Item archiveteam_archivebot_go_20221107013928_83408644

View on Internet Archive

Filename	Size
alexgriendling.com-inf-20221106-203437-2fmmx-00000.warc.gz	1538697540	download   job
alexgriendling.com-inf-20221106-203437-2fmmx-00000.warc.os.cdx.gz	498083	download
alexgriendling.com-inf-20221106-203437-2fmmx-meta.warc.gz	266865	download   job
alexgriendling.com-inf-20221106-203437-2fmmx-meta.warc.os.cdx.gz	47	download
alexgriendling.com-inf-20221106-203437-2fmmx.json	249	download   job
app.moegirl.org.cn-inf-20221106-225039-5m159-00000.warc.gz	152345443	download   job
app.moegirl.org.cn-inf-20221106-225039-5m159-00000.warc.os.cdx.gz	38768	download
app.moegirl.org.cn-inf-20221106-225039-5m159-meta.warc.gz	27121	download   job
app.moegirl.org.cn-inf-20221106-225039-5m159-meta.warc.os.cdx.gz	47	download
app.moegirl.org.cn-inf-20221106-225039-5m159.json	246	download   job
apps.lucidcentral.org-inf-20221106-174542-elkia-00000.warc.gz	3177078617	download   job
apps.lucidcentral.org-inf-20221106-174542-elkia-00000.warc.os.cdx.gz	1767306	download
apps.lucidcentral.org-inf-20221106-174542-elkia-meta.warc.gz	1037513	download   job
apps.lucidcentral.org-inf-20221106-174542-elkia-meta.warc.os.cdx.gz	47	download
apps.lucidcentral.org-inf-20221106-174542-elkia.json	251	download   job
archiveteam_archivebot_go_20221107013928_83408644.cdx.gz	250308027	download
archiveteam_archivebot_go_20221107013928_83408644.cdx.idx	307207	download
archiveteam_archivebot_go_20221107013928_83408644_files.xml	0	download
archiveteam_archivebot_go_20221107013928_83408644_meta.sqlite	843776	download
archiveteam_archivebot_go_20221107013928_83408644_meta.xml	997	download
balboaandbedford.com-inf-20221106-203447-dydyz-00000.warc.gz	247395345	download   job
balboaandbedford.com-inf-20221106-203447-dydyz-00000.warc.os.cdx.gz	216970	download
balboaandbedford.com-inf-20221106-203447-dydyz-meta.warc.gz	131833	download   job
balboaandbedford.com-inf-20221106-203447-dydyz-meta.warc.os.cdx.gz	47	download
balboaandbedford.com-inf-20221106-203447-dydyz.json	251	download   job
boic.org.au-inf-20221106-142204-e7iti-00000.warc.gz	1217518278	download   job
boic.org.au-inf-20221106-142204-e7iti-00000.warc.os.cdx.gz	674010	download
boic.org.au-inf-20221106-142204-e7iti-meta.warc.gz	425166	download   job
boic.org.au-inf-20221106-142204-e7iti-meta.warc.os.cdx.gz	47	download
boic.org.au-inf-20221106-142204-e7iti.json	241	download   job
bslabs.net-inf-20221106-223752-4afht-00000.warc.gz	853539970	download   job
bslabs.net-inf-20221106-223752-4afht-00000.warc.os.cdx.gz	246647	download
bslabs.net-inf-20221106-223752-4afht-meta.warc.gz	180848	download   job
bslabs.net-inf-20221106-223752-4afht-meta.warc.os.cdx.gz	47	download
bslabs.net-inf-20221106-223752-4afht.json	238	download   job
cdli.ucla.edu-inf-20221030-021528-2eg0a-00024.warc.gz	5371006084	download   job
cdli.ucla.edu-inf-20221030-021528-2eg0a-00024.warc.os.cdx.gz	1910918	download
chat.whatsapp.com-shallow-20221107-001201-drfk4-00000.warc.gz	601311	download   job
chat.whatsapp.com-shallow-20221107-001201-drfk4-00000.warc.os.cdx.gz	2065	download
chat.whatsapp.com-shallow-20221107-001201-drfk4-meta.warc.gz	4557	download   job
chat.whatsapp.com-shallow-20221107-001201-drfk4-meta.warc.os.cdx.gz	47	download
chat.whatsapp.com-shallow-20221107-001201-drfk4.json	271	download   job
compliance.podemos.org.br-inf-20221106-233502-czmz1-00000.warc.gz	43266089	download   job
compliance.podemos.org.br-inf-20221106-233502-czmz1-00000.warc.os.cdx.gz	51431	download
compliance.podemos.org.br-inf-20221106-233502-czmz1-meta.warc.gz	33952	download   job
compliance.podemos.org.br-inf-20221106-233502-czmz1-meta.warc.os.cdx.gz	47	download
compliance.podemos.org.br-inf-20221106-233502-czmz1.json	253	download   job
comunica.republicanos10.org.br-shallow-20221106-235535-4onmp-00000.warc.gz	3622354	download   job
comunica.republicanos10.org.br-shallow-20221106-235535-4onmp-00000.warc.os.cdx.gz	5828	download
comunica.republicanos10.org.br-shallow-20221106-235535-4onmp-meta.warc.gz	6678	download   job
comunica.republicanos10.org.br-shallow-20221106-235535-4onmp-meta.warc.os.cdx.gz	47	download
comunica.republicanos10.org.br-shallow-20221106-235535-4onmp.json	262	download   job
data.obamagatethemovie.com-inf-20221106-135519-3jjii-00000.warc.gz	4009403	download   job
data.obamagatethemovie.com-inf-20221106-135519-3jjii-00000.warc.os.cdx.gz	8749	download
data.obamagatethemovie.com-inf-20221106-135519-3jjii-meta.warc.gz	8318	download   job
data.obamagatethemovie.com-inf-20221106-135519-3jjii-meta.warc.os.cdx.gz	47	download
data.obamagatethemovie.com-inf-20221106-135519-3jjii.json	256	download   job
doe.haddadoficial.com.br-inf-20221107-001123-8qh87-00000.warc.gz	459195221	download   job
doe.haddadoficial.com.br-inf-20221107-001123-8qh87-00000.warc.os.cdx.gz	129870	download
doe.haddadoficial.com.br-inf-20221107-001123-8qh87-meta.warc.gz	84969	download   job
doe.haddadoficial.com.br-inf-20221107-001123-8qh87-meta.warc.os.cdx.gz	47	download
doe.haddadoficial.com.br-inf-20221107-001123-8qh87.json	252	download   job
duonotes.fandom.com-inf-20221105-033811-ahhm5-00007.warc.gz	5368723976	download   job
duonotes.fandom.com-inf-20221105-033811-ahhm5-00007.warc.os.cdx.gz	4537741	download
duonotes.fandom.com-inf-20221105-033811-ahhm5-00008.warc.gz	5368764821	download   job
duonotes.fandom.com-inf-20221105-033811-ahhm5-00008.warc.os.cdx.gz	4715475	download
ea.donntu.edu.ua-inf-20221103-005301-bf5ge-00003.warc.gz	5370526599	download   job
ea.donntu.edu.ua-inf-20221103-005301-bf5ge-00003.warc.os.cdx.gz	1609108	download
en.wikipedia.org-shallow-20221106-185633-exe7b-00000.warc.gz	534085	download   job
en.wikipedia.org-shallow-20221106-185633-exe7b-00000.warc.os.cdx.gz	3667	download
en.wikipedia.org-shallow-20221106-185633-exe7b-meta.warc.gz	5939	download   job
en.wikipedia.org-shallow-20221106-185633-exe7b-meta.warc.os.cdx.gz	47	download
en.wikipedia.org-shallow-20221106-185633-exe7b.json	272	download   job
en.wikipedia.org-shallow-20221106-185717-dqkye-00000.warc.gz	267673	download   job
en.wikipedia.org-shallow-20221106-185717-dqkye-00000.warc.os.cdx.gz	3861	download
en.wikipedia.org-shallow-20221106-185717-dqkye-meta.warc.gz	5930	download   job
en.wikipedia.org-shallow-20221106-185717-dqkye-meta.warc.os.cdx.gz	47	download
en.wikipedia.org-shallow-20221106-185717-dqkye.json	266	download   job
en.wikipedia.org-shallow-20221106-185725-5j0cl-00000.warc.gz	232929	download   job
en.wikipedia.org-shallow-20221106-185725-5j0cl-00000.warc.os.cdx.gz	3821	download
en.wikipedia.org-shallow-20221106-185725-5j0cl-meta.warc.gz	5643	download   job
en.wikipedia.org-shallow-20221106-185725-5j0cl-meta.warc.os.cdx.gz	47	download
en.wikipedia.org-shallow-20221106-185725-5j0cl.json	284	download   job
evangelicos.lula.com.br-inf-20221106-230444-5tkfn-00000.warc.gz	125732140	download   job
evangelicos.lula.com.br-inf-20221106-230444-5tkfn-00000.warc.os.cdx.gz	135467	download
evangelicos.lula.com.br-inf-20221106-230444-5tkfn-meta.warc.gz	85686	download   job
evangelicos.lula.com.br-inf-20221106-230444-5tkfn-meta.warc.os.cdx.gz	47	download
evangelicos.lula.com.br-inf-20221106-230444-5tkfn.json	251	download   job
financeiro.republicanos10.org.br-shallow-20221106-235712-8sggx-00000.warc.gz	327621	download   job
financeiro.republicanos10.org.br-shallow-20221106-235712-8sggx-00000.warc.os.cdx.gz	1814	download
financeiro.republicanos10.org.br-shallow-20221106-235712-8sggx-meta.warc.gz	4607	download   job
financeiro.republicanos10.org.br-shallow-20221106-235712-8sggx-meta.warc.os.cdx.gz	47	download
financeiro.republicanos10.org.br-shallow-20221106-235712-8sggx.json	264	download   job
flutters.org-inf-20221106-164216-cr0f9-00000.warc.gz	1947831395	download   job
flutters.org-inf-20221106-164216-cr0f9-00000.warc.os.cdx.gz	1125834	download
flutters.org-inf-20221106-164216-cr0f9-meta.warc.gz	608059	download   job
flutters.org-inf-20221106-164216-cr0f9-meta.warc.os.cdx.gz	47	download
flutters.org-inf-20221106-164216-cr0f9.json	241	download   job
forum.duome.eu-inf-20221103-051641-45l1e-00010.warc.gz	3519491489	download   job
forum.duome.eu-inf-20221103-051641-45l1e-00010.warc.os.cdx.gz	5702265	download
forum.duome.eu-inf-20221103-051641-45l1e-meta.warc.gz	18600780	download   job
forum.duome.eu-inf-20221103-051641-45l1e-meta.warc.os.cdx.gz	47	download
forum.duome.eu-inf-20221103-051641-45l1e.json	257	download   job
forum.vitrawian.eu-inf-20221105-061939-6vjib-00007.warc.gz	3382978912	download   job
forum.vitrawian.eu-inf-20221105-061939-6vjib-00007.warc.os.cdx.gz	3003101	download
forum.vitrawian.eu-inf-20221105-061939-6vjib-meta.warc.gz	20093508	download   job
forum.vitrawian.eu-inf-20221105-061939-6vjib-meta.warc.os.cdx.gz	47	download
forum.vitrawian.eu-inf-20221105-061939-6vjib.json	261	download   job
forums.phoenixrising.me-inf-20221020-134444-9m87s-00088.warc.gz	5379378240	download   job
forums.phoenixrising.me-inf-20221020-134444-9m87s-00088.warc.os.cdx.gz	4700313	download
gtaforums.com-inf-20221027-013544-2u4am-00012.warc.gz	5368711529	download   job
gtaforums.com-inf-20221027-013544-2u4am-00012.warc.os.cdx.gz	2607059	download
headlinesmasher.com-inf-20220430-225921-bvc2x-01070.warc.gz	5769612270	download   job
headlinesmasher.com-inf-20220430-225921-bvc2x-01070.warc.os.cdx.gz	1273038	download
homolog.pt.org.br-inf-20221106-225951-895rs-00000.warc.gz	43201	download   job
homolog.pt.org.br-inf-20221106-225951-895rs-00000.warc.os.cdx.gz	489	download
homolog.pt.org.br-inf-20221106-225951-895rs-meta.warc.gz	3636	download   job
homolog.pt.org.br-inf-20221106-225951-895rs-meta.warc.os.cdx.gz	47	download
homolog.pt.org.br-inf-20221106-225951-895rs.json	245	download   job
icecap.us-inf-20221106-050113-92i10-00003.warc.gz	5368715618	download   job
icecap.us-inf-20221106-050113-92i10-00003.warc.os.cdx.gz	2451996	download
icecap.us-inf-20221106-050113-92i10-00004.warc.gz	5547418548	download   job
icecap.us-inf-20221106-050113-92i10-00004.warc.os.cdx.gz	1619449	download
icecap.us-inf-20221106-050113-92i10-00005.warc.gz	5735479643	download   job
icecap.us-inf-20221106-050113-92i10-00005.warc.os.cdx.gz	3268474	download
icecap.us-inf-20221106-050113-92i10-00006.warc.gz	6053351739	download   job
icecap.us-inf-20221106-050113-92i10-00006.warc.os.cdx.gz	562666	download
juliepowell.blogspot.com-inf-20221105-130542-eb4p7-00003.warc.gz	5368861186	download   job
juliepowell.blogspot.com-inf-20221105-130542-eb4p7-00003.warc.os.cdx.gz	7045839	download
juntos.podemos.org.br-inf-20221106-233702-eqiq8-00000.warc.gz	238839954	download   job
juntos.podemos.org.br-inf-20221106-233702-eqiq8-00000.warc.os.cdx.gz	207260	download
juntos.podemos.org.br-inf-20221106-233702-eqiq8-meta.warc.gz	133544	download   job
juntos.podemos.org.br-inf-20221106-233702-eqiq8-meta.warc.os.cdx.gz	47	download
juntos.podemos.org.br-inf-20221106-233702-eqiq8.json	249	download   job
juventude.mdb.org.br-inf-20221106-232722-d8flc-00000.warc.gz	38206588	download   job
juventude.mdb.org.br-inf-20221106-232722-d8flc-00000.warc.os.cdx.gz	38485	download
juventude.mdb.org.br-inf-20221106-232722-d8flc-meta.warc.gz	27397	download   job
juventude.mdb.org.br-inf-20221106-232722-d8flc-meta.warc.os.cdx.gz	47	download
juventude.mdb.org.br-inf-20221106-232722-d8flc.json	248	download   job
keys.lucidcentral.org-inf-20221106-175956-4oq99-00000.warc.gz	28331478	download   job
keys.lucidcentral.org-inf-20221106-175956-4oq99-00000.warc.os.cdx.gz	57741	download
keys.lucidcentral.org-inf-20221106-175956-4oq99-meta.warc.gz	36472	download   job
keys.lucidcentral.org-inf-20221106-175956-4oq99-meta.warc.os.cdx.gz	47	download
keys.lucidcentral.org-inf-20221106-175956-4oq99.json	271	download   job
keyserver.lucidcentral.org-inf-20221106-180501-433xx-00000.warc.gz	19061790	download   job
keyserver.lucidcentral.org-inf-20221106-180501-433xx-00000.warc.os.cdx.gz	47474	download
keyserver.lucidcentral.org-inf-20221106-180501-433xx-meta.warc.gz	31320	download   job
keyserver.lucidcentral.org-inf-20221106-180501-433xx-meta.warc.os.cdx.gz	47	download
keyserver.lucidcentral.org-inf-20221106-180501-433xx.json	256	download   job
lemmasoft.renai.us-inf-20221031-221348-8vlby-00047.warc.gz	5388831081	download   job
lemmasoft.renai.us-inf-20221031-221348-8vlby-00047.warc.os.cdx.gz	3763348	download
lemmasoft.renai.us-inf-20221031-221348-8vlby-00048.warc.gz	5439514295	download   job
lemmasoft.renai.us-inf-20221031-221348-8vlby-00048.warc.os.cdx.gz	3809340	download
lemmasoft.renai.us-inf-20221031-221348-8vlby-00049.warc.gz	5409674223	download   job
lemmasoft.renai.us-inf-20221031-221348-8vlby-00049.warc.os.cdx.gz	3673451	download
library.vspu.net-inf-20221103-004709-barm9-00001.warc.gz	5368716792	download   job
library.vspu.net-inf-20221103-004709-barm9-00001.warc.os.cdx.gz	6899454	download
loja.democraciacrista.org.br-inf-20221106-230606-3epoh-00000.warc.gz	1033081	download   job
loja.democraciacrista.org.br-inf-20221106-230606-3epoh-00000.warc.os.cdx.gz	4600	download
loja.democraciacrista.org.br-inf-20221106-230606-3epoh-meta.warc.gz	6884	download   job
loja.democraciacrista.org.br-inf-20221106-230606-3epoh-meta.warc.os.cdx.gz	47	download
loja.democraciacrista.org.br-inf-20221106-230606-3epoh.json	256	download   job
loja.podemos.org.br-inf-20221106-234137-achu6-00000.warc.gz	132060075	download   job
loja.podemos.org.br-inf-20221106-234137-achu6-00000.warc.os.cdx.gz	101376	download
loja.podemos.org.br-inf-20221106-234137-achu6-meta.warc.gz	67058	download   job
loja.podemos.org.br-inf-20221106-234137-achu6-meta.warc.os.cdx.gz	47	download
loja.podemos.org.br-inf-20221106-234137-achu6.json	247	download   job
mailman.yale.edu-inf-20221106-174357-cxvp9-00000.warc.gz	21893	download   job
mailman.yale.edu-inf-20221106-174357-cxvp9-00000.warc.os.cdx.gz	427	download
mailman.yale.edu-inf-20221106-174357-cxvp9-meta.warc.gz	3681	download   job
mailman.yale.edu-inf-20221106-174357-cxvp9-meta.warc.os.cdx.gz	47	download
mailman.yale.edu-inf-20221106-174357-cxvp9.json	270	download   job
mauritiusbeetles.myspecies.info-inf-20221105-175836-edwl8-00000.warc.gz	4125304748	download   job
mauritiusbeetles.myspecies.info-inf-20221105-175836-edwl8-00000.warc.os.cdx.gz	2271719	download
mauritiusbeetles.myspecies.info-inf-20221105-175836-edwl8-meta.warc.gz	5974865	download   job
mauritiusbeetles.myspecies.info-inf-20221105-175836-edwl8-meta.warc.os.cdx.gz	47	download
mauritiusbeetles.myspecies.info-inf-20221105-175836-edwl8.json	261	download   job
moths.csiro.au-inf-20221105-152351-bvut6-00000.warc.gz	3834714462	download   job
moths.csiro.au-inf-20221105-152351-bvut6-00000.warc.os.cdx.gz	6113844	download
moths.csiro.au-inf-20221105-152351-bvut6-meta.warc.gz	4017378	download   job
moths.csiro.au-inf-20221105-152351-bvut6-meta.warc.os.cdx.gz	47	download
moths.csiro.au-inf-20221105-152351-bvut6.json	244	download   job
naruacom.lula.com.br-inf-20221106-231409-1bzcg-00000.warc.gz	36073599	download   job
naruacom.lula.com.br-inf-20221106-231409-1bzcg-00000.warc.os.cdx.gz	53718	download
naruacom.lula.com.br-inf-20221106-231409-1bzcg-meta.warc.gz	33578	download   job
naruacom.lula.com.br-inf-20221106-231409-1bzcg-meta.warc.os.cdx.gz	47	download
naruacom.lula.com.br-inf-20221106-231409-1bzcg.json	248	download   job
ptmg.pt.org.br-inf-20221106-230146-9a6xs-00000.warc.gz	49842	download   job
ptmg.pt.org.br-inf-20221106-230146-9a6xs-00000.warc.os.cdx.gz	480	download
ptmg.pt.org.br-inf-20221106-230146-9a6xs-meta.warc.gz	3613	download   job
ptmg.pt.org.br-inf-20221106-230146-9a6xs-meta.warc.os.cdx.gz	47	download
ptmg.pt.org.br-inf-20221106-230146-9a6xs.json	242	download   job
qualitipedia.miraheze.org-inf-20221031-232908-ct4kv-00010.warc.gz	5373137291	download   job
qualitipedia.miraheze.org-inf-20221031-232908-ct4kv-00010.warc.os.cdx.gz	11623744	download
recursoskajuru.carrd.co-inf-20221106-222738-bso91-00000.warc.gz	18927841	download   job
recursoskajuru.carrd.co-inf-20221106-222738-bso91-00000.warc.os.cdx.gz	32978	download
recursoskajuru.carrd.co-inf-20221106-222738-bso91-meta.warc.gz	22378	download   job
recursoskajuru.carrd.co-inf-20221106-222738-bso91-meta.warc.os.cdx.gz	47	download
recursoskajuru.carrd.co-inf-20221106-222738-bso91.json	251	download   job
rj.pcb.org.br-inf-20221106-230747-4udij-00000.warc.gz	4692998	download   job
rj.pcb.org.br-inf-20221106-230747-4udij-00000.warc.os.cdx.gz	10428	download
rj.pcb.org.br-inf-20221106-230747-4udij-meta.warc.gz	9807	download   job
rj.pcb.org.br-inf-20221106-230747-4udij-meta.warc.os.cdx.gz	47	download
rj.pcb.org.br-inf-20221106-230747-4udij.json	241	download   job
rusant-lv.myspecies.info-inf-20221105-152225-6zy9h-00000.warc.gz	417211470	download   job
rusant-lv.myspecies.info-inf-20221105-152225-6zy9h-00000.warc.os.cdx.gz	2079737	download
rusant-lv.myspecies.info-inf-20221105-152225-6zy9h-meta.warc.gz	19191019	download   job
rusant-lv.myspecies.info-inf-20221105-152225-6zy9h-meta.warc.os.cdx.gz	47	download
rusant-lv.myspecies.info-inf-20221105-152225-6zy9h.json	253	download   job
schraderbutterflies.blogspot.com-inf-20221106-222240-k6c2k-00000.warc.gz	26674113	download   job
schraderbutterflies.blogspot.com-inf-20221106-222240-k6c2k-00000.warc.os.cdx.gz	43641	download
schraderbutterflies.blogspot.com-inf-20221106-222240-k6c2k-meta.warc.gz	31936	download   job
schraderbutterflies.blogspot.com-inf-20221106-222240-k6c2k-meta.warc.os.cdx.gz	47	download
schraderbutterflies.blogspot.com-inf-20221106-222240-k6c2k.json	261	download   job
sites.google.com-inf-20221106-205508-a1lze-00000.warc.gz	445765956	download   job
sites.google.com-inf-20221106-205508-a1lze-00000.warc.os.cdx.gz	683732	download
sites.google.com-inf-20221106-205508-a1lze-meta.warc.gz	401507	download   job
sites.google.com-inf-20221106-205508-a1lze-meta.warc.os.cdx.gz	47	download
sites.google.com-inf-20221106-205508-a1lze.json	261	download   job
smclassiccars.com-shallow-20221106-205407-8dmwj-00000.warc.gz	615038	download   job
smclassiccars.com-shallow-20221106-205407-8dmwj-00000.warc.os.cdx.gz	291	download
smclassiccars.com-shallow-20221106-205407-8dmwj-meta.warc.gz	3587	download   job
smclassiccars.com-shallow-20221106-205407-8dmwj-meta.warc.os.cdx.gz	47	download
smclassiccars.com-shallow-20221106-205407-8dmwj.json	338	download   job
stis.las.ac.cn-inf-20221029-031320-82487-00008.warc.gz	5368715297	download   job
stis.las.ac.cn-inf-20221029-031320-82487-00008.warc.os.cdx.gz	21330925	download
support.apple.com-inf-20220725-015213-f1ds9-00093.warc.gz	5368719382	download   job
support.apple.com-inf-20220725-015213-f1ds9-00093.warc.os.cdx.gz	3993544	download
toc.qidianunderground.org-inf-20221107-000152-8pzwm-00000.warc.gz	150747	download   job
toc.qidianunderground.org-inf-20221107-000152-8pzwm-00000.warc.os.cdx.gz	1462	download
toc.qidianunderground.org-inf-20221107-000152-8pzwm-meta.warc.gz	4366	download   job
toc.qidianunderground.org-inf-20221107-000152-8pzwm-meta.warc.os.cdx.gz	47	download
toc.qidianunderground.org-inf-20221107-000152-8pzwm.json	253	download   job
totseans.com-inf-20221102-133244-2txf4-00037.warc.gz	5373007839	download   job
totseans.com-inf-20221102-133244-2txf4-00037.warc.os.cdx.gz	6083396	download
transfer.archivete.am-shallow-20221106-233506-6ebmk-00000.warc.gz	4230	download   job
transfer.archivete.am-shallow-20221106-233506-6ebmk-00000.warc.os.cdx.gz	282	download
transfer.archivete.am-shallow-20221106-233506-6ebmk-meta.warc.gz	3476	download   job
transfer.archivete.am-shallow-20221106-233506-6ebmk-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20221106-233506-6ebmk.json	301	download   job
urls-transfer.archivete.am-twitter-%23yyj-shallow-20221029-061110-2snty-00004.warc.gz	5373260076	download   job
urls-transfer.archivete.am-twitter-%23yyj-shallow-20221029-061110-2snty-00004.warc.os.cdx.gz	1744510	download
urls-transfer.archivete.am-twitter-%23yyj-shallow-20221029-061110-2snty-00005.warc.gz	5370554675	download   job
urls-transfer.archivete.am-twitter-%23yyj-shallow-20221029-061110-2snty-00005.warc.os.cdx.gz	1980982	download
urls-transfer.archivete.am-twitter-%23yyj-shallow-20221029-061110-2snty-00006.warc.gz	5368751703	download   job
urls-transfer.archivete.am-twitter-%23yyj-shallow-20221029-061110-2snty-00006.warc.os.cdx.gz	2470348	download
urls-transfer.archivete.am-twitter-@23cidadania-shallow-20221031-143729-9nwz9-00000.warc.gz	740348542	download   job
urls-transfer.archivete.am-twitter-@23cidadania-shallow-20221031-143729-9nwz9-00000.warc.os.cdx.gz	3047298	download
urls-transfer.archivete.am-twitter-@23cidadania-shallow-20221031-143729-9nwz9-meta.warc.gz	4186842	download   job
urls-transfer.archivete.am-twitter-@23cidadania-shallow-20221031-143729-9nwz9-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@23cidadania-shallow-20221031-143729-9nwz9-urls.txt	4670829	download
urls-transfer.archivete.am-twitter-@23cidadania-shallow-20221031-143729-9nwz9.json	336	download   job
urls-transfer.archivete.am-twitter-@9ManDoc-shallow-20221106-203502-7l13x-00000.warc.gz	5400047190	download   job
urls-transfer.archivete.am-twitter-@9ManDoc-shallow-20221106-203502-7l13x-00000.warc.os.cdx.gz	1164569	download
urls-transfer.archivete.am-twitter-@9ManDoc-shallow-20221106-203502-7l13x-00001.warc.gz	5380846847	download   job
urls-transfer.archivete.am-twitter-@9ManDoc-shallow-20221106-203502-7l13x-00001.warc.os.cdx.gz	1451236	download
urls-transfer.archivete.am-twitter-@AndreJanonesAdv-shallow-20221106-222835-3uity-00000.warc.gz	694898919	download   job
urls-transfer.archivete.am-twitter-@AndreJanonesAdv-shallow-20221106-222835-3uity-00000.warc.os.cdx.gz	1797607	download
urls-transfer.archivete.am-twitter-@AndreJanonesAdv-shallow-20221106-222835-3uity-meta.warc.gz	1322830	download   job
urls-transfer.archivete.am-twitter-@AndreJanonesAdv-shallow-20221106-222835-3uity-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@AndreJanonesAdv-shallow-20221106-222835-3uity-urls.txt	836918	download
urls-transfer.archivete.am-twitter-@AndreJanonesAdv-shallow-20221106-222835-3uity.json	344	download   job
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod-00000.warc.gz	6199167849	download   job
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod-00000.warc.os.cdx.gz	293476	download
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod-00001.warc.gz	2522	download   job
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod-00001.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod-meta.warc.gz	196044	download   job
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod-urls.txt	20665	download
urls-transfer.archivete.am-twitter-@BrettLewisJudo-shallow-20221106-211200-2ltod.json	342	download   job
urls-transfer.archivete.am-twitter-@Casagrande_ES-shallow-20221106-223355-ciwa5-00000.warc.gz	1619472292	download   job
urls-transfer.archivete.am-twitter-@Casagrande_ES-shallow-20221106-223355-ciwa5-00000.warc.os.cdx.gz	1516107	download
urls-transfer.archivete.am-twitter-@Casagrande_ES-shallow-20221106-223355-ciwa5-meta.warc.gz	1104569	download   job
urls-transfer.archivete.am-twitter-@Casagrande_ES-shallow-20221106-223355-ciwa5-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@Casagrande_ES-shallow-20221106-223355-ciwa5-urls.txt	692652	download
urls-transfer.archivete.am-twitter-@Casagrande_ES-shallow-20221106-223355-ciwa5.json	340	download   job
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5-00006.warc.gz	5898116146	download   job
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5-00006.warc.os.cdx.gz	4060873	download
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5-00007.warc.gz	4087656048	download   job
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5-00007.warc.os.cdx.gz	56584	download
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5-meta.warc.gz	6744797	download   job
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5-urls.txt	6452670	download
urls-transfer.archivete.am-twitter-@DevinCow-shallow-20221105-152606-u32x5.json	330	download   job
urls-transfer.archivete.am-twitter-@FreelanceWars-shallow-20221106-202810-3x9sk-00000.warc.gz	1732838	download   job
urls-transfer.archivete.am-twitter-@FreelanceWars-shallow-20221106-202810-3x9sk-00000.warc.os.cdx.gz	3654	download
urls-transfer.archivete.am-twitter-@FreelanceWars-shallow-20221106-202810-3x9sk-meta.warc.gz	6874	download   job
urls-transfer.archivete.am-twitter-@FreelanceWars-shallow-20221106-202810-3x9sk-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@FreelanceWars-shallow-20221106-202810-3x9sk-urls.txt	4480	download
urls-transfer.archivete.am-twitter-@FreelanceWars-shallow-20221106-202810-3x9sk.json	340	download   job
urls-transfer.archivete.am-twitter-@JaredForALGov-shallow-20221106-224823-80gxi-00000.warc.gz	278867070	download   job
urls-transfer.archivete.am-twitter-@JaredForALGov-shallow-20221106-224823-80gxi-00000.warc.os.cdx.gz	201636	download
urls-transfer.archivete.am-twitter-@JaredForALGov-shallow-20221106-224823-80gxi-meta.warc.gz	136407	download   job
urls-transfer.archivete.am-twitter-@JaredForALGov-shallow-20221106-224823-80gxi-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@JaredForALGov-shallow-20221106-224823-80gxi-urls.txt	46773	download
urls-transfer.archivete.am-twitter-@JaredForALGov-shallow-20221106-224823-80gxi.json	340	download   job
urls-transfer.archivete.am-twitter-@KyleLBAnimal91-shallow-20221106-203043-1bm9c-00000.warc.gz	485898000	download   job
urls-transfer.archivete.am-twitter-@KyleLBAnimal91-shallow-20221106-203043-1bm9c-00000.warc.os.cdx.gz	572855	download
urls-transfer.archivete.am-twitter-@KyleLBAnimal91-shallow-20221106-203043-1bm9c-meta.warc.gz	507915	download   job
urls-transfer.archivete.am-twitter-@KyleLBAnimal91-shallow-20221106-203043-1bm9c-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@KyleLBAnimal91-shallow-20221106-203043-1bm9c-urls.txt	608844	download
urls-transfer.archivete.am-twitter-@KyleLBAnimal91-shallow-20221106-203043-1bm9c.json	342	download   job
urls-transfer.archivete.am-twitter-@NSA_CSDirector-shallow-20221106-193550-ae8wt-00000.warc.gz	354169486	download   job
urls-transfer.archivete.am-twitter-@NSA_CSDirector-shallow-20221106-193550-ae8wt-00000.warc.os.cdx.gz	236323	download
urls-transfer.archivete.am-twitter-@NSA_CSDirector-shallow-20221106-193550-ae8wt-meta.warc.gz	156242	download   job
urls-transfer.archivete.am-twitter-@NSA_CSDirector-shallow-20221106-193550-ae8wt-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@NSA_CSDirector-shallow-20221106-193550-ae8wt-urls.txt	35632	download
urls-transfer.archivete.am-twitter-@NSA_CSDirector-shallow-20221106-193550-ae8wt.json	344	download   job
urls-transfer.archivete.am-twitter-@NaanNCurry-shallow-20221107-005148-6q5jz-00000.warc.gz	269042227	download   job
urls-transfer.archivete.am-twitter-@NaanNCurry-shallow-20221107-005148-6q5jz-00000.warc.os.cdx.gz	203461	download
urls-transfer.archivete.am-twitter-@NaanNCurry-shallow-20221107-005148-6q5jz-meta.warc.gz	130458	download   job
urls-transfer.archivete.am-twitter-@NaanNCurry-shallow-20221107-005148-6q5jz-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@NaanNCurry-shallow-20221107-005148-6q5jz-urls.txt	12609	download
urls-transfer.archivete.am-twitter-@NaanNCurry-shallow-20221107-005148-6q5jz.json	334	download   job
urls-transfer.archivete.am-twitter-@Noncompliant_F-shallow-20221106-203320-7ct7g-00000.warc.gz	828430269	download   job
urls-transfer.archivete.am-twitter-@Noncompliant_F-shallow-20221106-203320-7ct7g-00000.warc.os.cdx.gz	364022	download
urls-transfer.archivete.am-twitter-@Noncompliant_F-shallow-20221106-203320-7ct7g-meta.warc.gz	232894	download   job
urls-transfer.archivete.am-twitter-@Noncompliant_F-shallow-20221106-203320-7ct7g-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@Noncompliant_F-shallow-20221106-203320-7ct7g-urls.txt	13958	download
urls-transfer.archivete.am-twitter-@Noncompliant_F-shallow-20221106-203320-7ct7g.json	342	download   job
urls-transfer.archivete.am-twitter-@QualityIsKing-shallow-20221106-211251-8e8nm-00000.warc.gz	280569965	download   job
urls-transfer.archivete.am-twitter-@QualityIsKing-shallow-20221106-211251-8e8nm-00000.warc.os.cdx.gz	242593	download
urls-transfer.archivete.am-twitter-@QualityIsKing-shallow-20221106-211251-8e8nm-meta.warc.gz	164862	download   job
urls-transfer.archivete.am-twitter-@QualityIsKing-shallow-20221106-211251-8e8nm-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@QualityIsKing-shallow-20221106-211251-8e8nm-urls.txt	38574	download
urls-transfer.archivete.am-twitter-@QualityIsKing-shallow-20221106-211251-8e8nm.json	340	download   job
urls-transfer.archivete.am-twitter-@RealPatriota51-shallow-20221107-000805-5770v-00000.warc.gz	97222	download   job
urls-transfer.archivete.am-twitter-@RealPatriota51-shallow-20221107-000805-5770v-00000.warc.os.cdx.gz	578	download
urls-transfer.archivete.am-twitter-@RealPatriota51-shallow-20221107-000805-5770v-meta.warc.gz	3895	download   job
urls-transfer.archivete.am-twitter-@RealPatriota51-shallow-20221107-000805-5770v-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@RealPatriota51-shallow-20221107-000805-5770v-urls.txt	96	download
urls-transfer.archivete.am-twitter-@RealPatriota51-shallow-20221107-000805-5770v.json	342	download   job
urls-transfer.archivete.am-twitter-@Reguffe-shallow-20221106-223005-54efs-00000.warc.gz	40551062	download   job
urls-transfer.archivete.am-twitter-@Reguffe-shallow-20221106-223005-54efs-00000.warc.os.cdx.gz	106727	download
urls-transfer.archivete.am-twitter-@Reguffe-shallow-20221106-223005-54efs-meta.warc.gz	77530	download   job
urls-transfer.archivete.am-twitter-@Reguffe-shallow-20221106-223005-54efs-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@Reguffe-shallow-20221106-223005-54efs-urls.txt	58382	download
urls-transfer.archivete.am-twitter-@Reguffe-shallow-20221106-223005-54efs.json	330	download   job
urls-transfer.archivete.am-twitter-@RichardEKnowles-shallow-20221106-211036-bc16s-00000.warc.gz	36249301	download   job
urls-transfer.archivete.am-twitter-@RichardEKnowles-shallow-20221106-211036-bc16s-00000.warc.os.cdx.gz	43659	download
urls-transfer.archivete.am-twitter-@RichardEKnowles-shallow-20221106-211036-bc16s-meta.warc.gz	30544	download   job
urls-transfer.archivete.am-twitter-@RichardEKnowles-shallow-20221106-211036-bc16s-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@RichardEKnowles-shallow-20221106-211036-bc16s-urls.txt	10018	download
urls-transfer.archivete.am-twitter-@RichardEKnowles-shallow-20221106-211036-bc16s.json	344	download   job
urls-transfer.archivete.am-twitter-@RichardTol-shallow-20221106-184750-97tsf-00000.warc.gz	5370336150	download   job
urls-transfer.archivete.am-twitter-@RichardTol-shallow-20221106-184750-97tsf-00000.warc.os.cdx.gz	4861173	download
urls-transfer.archivete.am-twitter-@RichardTol-shallow-20221106-184750-97tsf-00001.warc.gz	5383089266	download   job
urls-transfer.archivete.am-twitter-@RichardTol-shallow-20221106-184750-97tsf-00001.warc.os.cdx.gz	788874	download
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2-00000.warc.gz	5391593960	download   job
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2-00000.warc.os.cdx.gz	3515216	download
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2-00001.warc.gz	389633180	download   job
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2-00001.warc.os.cdx.gz	62458	download
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2-meta.warc.gz	2489337	download   job
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2-urls.txt	1185812	download
urls-transfer.archivete.am-twitter-@SarahKSilverman-shallow-20221106-182700-3pok2.json	344	download   job
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00000.warc.gz	5693474447	download   job
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00000.warc.os.cdx.gz	1689530	download
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00001.warc.gz	5511649530	download   job
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00001.warc.os.cdx.gz	3784	download
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00002.warc.gz	5381590698	download   job
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00002.warc.os.cdx.gz	713976	download
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00003.warc.gz	5371221400	download   job
urls-transfer.archivete.am-twitter-@TheAdamGoldberg-shallow-20221106-183027-8ph87-00003.warc.os.cdx.gz	2371069	download
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499-00000.warc.gz	5368918275	download   job
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499-00000.warc.os.cdx.gz	1469732	download
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499-00001.warc.gz	2461152935	download   job
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499-00001.warc.os.cdx.gz	1937767	download
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499-meta.warc.gz	2281241	download   job
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499-urls.txt	974154	download
urls-transfer.archivete.am-twitter-@Wolfiesmom-shallow-20221106-183359-2a499.json	334	download   job
urls-transfer.archivete.am-twitter-@alexgriendling-shallow-20221106-202655-48gan-00000.warc.gz	284590684	download   job
urls-transfer.archivete.am-twitter-@alexgriendling-shallow-20221106-202655-48gan-00000.warc.os.cdx.gz	135868	download
urls-transfer.archivete.am-twitter-@alexgriendling-shallow-20221106-202655-48gan-meta.warc.gz	85440	download   job
urls-transfer.archivete.am-twitter-@alexgriendling-shallow-20221106-202655-48gan-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@alexgriendling-shallow-20221106-202655-48gan-urls.txt	8779	download
urls-transfer.archivete.am-twitter-@alexgriendling-shallow-20221106-202655-48gan.json	342	download   job
urls-transfer.archivete.am-twitter-@arhayward-shallow-20221106-211454-dmrud-00000.warc.gz	911987016	download   job
urls-transfer.archivete.am-twitter-@arhayward-shallow-20221106-211454-dmrud-00000.warc.os.cdx.gz	994822	download
urls-transfer.archivete.am-twitter-@arhayward-shallow-20221106-211454-dmrud-meta.warc.gz	745624	download   job
urls-transfer.archivete.am-twitter-@arhayward-shallow-20221106-211454-dmrud-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@arhayward-shallow-20221106-211454-dmrud-urls.txt	505306	download
urls-transfer.archivete.am-twitter-@arhayward-shallow-20221106-211454-dmrud.json	332	download   job
urls-transfer.archivete.am-twitter-@chrisdc77-shallow-20221106-204355-8730l-00000.warc.gz	5368712884	download   job
urls-transfer.archivete.am-twitter-@chrisdc77-shallow-20221106-204355-8730l-00000.warc.os.cdx.gz	2353762	download
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00000.warc.gz	5460594817	download   job
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00000.warc.os.cdx.gz	485116	download
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00001.warc.gz	5467388524	download   job
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00001.warc.os.cdx.gz	101154	download
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00002.warc.gz	5619146101	download   job
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00002.warc.os.cdx.gz	59478	download
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00003.warc.gz	5368984974	download   job
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00003.warc.os.cdx.gz	780884	download
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00004.warc.gz	5369672311	download   job
urls-transfer.archivete.am-twitter-@davidcsmalley-shallow-20221106-193412-ce6ru-00004.warc.os.cdx.gz	611102	download
urls-transfer.archivete.am-twitter-@dlitchfield-shallow-20221106-203300-6pg2o-00000.warc.gz	3813476115	download   job
urls-transfer.archivete.am-twitter-@dlitchfield-shallow-20221106-203300-6pg2o-00000.warc.os.cdx.gz	1721513	download
urls-transfer.archivete.am-twitter-@dlitchfield-shallow-20221106-203300-6pg2o-meta.warc.gz	1188030	download   job
urls-transfer.archivete.am-twitter-@dlitchfield-shallow-20221106-203300-6pg2o-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@dlitchfield-shallow-20221106-203300-6pg2o-urls.txt	452710	download
urls-transfer.archivete.am-twitter-@dlitchfield-shallow-20221106-203300-6pg2o.json	336	download   job
urls-transfer.archivete.am-twitter-@emilycrockett-shallow-20221106-184011-clqac-00000.warc.gz	5369406866	download   job
urls-transfer.archivete.am-twitter-@emilycrockett-shallow-20221106-184011-clqac-00000.warc.os.cdx.gz	2601201	download
urls-transfer.archivete.am-twitter-@emilycrockett-shallow-20221106-184011-clqac-00001.warc.gz	5369007553	download   job
urls-transfer.archivete.am-twitter-@emilycrockett-shallow-20221106-184011-clqac-00001.warc.os.cdx.gz	2506805	download
urls-transfer.archivete.am-twitter-@gerardkcohen-shallow-20221106-211027-dcn9q-00000.warc.gz	2359353527	download   job
urls-transfer.archivete.am-twitter-@gerardkcohen-shallow-20221106-211027-dcn9q-00000.warc.os.cdx.gz	869632	download
urls-transfer.archivete.am-twitter-@gerardkcohen-shallow-20221106-211027-dcn9q-meta.warc.gz	577147	download   job
urls-transfer.archivete.am-twitter-@gerardkcohen-shallow-20221106-211027-dcn9q-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@gerardkcohen-shallow-20221106-211027-dcn9q-urls.txt	164859	download
urls-transfer.archivete.am-twitter-@gerardkcohen-shallow-20221106-211027-dcn9q.json	340	download   job
urls-transfer.archivete.am-twitter-@jen_rice_-shallow-20221106-183216-3wuua-00000.warc.gz	3024119419	download   job
urls-transfer.archivete.am-twitter-@jen_rice_-shallow-20221106-183216-3wuua-00000.warc.os.cdx.gz	1247408	download
urls-transfer.archivete.am-twitter-@jen_rice_-shallow-20221106-183216-3wuua-meta.warc.gz	849470	download   job
urls-transfer.archivete.am-twitter-@jen_rice_-shallow-20221106-183216-3wuua-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@jen_rice_-shallow-20221106-183216-3wuua-urls.txt	332563	download
urls-transfer.archivete.am-twitter-@jen_rice_-shallow-20221106-183216-3wuua.json	332	download   job
urls-transfer.archivete.am-twitter-@jephjacques-shallow-20221106-182842-92abx-00000.warc.gz	2020439891	download   job
urls-transfer.archivete.am-twitter-@jephjacques-shallow-20221106-182842-92abx-00000.warc.os.cdx.gz	1352854	download
urls-transfer.archivete.am-twitter-@jephjacques-shallow-20221106-182842-92abx-meta.warc.gz	1189708	download   job
urls-transfer.archivete.am-twitter-@jephjacques-shallow-20221106-182842-92abx-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@jephjacques-shallow-20221106-182842-92abx-urls.txt	1511779	download
urls-transfer.archivete.am-twitter-@jephjacques-shallow-20221106-182842-92abx.json	336	download   job
urls-transfer.archivete.am-twitter-@jpmdbnacional15-shallow-20221106-232826-7ydlr-00000.warc.gz	69984400	download   job
urls-transfer.archivete.am-twitter-@jpmdbnacional15-shallow-20221106-232826-7ydlr-00000.warc.os.cdx.gz	90491	download
urls-transfer.archivete.am-twitter-@jpmdbnacional15-shallow-20221106-232826-7ydlr-meta.warc.gz	76072	download   job
urls-transfer.archivete.am-twitter-@jpmdbnacional15-shallow-20221106-232826-7ydlr-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@jpmdbnacional15-shallow-20221106-232826-7ydlr-urls.txt	4292	download
urls-transfer.archivete.am-twitter-@jpmdbnacional15-shallow-20221106-232826-7ydlr.json	344	download   job
urls-transfer.archivete.am-twitter-@lunarsaloon-shallow-20221106-202815-7q646-00000.warc.gz	524700623	download   job
urls-transfer.archivete.am-twitter-@lunarsaloon-shallow-20221106-202815-7q646-00000.warc.os.cdx.gz	268370	download
urls-transfer.archivete.am-twitter-@lunarsaloon-shallow-20221106-202815-7q646-meta.warc.gz	186675	download   job
urls-transfer.archivete.am-twitter-@lunarsaloon-shallow-20221106-202815-7q646-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@lunarsaloon-shallow-20221106-202815-7q646-urls.txt	35469	download
urls-transfer.archivete.am-twitter-@lunarsaloon-shallow-20221106-202815-7q646.json	336	download   job
urls-transfer.archivete.am-twitter-@timmytwits-shallow-20221106-211309-eev2z-00000.warc.gz	853006355	download   job
urls-transfer.archivete.am-twitter-@timmytwits-shallow-20221106-211309-eev2z-00000.warc.os.cdx.gz	490777	download
urls-transfer.archivete.am-twitter-@timmytwits-shallow-20221106-211309-eev2z-meta.warc.gz	365543	download   job
urls-transfer.archivete.am-twitter-@timmytwits-shallow-20221106-211309-eev2z-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-twitter-@timmytwits-shallow-20221106-211309-eev2z-urls.txt	214789	download
urls-transfer.archivete.am-twitter-@timmytwits-shallow-20221106-211309-eev2z.json	334	download   job
urls-transfer.archivete.am-twitter-@ursulaliang-shallow-20221106-203434-2jv68-00000.warc.gz	5369110212	download   job
urls-transfer.archivete.am-twitter-@ursulaliang-shallow-20221106-203434-2jv68-00000.warc.os.cdx.gz	1690676	download
urls-transfer.archivete.am-twitter-@ursulaliang-shallow-20221106-203434-2jv68-00001.warc.gz	5401726149	download   job
urls-transfer.archivete.am-twitter-@ursulaliang-shallow-20221106-203434-2jv68-00001.warc.os.cdx.gz	723636	download
urls-transfer.archivete.am-twitter-@ursulaliang-shallow-20221106-203434-2jv68-00002.warc.gz	5415242823	download   job
urls-transfer.archivete.am-twitter-@ursulaliang-shallow-20221106-203434-2jv68-00002.warc.os.cdx.gz	2329636	download
www.9-man.com-inf-20221106-203637-cq18t-00000.warc.gz	1065399872	download   job
www.9-man.com-inf-20221106-203637-cq18t-00000.warc.os.cdx.gz	604320	download
www.9-man.com-inf-20221106-203637-cq18t-meta.warc.gz	383367	download   job
www.9-man.com-inf-20221106-203637-cq18t-meta.warc.os.cdx.gz	47	download
www.9-man.com-inf-20221106-203637-cq18t.json	243	download   job
www.appearcomar.ipage.com-inf-20221106-222527-2thvl-00000.warc.gz	11891	download   job
www.appearcomar.ipage.com-inf-20221106-222527-2thvl-00000.warc.os.cdx.gz	227	download
www.appearcomar.ipage.com-inf-20221106-222527-2thvl-meta.warc.gz	3514	download   job
www.appearcomar.ipage.com-inf-20221106-222527-2thvl-meta.warc.os.cdx.gz	47	download
www.appearcomar.ipage.com-inf-20221106-222527-2thvl.json	258	download   job
www.appearcomar.ipage.com-inf-20221106-222554-ec7ov-00000.warc.gz	6288	download   job
www.appearcomar.ipage.com-inf-20221106-222554-ec7ov-00000.warc.os.cdx.gz	263	download
www.appearcomar.ipage.com-inf-20221106-222554-ec7ov-meta.warc.gz	3554	download   job
www.appearcomar.ipage.com-inf-20221106-222554-ec7ov-meta.warc.os.cdx.gz	47	download
www.appearcomar.ipage.com-inf-20221106-222554-ec7ov.json	270	download   job
www.apple.com-inf-20221030-175356-cblcc-00056.warc.gz	5408455452	download   job
www.apple.com-inf-20221030-175356-cblcc-00056.warc.os.cdx.gz	468798	download
www.apple.com-inf-20221030-175356-cblcc-00057.warc.gz	5480213184	download   job
www.apple.com-inf-20221030-175356-cblcc-00057.warc.os.cdx.gz	84550	download
www.apple.com-inf-20221030-175356-cblcc-00058.warc.gz	5441704943	download   job
www.apple.com-inf-20221030-175356-cblcc-00058.warc.os.cdx.gz	116219	download
www.atualisa.republicanos10.org.br-shallow-20221106-235305-8of4s-00000.warc.gz	454365	download   job
www.atualisa.republicanos10.org.br-shallow-20221106-235305-8of4s-00000.warc.os.cdx.gz	1687	download
www.atualisa.republicanos10.org.br-shallow-20221106-235305-8of4s-meta.warc.gz	4803	download   job
www.atualisa.republicanos10.org.br-shallow-20221106-235305-8of4s-meta.warc.os.cdx.gz	47	download
www.atualisa.republicanos10.org.br-shallow-20221106-235305-8of4s.json	266	download   job
www.bloggen.be-inf-20211103-191902-5alb5-00388.warc.gz	5368745146	download   job
www.bloggen.be-inf-20211103-191902-5alb5-00388.warc.os.cdx.gz	42293825	download
www.clickwrestle.com-inf-20221105-215445-4mpv3-00009.warc.gz	5370600820	download   job
www.clickwrestle.com-inf-20221105-215445-4mpv3-00009.warc.os.cdx.gz	932107	download
www.climategate.nl-inf-20221103-042209-5t9vs-00029.warc.gz	5483002760	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00029.warc.os.cdx.gz	2020429	download
www.climategate.nl-inf-20221103-042209-5t9vs-00030.warc.gz	5511071802	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00030.warc.os.cdx.gz	966778	download
www.climategate.nl-inf-20221103-042209-5t9vs-00031.warc.gz	5490916897	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00031.warc.os.cdx.gz	949587	download
www.climategate.nl-inf-20221103-042209-5t9vs-00032.warc.gz	5627578525	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00032.warc.os.cdx.gz	710106	download
www.climategate.nl-inf-20221103-042209-5t9vs-00033.warc.gz	5369412755	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00033.warc.os.cdx.gz	1087695	download
www.climategate.nl-inf-20221103-042209-5t9vs-00034.warc.gz	5374515320	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00034.warc.os.cdx.gz	1571033	download
www.climategate.nl-inf-20221103-042209-5t9vs-00035.warc.gz	6025923871	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00035.warc.os.cdx.gz	180962	download
www.climategate.nl-inf-20221103-042209-5t9vs-00036.warc.gz	5473991678	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00036.warc.os.cdx.gz	12364	download
www.climategate.nl-inf-20221103-042209-5t9vs-00037.warc.gz	5402857852	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00037.warc.os.cdx.gz	8983	download
www.climategate.nl-inf-20221103-042209-5t9vs-00038.warc.gz	5691861518	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00038.warc.os.cdx.gz	16611	download
www.climategate.nl-inf-20221103-042209-5t9vs-00039.warc.gz	5413610343	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00039.warc.os.cdx.gz	8509	download
www.climategate.nl-inf-20221103-042209-5t9vs-00040.warc.gz	5377008558	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00040.warc.os.cdx.gz	1518401	download
www.climategate.nl-inf-20221103-042209-5t9vs-00041.warc.gz	5527403179	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00041.warc.os.cdx.gz	2125290	download
www.climategate.nl-inf-20221103-042209-5t9vs-00042.warc.gz	5395264094	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00042.warc.os.cdx.gz	1091965	download
www.climategate.nl-inf-20221103-042209-5t9vs-00043.warc.gz	5379920044	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00043.warc.os.cdx.gz	1880670	download
www.climategate.nl-inf-20221103-042209-5t9vs-00044.warc.gz	5430237846	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00044.warc.os.cdx.gz	92024	download
www.climategate.nl-inf-20221103-042209-5t9vs-00045.warc.gz	5368865298	download   job
www.climategate.nl-inf-20221103-042209-5t9vs-00045.warc.os.cdx.gz	146063	download
www.davidlitchfield.com-inf-20221106-203552-cq8hq-00000.warc.gz	90203139	download   job
www.davidlitchfield.com-inf-20221106-203552-cq8hq-00000.warc.os.cdx.gz	145464	download
www.davidlitchfield.com-inf-20221106-203552-cq8hq-meta.warc.gz	97755	download   job
www.davidlitchfield.com-inf-20221106-203552-cq8hq-meta.warc.os.cdx.gz	47	download
www.davidlitchfield.com-inf-20221106-203552-cq8hq.json	253	download   job
www.flickr.com-inf-20221106-165134-6bjkd-00000.warc.gz	652754561	download   job
www.flickr.com-inf-20221106-165134-6bjkd-00000.warc.os.cdx.gz	360873	download
www.flickr.com-inf-20221106-165134-6bjkd-meta.warc.gz	213454	download   job
www.flickr.com-inf-20221106-165134-6bjkd-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20221106-165134-6bjkd.json	264	download   job
www.flickr.com-inf-20221106-165154-3q6ki-00000.warc.gz	1232252102	download   job
www.flickr.com-inf-20221106-165154-3q6ki-00000.warc.os.cdx.gz	552165	download
www.flickr.com-inf-20221106-165154-3q6ki-meta.warc.gz	298091	download   job
www.flickr.com-inf-20221106-165154-3q6ki-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20221106-165154-3q6ki.json	264	download   job
www.flickr.com-inf-20221106-222458-bpqtq-00000.warc.gz	933001004	download   job
www.flickr.com-inf-20221106-222458-bpqtq-00000.warc.os.cdx.gz	349640	download
www.flickr.com-inf-20221106-222458-bpqtq-meta.warc.gz	205953	download   job
www.flickr.com-inf-20221106-222458-bpqtq-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20221106-222458-bpqtq.json	263	download   job
www.flickr.com-inf-20221106-222505-73llk-00000.warc.gz	5373626037	download   job
www.flickr.com-inf-20221106-222505-73llk-00000.warc.os.cdx.gz	502025	download
www.flickr.com-inf-20221106-222505-73llk-00001.warc.gz	5374545300	download   job
www.flickr.com-inf-20221106-222505-73llk-00001.warc.os.cdx.gz	285643	download
www.flickr.com-inf-20221106-222505-73llk-00002.warc.gz	5369513012	download   job
www.flickr.com-inf-20221106-222505-73llk-00002.warc.os.cdx.gz	401815	download
www.flickr.com-inf-20221106-222505-73llk-00003.warc.gz	5375126842	download   job
www.flickr.com-inf-20221106-222505-73llk-00003.warc.os.cdx.gz	409356	download
www.flickr.com-inf-20221106-222505-73llk-00004.warc.gz	5371275567	download   job
www.flickr.com-inf-20221106-222505-73llk-00004.warc.os.cdx.gz	282578	download
www.flickr.com-inf-20221106-222505-73llk-00005.warc.gz	5371077263	download   job
www.flickr.com-inf-20221106-222505-73llk-00005.warc.os.cdx.gz	292133	download
www.flickr.com-inf-20221106-222647-c3jry-00000.warc.gz	969781279	download   job
www.flickr.com-inf-20221106-222647-c3jry-00000.warc.os.cdx.gz	399808	download
www.flickr.com-inf-20221106-222647-c3jry-meta.warc.gz	235360	download   job
www.flickr.com-inf-20221106-222647-c3jry-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20221106-222647-c3jry.json	260	download   job
www.flickr.com-inf-20221106-222700-2fgjh-00000.warc.gz	5377416781	download   job
www.flickr.com-inf-20221106-222700-2fgjh-00000.warc.os.cdx.gz	382647	download
www.flickr.com-inf-20221106-222700-2fgjh-00001.warc.gz	5368715328	download   job
www.flickr.com-inf-20221106-222700-2fgjh-00001.warc.os.cdx.gz	614038	download
www.flickr.com-inf-20221106-222700-2fgjh-00002.warc.gz	4326334647	download   job
www.flickr.com-inf-20221106-222700-2fgjh-00002.warc.os.cdx.gz	333268	download
www.flickr.com-inf-20221106-222700-2fgjh-meta.warc.gz	604322	download   job
www.flickr.com-inf-20221106-222700-2fgjh-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20221106-222700-2fgjh.json	263	download   job
www.gluecad-bio.com-inf-20221106-211615-3e172-00000.warc.gz	1756481123	download   job
www.gluecad-bio.com-inf-20221106-211615-3e172-00000.warc.os.cdx.gz	355884	download
www.gluecad-bio.com-inf-20221106-211615-3e172-meta.warc.gz	279001	download   job
www.gluecad-bio.com-inf-20221106-211615-3e172-meta.warc.os.cdx.gz	47	download
www.gluecad-bio.com-inf-20221106-211615-3e172.json	259	download   job
www.gluecad.com-inf-20221106-215225-2h1xj-00000.warc.gz	2466	download   job
www.gluecad.com-inf-20221106-215225-2h1xj-00000.warc.os.cdx.gz	47	download
www.gluecad.com-inf-20221106-215225-2h1xj-meta.warc.gz	3609	download   job
www.gluecad.com-inf-20221106-215225-2h1xj-meta.warc.os.cdx.gz	47	download
www.gluecad.com-inf-20221106-215225-2h1xj.json	245	download   job
www.ics.uci.edu-inf-20221103-202919-35ow5-00032.warc.gz	6165246498	download   job
www.ics.uci.edu-inf-20221103-202919-35ow5-00032.warc.os.cdx.gz	2060922	download
www.ics.uci.edu-inf-20221103-202919-35ow5-00033.warc.gz	42522240	download   job
www.ics.uci.edu-inf-20221103-202919-35ow5-00033.warc.os.cdx.gz	208922	download
www.ics.uci.edu-inf-20221103-202919-35ow5-meta.warc.gz	24618516	download   job
www.ics.uci.edu-inf-20221103-202919-35ow5-meta.warc.os.cdx.gz	47	download
www.ics.uci.edu-inf-20221103-202919-35ow5.json	245	download   job
www.jaredalgov.org-inf-20221106-224742-bo8f6-00000.warc.gz	112218584	download   job
www.jaredalgov.org-inf-20221106-224742-bo8f6-00000.warc.os.cdx.gz	106562	download
www.jaredalgov.org-inf-20221106-224742-bo8f6-meta.warc.gz	69941	download   job
www.jaredalgov.org-inf-20221106-224742-bo8f6-meta.warc.os.cdx.gz	47	download
www.jaredalgov.org-inf-20221106-224742-bo8f6.json	245	download   job
www.joaquimbarbosa.adv.br-inf-20221106-222722-bu7xi-00000.warc.gz	153520332	download   job
www.joaquimbarbosa.adv.br-inf-20221106-222722-bu7xi-00000.warc.os.cdx.gz	329663	download
www.joaquimbarbosa.adv.br-inf-20221106-222722-bu7xi-meta.warc.gz	223767	download   job
www.joaquimbarbosa.adv.br-inf-20221106-222722-bu7xi-meta.warc.os.cdx.gz	47	download
www.joaquimbarbosa.adv.br-inf-20221106-222722-bu7xi.json	253	download   job
www.kidsdown.com-inf-20220826-212919-2syf6-00410.warc.gz	5394451634	download   job
www.kidsdown.com-inf-20220826-212919-2syf6-00410.warc.os.cdx.gz	229249	download
www.kidsdown.com-inf-20220826-212919-2syf6-00411.warc.gz	5375867157	download   job
www.kidsdown.com-inf-20220826-212919-2syf6-00411.warc.os.cdx.gz	117774	download
www.kidsdown.com-inf-20220826-212919-2syf6-00412.warc.gz	5394650362	download   job
www.kidsdown.com-inf-20220826-212919-2syf6-00412.warc.os.cdx.gz	144375	download
www.kidsdown.com-inf-20220826-212919-2syf6-00413.warc.gz	5386613300	download   job
www.kidsdown.com-inf-20220826-212919-2syf6-00413.warc.os.cdx.gz	158531	download
www.kidsdown.com-inf-20220826-212919-2syf6-00414.warc.gz	5378388758	download   job
www.kidsdown.com-inf-20220826-212919-2syf6-00414.warc.os.cdx.gz	216181	download
www.leps.eu-inf-20221106-211356-63dr7-00000.warc.gz	205424	download   job
www.leps.eu-inf-20221106-211356-63dr7-00000.warc.os.cdx.gz	1675	download
www.leps.eu-inf-20221106-211356-63dr7-meta.warc.gz	4327	download   job
www.leps.eu-inf-20221106-211356-63dr7-meta.warc.os.cdx.gz	47	download
www.leps.eu-inf-20221106-211356-63dr7.json	240	download   job
www.lucidcentral.org-inf-20221106-181007-448q6-00000.warc.gz	1184568016	download   job
www.lucidcentral.org-inf-20221106-181007-448q6-00000.warc.os.cdx.gz	1713820	download
www.lucidcentral.org-inf-20221106-181007-448q6-meta.warc.gz	1476881	download   job
www.lucidcentral.org-inf-20221106-181007-448q6-meta.warc.os.cdx.gz	47	download
www.lucidcentral.org-inf-20221106-181007-448q6.json	250	download   job
www.naanncurry.com-inf-20221107-005129-b1olk-00000.warc.gz	222689538	download   job
www.naanncurry.com-inf-20221107-005129-b1olk-00000.warc.os.cdx.gz	599732	download
www.naanncurry.com-inf-20221107-005129-b1olk-meta.warc.gz	377495	download   job
www.naanncurry.com-inf-20221107-005129-b1olk-meta.warc.os.cdx.gz	47	download
www.naanncurry.com-inf-20221107-005129-b1olk.json	248	download   job
www.renesas.com-inf-20221105-192555-43jqc-00005.warc.gz	5368929648	download   job
www.renesas.com-inf-20221105-192555-43jqc-00005.warc.os.cdx.gz	1484670	download
www.seargentina.com.ar-inf-20221106-222846-3q17y-00000.warc.gz	2405	download   job
www.seargentina.com.ar-inf-20221106-222846-3q17y-00000.warc.os.cdx.gz	47	download
www.seargentina.com.ar-inf-20221106-222846-3q17y-meta.warc.gz	3491	download   job
www.seargentina.com.ar-inf-20221106-222846-3q17y-meta.warc.os.cdx.gz	47	download
www.seargentina.com.ar-inf-20221106-222846-3q17y.json	251	download   job
www.somalinet.com-inf-20221102-040258-ajog8-00023.warc.gz	5466814131	download   job
www.somalinet.com-inf-20221102-040258-ajog8-00023.warc.os.cdx.gz	3002401	download
www.somalinet.com-inf-20221102-040258-ajog8-00024.warc.gz	5368782244	download   job
www.somalinet.com-inf-20221102-040258-ajog8-00024.warc.os.cdx.gz	897969	download
www.somalinet.com-inf-20221102-040258-ajog8-00025.warc.gz	5653514915	download   job
www.somalinet.com-inf-20221102-040258-ajog8-00025.warc.os.cdx.gz	645584	download
www.thegaygamer.com-inf-20221104-195708-al3tj-00006.warc.gz	5368735081	download   job
www.thegaygamer.com-inf-20221104-195708-al3tj-00006.warc.os.cdx.gz	7725062	download
www.time.lula.com.br-shallow-20221106-230942-28ngc-00000.warc.gz	39796359	download   job
www.time.lula.com.br-shallow-20221106-230942-28ngc-00000.warc.os.cdx.gz	92419	download
www.time.lula.com.br-shallow-20221106-230942-28ngc-meta.warc.gz	47008	download   job
www.time.lula.com.br-shallow-20221106-230942-28ngc-meta.warc.os.cdx.gz	47	download
www.time.lula.com.br-shallow-20221106-230942-28ngc.json	252	download   job