gz	242491	download   job
portugues.kennedyforma.com-inf-20200901-232320-88mry-meta.warc.os.cdx.gz	47	download
psikoloji.29mayis.edu.tr-inf-20200901-230648-8snif-00000.warc.gz	172729922	download   job
psikoloji.29mayis.edu.tr-inf-20200901-230648-8snif-00000.warc.os.cdx.gz	218700	download
rpgcodex.net-inf-20200312-211149-2kji2-00404.warc.gz	5377124489	download   job
rpgcodex.net-inf-20200312-211149-2kji2-00404.warc.os.cdx.gz	7255373	download
sbe.29mayis.edu.tr-inf-20200902-002319-29w1e-00000.warc.gz	162945095	download   job
sbe.29mayis.edu.tr-inf-20200902-002319-29w1e-00000.warc.os.cdx.gz	52980	download
sbe.29mayis.edu.tr-inf-20200902-002319-29w1e-meta.warc.gz	33484	download   job
sbe.29mayis.edu.tr-inf-20200902-002319-29w1e-meta.warc.os.cdx.gz	47	download
sbe.29mayis.edu.tr-inf-20200902-002319-29w1e.json	249	download   job
sifre.29mayis.edu.tr-inf-20200901-235308-7n46p-00000.warc.gz	12842902	download   job
sifre.29mayis.edu.tr-inf-20200901-235308-7n46p-00000.warc.os.cdx.gz	11286	download
sifre.29mayis.edu.tr-inf-20200901-235308-7n46p-meta.warc.gz	9924	download   job
sifre.29mayis.edu.tr-inf-20200901-235308-7n46p-meta.warc.os.cdx.gz	47	download
sosyalhizmet.29mayis.edu.tr-inf-20200901-225813-3f8sb-00000.warc.gz	178377215	download   job
sosyalhizmet.29mayis.edu.tr-inf-20200901-225813-3f8sb-00000.warc.os.cdx.gz	248393	download
source.heropunch.io-inf-20200902-003234-3jy7j-00000.warc.gz	110319	download   job
source.heropunch.io-inf-20200902-003234-3jy7j-00000.warc.os.cdx.gz	1252	download
source.heropunch.io-inf-20200902-003234-3jy7j-meta.warc.gz	4300	download   job
source.heropunch.io-inf-20200902-003234-3jy7j-meta.warc.os.cdx.gz	47	download
source.heropunch.io-inf-20200902-003234-3jy7j.json	249	download   job
store.kennedyforma.com-inf-20200901-234536-20614-00000.warc.gz	61064766	download   job
store.kennedyforma.com-inf-20200901-234536-20614-00000.warc.os.cdx.gz	114750	download
store.kennedyforma.com-inf-20200901-234536-20614-meta.warc.gz	73467	download   job
store.kennedyforma.com-inf-20200901-234536-20614-meta.warc.os.cdx.gz	47	download
store.kennedyforma.com-inf-20200901-234536-20614.json	252	download   job
support.edmarkey.com-inf-20200901-230239-dkttb.json	250	download   job
surem.29mayis.edu.tr-inf-20200902-000055-qvynl.json	251	download   job
tre.29mayis.edu.tr-inf-20200901-230926-42s1t-meta.warc.gz	109946	download   job
tre.29mayis.edu.tr-inf-20200901-230926-42s1t-meta.warc.os.cdx.gz	47	download
tre.29mayis.edu.tr-inf-20200901-230926-42s1t.json	249	download   job
turkedebiyati.29mayis.edu.tr-inf-20200901-234639-8bsk2-00000.warc.gz	195258358	download   job
turkedebiyati.29mayis.edu.tr-inf-20200901-234639-8bsk2-00000.warc.os.cdx.gz	242323	download
turkedebiyati.29mayis.edu.tr-inf-20200901-234639-8bsk2-meta.warc.gz	151677	download   job
turkedebiyati.29mayis.edu.tr-inf-20200901-234639-8bsk2-meta.warc.os.cdx.gz	47	download
turkedebiyati.29mayis.edu.tr-inf-20200901-234639-8bsk2.json	259	download   job
turomer.29mayis.edu.tr-inf-20200901-234328-6a8wt-00000.warc.gz	27509824	download   job
turomer.29mayis.edu.tr-inf-20200901-234328-6a8wt-00000.warc.os.cdx.gz	53242	download
turomer.29mayis.edu.tr-inf-20200901-234328-6a8wt-meta.warc.gz	34584	download   job
turomer.29mayis.edu.tr-inf-20200901-234328-6a8wt-meta.warc.os.cdx.gz	47	download
turomer.29mayis.edu.tr-inf-20200901-234328-6a8wt.json	253	download   job
urls-transfer.notkiska.pw-facebook-@CongressmanJoeKennedyIII-shallow-20200901-205146-434sm-00004.warc.gz	5653795676	download   job
urls-transfer.notkiska.pw-facebook-@CongressmanJoeKennedyIII-shallow-20200901-205146-434sm-00004.warc.os.cdx.gz	33022	download
urls-transfer.notkiska.pw-facebook-@CongressmanJoeKennedyIII-shallow-20200901-205146-434sm-00005.warc.gz	5368964555	download   job
urls-transfer.notkiska.pw-facebook-@CongressmanJoeKennedyIII-shallow-20200901-205146-434sm-00005.warc.os.cdx.gz	256332	download
urls-transfer.notkiska.pw-facebook-@CongressmanJoeKennedyIII-shallow-20200901-205146-434sm-00006.warc.gz	5398175668	download   job
urls-transfer.notkiska.pw-facebook-@CongressmanJoeKennedyIII-shallow-20200901-205146-434sm-00006.warc.os.cdx.gz	189551	download
urls-transfer.notkiska.pw-facebook-@EdMarkeyforMA-shallow-20200901-200751-5d6xr-00000.warc.gz	5365862475	download   job
urls-transfer.notkiska.pw-facebook-@EdMarkeyforMA-shallow-20200901-200751-5d6xr-00000.warc.os.cdx.gz	1977959	download
urls-transfer.notkiska.pw-facebook-@EdMarkeyforMA-shallow-20200901-200751-5d6xr-urls.txt	241418	download
urls-transfer.notkiska.pw-facebook-@JoeKennedyIII-shallow-20200901-210601-eeamg-00003.warc.gz	5380721168	download   job
urls-transfer.notkiska.pw-facebook-@JoeKennedyIII-shallow-20200901-210601-eeamg-00003.warc.os.cdx.gz	169105	download
urls-transfer.notkiska.pw-facebook-@JoeKennedyIII-shallow-20200901-210601-eeamg-00004.warc.gz	5414463144	download   job
urls-transfer.notkiska.pw-facebook-@JoeKennedyIII-shallow-20200901-210601-eeamg-00004.warc.os.cdx.gz	199141	download
urls-transfer.notkiska.pw-facebook-@StudentsForADemocraticSocietyNational-shallow-20200901-224003-1yl6b-00000.warc.gz	2526392328	download   job
urls-transfer.notkiska.pw-facebook-@StudentsForADemocraticSocietyNational-shallow-20200901-224003-1yl6b-00000.warc.os.cdx.gz	1512535	download
urls-transfer.notkiska.pw-facebook-@StudentsForADemocraticSocietyNational-shallow-20200901-224003-1yl6b-meta.warc.gz	966979	download   job
urls-transfer.notkiska.pw-facebook-@StudentsForADemocraticSocietyNational-shallow-20200901-224003-1yl6b-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@StudentsForADemocraticSocietyNational-shallow-20200901-224003-1yl6b-urls.txt	138926	download
urls-transfer.notkiska.pw-facebook-@StudentsForADemocraticSocietyNational-shallow-20200901-224003-1yl6b.json	388	download   job
urls-transfer.notkiska.pw-twitter-@AdrienneRewi-shallow-20200901-073819-5hxc3-00009.warc.gz	5370103376	download   job
urls-transfer.notkiska.pw-twitter-@AdrienneRewi-shallow-20200901-073819-5hxc3-00009.warc.os.cdx.gz	2359884	download
urls-transfer.notkiska.pw-twitter-@NewSDS-shallow-20200901-223712-5i1tq-00000.warc.gz	244457766	download   job
urls-transfer.notkiska.pw-twitter-@NewSDS-shallow-20200901-223712-5i1tq-00000.warc.os.cdx.gz	442697	download
urls-transfer.notkiska.pw-twitter-@NewSDS-shallow-20200901-223712-5i1tq-urls.txt	38093	download
urls-transfer.notkiska.pw-twitter-@RepJoeKennedy-shallow-20200901-200738-8hheb-00000.warc.gz	5631564129	download   job
urls-transfer.notkiska.pw-twitter-@RepJoeKennedy-shallow-20200901-200738-8hheb-00000.warc.os.cdx.gz	4152403	download
urls-transfer.notkiska.pw-twitter-@RightsDissent-shallow-20200901-172025-32m35-00000.warc.gz	5541425218	download   job
urls-transfer.notkiska.pw-twitter-@RightsDissent-shallow-20200901-172025-32m35-00000.warc.os.cdx.gz	2407121	download
www.edmarkey.com-inf-20200901-200032-69kh4-00001.warc.gz	5383939288	download   job
www.edmarkey.com-inf-20200901-200032-69kh4-00001.warc.os.cdx.gz	1700297	download
www.edmarkey.com-inf-20200901-200032-69kh4.json	246	download   job
www.iafrikan.com-shallow-20200902-005151-afab1-00000.warc.gz	1696079	download   job
www.iafrikan.com-shallow-20200902-005151-afab1-00000.warc.os.cdx.gz	3346	download
www.iafrikan.com-shallow-20200902-005151-afab1-meta.warc.gz	5590	download   job
www.iafrikan.com-shallow-20200902-005151-afab1-meta.warc.os.cdx.gz	47	download
www.iafrikan.com-shallow-20200902-005151-afab1.json	329	download   job
www.nealforcongress.com-inf-20200902-005225-dmsv4.json	253	download   job
www.newsds.org-inf-20200902-000112-d6zcl-00000.warc.gz	75700233	download   job
www.newsds.org-inf-20200902-000112-d6zcl-00000.warc.os.cdx.gz	81146	download
www.newsds.org-inf-20200902-000112-d6zcl-meta.warc.gz	48934	download   job
www.newsds.org-inf-20200902-000112-d6zcl-meta.warc.os.cdx.gz	47	download
www.newsds.org-inf-20200902-000112-d6zcl.json	244	download   job
www.rosettastone.com-inf-20200831-200042-5dfa7-00045.warc.gz	5657289871	download   job
www.rosettastone.com-inf-20200831-200042-5dfa7-00045.warc.os.cdx.gz	12259	download
www.sk.gov.by-inf-20200819-052242-5tbt0-meta.warc.gz	5623363	download   job
www.sk.gov.by-inf-20200819-052242-5tbt0-meta.warc.os.cdx.gz	47	download
www.sk.gov.by-inf-20200819-052242-5tbt0.json	243	download   job
www.walmart.com-shallow-20200901-215403-ea7jr-00000.warc.gz	18785155	download   job
www.walmart.com-shallow-20200901-215403-ea7jr-00000.warc.os.cdx.gz	303508	download
www.walmart.com-shallow-20200901-215403-ea7jr-meta.warc.gz	210604	download   job
www.walmart.com-shallow-20200901-215403-ea7jr-meta.warc.os.cdx.gz	47	download
www.walmart.com-shallow-20200901-215403-ea7jr.json	321	download   job
www.walmart.com-shallow-20200901-220433-baicu-00000.warc.gz	21965956	download   job
www.walmart.com-shallow-20200901-220433-baicu-00000.warc.os.cdx.gz	304492	download
www.walmart.com-shallow-20200901-220433-baicu-meta.warc.gz	210301	download   job
www.walmart.com-shallow-20200901-220433-baicu-meta.warc.os.cdx.gz	47	download
www.walmart.com-shallow-20200901-220433-baicu.json	324	download   job
www.wired.com-shallow-20200901-175756-dp88e-00000.warc.gz	6440896	download   job
www.wired.com-shallow-20200901-175756-dp88e-00000.warc.os.cdx.gz	11579	download
www.wired.com-shallow-20200901-175756-dp88e-meta.warc.gz	11115	download   job
www.wired.com-shallow-20200901-175756-dp88e-meta.warc.os.cdx.gz	47	download
www.wired.com-shallow-20200901-175756-dp88e.json	321	download   job
www.youtube.com-shallow-20200901-200324-4dgd5-00000.warc.gz	12395112	download   job
www.youtube.com-shallow-20200901-200324-4dgd5-00000.warc.os.cdx.gz	12602	download
www.youtube.com-shallow-20200901-200324-4dgd5-meta.warc.gz	10797	download   job
www.youtube.com-shallow-20200901-200324-4dgd5-meta.warc.os.cdx.gz	47	download
www.youtube.com-shallow-20200901-200324-4dgd5.json	281	download   job
www.youtube.com-shallow-20200901-205000-d1jyk-00000.warc.gz	12310127	download   job
www.youtube.com-shallow-20200901-205000-d1jyk-00000.warc.os.cdx.gz	11754	download
www.youtube.com-shallow-20200901-205000-d1jyk-meta.warc.gz	10300	download   job
www.youtube.com-shallow-20200901-205000-d1jyk-meta.warc.os.cdx.gz	47	download
www.youtube.com-shallow-20200901-205000-d1jyk.json	281	download   job
www.youtube.com-shallow-20200901-205036-65ryn-00000.warc.gz	12354745	download   job
www.youtube.com-shallow-20200901-205036-65ryn-00000.warc.os.cdx.gz	12256	download
www.youtube.com-shallow-20200901-205036-65ryn-meta.warc.gz	10593	download   job
www.youtube.com-shallow-20200901-205036-65ryn-meta.warc.os.cdx.gz	47	download
www.youtube.com-shallow-20200901-205036-65ryn.json	281	download   job
www.youtube.com-shallow-20200901-231819-8qk0w.json	281	download   job
yadyok.29mayis.edu.tr-inf-20200901-232838-8xpuf.json	252	download   job
yosbasvuru.29mayis.edu.tr-inf-20200901-225723-6o40e-00000.warc.gz	877278	download   job
yosbasvuru.29mayis.edu.tr-inf-20200901-225723-6o40e-00000.warc.os.cdx.gz	3858	download
yosbasvuru.29mayis.edu.tr-inf-20200901-225723-6o40e-meta.warc.gz	6030	download   job
yosbasvuru.29mayis.edu.tr-inf-20200901-225723-6o40e-meta.warc.os.cdx.gz	47	download
yosbasvuru.29mayis.edu.tr-inf-20200901-225723-6o40e.json	256	download   job
yurt.29mayis.edu.tr-inf-20200902-000716-8eutu-00000.warc.gz	121042643	download   job
yurt.29mayis.edu.tr-inf-20200902-000716-8eutu-00000.warc.os.cdx.gz	102624	download
yurt.29mayis.edu.tr-inf-20200902-000716-8eutu-meta.warc.gz	70418	download   job
yurt.29mayis.edu.tr-inf-20200902-000716-8eutu-meta.warc.os.cdx.gz	47	download
yurt.29mayis.edu.tr-inf-20200902-000716-8eutu.json	250	download   job
yurtodeme.29mayis.edu.tr-inf-20200901-231120-9nmvr-00000.warc.gz	5222698	download   job
yurtodeme.29mayis.edu.tr-inf-20200901-231120-9nmvr-00000.warc.os.cdx.gz	9697	download
yurtodeme.29mayis.edu.tr-inf-20200901-231120-9nmvr-meta.warc.gz	9242	download   job
yurtodeme.29mayis.edu.tr-inf-20200901-231120-9nmvr-meta.warc.os.cdx.gz	47	download
yurtodeme.29mayis.edu.tr-inf-20200901-231120-9nmvr.json	255	download   job
yyodeme.29mayis.edu.tr-inf-20200901-231037-28lao-00000.warc.gz	1726858	download   job
yyodeme.29mayis.edu.tr-inf-20200901-231037-28lao-00000.warc.os.cdx.gz	5313	download
yyodeme.29mayis.edu.tr-inf-20200901-231037-28lao-meta.warc.gz	6360	download   job
yyodeme.29mayis.edu.tr-inf-20200901-231037-28lao-meta.warc.os.cdx.gz	47	download
yyodeme.29mayis.edu.tr-inf-20200901-231037-28lao.json	253	download   job