Item archiveteam_archivebot_go_20261004141957_e9b9a736

Filename	Size
antigo.mdb.org.br-inf-20261004-140431-1p7xk-00000.warc.gz	17941	download job
antigo.mdb.org.br-inf-20261004-140431-1p7xk-00000.warc.os.cdx.gz	328	download
antigo.mdb.org.br-inf-20261004-140431-1p7xk-meta.warc.gz	3438	download job
antigo.mdb.org.br-inf-20261004-140431-1p7xk-meta.warc.os.cdx.gz	47	download
antigo.mdb.org.br-inf-20261004-140431-1p7xk.json	245	download job
archiveteam_archivebot_go_20261004141957_e9b9a736.cdx.gz	96726565	download
archiveteam_archivebot_go_20261004141957_e9b9a736.cdx.idx	114152	download
archiveteam_archivebot_go_20261004141957_e9b9a736_files.xml	0	download
archiveteam_archivebot_go_20261004141957_e9b9a736_meta.sqlite	28672	download
archiveteam_archivebot_go_20261004141957_e9b9a736_meta.xml	910	download
candidatos.pco.org.br-inf-20261004-131930-ahn9n-00000.warc.gz	2935828574	download job
candidatos.pco.org.br-inf-20261004-131930-ahn9n-00000.warc.os.cdx.gz	664282	download
candidatos.pco.org.br-inf-20261004-131930-ahn9n-meta.warc.gz	381590	download job
candidatos.pco.org.br-inf-20261004-131930-ahn9n-meta.warc.os.cdx.gz	47	download
candidatos.pco.org.br-inf-20261004-131930-ahn9n.json	249	download job
compliance.podemos.org.br-inf-20261004-140012-czmz1-00000.warc.gz	371563664	download job
compliance.podemos.org.br-inf-20261004-140012-czmz1-00000.warc.os.cdx.gz	169342	download
compliance.podemos.org.br-inf-20261004-140012-czmz1-meta.warc.gz	106210	download job
compliance.podemos.org.br-inf-20261004-140012-czmz1-meta.warc.os.cdx.gz	47	download
compliance.podemos.org.br-inf-20261004-140012-czmz1.json	253	download job
cordis.europa.eu-inf-20260819-053344-a3je4-00036.warc.gz	5368747569	download job
cordis.europa.eu-inf-20260819-053344-a3je4-00036.warc.os.cdx.gz	8688289	download
dev.republicanos10.org.br-shallow-20261004-135222-1nzez-00000.warc.gz	7985166	download job
dev.republicanos10.org.br-shallow-20261004-135222-1nzez-00000.warc.os.cdx.gz	5725	download
dev.republicanos10.org.br-shallow-20261004-135222-1nzez-meta.warc.gz	7021	download job
dev.republicanos10.org.br-shallow-20261004-135222-1nzez-meta.warc.os.cdx.gz	47	download
dev.republicanos10.org.br-shallow-20261004-135222-1nzez.json	257	download job
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141443-6o0a0-00000.warc.gz	686274	download job
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141443-6o0a0-00000.warc.os.cdx.gz	247	download
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141443-6o0a0-meta.warc.gz	3541	download job
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141443-6o0a0-meta.warc.os.cdx.gz	47	download
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141443-6o0a0.json	284	download job
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141552-9ud4h-00000.warc.gz	730529	download job
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141552-9ud4h-00000.warc.os.cdx.gz	249	download
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141552-9ud4h-meta.warc.gz	3521	download job
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141552-9ud4h-meta.warc.os.cdx.gz	47	download
dtuitjyhwcl5y.cloudfront.net-shallow-20261004-141552-9ud4h.json	284	download job
eleicoes.podemos.org.br-inf-20261004-140056-aifwc-00000.warc.gz	18389583	download job
eleicoes.podemos.org.br-inf-20261004-140056-aifwc-00000.warc.os.cdx.gz	56025	download
eleicoes.podemos.org.br-inf-20261004-140056-aifwc-meta.warc.gz	38844	download job
eleicoes.podemos.org.br-inf-20261004-140056-aifwc-meta.warc.os.cdx.gz	47	download
eleicoes.podemos.org.br-inf-20261004-140056-aifwc.json	251	download job
en.causaoperaria.org.br-inf-20261004-133459-9k1tv-00000.warc.gz	309660487	download job
en.causaoperaria.org.br-inf-20261004-133459-9k1tv-00000.warc.os.cdx.gz	602436	download
en.causaoperaria.org.br-inf-20261004-133459-9k1tv-meta.warc.gz	400157	download job
en.causaoperaria.org.br-inf-20261004-133459-9k1tv-meta.warc.os.cdx.gz	47	download
en.causaoperaria.org.br-inf-20261004-133459-9k1tv.json	251	download job
es.causaoperaria.org.br-inf-20261004-135942-5ajd4-00000.warc.gz	13753	download job
es.causaoperaria.org.br-inf-20261004-135942-5ajd4-00000.warc.os.cdx.gz	337	download
es.causaoperaria.org.br-inf-20261004-135942-5ajd4-meta.warc.gz	3458	download job
es.causaoperaria.org.br-inf-20261004-135942-5ajd4-meta.warc.os.cdx.gz	47	download
es.causaoperaria.org.br-inf-20261004-135942-5ajd4.json	251	download job
europeanjournalists.org-inf-20261003-023855-371qm-00009.warc.gz	4064297738	download job
europeanjournalists.org-inf-20261003-023855-371qm-00009.warc.os.cdx.gz	6186150	download
europeanjournalists.org-inf-20261003-023855-371qm-meta.warc.gz	27496800	download job
europeanjournalists.org-inf-20261003-023855-371qm-meta.warc.os.cdx.gz	47	download
europeanjournalists.org-inf-20261003-023855-371qm.json	254	download job
filie.podemos.org.br-inf-20261004-140547-9hbge-00000.warc.gz	9110	download job
filie.podemos.org.br-inf-20261004-140547-9hbge-00000.warc.os.cdx.gz	370	download
filie.podemos.org.br-inf-20261004-140547-9hbge-meta.warc.gz	3610	download job
filie.podemos.org.br-inf-20261004-140547-9hbge-meta.warc.os.cdx.gz	47	download
filie.podemos.org.br-inf-20261004-140547-9hbge.json	248	download job
flb-ap.org.br-inf-20261004-134814-3pbwi-00000.warc.gz	21533	download job
flb-ap.org.br-inf-20261004-134814-3pbwi-00000.warc.os.cdx.gz	406	download
flb-ap.org.br-inf-20261004-134814-3pbwi-meta.warc.gz	3570	download job
flb-ap.org.br-inf-20261004-134814-3pbwi-meta.warc.os.cdx.gz	47	download
flb-ap.org.br-inf-20261004-134814-3pbwi.json	240	download job
forum.psaudio.com-inf-20260922-031957-3kivi-00039.warc.gz	5434011727	download job
forum.psaudio.com-inf-20260922-031957-3kivi-00039.warc.os.cdx.gz	3554300	download
fundacaopodemos.org.br-inf-20261004-082908-ej7pr-00001.warc.gz	5707374745	download job
fundacaopodemos.org.br-inf-20261004-082908-ej7pr-00001.warc.os.cdx.gz	1995484	download
g.hostfil.es-shallow-20261004-141307-ec0g5-00000.warc.gz	10922	download job
g.hostfil.es-shallow-20261004-141307-ec0g5-00000.warc.os.cdx.gz	273	download
g.hostfil.es-shallow-20261004-141307-ec0g5-meta.warc.gz	3542	download job
g.hostfil.es-shallow-20261004-141307-ec0g5-meta.warc.os.cdx.gz	47	download
g.hostfil.es-shallow-20261004-141307-ec0g5.json	322	download job
ipi.media-inf-20261003-025900-25zfs-00018.warc.gz	5385196498	download job
ipi.media-inf-20261003-025900-25zfs-00018.warc.os.cdx.gz	1386794	download
kp.ua-inf-20260925-061448-4xuh8-00057.warc.gz	5549415715	download job
kp.ua-inf-20260925-061448-4xuh8-00057.warc.os.cdx.gz	2676479	download
loja.podemos.org.br-inf-20261004-140933-achu6-00000.warc.gz	83395389	download job
loja.podemos.org.br-inf-20261004-140933-achu6-00000.warc.os.cdx.gz	132633	download
loja.podemos.org.br-inf-20261004-140933-achu6-meta.warc.gz	90056	download job
loja.podemos.org.br-inf-20261004-140933-achu6-meta.warc.os.cdx.gz	47	download
loja.podemos.org.br-inf-20261004-140933-achu6.json	247	download job
matsda2sh.com-inf-20261002-074628-arb57-00018.warc.gz	5368734529	download job
matsda2sh.com-inf-20261002-074628-arb57-00018.warc.os.cdx.gz	7429963	download
noticias.uol.com.br-inf-20261004-102503-brdbk-00000.warc.gz	5368742318	download job
noticias.uol.com.br-inf-20261004-102503-brdbk-00000.warc.os.cdx.gz	3296492	download
novo.solidariedade.org.br-inf-20261004-134939-ezz34-00000.warc.gz	15617455	download job
novo.solidariedade.org.br-inf-20261004-134939-ezz34-00000.warc.os.cdx.gz	14099	download
novo.solidariedade.org.br-inf-20261004-134939-ezz34-meta.warc.gz	11612	download job
novo.solidariedade.org.br-inf-20261004-134939-ezz34-meta.warc.os.cdx.gz	47	download
novo.solidariedade.org.br-inf-20261004-134939-ezz34.json	253	download job
pcf13.com-inf-20261003-055958-ddx9m-00000.warc.gz	2671840772	download job
pcf13.com-inf-20261003-055958-ddx9m-00000.warc.os.cdx.gz	2822676	download
pcf13.com-inf-20261003-055958-ddx9m-meta.warc.gz	2177012	download job
pcf13.com-inf-20261003-055958-ddx9m-meta.warc.os.cdx.gz	47	download
pcf13.com-inf-20261003-055958-ddx9m.json	237	download job
pesquisa.republicanos10.org.br-inf-20261004-135429-e0dup-00000.warc.gz	17821560	download job
pesquisa.republicanos10.org.br-inf-20261004-135429-e0dup-00000.warc.os.cdx.gz	56295	download
pesquisa.republicanos10.org.br-inf-20261004-135429-e0dup-meta.warc.gz	38562	download job
pesquisa.republicanos10.org.br-inf-20261004-135429-e0dup-meta.warc.os.cdx.gz	47	download
pesquisa.republicanos10.org.br-inf-20261004-135429-e0dup.json	258	download job
rd.solidariedade.org.br-inf-20261004-135149-95db0-00000.warc.gz	6331	download job
rd.solidariedade.org.br-inf-20261004-135149-95db0-00000.warc.os.cdx.gz	312	download
rd.solidariedade.org.br-inf-20261004-135149-95db0-meta.warc.gz	3556	download job
rd.solidariedade.org.br-inf-20261004-135149-95db0-meta.warc.os.cdx.gz	47	download
rd.solidariedade.org.br-inf-20261004-135149-95db0.json	251	download job
senateurscrce.fr-inf-20261003-103209-6l4k0-00001.warc.gz	5368734891	download job
senateurscrce.fr-inf-20261003-103209-6l4k0-00001.warc.os.cdx.gz	15881842	download
spark.podemos.org.br-inf-20261004-141722-8ejh9-00000.warc.gz	2472	download job
spark.podemos.org.br-inf-20261004-141722-8ejh9-00000.warc.os.cdx.gz	47	download
spark.podemos.org.br-inf-20261004-141722-8ejh9-meta.warc.gz	3616	download job
spark.podemos.org.br-inf-20261004-141722-8ejh9-meta.warc.os.cdx.gz	47	download
spark.podemos.org.br-inf-20261004-141722-8ejh9.json	248	download job
support.apple.com-inf-20260916-195705-f1ds9-00122.warc.gz	5368794181	download job
support.apple.com-inf-20260916-195705-f1ds9-00122.warc.os.cdx.gz	2615012	download
urls-transfer.archivete.am-berkeley.edu_subdomains.txt-inf-20260225-025210-bb9um-02101.warc.gz	5369349355	download job
urls-transfer.archivete.am-berkeley.edu_subdomains.txt-inf-20260225-025210-bb9um-02101.warc.os.cdx.gz	786598	download
urls-transfer.archivete.am-blog.sina.com.cn-no-offsite.txt-inf-20260820-204826-b33o1-00011.warc.gz	5368713733	download job
urls-transfer.archivete.am-blog.sina.com.cn-no-offsite.txt-inf-20260820-204826-b33o1-00011.warc.os.cdx.gz	18971866	download
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00536.warc.gz	5369761810	download job
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00536.warc.os.cdx.gz	387403	download
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00537.warc.gz	5368805950	download job
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00537.warc.os.cdx.gz	414096	download
urls-transfer.notkiska.pw-pco.org.br_junky-subdomains.txt-inf-20261004-132604-dqwqs-00000.warc.gz	497512400	download job
urls-transfer.notkiska.pw-pco.org.br_junky-subdomains.txt-inf-20261004-132604-dqwqs-00000.warc.os.cdx.gz	843257	download
urls-transfer.notkiska.pw-pco.org.br_junky-subdomains.txt-inf-20261004-132604-dqwqs-meta.warc.gz	511530	download job
urls-transfer.notkiska.pw-pco.org.br_junky-subdomains.txt-inf-20261004-132604-dqwqs-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-pco.org.br_junky-subdomains.txt-inf-20261004-132604-dqwqs-urls.txt	844	download
urls-transfer.notkiska.pw-pco.org.br_junky-subdomains.txt-inf-20261004-132604-dqwqs.json	349	download job
urls-transfer.notkiska.pw-republicanos10.org.br_junky-subdomains.txt-inf-20261004-135826-1cnn4-00000.warc.gz	315641	download job
urls-transfer.notkiska.pw-republicanos10.org.br_junky-subdomains.txt-inf-20261004-135826-1cnn4-00000.warc.os.cdx.gz	4698	download
urls-transfer.notkiska.pw-republicanos10.org.br_junky-subdomains.txt-inf-20261004-135826-1cnn4-meta.warc.gz	6635	download job
urls-transfer.notkiska.pw-republicanos10.org.br_junky-subdomains.txt-inf-20261004-135826-1cnn4-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-republicanos10.org.br_junky-subdomains.txt-inf-20261004-135826-1cnn4-urls.txt	510	download
urls-transfer.notkiska.pw-republicanos10.org.br_junky-subdomains.txt-inf-20261004-135826-1cnn4.json	371	download job
wrongplanet.net-inf-20260927-204317-95xke-00065.warc.gz	5570336340	download job
wrongplanet.net-inf-20260927-204317-95xke-00065.warc.os.cdx.gz	2496296	download
www.bancadaverde.org.br-shallow-20261004-140855-csbxg-00000.warc.gz	2481605	download job
www.bancadaverde.org.br-shallow-20261004-140855-csbxg-00000.warc.os.cdx.gz	12990	download
www.bancadaverde.org.br-shallow-20261004-140855-csbxg-meta.warc.gz	10741	download job
www.bancadaverde.org.br-shallow-20261004-140855-csbxg-meta.warc.os.cdx.gz	47	download
www.bancadaverde.org.br-shallow-20261004-140855-csbxg.json	255	download job
www.cncr.gob.cl-inf-20261003-132019-1ibfj-00006.warc.gz	5369233066	download job
www.cncr.gob.cl-inf-20261003-132019-1ibfj-00006.warc.os.cdx.gz	10102104	download
www.intermedia.ru-inf-20260930-220827-4s4om-00014.warc.gz	5369935938	download job
www.intermedia.ru-inf-20260930-220827-4s4om-00014.warc.os.cdx.gz	4056667	download
www.novo.solidariedade.org.br-inf-20261004-135245-7b3vk-00000.warc.gz	853578	download job
www.novo.solidariedade.org.br-inf-20261004-135245-7b3vk-00000.warc.os.cdx.gz	2547	download
www.novo.solidariedade.org.br-inf-20261004-135245-7b3vk-meta.warc.gz	5037	download job
www.novo.solidariedade.org.br-inf-20261004-135245-7b3vk-meta.warc.os.cdx.gz	47	download
www.novo.solidariedade.org.br-inf-20261004-135245-7b3vk.json	257	download job
www.samsung.com-inf-20260905-093652-37gk1-00151.warc.gz	5396633439	download job
www.samsung.com-inf-20260905-093652-37gk1-00151.warc.os.cdx.gz	270953	download
www.siemens.com-inf-20261002-045046-dezls-00025.warc.gz	5372507126	download job
www.siemens.com-inf-20261002-045046-dezls-00025.warc.os.cdx.gz	681018	download
www.stlucieco.gov-inf-20261002-231239-2r2vv-00004.warc.gz	5375004715	download job
www.stlucieco.gov-inf-20261002-231239-2r2vv-00004.warc.os.cdx.gz	3329480	download
www.tabnak.ir-inf-20260130-213526-8r7zi-02196.warc.gz	5378802381	download job
www.tabnak.ir-inf-20260130-213526-8r7zi-02196.warc.os.cdx.gz	215169	download