Item archiveteam_archivebot_go_20260905171705_c1e4dc02

View on Internet Archive

Filename	Size
anlage4.de-shallow-20260905-165821-deie6-00000.warc.gz	220124	download   job
anlage4.de-shallow-20260905-165821-deie6-00000.warc.os.cdx.gz	278	download
anlage4.de-shallow-20260905-165821-deie6-meta.warc.gz	3460	download   job
anlage4.de-shallow-20260905-165821-deie6-meta.warc.os.cdx.gz	47	download
anlage4.de-shallow-20260905-165821-deie6.json	241	download   job
archiveteam_archivebot_go_20260905171705_c1e4dc02.cdx.gz	574068	download
archiveteam_archivebot_go_20260905171705_c1e4dc02.cdx.idx	647	download
archiveteam_archivebot_go_20260905171705_c1e4dc02_files.xml	0	download
archiveteam_archivebot_go_20260905171705_c1e4dc02_meta.sqlite	348160	download
archiveteam_archivebot_go_20260905171705_c1e4dc02_meta.xml	1046	download
beteiligung.gruene-fraktion-lsa.de-inf-20260905-161758-1984e-00000.warc.gz	1419040900	download   job
beteiligung.gruene-fraktion-lsa.de-inf-20260905-161758-1984e-00000.warc.os.cdx.gz	589227	download
beteiligung.gruene-fraktion-lsa.de-inf-20260905-161758-1984e-meta.warc.gz	370133	download   job
beteiligung.gruene-fraktion-lsa.de-inf-20260905-161758-1984e-meta.warc.os.cdx.gz	47	download
beteiligung.gruene-fraktion-lsa.de-inf-20260905-161758-1984e.json	267	download   job
bielefelderstadtbibliothek.wordpress.com-inf-20260905-133723-225a1-00002.warc.gz	5428999400	download   job
bielefelderstadtbibliothek.wordpress.com-inf-20260905-133723-225a1-00002.warc.os.cdx.gz	466228	download
cyfrowy.wawel.krakow.pl-inf-20260905-165047-7ggny-00000.warc.gz	13322667	download   job
cyfrowy.wawel.krakow.pl-inf-20260905-165047-7ggny-00000.warc.os.cdx.gz	32535	download
cyfrowy.wawel.krakow.pl-inf-20260905-165047-7ggny-meta.warc.gz	26190	download   job
cyfrowy.wawel.krakow.pl-inf-20260905-165047-7ggny-meta.warc.os.cdx.gz	47	download
cyfrowy.wawel.krakow.pl-inf-20260905-165047-7ggny.json	251	download   job
das.sdss.org-inf-20250226-051304-5s39o-09666.warc.gz	5370486763	download   job
das.sdss.org-inf-20250226-051304-5s39o-09666.warc.os.cdx.gz	345752	download
die-partei-sachsen-anhalt.de-inf-20260905-165539-c4nal-00000.warc.gz	121539112	download   job
die-partei-sachsen-anhalt.de-inf-20260905-165539-c4nal-00000.warc.os.cdx.gz	95114	download
die-partei-sachsen-anhalt.de-inf-20260905-165539-c4nal-meta.warc.gz	71387	download   job
die-partei-sachsen-anhalt.de-inf-20260905-165539-c4nal-meta.warc.os.cdx.gz	47	download
die-partei-sachsen-anhalt.de-inf-20260905-165539-c4nal.json	261	download   job
diebasis-partei.de-inf-20260905-133648-5e4om-00001.warc.gz	5369219370	download   job
diebasis-partei.de-inf-20260905-133648-5e4om-00001.warc.os.cdx.gz	1295007	download
dielinke-fraktion-lsa.de-inf-20260905-165207-4bcrd-00000.warc.gz	6663	download   job
dielinke-fraktion-lsa.de-inf-20260905-165207-4bcrd-00000.warc.os.cdx.gz	272	download
dielinke-fraktion-lsa.de-inf-20260905-165207-4bcrd-meta.warc.gz	3549	download   job
dielinke-fraktion-lsa.de-inf-20260905-165207-4bcrd-meta.warc.os.cdx.gz	47	download
dielinke-fraktion-lsa.de-inf-20260905-165207-4bcrd.json	257	download   job
dielinke-fraktion-lsa.de-inf-20260905-165445-4bcrd-00000.warc.gz	57734342	download   job
dielinke-fraktion-lsa.de-inf-20260905-165445-4bcrd-00000.warc.os.cdx.gz	13294	download
dielinke-fraktion-lsa.de-inf-20260905-165445-4bcrd-meta.warc.gz	11271	download   job
dielinke-fraktion-lsa.de-inf-20260905-165445-4bcrd-meta.warc.os.cdx.gz	47	download
dielinke-fraktion-lsa.de-inf-20260905-165445-4bcrd.json	252	download   job
fanlore.org-inf-20260815-042033-6laty-00163.warc.gz	5370014883	download   job
fanlore.org-inf-20260815-042033-6laty-00163.warc.os.cdx.gz	2440618	download
gartenpartei.eu-inf-20260905-165522-2z22l-00000.warc.gz	668670139	download   job
gartenpartei.eu-inf-20260905-165522-2z22l-00000.warc.os.cdx.gz	329050	download
gartenpartei.eu-inf-20260905-165522-2z22l-meta.warc.gz	229177	download   job
gartenpartei.eu-inf-20260905-165522-2z22l-meta.warc.os.cdx.gz	47	download
gartenpartei.eu-inf-20260905-165522-2z22l.json	248	download   job
henryabrahammd.substack.com-inf-20260903-183939-5xu4k-00006.warc.gz	2053145219	download   job
henryabrahammd.substack.com-inf-20260903-183939-5xu4k-00006.warc.os.cdx.gz	1351064	download
henryabrahammd.substack.com-inf-20260903-183939-5xu4k-meta.warc.gz	4947172	download   job
henryabrahammd.substack.com-inf-20260903-183939-5xu4k-meta.warc.os.cdx.gz	47	download
henryabrahammd.substack.com-inf-20260903-183939-5xu4k.json	258	download   job
hentaiporns.net-inf-20260627-002407-21ute-00562.warc.gz	5369568556	download   job
hentaiporns.net-inf-20260627-002407-21ute-00562.warc.os.cdx.gz	755563	download
hypixel.net-inf-20260903-094200-cvr6x-00002.warc.gz	5368755715	download   job
hypixel.net-inf-20260903-094200-cvr6x-00002.warc.os.cdx.gz	12336041	download
landtagswahl-sachsen-anhalt.de-inf-20260905-163206-3qnnc-00000.warc.gz	481299676	download   job
landtagswahl-sachsen-anhalt.de-inf-20260905-163206-3qnnc-00000.warc.os.cdx.gz	656198	download
landtagswahl-sachsen-anhalt.de-inf-20260905-163206-3qnnc-meta.warc.gz	438084	download   job
landtagswahl-sachsen-anhalt.de-inf-20260905-163206-3qnnc-meta.warc.os.cdx.gz	47	download
landtagswahl-sachsen-anhalt.de-inf-20260905-163206-3qnnc.json	263	download   job
ltv-de.kanalb.org-inf-20260903-150053-egne6-00035.warc.gz	5368970000	download   job
ltv-de.kanalb.org-inf-20260903-150053-egne6-00035.warc.os.cdx.gz	80415	download
mai68.org-inf-20260828-162554-ada88-00299.warc.gz	5467046100	download   job
mai68.org-inf-20260828-162554-ada88-00299.warc.os.cdx.gz	1194706	download
mai68.org-inf-20260828-162554-ada88-00300.warc.gz	5631240791	download   job
mai68.org-inf-20260828-162554-ada88-00300.warc.os.cdx.gz	5165	download
mail.skt.weglew.pl-inf-20260905-170521-3pqcl-00000.warc.gz	2473	download   job
mail.skt.weglew.pl-inf-20260905-170521-3pqcl-00000.warc.os.cdx.gz	47	download
mail.skt.weglew.pl-inf-20260905-170521-3pqcl-meta.warc.gz	3614	download   job
mail.skt.weglew.pl-inf-20260905-170521-3pqcl-meta.warc.os.cdx.gz	47	download
mail.skt.weglew.pl-inf-20260905-170521-3pqcl.json	246	download   job
mail.sroda.wlkp.pl-inf-20260905-164442-3ahwy-aborted-00000.warc.gz	31292119	download   job
mail.sroda.wlkp.pl-inf-20260905-164442-3ahwy-aborted-00000.warc.os.cdx.gz	35715	download
mail.sroda.wlkp.pl-inf-20260905-164442-3ahwy-aborted-wpull.log.gz	21134	download
mail.sroda.wlkp.pl-inf-20260905-164442-3ahwy-aborted.json	245	download   job
mail.sroda.wlkp.pl-shallow-20260905-165020-3ahwy-00000.warc.gz	4451132	download   job
mail.sroda.wlkp.pl-shallow-20260905-165020-3ahwy-00000.warc.os.cdx.gz	10831	download
mail.sroda.wlkp.pl-shallow-20260905-165020-3ahwy-meta.warc.gz	9876	download   job
mail.sroda.wlkp.pl-shallow-20260905-165020-3ahwy-meta.warc.os.cdx.gz	47	download
mail.sroda.wlkp.pl-shallow-20260905-165020-3ahwy.json	250	download   job
mail.test.psp.wlkp.pl-inf-20260905-164034-anb5u-00000.warc.gz	53242290	download   job
mail.test.psp.wlkp.pl-inf-20260905-164034-anb5u-00000.warc.os.cdx.gz	227716	download
mail.test.psp.wlkp.pl-inf-20260905-164034-anb5u-meta.warc.gz	123149	download   job
mail.test.psp.wlkp.pl-inf-20260905-164034-anb5u-meta.warc.os.cdx.gz	47	download
mail.test.psp.wlkp.pl-inf-20260905-164034-anb5u.json	249	download   job
mail.weglew.pl-inf-20260905-170036-bmlaz-00000.warc.gz	2465	download   job
mail.weglew.pl-inf-20260905-170036-bmlaz-00000.warc.os.cdx.gz	47	download
mail.weglew.pl-inf-20260905-170036-bmlaz-meta.warc.gz	3618	download   job
mail.weglew.pl-inf-20260905-170036-bmlaz-meta.warc.os.cdx.gz	47	download
mail.weglew.pl-inf-20260905-170036-bmlaz.json	242	download   job
mail.wieza-gizycko.pl-inf-20260905-170630-2o6q3-00000.warc.gz	6451	download   job
mail.wieza-gizycko.pl-inf-20260905-170630-2o6q3-00000.warc.os.cdx.gz	305	download
mail.wieza-gizycko.pl-inf-20260905-170630-2o6q3-meta.warc.gz	3580	download   job
mail.wieza-gizycko.pl-inf-20260905-170630-2o6q3-meta.warc.os.cdx.gz	47	download
mail.wieza-gizycko.pl-inf-20260905-170630-2o6q3.json	249	download   job
mail.woia.pl-inf-20260905-170604-bo3io-00000.warc.gz	6022464	download   job
mail.woia.pl-inf-20260905-170604-bo3io-00000.warc.os.cdx.gz	37117	download
mail.woia.pl-inf-20260905-170604-bo3io-meta.warc.gz	26701	download   job
mail.woia.pl-inf-20260905-170604-bo3io-meta.warc.os.cdx.gz	47	download
mail.woia.pl-inf-20260905-170604-bo3io.json	240	download   job
mail.wolinpn.pl-inf-20260905-164914-1gal7-00000.warc.gz	2464	download   job
mail.wolinpn.pl-inf-20260905-164914-1gal7-00000.warc.os.cdx.gz	47	download
mail.wolinpn.pl-inf-20260905-164914-1gal7-meta.warc.gz	3615	download   job
mail.wolinpn.pl-inf-20260905-164914-1gal7-meta.warc.os.cdx.gz	47	download
mail.wolinpn.pl-inf-20260905-164914-1gal7.json	242	download   job
mail.zabytkowe-wiatraki.pl-shallow-20260905-170756-c6x54-00000.warc.gz	7313	download   job
mail.zabytkowe-wiatraki.pl-shallow-20260905-170756-c6x54-00000.warc.os.cdx.gz	229	download
mail.zabytkowe-wiatraki.pl-shallow-20260905-170756-c6x54-meta.warc.gz	3481	download   job
mail.zabytkowe-wiatraki.pl-shallow-20260905-170756-c6x54-meta.warc.os.cdx.gz	47	download
mail.zabytkowe-wiatraki.pl-shallow-20260905-170756-c6x54.json	258	download   job
mail.zyndranowa.org-inf-20260905-170404-e7pi1-00000.warc.gz	1065658	download   job
mail.zyndranowa.org-inf-20260905-170404-e7pi1-00000.warc.os.cdx.gz	2355	download
mail.zyndranowa.org-inf-20260905-170404-e7pi1-meta.warc.gz	5027	download   job
mail.zyndranowa.org-inf-20260905-170404-e7pi1-meta.warc.os.cdx.gz	47	download
mail.zyndranowa.org-inf-20260905-170404-e7pi1.json	247	download   job
mail7.skt.weglew.pl-inf-20260905-170145-7zh99-00000.warc.gz	2475	download   job
mail7.skt.weglew.pl-inf-20260905-170145-7zh99-00000.warc.os.cdx.gz	47	download
mail7.skt.weglew.pl-inf-20260905-170145-7zh99-meta.warc.gz	3620	download   job
mail7.skt.weglew.pl-inf-20260905-170145-7zh99-meta.warc.os.cdx.gz	47	download
mail7.skt.weglew.pl-inf-20260905-170145-7zh99.json	247	download   job
npa.liberationwarbangladesh.net-inf-20260902-013154-efhyp-00076.warc.gz	5368883417	download   job
npa.liberationwarbangladesh.net-inf-20260902-013154-efhyp-00076.warc.os.cdx.gz	1023326	download
sziborraseidlitz.de-inf-20260905-161845-8acrf-00000.warc.gz	1749039095	download   job
sziborraseidlitz.de-inf-20260905-161845-8acrf-00000.warc.os.cdx.gz	742372	download
sziborraseidlitz.de-inf-20260905-161845-8acrf-meta.warc.gz	554307	download   job
sziborraseidlitz.de-inf-20260905-161845-8acrf-meta.warc.os.cdx.gz	47	download
sziborraseidlitz.de-inf-20260905-161845-8acrf.json	252	download   job
thehumaneleague.org-inf-20260905-042536-2o98w-00010.warc.gz	5380892429	download   job
thehumaneleague.org-inf-20260905-042536-2o98w-00010.warc.os.cdx.gz	947689	download
theophiluslondon.wordpress.com-inf-20260905-134239-d1i1b-00001.warc.gz	581659200	download   job
theophiluslondon.wordpress.com-inf-20260905-134239-d1i1b-00001.warc.os.cdx.gz	1278174	download
theophiluslondon.wordpress.com-inf-20260905-134239-d1i1b-meta.warc.gz	2183409	download   job
theophiluslondon.wordpress.com-inf-20260905-134239-d1i1b-meta.warc.os.cdx.gz	47	download
theophiluslondon.wordpress.com-inf-20260905-134239-d1i1b.json	258	download   job
tierschutzallianz.de-inf-20260905-165551-c2lbs-00000.warc.gz	8683448	download   job
tierschutzallianz.de-inf-20260905-165551-c2lbs-00000.warc.os.cdx.gz	9853	download
tierschutzallianz.de-inf-20260905-165551-c2lbs-meta.warc.gz	9330	download   job
tierschutzallianz.de-inf-20260905-165551-c2lbs-meta.warc.os.cdx.gz	47	download
tierschutzallianz.de-inf-20260905-165551-c2lbs.json	253	download   job
urls-transfer.archivete.am-3948-shuai-9.1.txt-shallow-20260901-134642-af3mz-00001.warc.gz	3647368677	download   job
urls-transfer.archivete.am-3948-shuai-9.1.txt-shallow-20260901-134642-af3mz-00001.warc.os.cdx.gz	3482725	download
urls-transfer.archivete.am-3948-shuai-9.1.txt-shallow-20260901-134642-af3mz-meta.warc.gz	6755182	download   job
urls-transfer.archivete.am-3948-shuai-9.1.txt-shallow-20260901-134642-af3mz-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-3948-shuai-9.1.txt-shallow-20260901-134642-af3mz-urls.txt	97944	download
urls-transfer.archivete.am-3948-shuai-9.1.txt-shallow-20260901-134642-af3mz.json	327	download   job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260905-170141-6izn3-00000.warc.gz	5294654	download   job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260905-170141-6izn3-00000.warc.os.cdx.gz	18408	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260905-170141-6izn3-meta.warc.gz	13431	download   job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260905-170141-6izn3-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260905-170141-6izn3-urls.txt	29124	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260905-170141-6izn3.json	368	download   job
urls-transfer.archivete.am-eurocom.bg_ignored-or-failed_show_videos_urls_part-1-of-2.txt-shallow-20260831-102026-16bxp-00564.warc.gz	5945955564	download   job
urls-transfer.archivete.am-eurocom.bg_ignored-or-failed_show_videos_urls_part-1-of-2.txt-shallow-20260831-102026-16bxp-00564.warc.os.cdx.gz	823	download
urls-transfer.archivete.am-eurocom.bg_ignored-or-failed_show_videos_urls_part-1-of-2.txt-shallow-20260831-102026-16bxp-00565.warc.gz	9934074234	download   job
urls-transfer.archivete.am-eurocom.bg_ignored-or-failed_show_videos_urls_part-1-of-2.txt-shallow-20260831-102026-16bxp-00565.warc.os.cdx.gz	915	download
urls-transfer.archivete.am-eurocom.bg_ignored-or-failed_show_videos_urls_part-2-of-2.txt-shallow-20260831-102120-b8m0t-00383.warc.gz	5590498687	download   job
urls-transfer.archivete.am-eurocom.bg_ignored-or-failed_show_videos_urls_part-2-of-2.txt-shallow-20260831-102120-b8m0t-00383.warc.os.cdx.gz	421	download
waehlt-dielinke.de-inf-20260905-161903-6fk42-00000.warc.gz	486176470	download   job
waehlt-dielinke.de-inf-20260905-161903-6fk42-00000.warc.os.cdx.gz	304436	download
waehlt-dielinke.de-inf-20260905-161903-6fk42-meta.warc.gz	211616	download   job
waehlt-dielinke.de-inf-20260905-161903-6fk42-meta.warc.os.cdx.gz	47	download
waehlt-dielinke.de-inf-20260905-161903-6fk42.json	251	download   job
webmail.interpack.wlkp.pl-inf-20260905-170535-7cg3j-00000.warc.gz	1033288	download   job
webmail.interpack.wlkp.pl-inf-20260905-170535-7cg3j-00000.warc.os.cdx.gz	2427	download
webmail.interpack.wlkp.pl-inf-20260905-170535-7cg3j-meta.warc.gz	5067	download   job
webmail.interpack.wlkp.pl-inf-20260905-170535-7cg3j-meta.warc.os.cdx.gz	47	download
webmail.interpack.wlkp.pl-inf-20260905-170535-7cg3j.json	253	download   job
webmail.ptreh.wlkp.pl-shallow-20260905-170637-awzk9-00000.warc.gz	639452	download   job
webmail.ptreh.wlkp.pl-shallow-20260905-170637-awzk9-00000.warc.os.cdx.gz	2348	download
webmail.ptreh.wlkp.pl-shallow-20260905-170637-awzk9-meta.warc.gz	4649	download   job
webmail.ptreh.wlkp.pl-shallow-20260905-170637-awzk9-meta.warc.os.cdx.gz	47	download
webmail.ptreh.wlkp.pl-shallow-20260905-170637-awzk9.json	253	download   job
webmail.zyndranowa.org-inf-20260905-165920-5yebv-00000.warc.gz	1066172	download   job
webmail.zyndranowa.org-inf-20260905-165920-5yebv-00000.warc.os.cdx.gz	2369	download
webmail.zyndranowa.org-inf-20260905-165920-5yebv-meta.warc.gz	5043	download   job
webmail.zyndranowa.org-inf-20260905-165920-5yebv-meta.warc.os.cdx.gz	47	download
webmail.zyndranowa.org-inf-20260905-165920-5yebv.json	250	download   job
www.anlage4.de-inf-20260905-165842-dlzs6-00000.warc.gz	144783049	download   job
www.anlage4.de-inf-20260905-165842-dlzs6-00000.warc.os.cdx.gz	186721	download
www.anlage4.de-inf-20260905-165842-dlzs6-meta.warc.gz	144955	download   job
www.anlage4.de-inf-20260905-165842-dlzs6-meta.warc.os.cdx.gz	47	download
www.anlage4.de-inf-20260905-165842-dlzs6.json	241	download   job
www.billboard-japan.com-inf-20260816-101219-81q8b-00061.warc.gz	5368878070	download   job
www.billboard-japan.com-inf-20260816-101219-81q8b-00061.warc.os.cdx.gz	3159205	download
www.diebasis-st.de-inf-20260905-165220-c7a9h-00000.warc.gz	139576019	download   job
www.diebasis-st.de-inf-20260905-165220-c7a9h-00000.warc.os.cdx.gz	10766	download
www.diebasis-st.de-inf-20260905-165220-c7a9h-meta.warc.gz	9787	download   job
www.diebasis-st.de-inf-20260905-165220-c7a9h-meta.warc.os.cdx.gz	47	download
www.diebasis-st.de-inf-20260905-165220-c7a9h.json	251	download   job
www.dielinke-fraktion-lsa.de-inf-20260905-165213-cnztb-00000.warc.gz	6720	download   job
www.dielinke-fraktion-lsa.de-inf-20260905-165213-cnztb-00000.warc.os.cdx.gz	271	download
www.dielinke-fraktion-lsa.de-inf-20260905-165213-cnztb-meta.warc.gz	3512	download   job
www.dielinke-fraktion-lsa.de-inf-20260905-165213-cnztb-meta.warc.os.cdx.gz	47	download
www.dielinke-fraktion-lsa.de-inf-20260905-165213-cnztb.json	261	download   job
www.fdp-fraktion-lsa.de-inf-20260905-161748-8172x-00000.warc.gz	6317194	download   job
www.fdp-fraktion-lsa.de-inf-20260905-161748-8172x-00000.warc.os.cdx.gz	6890	download
www.fdp-fraktion-lsa.de-inf-20260905-161748-8172x-meta.warc.gz	7584	download   job
www.fdp-fraktion-lsa.de-inf-20260905-161748-8172x-meta.warc.os.cdx.gz	47	download
www.fdp-fraktion-lsa.de-inf-20260905-161748-8172x.json	256	download   job
www.fw-lsa.de-inf-20260905-165349-2y3q7-00000.warc.gz	1780846	download   job
www.fw-lsa.de-inf-20260905-165349-2y3q7-00000.warc.os.cdx.gz	4266	download
www.fw-lsa.de-inf-20260905-165349-2y3q7-meta.warc.gz	5809	download   job
www.fw-lsa.de-inf-20260905-165349-2y3q7-meta.warc.os.cdx.gz	47	download
www.fw-lsa.de-inf-20260905-165349-2y3q7.json	246	download   job
www.gartenpartei.eu-inf-20260905-165416-ac9co-00000.warc.gz	1669162	download   job
www.gartenpartei.eu-inf-20260905-165416-ac9co-00000.warc.os.cdx.gz	5820	download
www.gartenpartei.eu-inf-20260905-165416-ac9co-meta.warc.gz	7109	download   job
www.gartenpartei.eu-inf-20260905-165416-ac9co-meta.warc.os.cdx.gz	47	download
www.gartenpartei.eu-inf-20260905-165416-ac9co.json	252	download   job
www.kinosiska.si-inf-20260904-183731-2fbyg-00000.warc.gz	5370953108	download   job
www.kinosiska.si-inf-20260904-183731-2fbyg-00000.warc.os.cdx.gz	2897289	download
www.lg.com-inf-20260420-102409-9z7tb-00464.warc.gz	5369359317	download   job
www.lg.com-inf-20260420-102409-9z7tb-00464.warc.os.cdx.gz	1164538	download
www.mail.skt.weglew.pl-inf-20260905-170519-4sg50-00000.warc.gz	2481	download   job
www.mail.skt.weglew.pl-inf-20260905-170519-4sg50-00000.warc.os.cdx.gz	47	download
www.mail.skt.weglew.pl-inf-20260905-170519-4sg50-meta.warc.gz	3625	download   job
www.mail.skt.weglew.pl-inf-20260905-170519-4sg50-meta.warc.os.cdx.gz	47	download
www.mail.skt.weglew.pl-inf-20260905-170519-4sg50.json	250	download   job
www.mail.weglew.pl-inf-20260905-170255-1wdj8-00000.warc.gz	2470	download   job
www.mail.weglew.pl-inf-20260905-170255-1wdj8-00000.warc.os.cdx.gz	47	download
www.mail.weglew.pl-inf-20260905-170255-1wdj8-meta.warc.gz	3630	download   job
www.mail.weglew.pl-inf-20260905-170255-1wdj8-meta.warc.os.cdx.gz	47	download
www.mail.weglew.pl-inf-20260905-170255-1wdj8.json	246	download   job
www.mcst.ru-inf-20260831-021937-aqy39-00000.warc.gz	3020216347	download   job
www.mcst.ru-inf-20260831-021937-aqy39-00000.warc.os.cdx.gz	1805932	download
www.mcst.ru-inf-20260831-021937-aqy39-meta.warc.gz	1244502	download   job
www.mcst.ru-inf-20260831-021937-aqy39-meta.warc.os.cdx.gz	47	download
www.mcst.ru-inf-20260831-021937-aqy39.json	236	download   job
www.spd-lsa.de-inf-20260905-161845-7fqcm-00000.warc.gz	13403	download   job
www.spd-lsa.de-inf-20260905-161845-7fqcm-00000.warc.os.cdx.gz	392	download
www.spd-lsa.de-inf-20260905-161845-7fqcm-meta.warc.gz	3696	download   job
www.spd-lsa.de-inf-20260905-161845-7fqcm-meta.warc.os.cdx.gz	47	download
www.spd-lsa.de-inf-20260905-161845-7fqcm-wpull.log.gz	1033	download
www.spd-lsa.de-inf-20260905-161845-7fqcm.json	247	download   job
www.spdsachsenanhalt.de-inf-20260905-165257-7lf7j-00000.warc.gz	14655827	download   job
www.spdsachsenanhalt.de-inf-20260905-165257-7lf7j-00000.warc.os.cdx.gz	10955	download
www.spdsachsenanhalt.de-inf-20260905-165257-7lf7j-meta.warc.gz	10563	download   job
www.spdsachsenanhalt.de-inf-20260905-165257-7lf7j-meta.warc.os.cdx.gz	47	download
www.spdsachsenanhalt.de-inf-20260905-165257-7lf7j.json	256	download   job
www.svenschulzecdu.de-inf-20260905-162053-eei63-00000.warc.gz	311225552	download   job
www.svenschulzecdu.de-inf-20260905-162053-eei63-00000.warc.os.cdx.gz	421544	download
www.svenschulzecdu.de-inf-20260905-162053-eei63-meta.warc.gz	278974	download   job
www.svenschulzecdu.de-inf-20260905-162053-eei63-meta.warc.os.cdx.gz	47	download
www.svenschulzecdu.de-inf-20260905-162053-eei63.json	254	download   job
www.tierschutzallianz.de-inf-20260905-165635-dneez-00000.warc.gz	160570905	download   job
www.tierschutzallianz.de-inf-20260905-165635-dneez-00000.warc.os.cdx.gz	238150	download
www.tierschutzallianz.de-inf-20260905-165635-dneez-meta.warc.gz	169707	download   job
www.tierschutzallianz.de-inf-20260905-165635-dneez-meta.warc.os.cdx.gz	47	download
www.tierschutzallianz.de-inf-20260905-165635-dneez.json	257	download   job
www.vox.com-inf-20260520-145134-4zjgq-01002.warc.gz	5368879279	download   job
www.vox.com-inf-20260520-145134-4zjgq-01002.warc.os.cdx.gz	2260497	download