Item archiveteam_archivebot_go_20260625170819_9546d713

View on Internet Archive

Filename	Size
archiveteam_archivebot_go_20260625170819_9546d713.cdx.gz	50934446	download
archiveteam_archivebot_go_20260625170819_9546d713.cdx.idx	66398	download
archiveteam_archivebot_go_20260625170819_9546d713_files.xml	0	download
archiveteam_archivebot_go_20260625170819_9546d713_meta.sqlite	364544	download
archiveteam_archivebot_go_20260625170819_9546d713_meta.xml	1048	download
blog.setupad.com-inf-20260625-163834-1wqwz-00000.warc.gz	3266404	download   job
blog.setupad.com-inf-20260625-163834-1wqwz-00000.warc.os.cdx.gz	6439	download
blog.setupad.com-inf-20260625-163834-1wqwz-meta.warc.gz	7432	download   job
blog.setupad.com-inf-20260625-163834-1wqwz-meta.warc.os.cdx.gz	47	download
blog.setupad.com-inf-20260625-163834-1wqwz.json	241	download   job
chocolateclass.wordpress.com-inf-20260624-160120-18wn5-00002.warc.gz	5687685390	download   job
chocolateclass.wordpress.com-inf-20260624-160120-18wn5-00002.warc.os.cdx.gz	1613718	download
cloud.die-partei-wow.de-inf-20260625-165435-dbone-00000.warc.gz	12090	download   job
cloud.die-partei-wow.de-inf-20260625-165435-dbone-00000.warc.os.cdx.gz	348	download
cloud.die-partei-wow.de-inf-20260625-165435-dbone-meta.warc.gz	3646	download   job
cloud.die-partei-wow.de-inf-20260625-165435-dbone-meta.warc.os.cdx.gz	47	download
cloud.die-partei-wow.de-inf-20260625-165435-dbone.json	251	download   job
die-partei-hsk.de-inf-20260625-164909-67fti-00000.warc.gz	9886059	download   job
die-partei-hsk.de-inf-20260625-164909-67fti-00000.warc.os.cdx.gz	20875	download
die-partei-hsk.de-inf-20260625-164909-67fti-meta.warc.gz	15687	download   job
die-partei-hsk.de-inf-20260625-164909-67fti-meta.warc.os.cdx.gz	47	download
die-partei-hsk.de-inf-20260625-164909-67fti.json	245	download   job
die-partei-leverkusen.de-inf-20260625-164935-3e43g-00000.warc.gz	2482	download   job
die-partei-leverkusen.de-inf-20260625-164935-3e43g-00000.warc.os.cdx.gz	47	download
die-partei-leverkusen.de-inf-20260625-164935-3e43g-meta.warc.gz	3505	download   job
die-partei-leverkusen.de-inf-20260625-164935-3e43g-meta.warc.os.cdx.gz	47	download
die-partei-leverkusen.de-inf-20260625-164935-3e43g.json	252	download   job
die-partei-recklinghausen.de-inf-20260625-165354-1kuve-00000.warc.gz	285046	download   job
die-partei-recklinghausen.de-inf-20260625-165354-1kuve-00000.warc.os.cdx.gz	2108	download
die-partei-recklinghausen.de-inf-20260625-165354-1kuve-meta.warc.gz	4779	download   job
die-partei-recklinghausen.de-inf-20260625-165354-1kuve-meta.warc.os.cdx.gz	47	download
die-partei-recklinghausen.de-inf-20260625-165354-1kuve.json	256	download   job
die-partei-rk-neuss.de-inf-20260625-165421-1dc2e-00000.warc.gz	12887	download   job
die-partei-rk-neuss.de-inf-20260625-165421-1dc2e-00000.warc.os.cdx.gz	341	download
die-partei-rk-neuss.de-inf-20260625-165421-1dc2e-meta.warc.gz	3634	download   job
die-partei-rk-neuss.de-inf-20260625-165421-1dc2e-meta.warc.os.cdx.gz	47	download
die-partei-rk-neuss.de-inf-20260625-165421-1dc2e.json	250	download   job
die-partei-witten.de-inf-20260625-170440-5r238-00000.warc.gz	2473	download   job
die-partei-witten.de-inf-20260625-170440-5r238-00000.warc.os.cdx.gz	47	download
die-partei-witten.de-inf-20260625-170440-5r238-meta.warc.gz	3476	download   job
die-partei-witten.de-inf-20260625-170440-5r238-meta.warc.os.cdx.gz	47	download
die-partei-witten.de-inf-20260625-170440-5r238.json	248	download   job
die-partei-wuppertal.org-inf-20260625-165446-4r9an-00000.warc.gz	2482	download   job
die-partei-wuppertal.org-inf-20260625-165446-4r9an-00000.warc.os.cdx.gz	47	download
die-partei-wuppertal.org-inf-20260625-165446-4r9an-meta.warc.gz	3489	download   job
die-partei-wuppertal.org-inf-20260625-165446-4r9an-meta.warc.os.cdx.gz	47	download
die-partei-wuppertal.org-inf-20260625-165446-4r9an.json	252	download   job
die-partei.net-inf-20260625-161838-dr63l-00000.warc.gz	5375798046	download   job
die-partei.net-inf-20260625-161838-dr63l-00000.warc.os.cdx.gz	826081	download
diepartei-rheinberg.de-inf-20260625-170338-1z4et-00000.warc.gz	2479	download   job
diepartei-rheinberg.de-inf-20260625-170338-1z4et-00000.warc.os.cdx.gz	47	download
diepartei-rheinberg.de-inf-20260625-170338-1z4et-meta.warc.gz	3486	download   job
diepartei-rheinberg.de-inf-20260625-170338-1z4et-meta.warc.os.cdx.gz	47	download
diepartei-rheinberg.de-inf-20260625-170338-1z4et.json	250	download   job
discourse.a20xx.com-inf-20260625-170815-bw060-00000.warc.gz	2470	download   job
discourse.a20xx.com-inf-20260625-170815-bw060-00000.warc.os.cdx.gz	47	download
empireonenews.wordpress.com-inf-20260625-080514-cz9lo-00000.warc.gz	3789132299	download   job
empireonenews.wordpress.com-inf-20260625-080514-cz9lo-00000.warc.os.cdx.gz	7259432	download
empireonenews.wordpress.com-inf-20260625-080514-cz9lo-meta.warc.gz	5929351	download   job
empireonenews.wordpress.com-inf-20260625-080514-cz9lo-meta.warc.os.cdx.gz	47	download
empireonenews.wordpress.com-inf-20260625-080514-cz9lo.json	255	download   job
erincpowellcom.wordpress.com-inf-20260625-161608-ejm07-00000.warc.gz	1786250932	download   job
erincpowellcom.wordpress.com-inf-20260625-161608-ejm07-00000.warc.os.cdx.gz	615184	download
erincpowellcom.wordpress.com-inf-20260625-161608-ejm07-meta.warc.gz	399546	download   job
erincpowellcom.wordpress.com-inf-20260625-161608-ejm07-meta.warc.os.cdx.gz	47	download
erincpowellcom.wordpress.com-inf-20260625-161608-ejm07.json	256	download   job
feral-hart.tumblr.com-inf-20260625-165456-2th95-00000.warc.gz	13472	download   job
feral-hart.tumblr.com-inf-20260625-165456-2th95-00000.warc.os.cdx.gz	275	download
feral-hart.tumblr.com-inf-20260625-165456-2th95-meta.warc.gz	3547	download   job
feral-hart.tumblr.com-inf-20260625-165456-2th95-meta.warc.os.cdx.gz	47	download
feral-hart.tumblr.com-inf-20260625-165456-2th95.json	252	download   job
feral-hart.tumblr.com-inf-20260625-165604-2th95-aborted-00000.warc.gz	38369257	download   job
feral-hart.tumblr.com-inf-20260625-165604-2th95-aborted-00000.warc.os.cdx.gz	58635	download
feral-hart.tumblr.com-inf-20260625-165604-2th95-aborted-wpull.log.gz	49935	download
feral-hart.tumblr.com-inf-20260625-165604-2th95-aborted.json	251	download   job
fernexpress.wordpress.com-inf-20260625-130928-bgzox-00001.warc.gz	7051103901	download   job
fernexpress.wordpress.com-inf-20260625-130928-bgzox-00001.warc.os.cdx.gz	1182565	download
font.download-inf-20260617-212517-49jfh-00053.warc.gz	5383947174	download   job
font.download-inf-20260617-212517-49jfh-00053.warc.os.cdx.gz	1462469	download
gam-data-fetcher.setupad.com-inf-20260625-164038-af3m8-00000.warc.gz	30929522	download   job
gam-data-fetcher.setupad.com-inf-20260625-164038-af3m8-00000.warc.os.cdx.gz	65182	download
gam-data-fetcher.setupad.com-inf-20260625-164038-af3m8-meta.warc.gz	51832	download   job
gam-data-fetcher.setupad.com-inf-20260625-164038-af3m8-meta.warc.os.cdx.gz	47	download
gam-data-fetcher.setupad.com-inf-20260625-164038-af3m8.json	253	download   job
help.setupad.com-inf-20260625-164134-75uwg-00000.warc.gz	2659802	download   job
help.setupad.com-inf-20260625-164134-75uwg-00000.warc.os.cdx.gz	6007	download
help.setupad.com-inf-20260625-164134-75uwg-meta.warc.gz	7175	download   job
help.setupad.com-inf-20260625-164134-75uwg-meta.warc.os.cdx.gz	47	download
help.setupad.com-inf-20260625-164134-75uwg.json	241	download   job
hollawhenyougetthis.com-inf-20260625-165708-3sk48-00000.warc.gz	41447206	download   job
hollawhenyougetthis.com-inf-20260625-165708-3sk48-00000.warc.os.cdx.gz	78622	download
hollawhenyougetthis.com-inf-20260625-165708-3sk48-meta.warc.gz	59956	download   job
hollawhenyougetthis.com-inf-20260625-165708-3sk48-meta.warc.os.cdx.gz	47	download
hollawhenyougetthis.com-inf-20260625-165708-3sk48.json	256	download   job
konstantinovka.dn.ua-inf-20260623-111759-6mcgb-00003.warc.gz	3552053066	download   job
konstantinovka.dn.ua-inf-20260623-111759-6mcgb-00003.warc.os.cdx.gz	8473945	download
manuelsimbuerger.wordpress.com-inf-20260625-153049-fmryu-00000.warc.gz	5458812210	download   job
manuelsimbuerger.wordpress.com-inf-20260625-153049-fmryu-00000.warc.os.cdx.gz	1320543	download
matthewbutterick.com-inf-20260625-115917-4a8vt-00002.warc.gz	1386106926	download   job
matthewbutterick.com-inf-20260625-115917-4a8vt-00002.warc.os.cdx.gz	1305695	download
matthewbutterick.com-inf-20260625-115917-4a8vt-meta.warc.gz	2490528	download   job
matthewbutterick.com-inf-20260625-115917-4a8vt-meta.warc.os.cdx.gz	47	download
matthewbutterick.com-inf-20260625-115917-4a8vt.json	248	download   job
muddystiletto.wordpress.com-inf-20260625-130834-3gu2h-00000.warc.gz	5369348133	download   job
muddystiletto.wordpress.com-inf-20260625-130834-3gu2h-00000.warc.os.cdx.gz	3522426	download
offer.setupad.com-inf-20260625-164013-eekoz-00000.warc.gz	7375	download   job
offer.setupad.com-inf-20260625-164013-eekoz-00000.warc.os.cdx.gz	302	download
offer.setupad.com-inf-20260625-164013-eekoz-meta.warc.gz	3555	download   job
offer.setupad.com-inf-20260625-164013-eekoz-meta.warc.os.cdx.gz	47	download
offer.setupad.com-inf-20260625-164013-eekoz.json	242	download   job
partei-ldk.de-inf-20260625-153652-e5ukk-00000.warc.gz	1565934250	download   job
partei-ldk.de-inf-20260625-153652-e5ukk-00000.warc.os.cdx.gz	1104997	download
partei-ldk.de-inf-20260625-153652-e5ukk-meta.warc.gz	734997	download   job
partei-ldk.de-inf-20260625-153652-e5ukk-meta.warc.os.cdx.gz	47	download
partei-ldk.de-inf-20260625-153652-e5ukk.json	241	download   job
policies.paidwork.com-inf-20260625-155322-6y2w1-00000.warc.gz	201352167	download   job
policies.paidwork.com-inf-20260625-155322-6y2w1-00000.warc.os.cdx.gz	622132	download
policies.paidwork.com-inf-20260625-155322-6y2w1-meta.warc.gz	495262	download   job
policies.paidwork.com-inf-20260625-155322-6y2w1-meta.warc.os.cdx.gz	47	download
policies.paidwork.com-inf-20260625-155322-6y2w1.json	246	download   job
practicaltypography.com-inf-20260625-115551-2ye1o-00001.warc.gz	5763086728	download   job
practicaltypography.com-inf-20260625-115551-2ye1o-00001.warc.os.cdx.gz	1644517	download
reports.setupad.com-inf-20260625-163936-249n3-00000.warc.gz	2083931	download   job
reports.setupad.com-inf-20260625-163936-249n3-00000.warc.os.cdx.gz	12713	download
reports.setupad.com-inf-20260625-163936-249n3-meta.warc.gz	14220	download   job
reports.setupad.com-inf-20260625-163936-249n3-meta.warc.os.cdx.gz	47	download
reports.setupad.com-inf-20260625-163936-249n3.json	244	download   job
rjakka.wordpress.com-inf-20260625-160321-drjot-00000.warc.gz	594457489	download   job
rjakka.wordpress.com-inf-20260625-160321-drjot-00000.warc.os.cdx.gz	458356	download
rjakka.wordpress.com-inf-20260625-160321-drjot-meta.warc.gz	277414	download   job
rjakka.wordpress.com-inf-20260625-160321-drjot-meta.warc.os.cdx.gz	47	download
rjakka.wordpress.com-inf-20260625-160321-drjot.json	248	download   job
sandbox.setupad.com-inf-20260625-165205-d7o8i-00000.warc.gz	54125939	download   job
sandbox.setupad.com-inf-20260625-165205-d7o8i-00000.warc.os.cdx.gz	57066	download
sandbox.setupad.com-inf-20260625-165205-d7o8i-meta.warc.gz	36828	download   job
sandbox.setupad.com-inf-20260625-165205-d7o8i-meta.warc.os.cdx.gz	47	download
sandbox.setupad.com-inf-20260625-165205-d7o8i.json	244	download   job
seunnuberublog.wordpress.com-inf-20260625-115749-dweh6-00000.warc.gz	2563567851	download   job
seunnuberublog.wordpress.com-inf-20260625-115749-dweh6-00000.warc.os.cdx.gz	4390286	download
seunnuberublog.wordpress.com-inf-20260625-115749-dweh6-meta.warc.gz	4047771	download   job
seunnuberublog.wordpress.com-inf-20260625-115749-dweh6-meta.warc.os.cdx.gz	47	download
seunnuberublog.wordpress.com-inf-20260625-115749-dweh6.json	256	download   job
signup-dev.setupad.com-inf-20260625-165104-dlgn0-00000.warc.gz	70655168	download   job
signup-dev.setupad.com-inf-20260625-165104-dlgn0-00000.warc.os.cdx.gz	96950	download
signup-dev.setupad.com-inf-20260625-165104-dlgn0-meta.warc.gz	73437	download   job
signup-dev.setupad.com-inf-20260625-165104-dlgn0-meta.warc.os.cdx.gz	47	download
signup-dev.setupad.com-inf-20260625-165104-dlgn0.json	247	download   job
signup.setupad.com-inf-20260625-165116-d8ks1-00000.warc.gz	69326719	download   job
signup.setupad.com-inf-20260625-165116-d8ks1-00000.warc.os.cdx.gz	88446	download
signup.setupad.com-inf-20260625-165116-d8ks1-meta.warc.gz	67043	download   job
signup.setupad.com-inf-20260625-165116-d8ks1-meta.warc.os.cdx.gz	47	download
signup.setupad.com-inf-20260625-165116-d8ks1.json	243	download   job
store.whiteclouds.com-inf-20260618-092140-7zmi7-00843.warc.gz	5401433162	download   job
store.whiteclouds.com-inf-20260618-092140-7zmi7-00843.warc.os.cdx.gz	21805	download
store.whiteclouds.com-inf-20260618-092140-7zmi7-00844.warc.gz	5389262837	download   job
store.whiteclouds.com-inf-20260618-092140-7zmi7-00844.warc.os.cdx.gz	21065	download
store.whiteclouds.com-inf-20260618-092140-7zmi7-00845.warc.gz	5371011281	download   job
store.whiteclouds.com-inf-20260618-092140-7zmi7-00845.warc.os.cdx.gz	21835	download
store.whiteclouds.com-inf-20260618-092140-7zmi7-00846.warc.gz	5398765955	download   job
store.whiteclouds.com-inf-20260618-092140-7zmi7-00846.warc.os.cdx.gz	22231	download
tassenfuertoleranz.de-inf-20260625-164307-97542-00000.warc.gz	446952873	download   job
tassenfuertoleranz.de-inf-20260625-164307-97542-00000.warc.os.cdx.gz	197815	download
tassenfuertoleranz.de-inf-20260625-164307-97542-meta.warc.gz	127080	download   job
tassenfuertoleranz.de-inf-20260625-164307-97542-meta.warc.os.cdx.gz	47	download
tassenfuertoleranz.de-inf-20260625-164307-97542.json	249	download   job
td.setupad.com-inf-20260625-165347-34e7z-00000.warc.gz	982307	download   job
td.setupad.com-inf-20260625-165347-34e7z-00000.warc.os.cdx.gz	3404	download
td.setupad.com-inf-20260625-165347-34e7z-meta.warc.gz	5520	download   job
td.setupad.com-inf-20260625-165347-34e7z-meta.warc.os.cdx.gz	47	download
td.setupad.com-inf-20260625-165347-34e7z.json	239	download   job
tempreports.setupad.com-inf-20260625-165147-5ikla-00000.warc.gz	129908310	download   job
tempreports.setupad.com-inf-20260625-165147-5ikla-00000.warc.os.cdx.gz	90419	download
tempreports.setupad.com-inf-20260625-165147-5ikla-meta.warc.gz	68414	download   job
tempreports.setupad.com-inf-20260625-165147-5ikla-meta.warc.os.cdx.gz	47	download
tempreports.setupad.com-inf-20260625-165147-5ikla.json	248	download   job
urls-transfer.archivete.am-anker.com-28-shopify-and-shopify-adjacent-websites-inf-20260618-201608-c22ti-00051.warc.gz	5369963648	download   job
urls-transfer.archivete.am-anker.com-28-shopify-and-shopify-adjacent-websites-inf-20260618-201608-c22ti-00051.warc.os.cdx.gz	772486	download
urls-transfer.archivete.am-chrisbreebaart.com_429-403-or-ignored-flickr-urls.txt-shallow-20260625-162949-cwjtr-00000.warc.gz	278477157	download   job
urls-transfer.archivete.am-chrisbreebaart.com_429-403-or-ignored-flickr-urls.txt-shallow-20260625-162949-cwjtr-00000.warc.os.cdx.gz	80297	download
urls-transfer.archivete.am-chrisbreebaart.com_429-403-or-ignored-flickr-urls.txt-shallow-20260625-162949-cwjtr-meta.warc.gz	45890	download   job
urls-transfer.archivete.am-chrisbreebaart.com_429-403-or-ignored-flickr-urls.txt-shallow-20260625-162949-cwjtr-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-chrisbreebaart.com_429-403-or-ignored-flickr-urls.txt-shallow-20260625-162949-cwjtr-urls.txt	92353	download
urls-transfer.archivete.am-chrisbreebaart.com_429-403-or-ignored-flickr-urls.txt-shallow-20260625-162949-cwjtr.json	399	download   job
urls-transfer.archivete.am-ugandacoffee.go.ug_429-403-or-ignored-flickr-urls.txt-shallow-20260625-170109-6n3hn-00000.warc.gz	148679907	download   job
urls-transfer.archivete.am-ugandacoffee.go.ug_429-403-or-ignored-flickr-urls.txt-shallow-20260625-170109-6n3hn-00000.warc.os.cdx.gz	16856	download
wachturm.die-partei-berlin.de-inf-20260625-164544-9k43i-00000.warc.gz	20094642	download   job
wachturm.die-partei-berlin.de-inf-20260625-164544-9k43i-00000.warc.os.cdx.gz	902	download
wachturm.die-partei-berlin.de-inf-20260625-164544-9k43i-meta.warc.gz	4215	download   job
wachturm.die-partei-berlin.de-inf-20260625-164544-9k43i-meta.warc.os.cdx.gz	47	download
wachturm.die-partei-berlin.de-inf-20260625-164544-9k43i.json	257	download   job
websites-next.setupad.com-inf-20260625-162720-94a1i-00000.warc.gz	291612661	download   job
websites-next.setupad.com-inf-20260625-162720-94a1i-00000.warc.os.cdx.gz	386526	download
websites-next.setupad.com-inf-20260625-162720-94a1i-meta.warc.gz	246144	download   job
websites-next.setupad.com-inf-20260625-162720-94a1i-meta.warc.os.cdx.gz	47	download
websites-next.setupad.com-inf-20260625-162720-94a1i.json	250	download   job
wohnungssuche.die-partei-berlin.de-inf-20260625-164625-m7ykv-00000.warc.gz	2319452	download   job
wohnungssuche.die-partei-berlin.de-inf-20260625-164625-m7ykv-00000.warc.os.cdx.gz	4325	download
wohnungssuche.die-partei-berlin.de-inf-20260625-164625-m7ykv-meta.warc.gz	6087	download   job
wohnungssuche.die-partei-berlin.de-inf-20260625-164625-m7ykv-meta.warc.os.cdx.gz	47	download
wohnungssuche.die-partei-berlin.de-inf-20260625-164625-m7ykv.json	262	download   job
www.14ymedio.com-inf-20260624-170336-4g7kp-00004.warc.gz	5368934211	download   job
www.14ymedio.com-inf-20260624-170336-4g7kp-00004.warc.os.cdx.gz	4233054	download
www.asriran.com-inf-20260131-055905-eawh4-00388.warc.gz	5368724054	download   job
www.asriran.com-inf-20260131-055905-eawh4-00388.warc.os.cdx.gz	7544363	download
www.die-partei-duesseldorf.de-inf-20260625-163848-c44ug-00000.warc.gz	27293656	download   job
www.die-partei-duesseldorf.de-inf-20260625-163848-c44ug-00000.warc.os.cdx.gz	18219	download
www.die-partei-duesseldorf.de-inf-20260625-163848-c44ug-meta.warc.gz	13452	download   job
www.die-partei-duesseldorf.de-inf-20260625-163848-c44ug-meta.warc.os.cdx.gz	47	download
www.die-partei-duesseldorf.de-inf-20260625-163848-c44ug.json	257	download   job
www.die-partei-hagen.de-inf-20260625-164840-dhkmw-00000.warc.gz	2331966	download   job
www.die-partei-hagen.de-inf-20260625-164840-dhkmw-00000.warc.os.cdx.gz	4611	download
www.die-partei-hagen.de-inf-20260625-164840-dhkmw-meta.warc.gz	6248	download   job
www.die-partei-hagen.de-inf-20260625-164840-dhkmw-meta.warc.os.cdx.gz	47	download
www.die-partei-hagen.de-inf-20260625-164840-dhkmw.json	251	download   job
www.die-partei-hsk.de-inf-20260625-164907-21p34-00000.warc.gz	9882477	download   job
www.die-partei-hsk.de-inf-20260625-164907-21p34-00000.warc.os.cdx.gz	20882	download
www.die-partei-hsk.de-inf-20260625-164907-21p34-meta.warc.gz	15481	download   job
www.die-partei-hsk.de-inf-20260625-164907-21p34-meta.warc.os.cdx.gz	47	download
www.die-partei-hsk.de-inf-20260625-164907-21p34.json	249	download   job
www.die-partei-leverkusen.de-inf-20260625-164916-59l30-00000.warc.gz	2487	download   job
www.die-partei-leverkusen.de-inf-20260625-164916-59l30-00000.warc.os.cdx.gz	47	download
www.die-partei-leverkusen.de-inf-20260625-164916-59l30-meta.warc.gz	3526	download   job
www.die-partei-leverkusen.de-inf-20260625-164916-59l30-meta.warc.os.cdx.gz	47	download
www.die-partei-leverkusen.de-inf-20260625-164916-59l30.json	256	download   job
www.die-partei-recklinghausen.de-inf-20260625-165409-bapjr-00000.warc.gz	285447	download   job
www.die-partei-recklinghausen.de-inf-20260625-165409-bapjr-00000.warc.os.cdx.gz	2151	download
www.die-partei-recklinghausen.de-inf-20260625-165409-bapjr-meta.warc.gz	4771	download   job
www.die-partei-recklinghausen.de-inf-20260625-165409-bapjr-meta.warc.os.cdx.gz	47	download
www.die-partei-recklinghausen.de-inf-20260625-165409-bapjr.json	260	download   job
www.die-partei-rk-neuss.de-inf-20260625-165424-104l2-00000.warc.gz	13000	download   job
www.die-partei-rk-neuss.de-inf-20260625-165424-104l2-00000.warc.os.cdx.gz	351	download
www.die-partei-rk-neuss.de-inf-20260625-165424-104l2-meta.warc.gz	3647	download   job
www.die-partei-rk-neuss.de-inf-20260625-165424-104l2-meta.warc.os.cdx.gz	47	download
www.die-partei-rk-neuss.de-inf-20260625-165424-104l2.json	254	download   job
www.die-partei-witten.de-inf-20260625-170440-2utdu-00000.warc.gz	2483	download   job
www.die-partei-witten.de-inf-20260625-170440-2utdu-00000.warc.os.cdx.gz	47	download
www.die-partei-witten.de-inf-20260625-170440-2utdu-meta.warc.gz	3575	download   job
www.die-partei-witten.de-inf-20260625-170440-2utdu-meta.warc.os.cdx.gz	47	download
www.die-partei-witten.de-inf-20260625-170440-2utdu.json	252	download   job
www.die-partei-wuppertal.org-inf-20260625-165446-d5nyl-00000.warc.gz	2489	download   job
www.die-partei-wuppertal.org-inf-20260625-165446-d5nyl-00000.warc.os.cdx.gz	47	download
www.die-partei-wuppertal.org-inf-20260625-165446-d5nyl-meta.warc.gz	3507	download   job
www.die-partei-wuppertal.org-inf-20260625-165446-d5nyl-meta.warc.os.cdx.gz	47	download
www.die-partei-wuppertal.org-inf-20260625-165446-d5nyl.json	256	download   job
www.diepartei-rheinberg.de-inf-20260625-170339-3p50l-00000.warc.gz	2486	download   job
www.diepartei-rheinberg.de-inf-20260625-170339-3p50l-00000.warc.os.cdx.gz	47	download
www.diepartei-rheinberg.de-inf-20260625-170339-3p50l-meta.warc.gz	3596	download   job
www.diepartei-rheinberg.de-inf-20260625-170339-3p50l-meta.warc.os.cdx.gz	47	download
www.diepartei-rheinberg.de-inf-20260625-170339-3p50l.json	254	download   job
www.ilna.ir-inf-20260130-213111-e3fs1-00462.warc.gz	5375687756	download   job
www.ilna.ir-inf-20260130-213111-e3fs1-00462.warc.os.cdx.gz	1626144	download
www.kianbattery.com-inf-20260625-063256-btye2-00010.warc.gz	5409847561	download   job
www.kianbattery.com-inf-20260625-063256-btye2-00010.warc.os.cdx.gz	126721	download
www.pravda.com.ua-inf-20260429-161905-8hc8n-00272.warc.gz	5452690394	download   job
www.pravda.com.ua-inf-20260429-161905-8hc8n-00272.warc.os.cdx.gz	832365	download
www.tabnak.ir-inf-20260130-213526-8r7zi-01769.warc.gz	6221484340	download   job
www.tabnak.ir-inf-20260130-213526-8r7zi-01769.warc.os.cdx.gz	1394531	download
www.tassenfuertoleranz.de-inf-20260625-164135-7b3ru-00000.warc.gz	45602274	download   job
www.tassenfuertoleranz.de-inf-20260625-164135-7b3ru-00000.warc.os.cdx.gz	5002	download
www.tassenfuertoleranz.de-inf-20260625-164135-7b3ru-meta.warc.gz	6233	download   job
www.tassenfuertoleranz.de-inf-20260625-164135-7b3ru-meta.warc.os.cdx.gz	47	download
www.tassenfuertoleranz.de-inf-20260625-164135-7b3ru.json	253	download   job
www.wachturm.die-partei-berlin.de-inf-20260625-164559-7bxct-00000.warc.gz	20086112	download   job
www.wachturm.die-partei-berlin.de-inf-20260625-164559-7bxct-00000.warc.os.cdx.gz	684	download
www.wachturm.die-partei-berlin.de-inf-20260625-164559-7bxct-meta.warc.gz	3913	download   job
www.wachturm.die-partei-berlin.de-inf-20260625-164559-7bxct-meta.warc.os.cdx.gz	47	download
www.wachturm.die-partei-berlin.de-inf-20260625-164559-7bxct.json	261	download   job