Item archiveteam_archivebot_go_20240804161707_41c2b32a

Filename	Size
archiveteam_archivebot_go_20240804161707_41c2b32a.cdx.gz	1190463	download
archiveteam_archivebot_go_20240804161707_41c2b32a.cdx.idx	1343	download
archiveteam_archivebot_go_20240804161707_41c2b32a_files.xml	0	download
archiveteam_archivebot_go_20240804161707_41c2b32a_meta.sqlite	139264	download
archiveteam_archivebot_go_20240804161707_41c2b32a_meta.xml	1046	download
data.worldpop.org-inf-20240515-011446-esx2x-03393.warc.gz	5529078778	download job
data.worldpop.org-inf-20240515-011446-esx2x-03393.warc.os.cdx.gz	1074	download
iycfimagebank.org-inf-20240804-131317-g2dy8-00004.warc.gz	5380373668	download job
iycfimagebank.org-inf-20240804-131317-g2dy8-00004.warc.os.cdx.gz	313709	download
kreis-siegen-wittgenstein.die-basis.nrw-inf-20240804-152503-d5302-00000.warc.gz	1114501836	download job
kreis-siegen-wittgenstein.die-basis.nrw-inf-20240804-152503-d5302-00000.warc.os.cdx.gz	478091	download
kreis-siegen-wittgenstein.die-basis.nrw-inf-20240804-152503-d5302-meta.warc.gz	308459	download job
kreis-siegen-wittgenstein.die-basis.nrw-inf-20240804-152503-d5302-meta.warc.os.cdx.gz	47	download
kreis-siegen-wittgenstein.die-basis.nrw-inf-20240804-152503-d5302.json	267	download job
kreis-viersen.die-basis.nrw-inf-20240804-153524-4ljho-00000.warc.gz	1029721669	download job
kreis-viersen.die-basis.nrw-inf-20240804-153524-4ljho-00000.warc.os.cdx.gz	408183	download
kreis-viersen.die-basis.nrw-inf-20240804-153524-4ljho-meta.warc.gz	258687	download job
kreis-viersen.die-basis.nrw-inf-20240804-153524-4ljho-meta.warc.os.cdx.gz	47	download
kreis-viersen.die-basis.nrw-inf-20240804-153524-4ljho.json	255	download job
leverkusen.die-basis.nrw-inf-20240804-154543-edlk7-00000.warc.gz	374771110	download job
leverkusen.die-basis.nrw-inf-20240804-154543-edlk7-00000.warc.os.cdx.gz	232084	download
leverkusen.die-basis.nrw-inf-20240804-154543-edlk7-meta.warc.gz	154903	download job
leverkusen.die-basis.nrw-inf-20240804-154543-edlk7-meta.warc.os.cdx.gz	47	download
leverkusen.die-basis.nrw-inf-20240804-154543-edlk7.json	252	download job
license.hashicorp.com-inf-20240424-223809-8765g-02162.warc.gz	7764874003	download job
license.hashicorp.com-inf-20240424-223809-8765g-02162.warc.os.cdx.gz	469	download
lists.pld-linux.org-inf-20240803-082014-6ra6e-00030.warc.gz	5410222450	download job
lists.pld-linux.org-inf-20240803-082014-6ra6e-00030.warc.os.cdx.gz	163093	download
muelheim-adr.die-basis.nrw-inf-20240804-155401-dpdkg-00000.warc.gz	305167481	download job
muelheim-adr.die-basis.nrw-inf-20240804-155401-dpdkg-00000.warc.os.cdx.gz	238515	download
muelheim-adr.die-basis.nrw-inf-20240804-155401-dpdkg-meta.warc.gz	149357	download job
muelheim-adr.die-basis.nrw-inf-20240804-155401-dpdkg-meta.warc.os.cdx.gz	47	download
muelheim-adr.die-basis.nrw-inf-20240804-155401-dpdkg.json	254	download job
muenster.die-basis.nrw-inf-20240804-155759-9m8wc-00000.warc.gz	5148666	download job
muenster.die-basis.nrw-inf-20240804-155759-9m8wc-00000.warc.os.cdx.gz	56699	download
muenster.die-basis.nrw-inf-20240804-155759-9m8wc-meta.warc.gz	41572	download job
muenster.die-basis.nrw-inf-20240804-155759-9m8wc-meta.warc.os.cdx.gz	47	download
muenster.die-basis.nrw-inf-20240804-155759-9m8wc.json	250	download job
new.twit.tv-inf-20240714-003218-71uhe-02018.warc.gz	5870563255	download job
new.twit.tv-inf-20240714-003218-71uhe-02018.warc.os.cdx.gz	6043	download
new.twit.tv-inf-20240714-003218-71uhe-02019.warc.gz	5941368880	download job
new.twit.tv-inf-20240714-003218-71uhe-02019.warc.os.cdx.gz	8846	download
nsportal.ru-inf-20230714-165720-3lzb3-01026.warc.gz	5368745316	download job
nsportal.ru-inf-20230714-165720-3lzb3-01026.warc.os.cdx.gz	5584176	download
oberhausen.die-basis.nrw-inf-20240804-160044-868t4-00000.warc.gz	17909612	download job
oberhausen.die-basis.nrw-inf-20240804-160044-868t4-00000.warc.os.cdx.gz	11482	download
oberhausen.die-basis.nrw-inf-20240804-160044-868t4-meta.warc.gz	10601	download job
oberhausen.die-basis.nrw-inf-20240804-160044-868t4-meta.warc.os.cdx.gz	47	download
oberhausen.die-basis.nrw-inf-20240804-160044-868t4.json	252	download job
onewelt.eu-inf-20240728-161248-17pcg-00022.warc.gz	5368935799	download job
onewelt.eu-inf-20240728-161248-17pcg-00022.warc.os.cdx.gz	6786007	download
paderborn.die-basis.nrw-inf-20240804-160448-6xqdq-00000.warc.gz	477565	download job
paderborn.die-basis.nrw-inf-20240804-160448-6xqdq-00000.warc.os.cdx.gz	3113	download
paderborn.die-basis.nrw-inf-20240804-160448-6xqdq-meta.warc.gz	5176	download job
paderborn.die-basis.nrw-inf-20240804-160448-6xqdq-meta.warc.os.cdx.gz	47	download
paderborn.die-basis.nrw-inf-20240804-160448-6xqdq.json	251	download job
rbk.die-basis.nrw-inf-20240804-160540-2ne09-00000.warc.gz	315110218	download job
rbk.die-basis.nrw-inf-20240804-160540-2ne09-00000.warc.os.cdx.gz	243379	download
rbk.die-basis.nrw-inf-20240804-160540-2ne09-meta.warc.gz	150417	download job
rbk.die-basis.nrw-inf-20240804-160540-2ne09-meta.warc.os.cdx.gz	47	download
rbk.die-basis.nrw-inf-20240804-160540-2ne09.json	245	download job
remscheid.die-basis.nrw-inf-20240804-161154-c87q7-00000.warc.gz	27281510	download job
remscheid.die-basis.nrw-inf-20240804-161154-c87q7-00000.warc.os.cdx.gz	5500	download
remscheid.die-basis.nrw-inf-20240804-161154-c87q7-meta.warc.gz	6719	download job
remscheid.die-basis.nrw-inf-20240804-161154-c87q7-meta.warc.os.cdx.gz	47	download
remscheid.die-basis.nrw-inf-20240804-161154-c87q7.json	251	download job
rhein-bergischer-kreis.die-basis.nrw-inf-20240804-161616-4beol-00000.warc.gz	480015	download job
rhein-bergischer-kreis.die-basis.nrw-inf-20240804-161616-4beol-00000.warc.os.cdx.gz	3139	download
rhein-bergischer-kreis.die-basis.nrw-inf-20240804-161616-4beol-meta.warc.gz	5259	download job
rhein-bergischer-kreis.die-basis.nrw-inf-20240804-161616-4beol-meta.warc.os.cdx.gz	47	download
rhein-bergischer-kreis.die-basis.nrw-inf-20240804-161616-4beol.json	264	download job
spaceweather.izmiran.ru-inf-20240804-152525-759vu-00000.warc.gz	5370064219	download job
spaceweather.izmiran.ru-inf-20240804-152525-759vu-00000.warc.os.cdx.gz	520440	download
twit.tv-inf-20240714-000325-5hbsl-01973.warc.gz	7256898543	download job
twit.tv-inf-20240714-000325-5hbsl-01973.warc.os.cdx.gz	10494	download
twit.tv-inf-20240714-000325-5hbsl-01974.warc.gz	5515697505	download job
twit.tv-inf-20240714-000325-5hbsl-01974.warc.os.cdx.gz	11875	download
twit.tv-inf-20240714-000325-5hbsl-01975.warc.gz	7066958539	download job
twit.tv-inf-20240714-000325-5hbsl-01975.warc.os.cdx.gz	8219	download
urls-transfer.archivete.am-www.rtvs.sk_json_audio5f.json_urls_through_500k.txt-shallow-20240727-044118-a45qu-00223.warc.gz	5382643463	download job
urls-transfer.archivete.am-www.rtvs.sk_json_audio5f.json_urls_through_500k.txt-shallow-20240727-044118-a45qu-00223.warc.os.cdx.gz	24695	download
www.atomseek.com-inf-20240203-212558-8gi8p-00616.warc.gz	5369618866	download job
www.atomseek.com-inf-20240203-212558-8gi8p-00616.warc.os.cdx.gz	2090008	download
www.derstrudel.org-inf-20240804-161503-8k4x0-00000.warc.gz	8006871	download job
www.derstrudel.org-inf-20240804-161503-8k4x0-00000.warc.os.cdx.gz	5731	download
www.derstrudel.org-inf-20240804-161503-8k4x0-meta.warc.gz	6956	download job
www.derstrudel.org-inf-20240804-161503-8k4x0-meta.warc.os.cdx.gz	47	download
www.derstrudel.org-inf-20240804-161503-8k4x0.json	246	download job
www.flickr.com-inf-20240804-154749-7sa2y-00000.warc.gz	771930505	download job
www.flickr.com-inf-20240804-154749-7sa2y-00000.warc.os.cdx.gz	713713	download
www.flickr.com-inf-20240804-154749-7sa2y-meta.warc.gz	368995	download job
www.flickr.com-inf-20240804-154749-7sa2y-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20240804-154749-7sa2y.json	274	download job
www.flickr.com-inf-20240804-154752-4anub-00000.warc.gz	5380551805	download job
www.flickr.com-inf-20240804-154752-4anub-00000.warc.os.cdx.gz	301429	download
www.frontiersin.org-inf-20240117-203250-6tu94-01303.warc.gz	5368993985	download job
www.frontiersin.org-inf-20240117-203250-6tu94-01303.warc.os.cdx.gz	2576545	download
www.keysight.com-inf-20240711-052449-9325w-00147.warc.gz	5371383294	download job
www.keysight.com-inf-20240711-052449-9325w-00147.warc.os.cdx.gz	228076	download
www.replaymag.com-inf-20240802-195758-1npct-00021.warc.gz	5374799911	download job
www.replaymag.com-inf-20240802-195758-1npct-00021.warc.os.cdx.gz	1645667	download