Item archiveteam_archivebot_go_20230707085827_0bc4047f

Filename	Size
aldor.org-inf-20230707-053512-48zqb-00000.warc.gz	559719	download job
aldor.org-inf-20230707-053512-48zqb-00000.warc.os.cdx.gz	2711	download
aldor.org-inf-20230707-053512-48zqb-meta.warc.gz	4970	download job
aldor.org-inf-20230707-053512-48zqb-meta.warc.os.cdx.gz	47	download
aldor.org-inf-20230707-053512-48zqb.json	251	download job
aldor.org-inf-20230707-053544-6dybq-00000.warc.gz	2514737	download job
aldor.org-inf-20230707-053544-6dybq-00000.warc.os.cdx.gz	12826	download
aldor.org-inf-20230707-053544-6dybq-meta.warc.gz	11646	download job
aldor.org-inf-20230707-053544-6dybq-meta.warc.os.cdx.gz	47	download
aldor.org-inf-20230707-053544-6dybq.json	263	download job
aldor.org-shallow-20230707-053906-3pgqj-00000.warc.gz	5351	download job
aldor.org-shallow-20230707-053906-3pgqj-00000.warc.os.cdx.gz	245	download
aldor.org-shallow-20230707-053906-3pgqj-meta.warc.gz	3473	download job
aldor.org-shallow-20230707-053906-3pgqj-meta.warc.os.cdx.gz	47	download
aldor.org-shallow-20230707-053906-3pgqj.json	292	download job
archiveteam_archivebot_go_20230707085827_0bc4047f_files.xml	0	download
archiveteam_archivebot_go_20230707085827_0bc4047f_meta.sqlite	565248	download
archiveteam_archivebot_go_20230707085827_0bc4047f_meta.xml	830	download
blog.paperspace.com-inf-20230706-175825-5pp8l-00008.warc.gz	7652117824	download job
blog.paperspace.com-inf-20230706-175825-5pp8l-00008.warc.os.cdx.gz	2467572	download
bpi.harvestplus.org-inf-20230707-043211-a1srd-00000.warc.gz	302037852	download job
bpi.harvestplus.org-inf-20230707-043211-a1srd-00000.warc.os.cdx.gz	428041	download
bpi.harvestplus.org-inf-20230707-043211-a1srd-meta.warc.gz	255236	download job
bpi.harvestplus.org-inf-20230707-043211-a1srd-meta.warc.os.cdx.gz	47	download
bpi.harvestplus.org-inf-20230707-043211-a1srd.json	249	download job
cs.uwaterloo.ca-inf-20230707-054325-d4z94-00000.warc.gz	234949046	download job
cs.uwaterloo.ca-inf-20230707-054325-d4z94-00000.warc.os.cdx.gz	137816	download
cs.uwaterloo.ca-inf-20230707-054325-d4z94-meta.warc.gz	89814	download job
cs.uwaterloo.ca-inf-20230707-054325-d4z94-meta.warc.os.cdx.gz	47	download
cs.uwaterloo.ca-inf-20230707-054325-d4z94.json	249	download job
ctroper.tumblr.com-inf-20230707-061928-479zl-00000.warc.gz	149546658	download job
ctroper.tumblr.com-inf-20230707-061928-479zl-00000.warc.os.cdx.gz	221116	download
ctroper.tumblr.com-inf-20230707-061928-479zl-meta.warc.gz	373864	download job
ctroper.tumblr.com-inf-20230707-061928-479zl-meta.warc.os.cdx.gz	47	download
ctroper.tumblr.com-inf-20230707-061928-479zl.json	244	download job
digitalcommons.mtu.edu-inf-20230707-023411-dsm15-00002.warc.gz	5385624793	download job
digitalcommons.mtu.edu-inf-20230707-023411-dsm15-00002.warc.os.cdx.gz	2305775	download
docs.historyrussia.org-inf-20230706-181125-f0z4p-00000.warc.gz	5454329859	download job
docs.historyrussia.org-inf-20230706-181125-f0z4p-00000.warc.os.cdx.gz	20070479	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00003.warc.gz	5380612351	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00003.warc.os.cdx.gz	129194	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00004.warc.gz	5384941260	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00004.warc.os.cdx.gz	76872	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00005.warc.gz	5385524931	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00005.warc.os.cdx.gz	40514	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00006.warc.gz	5450287590	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00006.warc.os.cdx.gz	78305	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00007.warc.gz	5390373054	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00007.warc.os.cdx.gz	79215	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00008.warc.gz	5422138558	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00008.warc.os.cdx.gz	52102	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00009.warc.gz	5375922505	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00009.warc.os.cdx.gz	27555	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00010.warc.gz	5375862647	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00010.warc.os.cdx.gz	27403	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00011.warc.gz	5381625631	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00011.warc.os.cdx.gz	33420	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00012.warc.gz	5387051073	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00012.warc.os.cdx.gz	45051	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00013.warc.gz	5393706681	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00013.warc.os.cdx.gz	62660	download
elib.uraic.ru-inf-20230706-181220-1ewa6-00014.warc.gz	5383967626	download job
elib.uraic.ru-inf-20230706-181220-1ewa6-00014.warc.os.cdx.gz	116899	download
evernote.com-inf-20230706-142112-auh0j-00005.warc.gz	5491988570	download job
evernote.com-inf-20230706-142112-auh0j-00005.warc.os.cdx.gz	1713326	download
evernote.com-inf-20230706-142112-auh0j-00006.warc.gz	5369136729	download job
evernote.com-inf-20230706-142112-auh0j-00006.warc.os.cdx.gz	457701	download
express.adobe.com-inf-20230707-041318-6a581-00000.warc.gz	132249085	download job
express.adobe.com-inf-20230707-041318-6a581-00000.warc.os.cdx.gz	161816	download
express.adobe.com-inf-20230707-041318-6a581-meta.warc.gz	105142	download job
express.adobe.com-inf-20230707-041318-6a581-meta.warc.os.cdx.gz	47	download
express.adobe.com-inf-20230707-041318-6a581.json	266	download job
express.adobe.com-inf-20230707-042825-5y05x-00000.warc.gz	11228164	download job
express.adobe.com-inf-20230707-042825-5y05x-00000.warc.os.cdx.gz	41265	download
express.adobe.com-inf-20230707-042825-5y05x-meta.warc.gz	27364	download job
express.adobe.com-inf-20230707-042825-5y05x-meta.warc.os.cdx.gz	47	download
express.adobe.com-inf-20230707-042825-5y05x.json	266	download job
express.adobe.com-inf-20230707-042836-466ir-00000.warc.gz	10171224	download job
express.adobe.com-inf-20230707-042836-466ir-00000.warc.os.cdx.gz	37986	download
express.adobe.com-inf-20230707-042836-466ir-meta.warc.gz	25494	download job
express.adobe.com-inf-20230707-042836-466ir-meta.warc.os.cdx.gz	47	download
express.adobe.com-inf-20230707-042836-466ir.json	266	download job
express.adobe.com-inf-20230707-042851-a7qut-00000.warc.gz	18286233	download job
express.adobe.com-inf-20230707-042851-a7qut-00000.warc.os.cdx.gz	45485	download
express.adobe.com-inf-20230707-042851-a7qut-meta.warc.gz	29532	download job
express.adobe.com-inf-20230707-042851-a7qut-meta.warc.os.cdx.gz	47	download
express.adobe.com-inf-20230707-042851-a7qut.json	266	download job
freewechat.com-inf-20221128-202335-8k26b-02080.warc.gz	5368736523	download job
freewechat.com-inf-20221128-202335-8k26b-02080.warc.os.cdx.gz	5026294	download
gfycat.com-inf-20230702-031508-b32xg-00091.warc.gz	5368755549	download job
gfycat.com-inf-20230702-031508-b32xg-00091.warc.os.cdx.gz	478157	download
gfycat.com-inf-20230702-031508-b32xg-00092.warc.gz	5370710025	download job
gfycat.com-inf-20230702-031508-b32xg-00092.warc.os.cdx.gz	437026	download
homepage.powerup.com.au-inf-20230707-011131-6p7tu-00000.warc.gz	343000143	download job
homepage.powerup.com.au-inf-20230707-011131-6p7tu-00000.warc.os.cdx.gz	540705	download
homepage.powerup.com.au-inf-20230707-011131-6p7tu-meta.warc.gz	345709	download job
homepage.powerup.com.au-inf-20230707-011131-6p7tu-meta.warc.os.cdx.gz	47	download
homepage.powerup.com.au-inf-20230707-011131-6p7tu.json	272	download job
homepages.ihug.com.au-inf-20230706-093215-8fybf-00000.warc.gz	3640212528	download job
homepages.ihug.com.au-inf-20230706-093215-8fybf-00000.warc.os.cdx.gz	3608588	download
homepages.ihug.com.au-inf-20230706-093215-8fybf-meta.warc.gz	2332179	download job
homepages.ihug.com.au-inf-20230706-093215-8fybf-meta.warc.os.cdx.gz	47	download
homepages.ihug.com.au-inf-20230706-093215-8fybf.json	272	download job
homepages.ihug.com.au-inf-20230707-005717-a0s4e-00000.warc.gz	1692025353	download job
homepages.ihug.com.au-inf-20230707-005717-a0s4e-00000.warc.os.cdx.gz	1191699	download
homepages.ihug.com.au-inf-20230707-005717-a0s4e-meta.warc.gz	723645	download job
homepages.ihug.com.au-inf-20230707-005717-a0s4e-meta.warc.os.cdx.gz	47	download
homepages.ihug.com.au-inf-20230707-005717-a0s4e.json	261	download job
icarda.org-inf-20230707-011844-bkn2i-00000.warc.gz	5041857164	download job
icarda.org-inf-20230707-011844-bkn2i-00000.warc.os.cdx.gz	2659367	download
icarda.org-inf-20230707-011844-bkn2i-meta.warc.gz	1543516	download job
icarda.org-inf-20230707-011844-bkn2i-meta.warc.os.cdx.gz	47	download
icarda.org-inf-20230707-011844-bkn2i.json	240	download job
iufro2014.com-inf-20230707-044208-93zf0-00000.warc.gz	1526441715	download job
iufro2014.com-inf-20230707-044208-93zf0-00000.warc.os.cdx.gz	779424	download
iufro2014.com-inf-20230707-044208-93zf0-meta.warc.gz	509017	download job
iufro2014.com-inf-20230707-044208-93zf0-meta.warc.os.cdx.gz	47	download
iufro2014.com-inf-20230707-044208-93zf0.json	243	download job
kimspireddiy.com-inf-20230704-144435-barp5-00010.warc.gz	5404736118	download job
kimspireddiy.com-inf-20230704-144435-barp5-00010.warc.os.cdx.gz	7801688	download
kimspireddiy.com-inf-20230704-144435-barp5-00011.warc.gz	3918228300	download job
kimspireddiy.com-inf-20230704-144435-barp5-00011.warc.os.cdx.gz	794076	download
kimspireddiy.com-inf-20230704-144435-barp5-meta.warc.gz	27720788	download job
kimspireddiy.com-inf-20230704-144435-barp5-meta.warc.os.cdx.gz	47	download
kimspireddiy.com-inf-20230704-144435-barp5.json	241	download job
lookpic.com-shallow-20230707-045713-139tg-00000.warc.gz	1436459	download job
lookpic.com-shallow-20230707-045713-139tg-00000.warc.os.cdx.gz	240	download
lookpic.com-shallow-20230707-045713-139tg-meta.warc.gz	3494	download job
lookpic.com-shallow-20230707-045713-139tg-meta.warc.os.cdx.gz	47	download
lookpic.com-shallow-20230707-045713-139tg.json	280	download job
lookpic.com-shallow-20230707-045718-196xg-00000.warc.gz	1156445	download job
lookpic.com-shallow-20230707-045718-196xg-00000.warc.os.cdx.gz	238	download
lookpic.com-shallow-20230707-045718-196xg-meta.warc.gz	3486	download job
lookpic.com-shallow-20230707-045718-196xg-meta.warc.os.cdx.gz	47	download
lookpic.com-shallow-20230707-045718-196xg.json	280	download job
lookpic.com-shallow-20230707-045724-457hb-00000.warc.gz	1489485	download job
lookpic.com-shallow-20230707-045724-457hb-00000.warc.os.cdx.gz	242	download
lookpic.com-shallow-20230707-045724-457hb-meta.warc.gz	3476	download job
lookpic.com-shallow-20230707-045724-457hb-meta.warc.os.cdx.gz	47	download
lookpic.com-shallow-20230707-045724-457hb.json	280	download job
members.ozemail.com.au-inf-20230707-023226-4o4n7-00000.warc.gz	852662206	download job
members.ozemail.com.au-inf-20230707-023226-4o4n7-00000.warc.os.cdx.gz	539813	download
members.ozemail.com.au-inf-20230707-023226-4o4n7-meta.warc.gz	343055	download job
members.ozemail.com.au-inf-20230707-023226-4o4n7-meta.warc.os.cdx.gz	47	download
members.ozemail.com.au-inf-20230707-023226-4o4n7.json	266	download job
members.upnaway.com-inf-20230706-232800-83oj7-00000.warc.gz	1137159297	download job
members.upnaway.com-inf-20230706-232800-83oj7-00000.warc.os.cdx.gz	1554772	download
members.upnaway.com-inf-20230706-232800-83oj7-meta.warc.gz	920113	download job
members.upnaway.com-inf-20230706-232800-83oj7-meta.warc.os.cdx.gz	47	download
members.upnaway.com-inf-20230706-232800-83oj7.json	280	download job
members.upnaway.com-inf-20230706-232903-9cbdv-00000.warc.gz	1103870935	download job
members.upnaway.com-inf-20230706-232903-9cbdv-00000.warc.os.cdx.gz	1489491	download
members.upnaway.com-inf-20230706-232903-9cbdv-meta.warc.gz	885055	download job
members.upnaway.com-inf-20230706-232903-9cbdv-meta.warc.os.cdx.gz	47	download
members.upnaway.com-inf-20230706-232903-9cbdv.json	279	download job
members.upnaway.com-inf-20230706-233007-6a61d-00000.warc.gz	1138607571	download job
members.upnaway.com-inf-20230706-233007-6a61d-00000.warc.os.cdx.gz	1543262	download
members.upnaway.com-inf-20230706-233007-6a61d-meta.warc.gz	911996	download job
members.upnaway.com-inf-20230706-233007-6a61d-meta.warc.os.cdx.gz	47	download
members.upnaway.com-inf-20230706-233007-6a61d.json	274	download job
members.upnaway.com-inf-20230706-233038-6rf69-00000.warc.gz	1113604584	download job
members.upnaway.com-inf-20230706-233038-6rf69-00000.warc.os.cdx.gz	1505662	download
members.upnaway.com-inf-20230706-233038-6rf69-meta.warc.gz	895443	download job
members.upnaway.com-inf-20230706-233038-6rf69-meta.warc.os.cdx.gz	47	download
members.upnaway.com-inf-20230706-233038-6rf69.json	275	download job
members.upnaway.com-inf-20230706-233053-47nkl-00000.warc.gz	1117723752	download job
members.upnaway.com-inf-20230706-233053-47nkl-00000.warc.os.cdx.gz	1507164	download
members.upnaway.com-inf-20230706-233053-47nkl-meta.warc.gz	897445	download job
members.upnaway.com-inf-20230706-233053-47nkl-meta.warc.os.cdx.gz	47	download
members.upnaway.com-inf-20230706-233053-47nkl.json	277	download job
members.upnaway.com-inf-20230706-233125-6m4ij-00000.warc.gz	1118264918	download job
members.upnaway.com-inf-20230706-233125-6m4ij-00000.warc.os.cdx.gz	1510215	download
members.upnaway.com-inf-20230706-233125-6m4ij-meta.warc.gz	890939	download job
members.upnaway.com-inf-20230706-233125-6m4ij-meta.warc.os.cdx.gz	47	download
members.upnaway.com-inf-20230706-233125-6m4ij.json	279	download job
members.upnaway.com-inf-20230706-233212-c4876-00000.warc.gz	1136249649	download job
members.upnaway.com-inf-20230706-233212-c4876-00000.warc.os.cdx.gz	1611503	download
members.upnaway.com-inf-20230706-233212-c4876-meta.warc.gz	940563	download job
members.upnaway.com-inf-20230706-233212-c4876-meta.warc.os.cdx.gz	47	download
members.upnaway.com-inf-20230706-233212-c4876.json	276	download job
mk2k.net-inf-20230707-034827-5kk43-00000.warc.gz	74632653	download job
mk2k.net-inf-20230707-034827-5kk43-00000.warc.os.cdx.gz	159798	download
mk2k.net-inf-20230707-034827-5kk43-meta.warc.gz	98575	download job
mk2k.net-inf-20230707-034827-5kk43-meta.warc.os.cdx.gz	47	download
mk2k.net-inf-20230707-034827-5kk43.json	246	download job
newsroom.arianespace.com-inf-20230705-225100-dn4o5-00000.warc.gz	3909120328	download job
newsroom.arianespace.com-inf-20230705-225100-dn4o5-00000.warc.os.cdx.gz	1423735	download
newsroom.arianespace.com-inf-20230705-225100-dn4o5-meta.warc.gz	1065907	download job
newsroom.arianespace.com-inf-20230705-225100-dn4o5-meta.warc.os.cdx.gz	47	download
newsroom.arianespace.com-inf-20230705-225100-dn4o5.json	251	download job
nolfgirl.net-inf-20230701-202358-8dzkd-00041.warc.gz	5741599031	download job
nolfgirl.net-inf-20230701-202358-8dzkd-00041.warc.os.cdx.gz	2767812	download
notacamp.tbd.camp-inf-20230707-063446-8lmii-00000.warc.gz	8510876	download job
notacamp.tbd.camp-inf-20230707-063446-8lmii-00000.warc.os.cdx.gz	34407	download
notacamp.tbd.camp-inf-20230707-063446-8lmii-meta.warc.gz	24767	download job
notacamp.tbd.camp-inf-20230707-063446-8lmii-meta.warc.os.cdx.gz	47	download
notacamp.tbd.camp-inf-20230707-063446-8lmii.json	243	download job
pbs.twimg.com-shallow-20230707-043436-almo5-00000.warc.gz	303448	download job
pbs.twimg.com-shallow-20230707-043436-almo5-00000.warc.os.cdx.gz	248	download
pbs.twimg.com-shallow-20230707-043436-almo5-meta.warc.gz	3408	download job
pbs.twimg.com-shallow-20230707-043436-almo5-meta.warc.os.cdx.gz	47	download
pbs.twimg.com-shallow-20230707-043436-almo5.json	267	download job
pbs.twimg.com-shallow-20230707-043443-874q2-00000.warc.gz	240269	download job
pbs.twimg.com-shallow-20230707-043443-874q2-00000.warc.os.cdx.gz	246	download
pbs.twimg.com-shallow-20230707-043443-874q2-meta.warc.gz	3483	download job
pbs.twimg.com-shallow-20230707-043443-874q2-meta.warc.os.cdx.gz	47	download
pbs.twimg.com-shallow-20230707-043443-874q2.json	267	download job
profile.typepad.com-inf-20230707-061907-5d5ec-00000.warc.gz	23505750	download job
profile.typepad.com-inf-20230707-061907-5d5ec-00000.warc.os.cdx.gz	12532	download
profile.typepad.com-inf-20230707-061907-5d5ec-meta.warc.gz	10806	download job
profile.typepad.com-inf-20230707-061907-5d5ec-meta.warc.os.cdx.gz	47	download
profile.typepad.com-inf-20230707-061907-5d5ec.json	262	download job
sarahscoop.com-inf-20230630-181349-9am7t-00046.warc.gz	5368723870	download job
sarahscoop.com-inf-20230630-181349-9am7t-00046.warc.os.cdx.gz	1989724	download
sfcathletics.com-inf-20230706-130116-2ku5w-00004.warc.gz	5368760246	download job
sfcathletics.com-inf-20230706-130116-2ku5w-00004.warc.os.cdx.gz	736927	download
sfcathletics.com-inf-20230706-130116-2ku5w-00005.warc.gz	5369755624	download job
sfcathletics.com-inf-20230706-130116-2ku5w-00005.warc.os.cdx.gz	1211458	download
sfcathletics.com-inf-20230706-130116-2ku5w-00006.warc.gz	5370060932	download job
sfcathletics.com-inf-20230706-130116-2ku5w-00006.warc.os.cdx.gz	690982	download
sfcathletics.com-inf-20230706-130116-2ku5w-00007.warc.gz	5376700389	download job
sfcathletics.com-inf-20230706-130116-2ku5w-00007.warc.os.cdx.gz	335905	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00254.warc.gz	5368843538	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00254.warc.os.cdx.gz	2190664	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00255.warc.gz	5369696037	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00255.warc.os.cdx.gz	2006971	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00256.warc.gz	5368840133	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00256.warc.os.cdx.gz	2281559	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00257.warc.gz	5369106357	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00257.warc.os.cdx.gz	1956602	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00258.warc.gz	5368713006	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00258.warc.os.cdx.gz	2010027	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00259.warc.gz	5376746283	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00259.warc.os.cdx.gz	2369609	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00260.warc.gz	5369391314	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00261.warc.gz	5369058534	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00261.warc.os.cdx.gz	2293957	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00262.warc.gz	5368996715	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00262.warc.os.cdx.gz	2224795	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00263.warc.gz	5370111722	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00263.warc.os.cdx.gz	1997515	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00264.warc.gz	5369029541	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00264.warc.os.cdx.gz	2112732	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00265.warc.gz	5377908860	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00265.warc.os.cdx.gz	2229739	download
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00266.warc.gz	5369368573	download job
shinjinotikari17.tumblr.com-inf-20230701-090924-e9uq4-00266.warc.os.cdx.gz	2030125	download
sites.google.com-inf-20230707-071910-bollk-00000.warc.gz	26041665	download job
sites.google.com-inf-20230707-071910-bollk-00000.warc.os.cdx.gz	47577	download
sites.google.com-inf-20230707-071910-bollk-meta.warc.gz	33939	download job
sites.google.com-inf-20230707-071910-bollk-meta.warc.os.cdx.gz	47	download
sites.google.com-inf-20230707-071910-bollk.json	263	download job
slovodel.com-inf-20230702-125226-1u8kj-00008.warc.gz	5562248023	download job
slovodel.com-inf-20230702-125226-1u8kj-00008.warc.os.cdx.gz	1261405	download
slovodel.com-inf-20230702-125226-1u8kj-00009.warc.gz	5368716562	download job
slovodel.com-inf-20230702-125226-1u8kj-00009.warc.os.cdx.gz	850720	download
slovodel.com-inf-20230702-125226-1u8kj-00010.warc.gz	5816983026	download job
slovodel.com-inf-20230702-125226-1u8kj-00010.warc.os.cdx.gz	648807	download
slovodel.com-inf-20230702-125226-1u8kj-00011.warc.gz	5801149069	download job
slovodel.com-inf-20230702-125226-1u8kj-00011.warc.os.cdx.gz	622739	download
soundcloud.com-inf-20230707-072314-8bak1-00000.warc.gz	4029	download job
soundcloud.com-inf-20230707-072314-8bak1-00000.warc.os.cdx.gz	47	download
soundcloud.com-inf-20230707-072314-8bak1-meta.warc.gz	3456	download job
soundcloud.com-inf-20230707-072314-8bak1-meta.warc.os.cdx.gz	47	download
soundcloud.com-inf-20230707-072314-8bak1.json	255	download job
soylentnews.org-inf-20230523-205459-bxyzg-00396.warc.gz	5392043558	download job
soylentnews.org-inf-20230523-205459-bxyzg-00396.warc.os.cdx.gz	1438583	download
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00914.warc.gz	5370449000	download job
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00914.warc.os.cdx.gz	2829250	download
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00915.warc.gz	5369240883	download job
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00915.warc.os.cdx.gz	2943125	download
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00916.warc.gz	5368710371	download job
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00916.warc.os.cdx.gz	2791068	download
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00917.warc.gz	5368735760	download job
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00917.warc.os.cdx.gz	2691566	download
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00918.warc.gz	5368778636	download job
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00918.warc.os.cdx.gz	2930359	download
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00919.warc.gz	5368719607	download job
spockvarietyhour.tumblr.com-inf-20230601-082859-e7qti-00919.warc.os.cdx.gz	3362367	download
tbd.camp-inf-20230707-063412-4782h-00000.warc.gz	7345091	download job
tbd.camp-inf-20230707-063412-4782h-00000.warc.os.cdx.gz	42143	download
tbd.camp-inf-20230707-063412-4782h-meta.warc.gz	33392	download job
tbd.camp-inf-20230707-063412-4782h-meta.warc.os.cdx.gz	47	download
tbd.camp-inf-20230707-063412-4782h.json	234	download job
teamster.org-inf-20230702-032402-j6mom-00136.warc.gz	8256875136	download job
teamster.org-inf-20230702-032402-j6mom-00136.warc.os.cdx.gz	1450076	download
teamster.org-inf-20230702-032402-j6mom-00137.warc.gz	5402984088	download job
teamster.org-inf-20230702-032402-j6mom-00137.warc.os.cdx.gz	227920	download
teamster.org-inf-20230702-032402-j6mom-00138.warc.gz	5393934627	download job
teamster.org-inf-20230702-032402-j6mom-00138.warc.os.cdx.gz	22357	download
teamster.org-inf-20230702-032402-j6mom-00139.warc.gz	5412690257	download job
teamster.org-inf-20230702-032402-j6mom-00139.warc.os.cdx.gz	22374	download
teamster.org-inf-20230702-032402-j6mom-00140.warc.gz	5376484413	download job
teamster.org-inf-20230702-032402-j6mom-00140.warc.os.cdx.gz	113471	download
teamster.org-inf-20230702-032402-j6mom-00141.warc.gz	5371466209	download job
teamster.org-inf-20230702-032402-j6mom-00141.warc.os.cdx.gz	228609	download
teamster.org-inf-20230702-032402-j6mom-00142.warc.gz	5401910261	download job
teamster.org-inf-20230702-032402-j6mom-00142.warc.os.cdx.gz	114033	download
teamster.org-inf-20230702-032402-j6mom-00143.warc.gz	5434004252	download job
teamster.org-inf-20230702-032402-j6mom-00143.warc.os.cdx.gz	28804	download
teamster.org-inf-20230702-032402-j6mom-00144.warc.gz	5398948264	download job
teamster.org-inf-20230702-032402-j6mom-00144.warc.os.cdx.gz	54028	download
teamster.org-inf-20230702-032402-j6mom-00145.warc.gz	5387818145	download job
teamster.org-inf-20230702-032402-j6mom-00145.warc.os.cdx.gz	138151	download
teamster.org-inf-20230702-032402-j6mom-00146.warc.gz	5376023268	download job
teamster.org-inf-20230702-032402-j6mom-00146.warc.os.cdx.gz	133653	download
teamster.org-inf-20230702-032402-j6mom-00147.warc.gz	5370411702	download job
teamster.org-inf-20230702-032402-j6mom-00147.warc.os.cdx.gz	266643	download
transfer.archivete.am-shallow-20230707-051305-2pjkd-00000.warc.gz	4960	download job
transfer.archivete.am-shallow-20230707-051305-2pjkd-00000.warc.os.cdx.gz	244	download
transfer.archivete.am-shallow-20230707-051305-2pjkd-meta.warc.gz	3503	download job
transfer.archivete.am-shallow-20230707-051305-2pjkd-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20230707-051305-2pjkd.json	283	download job
urls-transfer.archivete.am-irc-urls-20230705-shallow-20230706-054702-ywshy-00003.warc.gz	5368715870	download job
urls-transfer.archivete.am-irc-urls-20230705-shallow-20230706-054702-ywshy-00003.warc.os.cdx.gz	2872836	download
usesthis.com-inf-20230706-190643-4210z-00003.warc.gz	5368871312	download job
usesthis.com-inf-20230706-190643-4210z-00003.warc.os.cdx.gz	1599171	download
usesthis.com-inf-20230706-190643-4210z-00004.warc.gz	5370072735	download job
usesthis.com-inf-20230706-190643-4210z-00004.warc.os.cdx.gz	2822104	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00376.warc.gz	5370193669	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00376.warc.os.cdx.gz	2123827	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00377.warc.gz	5375007798	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00377.warc.os.cdx.gz	2027779	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00378.warc.gz	5369911024	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00378.warc.os.cdx.gz	1941336	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00379.warc.gz	5371234209	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00379.warc.os.cdx.gz	2262394	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00380.warc.gz	5369651653	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00380.warc.os.cdx.gz	1832902	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00381.warc.gz	5373226806	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00381.warc.os.cdx.gz	1770447	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00382.warc.gz	5371239037	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00382.warc.os.cdx.gz	2004764	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00383.warc.gz	5368730420	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00384.warc.gz	5369861164	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00384.warc.os.cdx.gz	2299264	download
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00385.warc.gz	5372338016	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00386.warc.gz	5368835329	download job
watsonlove.tumblr.com-inf-20230630-014534-d0wwb-00386.warc.os.cdx.gz	2335606	download
wetheitalians.com-inf-20230513-010427-7qx5s-00197.warc.gz	5444690181	download job
wetheitalians.com-inf-20230513-010427-7qx5s-00197.warc.os.cdx.gz	1066157	download
www-sop.inria.fr-inf-20230707-054035-8aru7-00000.warc.gz	596109997	download job
www-sop.inria.fr-inf-20230707-054035-8aru7-meta.warc.gz	289235	download job
www-sop.inria.fr-inf-20230707-054035-8aru7.json	246	download job
www.aldor.org-inf-20230707-053345-erbm8-00000.warc.gz	53719826	download job
www.aldor.org-inf-20230707-053345-erbm8-00000.warc.os.cdx.gz	11708	download
www.aldor.org-inf-20230707-053345-erbm8-meta.warc.gz	10520	download job
www.aldor.org-inf-20230707-053345-erbm8-meta.warc.os.cdx.gz	47	download
www.aldor.org-inf-20230707-053345-erbm8.json	239	download job
www.boekwinkeltjes.nl-inf-20230611-010158-3ebu7-00034.warc.gz	5369044662	download job
www.boekwinkeltjes.nl-inf-20230611-010158-3ebu7-00034.warc.os.cdx.gz	20633601	download
www.bund.net-inf-20230703-190359-7xmmg-00007.warc.gz	5368746756	download job
www.bund.net-inf-20230703-190359-7xmmg-00007.warc.os.cdx.gz	8603885	download
www.buzzfeednews.com-inf-20230420-160602-d4rha-00986.warc.gz	5368795337	download job
www.buzzfeednews.com-inf-20230420-160602-d4rha-00986.warc.os.cdx.gz	1607517	download
www.csd.uwo.ca-inf-20230707-054152-913r0-00000.warc.gz	1974004	download job
www.csd.uwo.ca-inf-20230707-054152-913r0-meta.warc.gz	8904	download job
www.csd.uwo.ca-inf-20230707-054152-913r0-meta.warc.os.cdx.gz	47	download
www.csd.uwo.ca-inf-20230707-054152-913r0.json	246	download job
www.flickr.com-inf-20230707-062309-571hf-00000.warc.gz	5368713025	download job
www.flickr.com-inf-20230707-062309-571hf-00000.warc.os.cdx.gz	1266193	download
www.flickr.com-inf-20230707-062309-571hf-00001.warc.gz	2183925197	download job
www.flickr.com-inf-20230707-062309-571hf-00001.warc.os.cdx.gz	447694	download
www.flickr.com-inf-20230707-062309-571hf-meta.warc.gz	762274	download job
www.flickr.com-inf-20230707-062309-571hf-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20230707-062309-571hf.json	256	download job
www.icarda.org-inf-20230707-004359-9sb3e-00001.warc.gz	4929401066	download job
www.icarda.org-inf-20230707-004359-9sb3e-00001.warc.os.cdx.gz	5253379	download
www.icarda.org-inf-20230707-004359-9sb3e-meta.warc.gz	5644018	download job
www.icarda.org-inf-20230707-004359-9sb3e-meta.warc.os.cdx.gz	47	download
www.icarda.org-inf-20230707-004359-9sb3e.json	244	download job
www.imcdb.org-inf-20230702-053733-eccs9-00000.warc.gz	5369155099	download job
www.informationphilosopher.com-inf-20230707-063821-788ac-00000.warc.gz	10284665	download job
www.informationphilosopher.com-inf-20230707-063821-788ac-meta.warc.gz	25647	download job
www.informationphilosopher.com-inf-20230707-063821-788ac.json	285	download job
www.last.fm-inf-20230707-062223-8l6xy-aborted-00000.warc.gz	18199094	download job
www.last.fm-inf-20230707-062223-8l6xy-aborted-wpull.log.gz	30515	download
www.last.fm-inf-20230707-062223-8l6xy-aborted.json	257	download job
www.librarything.com-shallow-20230707-061938-7v8j4-00000.warc.gz	9280016	download job
www.librarything.com-shallow-20230707-061938-7v8j4-meta.warc.gz	9974	download job
www.librarything.com-shallow-20230707-061938-7v8j4-meta.warc.os.cdx.gz	47	download
www.librarything.com-shallow-20230707-061938-7v8j4.json	266	download job
www.librarything.com-shallow-20230707-061947-bc5i2-00000.warc.gz	8132182	download job
www.librarything.com-shallow-20230707-061947-bc5i2-meta.warc.gz	18431	download job
www.librarything.com-shallow-20230707-061947-bc5i2.json	266	download job
www.librarything.com-shallow-20230707-061947-mk8pa-00000.warc.gz	5482926	download job
www.librarything.com-shallow-20230707-061947-mk8pa-meta.warc.gz	7954	download job
www.librarything.com-shallow-20230707-061947-mk8pa.json	266	download job
www.mersenneforum.org-inf-20230706-040240-7gczj-00006.warc.gz	5369621721	download job
www.mk2k.net-inf-20230707-034915-8duzc-00000.warc.gz	81587190	download job
www.mk2k.net-inf-20230707-034915-8duzc-meta.warc.gz	70585	download job
www.mk2k.net-inf-20230707-034915-8duzc.json	250	download job
www.roper.org.uk-inf-20230707-061211-6okws-00000.warc.gz	5391146327	download job
www.roper.org.uk-inf-20230707-061458-3js3i-00000.warc.gz	123232523	download job
www.roper.org.uk-inf-20230707-061458-3js3i-meta.warc.gz	145081	download job
www.roper.org.uk-inf-20230707-061458-3js3i.json	255	download job
www.roper.org.uk-inf-20230707-061734-89b3c-00000.warc.gz	2687304127	download job
www.roper.org.uk-inf-20230707-061734-89b3c-meta.warc.gz	1258011	download job
www.roper.org.uk-inf-20230707-061734-89b3c.json	255	download job
www.rudyrucker.com-inf-20230707-031910-es9ha-00000.warc.gz	5385509274	download job
www.rudyrucker.com-inf-20230707-031910-es9ha-00000.warc.os.cdx.gz	615934	download
www.rudyrucker.com-inf-20230707-031910-es9ha-00001.warc.gz	5369209624	download job
www.rudyrucker.com-inf-20230707-031910-es9ha-00002.warc.gz	5368769662	download job
www.simplemost.com-inf-20230610-044317-at6jv-00246.warc.gz	5375239061	download job
www.tomroper.net-inf-20230707-061058-7njd1-00000.warc.gz	22909081	download job
www.tomroper.net-inf-20230707-061058-7njd1-meta.warc.gz	36498	download job
www.tomroper.net-inf-20230707-061058-7njd1.json	242	download job
www.vice.com-inf-20230502-094429-3m7tt-00567.warc.gz	5448226915	download job
www.virtualnights.com-inf-20230612-185151-dez6r-00087.warc.gz	5368812100	download job
www.wolftune.com-inf-20230707-072139-2jgpl-00000.warc.gz	460088841	download job
www.wolftune.com-inf-20230707-072139-2jgpl-meta.warc.gz	115173	download job
www.wolftune.com-inf-20230707-072139-2jgpl.json	241	download job