Item archiveteam_archivebot_go_20250324164600_1a648d83

Filename	Size
2019.fotografestival.cz-inf-20250324-161228-5tp7w-00000.warc.gz	248874039	download job
2019.fotografestival.cz-inf-20250324-161228-5tp7w-00000.warc.os.cdx.gz	153585	download
2019.fotografestival.cz-inf-20250324-161228-5tp7w-meta.warc.gz	140844	download job
2019.fotografestival.cz-inf-20250324-161228-5tp7w-meta.warc.os.cdx.gz	47	download
2019.fotografestival.cz-inf-20250324-161228-5tp7w.json	251	download job
almada-seixal.pan.com.pt-inf-20250324-161555-8s34b.json	252	download job
alumnos.astoreca.cl-inf-20250324-163817-8q2yk-00000.warc.gz	18316	download job
alumnos.astoreca.cl-inf-20250324-163817-8q2yk-00000.warc.os.cdx.gz	470	download
alumnos.astoreca.cl-inf-20250324-163817-8q2yk-meta.warc.gz	3656	download job
alumnos.astoreca.cl-inf-20250324-163817-8q2yk-meta.warc.os.cdx.gz	47	download
alumnos.astoreca.cl-inf-20250324-163817-8q2yk.json	244	download job
anexos.astoreca.cl-inf-20250324-163716-af8pr-00000.warc.gz	83003718	download job
anexos.astoreca.cl-inf-20250324-163716-af8pr-00000.warc.os.cdx.gz	102456	download
anexos.astoreca.cl-inf-20250324-163716-af8pr-meta.warc.gz	70046	download job
anexos.astoreca.cl-inf-20250324-163716-af8pr-meta.warc.os.cdx.gz	47	download
anexos.astoreca.cl-inf-20250324-163716-af8pr.json	243	download job
archiveteam_archivebot_go_20250324164600_1a648d83.cdx.gz	249735	download
archiveteam_archivebot_go_20250324164600_1a648d83.cdx.idx	302	download
archiveteam_archivebot_go_20250324164600_1a648d83_files.xml	0	download
archiveteam_archivebot_go_20250324164600_1a648d83_meta.sqlite	466944	download
archiveteam_archivebot_go_20250324164600_1a648d83_meta.xml	1045	download
cirrus.ucsd.edu-inf-20250204-222623-178n0-04089.warc.gz	7461542351	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-04089.warc.os.cdx.gz	1323	download
cirrus.ucsd.edu-inf-20250204-222623-178n0-04090.warc.gz	6693425291	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-04090.warc.os.cdx.gz	878	download
cirrus.ucsd.edu-inf-20250204-222623-178n0-04091.warc.gz	5946900835	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-04091.warc.os.cdx.gz	583	download
coimbra.pan.com.pt-inf-20250324-161626-crcgr-00000.warc.gz	12903	download job
coimbra.pan.com.pt-inf-20250324-161626-crcgr-00000.warc.os.cdx.gz	339	download
coimbra.pan.com.pt-inf-20250324-161626-crcgr-meta.warc.gz	3701	download job
coimbra.pan.com.pt-inf-20250324-161626-crcgr-meta.warc.os.cdx.gz	47	download
coimbra.pan.com.pt-inf-20250324-161626-crcgr.json	246	download job
cpanel.pan.com.pt-inf-20250324-161814-d81ez-00000.warc.gz	4285397	download job
cpanel.pan.com.pt-inf-20250324-161814-d81ez-00000.warc.os.cdx.gz	10453	download
cpanel.pan.com.pt-inf-20250324-161814-d81ez-meta.warc.gz	8560	download job
cpanel.pan.com.pt-inf-20250324-161814-d81ez-meta.warc.os.cdx.gz	47	download
cpanel.pan.com.pt-inf-20250324-161814-d81ez.json	245	download job
cpcalendars.pan.com.pt-inf-20250324-161816-22lbg-00000.warc.gz	6429	download job
cpcalendars.pan.com.pt-inf-20250324-161816-22lbg-00000.warc.os.cdx.gz	274	download
cpcalendars.pan.com.pt-inf-20250324-161816-22lbg-meta.warc.gz	3554	download job
cpcalendars.pan.com.pt-inf-20250324-161816-22lbg-meta.warc.os.cdx.gz	47	download
cpcalendars.pan.com.pt-inf-20250324-161816-22lbg.json	250	download job
cpcontacts.pan.com.pt-inf-20250324-161840-96864-00000.warc.gz	6421	download job
cpcontacts.pan.com.pt-inf-20250324-161840-96864-00000.warc.os.cdx.gz	269	download
cpcontacts.pan.com.pt-inf-20250324-161840-96864-meta.warc.gz	3552	download job
cpcontacts.pan.com.pt-inf-20250324-161840-96864-meta.warc.os.cdx.gz	47	download
cpcontacts.pan.com.pt-inf-20250324-161840-96864.json	249	download job
diversityarts.stanford.edu-inf-20250324-161222-9shpp-00000.warc.gz	309523491	download job
diversityarts.stanford.edu-inf-20250324-161222-9shpp-00000.warc.os.cdx.gz	261784	download
diversityarts.stanford.edu-inf-20250324-161222-9shpp-meta.warc.gz	249466	download job
diversityarts.stanford.edu-inf-20250324-161222-9shpp-meta.warc.os.cdx.gz	47	download
diversityarts.stanford.edu-inf-20250324-161222-9shpp.json	254	download job
envolve-te.pan.com.pt-inf-20250324-161841-djg6q-00000.warc.gz	24353	download job
envolve-te.pan.com.pt-inf-20250324-161841-djg6q-00000.warc.os.cdx.gz	602	download
envolve-te.pan.com.pt-inf-20250324-161841-djg6q-meta.warc.gz	3783	download job
envolve-te.pan.com.pt-inf-20250324-161841-djg6q-meta.warc.os.cdx.gz	47	download
envolve-te.pan.com.pt-inf-20250324-161841-djg6q.json	249	download job
foxsearchlightpictures.tumblr.com-inf-20250311-214238-9dlap-00370.warc.gz	5404714854	download job
foxsearchlightpictures.tumblr.com-inf-20250311-214238-9dlap-00370.warc.os.cdx.gz	405358	download
fragdenstaat.de-inf-20250215-082121-boxqa-00480.warc.gz	5369199742	download job
fragdenstaat.de-inf-20250215-082121-boxqa-00480.warc.os.cdx.gz	1667120	download
gml.noaa.gov-inf-20250314-174302-2v6lt-00610.warc.gz	5380840253	download job
gml.noaa.gov-inf-20250314-174302-2v6lt-00610.warc.os.cdx.gz	6585	download
gml.noaa.gov-inf-20250314-174302-2v6lt-00611.warc.gz	5418855359	download job
gml.noaa.gov-inf-20250314-174302-2v6lt-00611.warc.os.cdx.gz	6013	download
guarda.pan.com.pt-inf-20250324-162032-7cw1r-00000.warc.gz	24161	download job
guarda.pan.com.pt-inf-20250324-162032-7cw1r-00000.warc.os.cdx.gz	599	download
guarda.pan.com.pt-inf-20250324-162032-7cw1r-meta.warc.gz	3772	download job
guarda.pan.com.pt-inf-20250324-162032-7cw1r-meta.warc.os.cdx.gz	47	download
guarda.pan.com.pt-inf-20250324-162032-7cw1r.json	245	download job
hometechnology.aspensound.com-inf-20250324-161614-9xkc6-00000.warc.gz	27925775	download job
hometechnology.aspensound.com-inf-20250324-161614-9xkc6-00000.warc.os.cdx.gz	62426	download
hometechnology.aspensound.com-inf-20250324-161614-9xkc6-meta.warc.gz	40772	download job
hometechnology.aspensound.com-inf-20250324-161614-9xkc6-meta.warc.os.cdx.gz	47	download
hometechnology.aspensound.com-inf-20250324-161614-9xkc6.json	254	download job
ipsw.me-inf-20241201-145231-9lrev-06069.warc.gz	5942392033	download job
ipsw.me-inf-20241201-145231-9lrev-06069.warc.os.cdx.gz	993	download
ipsw.me-inf-20241201-145231-9lrev-06070.warc.gz	5545784752	download job
ipsw.me-inf-20241201-145231-9lrev-06070.warc.os.cdx.gz	869	download
irc.digitaldragon.dev-shallow-20250324-163425-a35fv-00000.warc.gz	44684	download job
irc.digitaldragon.dev-shallow-20250324-163425-a35fv-00000.warc.os.cdx.gz	248	download
irc.digitaldragon.dev-shallow-20250324-163425-a35fv-meta.warc.gz	3529	download job
irc.digitaldragon.dev-shallow-20250324-163425-a35fv-meta.warc.os.cdx.gz	47	download
irc.digitaldragon.dev-shallow-20250324-163425-a35fv.json	284	download job
joomla25.pan.com.pt-inf-20250324-162102-dfz5q-00000.warc.gz	24281	download job
joomla25.pan.com.pt-inf-20250324-162102-dfz5q-00000.warc.os.cdx.gz	594	download
joomla25.pan.com.pt-inf-20250324-162102-dfz5q-meta.warc.gz	3778	download job
joomla25.pan.com.pt-inf-20250324-162102-dfz5q-meta.warc.os.cdx.gz	47	download
joomla25.pan.com.pt-inf-20250324-162102-dfz5q.json	247	download job
joomla3.pan.com.pt-inf-20250324-162105-diol9-00000.warc.gz	24207	download job
joomla3.pan.com.pt-inf-20250324-162105-diol9-00000.warc.os.cdx.gz	600	download
joomla3.pan.com.pt-inf-20250324-162105-diol9-meta.warc.gz	3788	download job
joomla3.pan.com.pt-inf-20250324-162105-diol9-meta.warc.os.cdx.gz	47	download
joomla3.pan.com.pt-inf-20250324-162105-diol9.json	246	download job
kuppelkucker.de-inf-20250324-161718-764tl-00000.warc.gz	39029580	download job
kuppelkucker.de-inf-20250324-161718-764tl-00000.warc.os.cdx.gz	14234	download
kuppelkucker.de-inf-20250324-161718-764tl-meta.warc.gz	11442	download job
kuppelkucker.de-inf-20250324-161718-764tl-meta.warc.os.cdx.gz	47	download
kuppelkucker.de-inf-20250324-161718-764tl.json	243	download job
legislativas2015.pan.com.pt-inf-20250324-162141-8gkoy-00000.warc.gz	24755	download job
legislativas2015.pan.com.pt-inf-20250324-162141-8gkoy-00000.warc.os.cdx.gz	613	download
legislativas2015.pan.com.pt-inf-20250324-162141-8gkoy-meta.warc.gz	3807	download job
legislativas2015.pan.com.pt-inf-20250324-162141-8gkoy-meta.warc.os.cdx.gz	47	download
legislativas2015.pan.com.pt-inf-20250324-162141-8gkoy.json	255	download job
legislativas2024.pan.com.pt-inf-20250324-162216-d4kt2-00000.warc.gz	24751	download job
legislativas2024.pan.com.pt-inf-20250324-162216-d4kt2-00000.warc.os.cdx.gz	609	download
legislativas2024.pan.com.pt-inf-20250324-162216-d4kt2-meta.warc.gz	3806	download job
legislativas2024.pan.com.pt-inf-20250324-162216-d4kt2-meta.warc.os.cdx.gz	47	download
legislativas2024.pan.com.pt-inf-20250324-162216-d4kt2.json	255	download job
libertaroeiras.pan.com.pt-inf-20250324-162219-don0p-00000.warc.gz	24590	download job
libertaroeiras.pan.com.pt-inf-20250324-162219-don0p-00000.warc.os.cdx.gz	616	download
libertaroeiras.pan.com.pt-inf-20250324-162219-don0p-meta.warc.gz	3810	download job
libertaroeiras.pan.com.pt-inf-20250324-162219-don0p-meta.warc.os.cdx.gz	47	download
libertaroeiras.pan.com.pt-inf-20250324-162219-don0p.json	253	download job
liquidadvertising.com-inf-20250324-074009-ei446-00001.warc.gz	1481074605	download job
liquidadvertising.com-inf-20250324-074009-ei446-00001.warc.os.cdx.gz	1710082	download
liquidadvertising.com-inf-20250324-074009-ei446-meta.warc.gz	2624996	download job
liquidadvertising.com-inf-20250324-074009-ei446-meta.warc.os.cdx.gz	47	download
liquidadvertising.com-inf-20250324-074009-ei446.json	246	download job
lisboa.pan.com.pt-inf-20250324-162252-dzo7l-00000.warc.gz	24159	download job
lisboa.pan.com.pt-inf-20250324-162252-dzo7l-00000.warc.os.cdx.gz	600	download
lisboa.pan.com.pt-inf-20250324-162252-dzo7l-meta.warc.gz	3772	download job
lisboa.pan.com.pt-inf-20250324-162252-dzo7l-meta.warc.os.cdx.gz	47	download
lisboa.pan.com.pt-inf-20250324-162252-dzo7l.json	245	download job
maia.pan.com.pt-inf-20250324-162329-5j0pw-00000.warc.gz	24031	download job
maia.pan.com.pt-inf-20250324-162329-5j0pw-00000.warc.os.cdx.gz	589	download
maia.pan.com.pt-inf-20250324-162329-5j0pw-meta.warc.gz	3765	download job
maia.pan.com.pt-inf-20250324-162329-5j0pw-meta.warc.os.cdx.gz	47	download
maia.pan.com.pt-inf-20250324-162329-5j0pw.json	243	download job
mail.pan.com.pt-shallow-20250324-162144-3y5eh-00000.warc.gz	17018492	download job
mail.pan.com.pt-shallow-20250324-162144-3y5eh-00000.warc.os.cdx.gz	12435	download
mail.pan.com.pt-shallow-20250324-162144-3y5eh-meta.warc.gz	10496	download job
mail.pan.com.pt-shallow-20250324-162144-3y5eh-meta.warc.os.cdx.gz	47	download
mail.pan.com.pt-shallow-20250324-162144-3y5eh.json	247	download job
mail.web.pan.com.pt-shallow-20250324-162206-6keyh-00000.warc.gz	17022944	download job
mail.web.pan.com.pt-shallow-20250324-162206-6keyh-00000.warc.os.cdx.gz	12428	download
mail.web.pan.com.pt-shallow-20250324-162206-6keyh-meta.warc.gz	10478	download job
mail.web.pan.com.pt-shallow-20250324-162206-6keyh-meta.warc.os.cdx.gz	47	download
mail.web.pan.com.pt-shallow-20250324-162206-6keyh.json	251	download job
moita.pan.com.pt-inf-20250324-162333-50fwd-00000.warc.gz	24110	download job
moita.pan.com.pt-inf-20250324-162333-50fwd-00000.warc.os.cdx.gz	593	download
moita.pan.com.pt-inf-20250324-162333-50fwd-meta.warc.gz	3762	download job
moita.pan.com.pt-inf-20250324-162333-50fwd-meta.warc.os.cdx.gz	47	download
moita.pan.com.pt-inf-20250324-162333-50fwd.json	244	download job
no.pan.com.pt-inf-20250324-162404-2rphv-00000.warc.gz	23942	download job
no.pan.com.pt-inf-20250324-162404-2rphv-00000.warc.os.cdx.gz	588	download
no.pan.com.pt-inf-20250324-162404-2rphv-meta.warc.gz	3764	download job
no.pan.com.pt-inf-20250324-162404-2rphv-meta.warc.os.cdx.gz	47	download
no.pan.com.pt-inf-20250324-162404-2rphv.json	241	download job
nonocongresso.pan.com.pt-inf-20250324-162443-5kg61-00000.warc.gz	24507	download job
nonocongresso.pan.com.pt-inf-20250324-162443-5kg61-00000.warc.os.cdx.gz	608	download
nonocongresso.pan.com.pt-inf-20250324-162443-5kg61-meta.warc.gz	3793	download job
nonocongresso.pan.com.pt-inf-20250324-162443-5kg61-meta.warc.os.cdx.gz	47	download
nonocongresso.pan.com.pt-inf-20250324-162443-5kg61.json	252	download job
novojoomla.pan.com.pt-inf-20250324-162448-1ogt3-00000.warc.gz	24431	download job
novojoomla.pan.com.pt-inf-20250324-162448-1ogt3-00000.warc.os.cdx.gz	611	download
novojoomla.pan.com.pt-inf-20250324-162448-1ogt3-meta.warc.gz	3778	download job
novojoomla.pan.com.pt-inf-20250324-162448-1ogt3-meta.warc.os.cdx.gz	47	download
novojoomla.pan.com.pt-inf-20250324-162448-1ogt3.json	249	download job
novojoomla2.pan.com.pt-inf-20250324-162515-e7cis-00000.warc.gz	24494	download job
novojoomla2.pan.com.pt-inf-20250324-162515-e7cis-00000.warc.os.cdx.gz	605	download
novojoomla2.pan.com.pt-inf-20250324-162515-e7cis-meta.warc.gz	3794	download job
novojoomla2.pan.com.pt-inf-20250324-162515-e7cis-meta.warc.os.cdx.gz	47	download
novojoomla2.pan.com.pt-inf-20250324-162515-e7cis.json	250	download job
pangeia-api.pan.com.pt-inf-20250324-162557-7lapy-00000.warc.gz	24370	download job
pangeia-api.pan.com.pt-inf-20250324-162557-7lapy-00000.warc.os.cdx.gz	604	download
pangeia-api.pan.com.pt-inf-20250324-162557-7lapy-meta.warc.gz	3799	download job
pangeia-api.pan.com.pt-inf-20250324-162557-7lapy-meta.warc.os.cdx.gz	47	download
pangeia-api.pan.com.pt-inf-20250324-162557-7lapy.json	250	download job
partidotrabalhista.com-inf-20250324-162849-ddf1a-00000.warc.gz	2424822	download job
partidotrabalhista.com-inf-20250324-162849-ddf1a-00000.warc.os.cdx.gz	7490	download
partidotrabalhista.com-inf-20250324-162849-ddf1a-meta.warc.gz	8090	download job
partidotrabalhista.com-inf-20250324-162849-ddf1a-meta.warc.os.cdx.gz	47	download
partidotrabalhista.com-inf-20250324-162849-ddf1a.json	249	download job
rede.pan.com.pt-inf-20250324-163223-d22ls-00000.warc.gz	24061	download job
rede.pan.com.pt-inf-20250324-163223-d22ls-00000.warc.os.cdx.gz	597	download
rede.pan.com.pt-inf-20250324-163223-d22ls-meta.warc.gz	3760	download job
rede.pan.com.pt-inf-20250324-163223-d22ls-meta.warc.os.cdx.gz	47	download
rede.pan.com.pt-inf-20250324-163223-d22ls.json	243	download job
routakoto.com-inf-20250324-131347-ajfd3-00000.warc.gz	3437520641	download job
routakoto.com-inf-20250324-131347-ajfd3-00000.warc.os.cdx.gz	2905239	download
routakoto.com-inf-20250324-131347-ajfd3-meta.warc.gz	1874356	download job
routakoto.com-inf-20250324-131347-ajfd3-meta.warc.os.cdx.gz	47	download
routakoto.com-inf-20250324-131347-ajfd3.json	246	download job
sesimbra.pan.com.pt-inf-20250324-163233-b0pd5-00000.warc.gz	24263	download job
sesimbra.pan.com.pt-inf-20250324-163233-b0pd5-00000.warc.os.cdx.gz	604	download
sesimbra.pan.com.pt-inf-20250324-163233-b0pd5-meta.warc.gz	3775	download job
sesimbra.pan.com.pt-inf-20250324-163233-b0pd5-meta.warc.os.cdx.gz	47	download
sesimbra.pan.com.pt-inf-20250324-163233-b0pd5.json	247	download job
setubal.pan.com.pt-inf-20250324-163250-234wx-00000.warc.gz	24233	download job
setubal.pan.com.pt-inf-20250324-163250-234wx-00000.warc.os.cdx.gz	590	download
setubal.pan.com.pt-inf-20250324-163250-234wx-meta.warc.gz	3763	download job
setubal.pan.com.pt-inf-20250324-163250-234wx-meta.warc.os.cdx.gz	47	download
setubal.pan.com.pt-inf-20250324-163250-234wx.json	246	download job
soporte.astoreca.cl-inf-20250324-163603-dohan-00000.warc.gz	10888	download job
soporte.astoreca.cl-inf-20250324-163603-dohan-00000.warc.os.cdx.gz	290	download
soporte.astoreca.cl-inf-20250324-163603-dohan-meta.warc.gz	3608	download job
soporte.astoreca.cl-inf-20250324-163603-dohan-meta.warc.os.cdx.gz	47	download
soporte.astoreca.cl-inf-20250324-163603-dohan-wpull.log.gz	926	download
soporte.astoreca.cl-inf-20250324-163603-dohan.json	244	download job
tienda.astoreca.cl-inf-20250324-163112-8cjwl-00000.warc.gz	6204531	download job
tienda.astoreca.cl-inf-20250324-163112-8cjwl-00000.warc.os.cdx.gz	10319	download
tienda.astoreca.cl-inf-20250324-163112-8cjwl-meta.warc.gz	10784	download job
tienda.astoreca.cl-inf-20250324-163112-8cjwl-meta.warc.os.cdx.gz	47	download
tienda.astoreca.cl-inf-20250324-163112-8cjwl.json	243	download job
urls-transfer.archivete.am-www.sjm.pcp.pt.txt-inf-20250324-161127-7z9cy-00000.warc.gz	274893894	download job
urls-transfer.archivete.am-www.sjm.pcp.pt.txt-inf-20250324-161127-7z9cy-00000.warc.os.cdx.gz	320092	download
urls-transfer.archivete.am-www.sjm.pcp.pt.txt-inf-20250324-161127-7z9cy-meta.warc.gz	206551	download job
urls-transfer.archivete.am-www.sjm.pcp.pt.txt-inf-20250324-161127-7z9cy-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-www.sjm.pcp.pt.txt-inf-20250324-161127-7z9cy-urls.txt	44	download
urls-transfer.archivete.am-www.sjm.pcp.pt.txt-inf-20250324-161127-7z9cy.json	327	download job
warm1069.com-inf-20250319-191001-c6rpx-00098.warc.gz	5368845606	download job
warm1069.com-inf-20250319-191001-c6rpx-00098.warc.os.cdx.gz	4733904	download
web.pan.com.pt-shallow-20250324-163214-5dub3-00000.warc.gz	17019566	download job
web.pan.com.pt-shallow-20250324-163214-5dub3-00000.warc.os.cdx.gz	12411	download
web.pan.com.pt-shallow-20250324-163214-5dub3-meta.warc.gz	10493	download job
web.pan.com.pt-shallow-20250324-163214-5dub3-meta.warc.os.cdx.gz	47	download
web.pan.com.pt-shallow-20250324-163214-5dub3.json	246	download job
webdisk.pan.com.pt-inf-20250324-163340-6a13c-00000.warc.gz	6394	download job
webdisk.pan.com.pt-inf-20250324-163340-6a13c-00000.warc.os.cdx.gz	270	download
webdisk.pan.com.pt-inf-20250324-163340-6a13c-meta.warc.gz	3545	download job
webdisk.pan.com.pt-inf-20250324-163340-6a13c-meta.warc.os.cdx.gz	47	download
webdisk.pan.com.pt-inf-20250324-163340-6a13c.json	246	download job
webmail.pan.com.pt-inf-20250324-163356-4nee2-00000.warc.gz	4292240	download job
webmail.pan.com.pt-inf-20250324-163356-4nee2-00000.warc.os.cdx.gz	10557	download
webmail.pan.com.pt-inf-20250324-163356-4nee2-meta.warc.gz	8493	download job
webmail.pan.com.pt-inf-20250324-163356-4nee2-meta.warc.os.cdx.gz	47	download
webmail.pan.com.pt-inf-20250324-163356-4nee2.json	246	download job
whm.pan.com.pt-inf-20250324-163416-1xtf4-00000.warc.gz	11117409	download job
whm.pan.com.pt-inf-20250324-163416-1xtf4-00000.warc.os.cdx.gz	31908	download
whm.pan.com.pt-inf-20250324-163416-1xtf4-meta.warc.gz	17273	download job
whm.pan.com.pt-inf-20250324-163416-1xtf4-meta.warc.os.cdx.gz	47	download
whm.pan.com.pt-inf-20250324-163416-1xtf4.json	242	download job
wiki.pan.com.pt-inf-20250324-163452-4nnb5-00000.warc.gz	24045	download job
wiki.pan.com.pt-inf-20250324-163452-4nnb5-00000.warc.os.cdx.gz	589	download
wiki.pan.com.pt-inf-20250324-163452-4nnb5-meta.warc.gz	3764	download job
wiki.pan.com.pt-inf-20250324-163452-4nnb5-meta.warc.os.cdx.gz	47	download
wiki.pan.com.pt-inf-20250324-163452-4nnb5.json	243	download job
www.2semcarne.pan.com.pt-inf-20250324-163453-f36x1-00000.warc.gz	24585	download job
www.2semcarne.pan.com.pt-inf-20250324-163453-f36x1-00000.warc.os.cdx.gz	611	download
www.2semcarne.pan.com.pt-inf-20250324-163453-f36x1-meta.warc.gz	3799	download job
www.2semcarne.pan.com.pt-inf-20250324-163453-f36x1-meta.warc.os.cdx.gz	47	download
www.2semcarne.pan.com.pt-inf-20250324-163453-f36x1.json	252	download job
www.almada-seixal.pan.com.pt-inf-20250324-163514-cinxh-00000.warc.gz	16286	download job
www.almada-seixal.pan.com.pt-inf-20250324-163514-cinxh-00000.warc.os.cdx.gz	340	download
www.almada-seixal.pan.com.pt-inf-20250324-163514-cinxh-meta.warc.gz	3671	download job
www.almada-seixal.pan.com.pt-inf-20250324-163514-cinxh-meta.warc.os.cdx.gz	47	download
www.almada-seixal.pan.com.pt-inf-20250324-163514-cinxh.json	256	download job
www.almada.pan.com.pt-inf-20250324-163536-7xgkc-00000.warc.gz	24389	download job
www.almada.pan.com.pt-inf-20250324-163536-7xgkc-00000.warc.os.cdx.gz	605	download
www.almada.pan.com.pt-inf-20250324-163536-7xgkc-meta.warc.gz	3786	download job
www.almada.pan.com.pt-inf-20250324-163536-7xgkc-meta.warc.os.cdx.gz	47	download
www.almada.pan.com.pt-inf-20250324-163536-7xgkc.json	249	download job
www.aspensound.com-inf-20250324-161314-azv0w-00000.warc.gz	175247491	download job
www.aspensound.com-inf-20250324-161314-azv0w-00000.warc.os.cdx.gz	382134	download
www.aspensound.com-inf-20250324-161314-azv0w-meta.warc.gz	284083	download job
www.aspensound.com-inf-20250324-161314-azv0w-meta.warc.os.cdx.gz	47	download
www.aspensound.com-inf-20250324-161314-azv0w.json	243	download job
www.coimbra.pan.com.pt-inf-20250324-163555-c144e-00000.warc.gz	24452	download job
www.coimbra.pan.com.pt-inf-20250324-163555-c144e-00000.warc.os.cdx.gz	610	download
www.coimbra.pan.com.pt-inf-20250324-163555-c144e-meta.warc.gz	3788	download job
www.coimbra.pan.com.pt-inf-20250324-163555-c144e-meta.warc.os.cdx.gz	47	download
www.coimbra.pan.com.pt-inf-20250324-163555-c144e.json	250	download job
www.envolve-te.pan.com.pt-inf-20250324-163614-96ifp-00000.warc.gz	24611	download job
www.envolve-te.pan.com.pt-inf-20250324-163614-96ifp-00000.warc.os.cdx.gz	603	download
www.envolve-te.pan.com.pt-inf-20250324-163614-96ifp-meta.warc.gz	3805	download job
www.envolve-te.pan.com.pt-inf-20250324-163614-96ifp-meta.warc.os.cdx.gz	47	download
www.envolve-te.pan.com.pt-inf-20250324-163614-96ifp.json	253	download job
www.filiacao.pan.com.pt-shallow-20250324-163636-6z0o8-00000.warc.gz	17959522	download job
www.filiacao.pan.com.pt-shallow-20250324-163636-6z0o8-00000.warc.os.cdx.gz	12493	download
www.filiacao.pan.com.pt-shallow-20250324-163636-6z0o8-meta.warc.gz	10790	download job
www.filiacao.pan.com.pt-shallow-20250324-163636-6z0o8-meta.warc.os.cdx.gz	47	download
www.filiacao.pan.com.pt-shallow-20250324-163636-6z0o8.json	255	download job
www.guarda.pan.com.pt-inf-20250324-163829-8bko4-00000.warc.gz	24428	download job
www.guarda.pan.com.pt-inf-20250324-163829-8bko4-00000.warc.os.cdx.gz	609	download
www.guarda.pan.com.pt-inf-20250324-163829-8bko4-meta.warc.gz	3802	download job
www.guarda.pan.com.pt-inf-20250324-163829-8bko4-meta.warc.os.cdx.gz	47	download
www.guarda.pan.com.pt-inf-20250324-163829-8bko4.json	249	download job
www.joomla25.pan.com.pt-inf-20250324-163933-bmcoc-00000.warc.gz	24493	download job
www.joomla25.pan.com.pt-inf-20250324-163933-bmcoc-00000.warc.os.cdx.gz	613	download
www.joomla25.pan.com.pt-inf-20250324-163933-bmcoc-meta.warc.gz	3801	download job
www.joomla25.pan.com.pt-inf-20250324-163933-bmcoc-meta.warc.os.cdx.gz	47	download
www.joomla25.pan.com.pt-inf-20250324-163933-bmcoc.json	251	download job
www.joomla3.pan.com.pt-inf-20250324-163946-9cqy9-00000.warc.gz	24515	download job
www.joomla3.pan.com.pt-inf-20250324-163946-9cqy9-00000.warc.os.cdx.gz	606	download
www.joomla3.pan.com.pt-inf-20250324-163946-9cqy9-meta.warc.gz	3795	download job
www.joomla3.pan.com.pt-inf-20250324-163946-9cqy9-meta.warc.os.cdx.gz	47	download
www.joomla3.pan.com.pt-inf-20250324-163946-9cqy9.json	250	download job
www.legislativas2015.pan.com.pt-inf-20250324-164052-321a1-00000.warc.gz	24979	download job
www.legislativas2015.pan.com.pt-inf-20250324-164052-321a1-00000.warc.os.cdx.gz	613	download
www.legislativas2015.pan.com.pt-inf-20250324-164052-321a1-meta.warc.gz	3822	download job
www.legislativas2015.pan.com.pt-inf-20250324-164052-321a1-meta.warc.os.cdx.gz	47	download
www.legislativas2015.pan.com.pt-inf-20250324-164052-321a1.json	259	download job
www.legislativas2024.pan.com.pt-inf-20250324-164104-a04qv-00000.warc.gz	24953	download job
www.legislativas2024.pan.com.pt-inf-20250324-164104-a04qv-00000.warc.os.cdx.gz	617	download
www.legislativas2024.pan.com.pt-inf-20250324-164104-a04qv-meta.warc.gz	3821	download job
www.legislativas2024.pan.com.pt-inf-20250324-164104-a04qv-meta.warc.os.cdx.gz	47	download
www.legislativas2024.pan.com.pt-inf-20250324-164104-a04qv.json	259	download job
www.libertaroeiras.pan.com.pt-inf-20250324-164214-2p2a1-00000.warc.gz	24826	download job
www.libertaroeiras.pan.com.pt-inf-20250324-164214-2p2a1-00000.warc.os.cdx.gz	608	download
www.libertaroeiras.pan.com.pt-inf-20250324-164214-2p2a1-meta.warc.gz	3796	download job
www.libertaroeiras.pan.com.pt-inf-20250324-164214-2p2a1-meta.warc.os.cdx.gz	47	download
www.libertaroeiras.pan.com.pt-inf-20250324-164214-2p2a1.json	257	download job
www.lisboa.pan.com.pt-inf-20250324-164222-2n7n3-00000.warc.gz	24424	download job
www.lisboa.pan.com.pt-inf-20250324-164222-2n7n3-00000.warc.os.cdx.gz	606	download
www.lisboa.pan.com.pt-inf-20250324-164222-2n7n3-meta.warc.gz	3791	download job
www.lisboa.pan.com.pt-inf-20250324-164222-2n7n3-meta.warc.os.cdx.gz	47	download
www.lisboa.pan.com.pt-inf-20250324-164222-2n7n3.json	249	download job
www.maia.pan.com.pt-inf-20250324-164336-b84qu-00000.warc.gz	24285	download job
www.maia.pan.com.pt-inf-20250324-164336-b84qu-00000.warc.os.cdx.gz	604	download
www.maia.pan.com.pt-inf-20250324-164336-b84qu-meta.warc.gz	3785	download job
www.maia.pan.com.pt-inf-20250324-164336-b84qu-meta.warc.os.cdx.gz	47	download
www.maia.pan.com.pt-inf-20250324-164336-b84qu.json	247	download job
www.moita.pan.com.pt-inf-20250324-164340-8m5ue-00000.warc.gz	24368	download job
www.moita.pan.com.pt-inf-20250324-164340-8m5ue-00000.warc.os.cdx.gz	599	download
www.moita.pan.com.pt-inf-20250324-164340-8m5ue-meta.warc.gz	3790	download job
www.moita.pan.com.pt-inf-20250324-164340-8m5ue-meta.warc.os.cdx.gz	47	download
www.moita.pan.com.pt-inf-20250324-164340-8m5ue.json	248	download job
www.mpt.pt-inf-20250324-163001-bmql2-00000.warc.gz	6362387	download job
www.mpt.pt-inf-20250324-163001-bmql2-00000.warc.os.cdx.gz	14459	download
www.mpt.pt-inf-20250324-163001-bmql2-meta.warc.gz	11991	download job
www.mpt.pt-inf-20250324-163001-bmql2-meta.warc.os.cdx.gz	47	download
www.mpt.pt-inf-20250324-163001-bmql2.json	238	download job
www.newyorkalmanack.com-inf-20250322-075213-cee6l-00019.warc.gz	5420894882	download job
www.newyorkalmanack.com-inf-20250322-075213-cee6l-00019.warc.os.cdx.gz	1696812	download
www.pangeia.pan.com.pt-inf-20250324-162603-5i2v6-00000.warc.gz	57855522	download job
www.pangeia.pan.com.pt-inf-20250324-162603-5i2v6-00000.warc.os.cdx.gz	120251	download
www.pangeia.pan.com.pt-inf-20250324-162603-5i2v6-meta.warc.gz	70648	download job
www.pangeia.pan.com.pt-inf-20250324-162603-5i2v6-meta.warc.os.cdx.gz	47	download
www.pangeia.pan.com.pt-inf-20250324-162603-5i2v6.json	250	download job
www.partidolivre.pt-inf-20250324-162626-3feow-00000.warc.gz	9575975	download job
www.partidolivre.pt-inf-20250324-162626-3feow-00000.warc.os.cdx.gz	26179	download
www.partidolivre.pt-inf-20250324-162626-3feow-meta.warc.gz	18546	download job
www.partidolivre.pt-inf-20250324-162626-3feow-meta.warc.os.cdx.gz	47	download
www.partidolivre.pt-inf-20250324-162626-3feow.json	247	download job
www.partidotrabalhista.com-inf-20250324-162737-c53d8-00000.warc.gz	2452845	download job
www.partidotrabalhista.com-inf-20250324-162737-c53d8-00000.warc.os.cdx.gz	7548	download
www.partidotrabalhista.com-inf-20250324-162737-c53d8-meta.warc.gz	8201	download job
www.partidotrabalhista.com-inf-20250324-162737-c53d8-meta.warc.os.cdx.gz	47	download
www.partidotrabalhista.com-inf-20250324-162737-c53d8.json	253	download job
www.patersonnj.gov-inf-20250324-131522-6dnkp-00000.warc.gz	5645016564	download job
www.patersonnj.gov-inf-20250324-131522-6dnkp-00000.warc.os.cdx.gz	1784618	download
www.sciencebase.gov-inf-20250204-024621-3gyep-01317.warc.gz	5376241619	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-01317.warc.os.cdx.gz	69507	download
www.sciencebase.gov-inf-20250204-024621-3gyep-01318.warc.gz	5486073244	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-01318.warc.os.cdx.gz	69151	download
www.sciencebase.gov-inf-20250204-024621-3gyep-01319.warc.gz	5515502468	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-01319.warc.os.cdx.gz	93493	download
www.voaafrica.com-inf-20250318-081912-1fye9-00853.warc.gz	5523512718	download job
www.voaafrica.com-inf-20250318-081912-1fye9-00853.warc.os.cdx.gz	11283	download
www.voaafrica.com-inf-20250318-081912-1fye9-00854.warc.gz	5456257418	download job
www.voaafrica.com-inf-20250318-081912-1fye9-00854.warc.os.cdx.gz	8349	download
www.voaafrica.com-inf-20250318-081912-1fye9-00855.warc.gz	5777287261	download job
www.voaafrica.com-inf-20250318-081912-1fye9-00855.warc.os.cdx.gz	8939	download
www.voadeewanews.com-inf-20250318-081603-6w6oc-00451.warc.gz	5371466391	download job
www.voadeewanews.com-inf-20250318-081603-6w6oc-00451.warc.os.cdx.gz	44101	download
www.voadeewanews.com-inf-20250318-081603-6w6oc-00452.warc.gz	5390473355	download job
www.voadeewanews.com-inf-20250318-081603-6w6oc-00452.warc.os.cdx.gz	48847	download
www.web.pan.com.pt-shallow-20250324-164231-cjmqf-00000.warc.gz	17030482	download job
www.web.pan.com.pt-shallow-20250324-164231-cjmqf-00000.warc.os.cdx.gz	12372	download
www.web.pan.com.pt-shallow-20250324-164231-cjmqf-meta.warc.gz	10555	download job
www.web.pan.com.pt-shallow-20250324-164231-cjmqf-meta.warc.os.cdx.gz	47	download
www.web.pan.com.pt-shallow-20250324-164231-cjmqf.json	250	download job
x0.at-shallow-20250324-162816-dewkp-00000.warc.gz	136024	download job
x0.at-shallow-20250324-162816-dewkp-00000.warc.os.cdx.gz	216	download
x0.at-shallow-20250324-162816-dewkp-meta.warc.gz	3428	download job
x0.at-shallow-20250324-162816-dewkp-meta.warc.os.cdx.gz	47	download
x0.at-shallow-20250324-162816-dewkp.json	242	download job