Item archiveteam_archivebot_go_20250123103136_afe0b633

Filename	Size
archiveteam_archivebot_go_20250123103136_afe0b633.cdx.gz	307016	download
archiveteam_archivebot_go_20250123103136_afe0b633.cdx.idx	395	download
archiveteam_archivebot_go_20250123103136_afe0b633_files.xml	0	download
archiveteam_archivebot_go_20250123103136_afe0b633_meta.sqlite	143360	download
archiveteam_archivebot_go_20250123103136_afe0b633_meta.xml	1045	download
bdk.gruene.de-inf-20250123-100749-c048r-00000.warc.gz	323941467	download job
bdk.gruene.de-inf-20250123-100749-c048r-00000.warc.os.cdx.gz	292346	download
bdk.gruene.de-inf-20250123-100749-c048r-meta.warc.gz	177530	download job
bdk.gruene.de-inf-20250123-100749-c048r-meta.warc.os.cdx.gz	47	download
bdk.gruene.de-inf-20250123-100749-c048r.json	241	download job
digitalisierungsrunde.gruene.de-inf-20250123-102449-3tx6h-00000.warc.gz	3621641	download job
digitalisierungsrunde.gruene.de-inf-20250123-102449-3tx6h-00000.warc.os.cdx.gz	16179	download
digitalisierungsrunde.gruene.de-inf-20250123-102449-3tx6h-meta.warc.gz	13657	download job
digitalisierungsrunde.gruene.de-inf-20250123-102449-3tx6h-meta.warc.os.cdx.gz	47	download
digitalisierungsrunde.gruene.de-inf-20250123-102449-3tx6h.json	259	download job
diskussion.gruene.de-inf-20250123-102542-3w67c-00000.warc.gz	10011909	download job
diskussion.gruene.de-inf-20250123-102542-3w67c-00000.warc.os.cdx.gz	12214	download
diskussion.gruene.de-inf-20250123-102542-3w67c-meta.warc.gz	9506	download job
diskussion.gruene.de-inf-20250123-102542-3w67c-meta.warc.os.cdx.gz	47	download
diskussion.gruene.de-inf-20250123-102542-3w67c.json	248	download job
downloads.dbpedia.org-inf-20241213-105718-8lci4-00981.warc.gz	6378081837	download job
downloads.dbpedia.org-inf-20241213-105718-8lci4-00981.warc.os.cdx.gz	2791	download
eshop-dev.gruene.de-inf-20250123-102703-2ydgv-00000.warc.gz	10004784	download job
eshop-dev.gruene.de-inf-20250123-102703-2ydgv-00000.warc.os.cdx.gz	12205	download
eshop-dev.gruene.de-inf-20250123-102703-2ydgv-meta.warc.gz	9263	download job
eshop-dev.gruene.de-inf-20250123-102703-2ydgv-meta.warc.os.cdx.gz	47	download
eshop-dev.gruene.de-inf-20250123-102703-2ydgv.json	247	download job
eshop.gruene.de-inf-20250123-102729-2z4sd-00000.warc.gz	1029621	download job
eshop.gruene.de-inf-20250123-102729-2z4sd-00000.warc.os.cdx.gz	641	download
eshop.gruene.de-inf-20250123-102729-2z4sd-meta.warc.gz	3671	download job
eshop.gruene.de-inf-20250123-102729-2z4sd-meta.warc.os.cdx.gz	47	download
eshop.gruene.de-inf-20250123-102729-2z4sd.json	243	download job
exhibits.lgbtran.org-inf-20250120-034015-b3w6a-00012.warc.gz	3644567028	download job
exhibits.lgbtran.org-inf-20250120-034015-b3w6a-00012.warc.os.cdx.gz	2750464	download
exhibits.lgbtran.org-inf-20250120-034015-b3w6a-meta.warc.gz	18904687	download job
exhibits.lgbtran.org-inf-20250120-034015-b3w6a-meta.warc.os.cdx.gz	47	download
exhibits.lgbtran.org-inf-20250120-034015-b3w6a.json	251	download job
forum.openvz.org-inf-20241230-104324-3rdvj-00016.warc.gz	5368712064	download job
forum.openvz.org-inf-20241230-104324-3rdvj-00016.warc.os.cdx.gz	27130938	download
no-sopa-wiki.piratenpartei.de-inf-20250123-100415-3kt64-00000.warc.gz	745662	download job
no-sopa-wiki.piratenpartei.de-inf-20250123-100415-3kt64-00000.warc.os.cdx.gz	6811	download
no-sopa-wiki.piratenpartei.de-inf-20250123-100415-3kt64-meta.warc.gz	7557	download job
no-sopa-wiki.piratenpartei.de-inf-20250123-100415-3kt64-meta.warc.os.cdx.gz	47	download
no-sopa-wiki.piratenpartei.de-inf-20250123-100415-3kt64.json	257	download job
sciencebasedmedicine.org-inf-20250120-210703-c9oax-00045.warc.gz	5462871445	download job
sciencebasedmedicine.org-inf-20250120-210703-c9oax-00045.warc.os.cdx.gz	598516	download
staging.photographyblog.com-inf-20250123-002838-48d0e-00064.warc.gz	5369362591	download job
staging.photographyblog.com-inf-20250123-002838-48d0e-00064.warc.os.cdx.gz	31409	download
staging.photographyblog.com-inf-20250123-002838-48d0e-00065.warc.gz	5382942682	download job
staging.photographyblog.com-inf-20250123-002838-48d0e-00065.warc.os.cdx.gz	81750	download
tardis.tiny-vps.com-inf-20240918-195055-4y01y-01959.warc.gz	5586536821	download job
tardis.tiny-vps.com-inf-20240918-195055-4y01y-01959.warc.os.cdx.gz	2682	download
theminjoo.kr-inf-20240414-225933-46nqc-01076.warc.gz	5368972023	download job
theminjoo.kr-inf-20240414-225933-46nqc-01076.warc.os.cdx.gz	421867	download
urls-transfer.archivete.am-cdn-prod.playfirst.com_urls_part_01.txt-shallow-20250120-210508-7jwqp-00240.warc.gz	5369434967	download job
urls-transfer.archivete.am-cdn-prod.playfirst.com_urls_part_01.txt-shallow-20250120-210508-7jwqp-00240.warc.os.cdx.gz	658460	download
urls-transfer.archivete.am-dornsife.usc.edu_seed_urls.txt-inf-20250117-211326-1r4de-00050.warc.gz	5385958570	download job
urls-transfer.archivete.am-dornsife.usc.edu_seed_urls.txt-inf-20250117-211326-1r4de-00050.warc.os.cdx.gz	3875432	download
urls-transfer.archivete.am-download.opencontent.netflix.com.s3.amazonaws.com_under_1GB.txt-shallow-20250116-052616-l2cdn-01006.warc.gz	5402700156	download job
urls-transfer.archivete.am-download.opencontent.netflix.com.s3.amazonaws.com_under_1GB.txt-shallow-20250116-052616-l2cdn-01006.warc.os.cdx.gz	7146	download
urls-transfer.archivete.am-hypendium.com_downloads_superbestfriendsplay_ThemedCollections_Friday%20Night%20Fisticuffs.txt-shallow-20250123-041758-7fbb0-00014.warc.gz	5941059733	download job
urls-transfer.archivete.am-hypendium.com_downloads_superbestfriendsplay_ThemedCollections_Friday%20Night%20Fisticuffs.txt-shallow-20250123-041758-7fbb0-00014.warc.os.cdx.gz	1823	download
www.antiplagiat.utm.md-inf-20250123-094717-93mlp-00000.warc.gz	6496	download job
www.antiplagiat.utm.md-inf-20250123-094717-93mlp-00000.warc.os.cdx.gz	274	download
www.antiplagiat.utm.md-inf-20250123-094717-93mlp-meta.warc.gz	3551	download job
www.antiplagiat.utm.md-inf-20250123-094717-93mlp-meta.warc.os.cdx.gz	47	download
www.antiplagiat.utm.md-inf-20250123-094717-93mlp.json	250	download job
www.artlaboratory-berlin.org-inf-20250123-102027-eyf9d-00000.warc.gz	4897380	download job
www.artlaboratory-berlin.org-inf-20250123-102027-eyf9d-00000.warc.os.cdx.gz	6600	download
www.artlaboratory-berlin.org-inf-20250123-102027-eyf9d-meta.warc.gz	7424	download job
www.artlaboratory-berlin.org-inf-20250123-102027-eyf9d-meta.warc.os.cdx.gz	47	download
www.artlaboratory-berlin.org-inf-20250123-102027-eyf9d.json	256	download job
www.blogtalkradio.com-inf-20250122-073143-4df97-00119.warc.gz	5396778155	download job
www.blogtalkradio.com-inf-20250122-073143-4df97-00119.warc.os.cdx.gz	88612	download
www.blogtalkradio.com-inf-20250122-073143-4df97-00120.warc.gz	5397305486	download job
www.blogtalkradio.com-inf-20250122-073143-4df97-00120.warc.os.cdx.gz	77157	download
www.cfc.utm.md-inf-20250123-094831-3m72e-00000.warc.gz	2381	download job
www.cfc.utm.md-inf-20250123-094831-3m72e-00000.warc.os.cdx.gz	47	download
www.cfc.utm.md-inf-20250123-094831-3m72e-meta.warc.gz	3530	download job
www.cfc.utm.md-inf-20250123-094831-3m72e-meta.warc.os.cdx.gz	47	download
www.cfc.utm.md-inf-20250123-094831-3m72e.json	242	download job
www.creatures-eu.org-inf-20250123-101952-4t814-00000.warc.gz	25431970	download job
www.creatures-eu.org-inf-20250123-101952-4t814-00000.warc.os.cdx.gz	7505	download
www.creatures-eu.org-inf-20250123-101952-4t814-meta.warc.gz	7689	download job
www.creatures-eu.org-inf-20250123-101952-4t814-meta.warc.os.cdx.gz	47	download
www.creatures-eu.org-inf-20250123-101952-4t814.json	248	download job
www.foxsports.com.au-inf-20241223-003224-6ol5d-00034.warc.gz	5369117534	download job
www.foxsports.com.au-inf-20241223-003224-6ol5d-00034.warc.os.cdx.gz	2214250	download
www.mysticmamma.com-inf-20250123-101408-1i8i3-00000.warc.gz	15341301	download job
www.mysticmamma.com-inf-20250123-101408-1i8i3-00000.warc.os.cdx.gz	28322	download
www.mysticmamma.com-inf-20250123-101408-1i8i3-meta.warc.gz	19601	download job
www.mysticmamma.com-inf-20250123-101408-1i8i3-meta.warc.os.cdx.gz	47	download
www.mysticmamma.com-inf-20250123-101408-1i8i3.json	247	download job
www.nationalguard.mil-inf-20241102-181205-4gbwg-03677.warc.gz	5438132260	download job
www.nationalguard.mil-inf-20241102-181205-4gbwg-03677.warc.os.cdx.gz	2431	download
www.nrel.gov-inf-20250122-201302-cdwwa-00006.warc.gz	5410756941	download job
www.nrel.gov-inf-20250122-201302-cdwwa-00006.warc.os.cdx.gz	90498	download
www.photographyblog.com-inf-20250123-002053-cu6af-00078.warc.gz	5371756887	download job
www.photographyblog.com-inf-20250123-002053-cu6af-00078.warc.os.cdx.gz	51692	download
www.photographyblog.com-inf-20250123-002053-cu6af-00079.warc.gz	5873840409	download job
www.photographyblog.com-inf-20250123-002053-cu6af-00079.warc.os.cdx.gz	13095	download
www.shroomery.org-inf-20240128-014509-32tge-00182.warc.gz	5368723157	download job
www.shroomery.org-inf-20240128-014509-32tge-00182.warc.os.cdx.gz	14136589	download