Item archiveteam_archivebot_go_20240122075601_6b795128

Filename	Size
350brooklyn.org-inf-20240122-025043-8x23u-00004.warc.gz	4309341051	download job
350brooklyn.org-inf-20240122-025043-8x23u-00004.warc.os.cdx.gz	122306	download
350brooklyn.org-inf-20240122-025043-8x23u-meta.warc.gz	3601255	download job
350brooklyn.org-inf-20240122-025043-8x23u-meta.warc.os.cdx.gz	47	download
350brooklyn.org-inf-20240122-025043-8x23u.json	246	download job
archiveteam_archivebot_go_20240122075601_6b795128.cdx.gz	32688349	download
archiveteam_archivebot_go_20240122075601_6b795128.cdx.idx	38131	download
archiveteam_archivebot_go_20240122075601_6b795128_files.xml	0	download
archiveteam_archivebot_go_20240122075601_6b795128_meta.sqlite	180224	download
archiveteam_archivebot_go_20240122075601_6b795128_meta.xml	996	download
au.shein.com-inf-20240108-004927-dusb5-00122.warc.gz	5369014845	download job
au.shein.com-inf-20240108-004927-dusb5-00122.warc.os.cdx.gz	2332856	download
dc.lib.jjay.cuny.edu-inf-20240121-190530-4uu1m-00007.warc.gz	5433931895	download job
dc.lib.jjay.cuny.edu-inf-20240121-190530-4uu1m-00007.warc.os.cdx.gz	2576585	download
erasmus-stiftung.de-inf-20240122-065309-itgqq-00000.warc.gz	494384282	download job
erasmus-stiftung.de-inf-20240122-065309-itgqq-00000.warc.os.cdx.gz	647003	download
erasmus-stiftung.de-inf-20240122-065309-itgqq-meta.warc.gz	386999	download job
erasmus-stiftung.de-inf-20240122-065309-itgqq-meta.warc.os.cdx.gz	47	download
erasmus-stiftung.de-inf-20240122-065309-itgqq.json	246	download job
gata.org-inf-20240121-152251-awskh-00011.warc.gz	5394667819	download job
gata.org-inf-20240121-152251-awskh-00011.warc.os.cdx.gz	519138	download
gfmc.online-inf-20240118-211655-2pdiw-00023.warc.gz	5370777092	download job
gfmc.online-inf-20240118-211655-2pdiw-00023.warc.os.cdx.gz	2063881	download
hg.osdn.net-shallow-20240122-072741-bd4nr-aborted-00000.warc.gz	6261	download job
hg.osdn.net-shallow-20240122-072741-bd4nr-aborted-00000.warc.os.cdx.gz	246	download
hg.osdn.net-shallow-20240122-072741-bd4nr-aborted-wpull.log.gz	821	download
hg.osdn.net-shallow-20240122-072741-bd4nr-aborted.json	249	download job
hg.osdn.net-shallow-20240122-072829-a809f-00000.warc.gz	44481	download job
hg.osdn.net-shallow-20240122-072829-a809f-00000.warc.os.cdx.gz	539	download
hg.osdn.net-shallow-20240122-072829-a809f-meta.warc.gz	3669	download job
hg.osdn.net-shallow-20240122-072829-a809f-meta.warc.os.cdx.gz	47	download
hg.osdn.net-shallow-20240122-072829-a809f.json	261	download job
hg.osdn.net-shallow-20240122-072902-6kgwv-00000.warc.gz	44110	download job
hg.osdn.net-shallow-20240122-072902-6kgwv-00000.warc.os.cdx.gz	541	download
hg.osdn.net-shallow-20240122-072902-6kgwv-meta.warc.gz	3728	download job
hg.osdn.net-shallow-20240122-072902-6kgwv-meta.warc.os.cdx.gz	47	download
hg.osdn.net-shallow-20240122-072902-6kgwv.json	254	download job
hg.osdn.net-shallow-20240122-072906-b2u7y-00000.warc.gz	43670	download job
hg.osdn.net-shallow-20240122-072906-b2u7y-00000.warc.os.cdx.gz	542	download
hg.osdn.net-shallow-20240122-072906-b2u7y-meta.warc.gz	3665	download job
hg.osdn.net-shallow-20240122-072906-b2u7y-meta.warc.os.cdx.gz	47	download
hg.osdn.net-shallow-20240122-072906-b2u7y.json	260	download job
juergenelsaesser.wordpress.com-inf-20240121-163558-c98pq-00024.warc.gz	5368947597	download job
juergenelsaesser.wordpress.com-inf-20240121-163558-c98pq-00024.warc.os.cdx.gz	900556	download
krautreporter.de-inf-20240120-111316-bu19q-00046.warc.gz	5369802384	download job
krautreporter.de-inf-20240120-111316-bu19q-00046.warc.os.cdx.gz	804906	download
nitter.vloup.ch-inf-20240122-032653-5ib59-00000.warc.gz	759762438	download job
nitter.vloup.ch-inf-20240122-032653-5ib59-00000.warc.os.cdx.gz	4144015	download
nitter.vloup.ch-inf-20240122-032653-5ib59-meta.warc.gz	2348438	download job
nitter.vloup.ch-inf-20240122-032653-5ib59-meta.warc.os.cdx.gz	47	download
nitter.vloup.ch-inf-20240122-032653-5ib59.json	256	download job
nitter.vloup.ch-inf-20240122-054536-cjbfy-00000.warc.gz	509168875	download job
nitter.vloup.ch-inf-20240122-054536-cjbfy-00000.warc.os.cdx.gz	2086414	download
nitter.vloup.ch-inf-20240122-054536-cjbfy-meta.warc.gz	1273500	download job
nitter.vloup.ch-inf-20240122-054536-cjbfy-meta.warc.os.cdx.gz	47	download
nitter.vloup.ch-inf-20240122-054536-cjbfy.json	262	download job
nitter.vloup.ch-inf-20240122-074355-2hs7z-00000.warc.gz	36539069	download job
nitter.vloup.ch-inf-20240122-074355-2hs7z-00000.warc.os.cdx.gz	108586	download
nitter.vloup.ch-inf-20240122-074355-2hs7z-meta.warc.gz	65054	download job
nitter.vloup.ch-inf-20240122-074355-2hs7z-meta.warc.os.cdx.gz	47	download
nitter.vloup.ch-inf-20240122-074355-2hs7z.json	257	download job
openscholarship.wustl.edu-inf-20240121-125839-d86ig-00012.warc.gz	12667643756	download job
openscholarship.wustl.edu-inf-20240121-125839-d86ig-00012.warc.os.cdx.gz	182677	download
pdf.defence.pk-inf-20231205-223022-7v1ux-00096.warc.gz	6205525530	download job
pdf.defence.pk-inf-20231205-223022-7v1ux-00096.warc.os.cdx.gz	4307603	download
report24.news-inf-20240120-112143-4wu6p-00061.warc.gz	5508613182	download job
report24.news-inf-20240120-112143-4wu6p-00061.warc.os.cdx.gz	46839	download
report24.news-inf-20240120-112143-4wu6p-00062.warc.gz	5386271518	download job
report24.news-inf-20240120-112143-4wu6p-00062.warc.os.cdx.gz	203144	download
rian.com.ua-inf-20240116-062825-2b69v-00008.warc.gz	5368713572	download job
rian.com.ua-inf-20240116-062825-2b69v-00008.warc.os.cdx.gz	6950556	download
secure.osdn.jp-shallow-20240122-073931-3nrtx-00000.warc.gz	5189	download job
secure.osdn.jp-shallow-20240122-073931-3nrtx-00000.warc.os.cdx.gz	270	download
secure.osdn.jp-shallow-20240122-073931-3nrtx-meta.warc.gz	3488	download job
secure.osdn.jp-shallow-20240122-073931-3nrtx-meta.warc.os.cdx.gz	47	download
secure.osdn.jp-shallow-20240122-073931-3nrtx.json	244	download job
static.frontiersin.org-inf-20240117-221556-dkqqp-00050.warc.gz	5368744174	download job
static.frontiersin.org-inf-20240117-221556-dkqqp-00050.warc.os.cdx.gz	2885146	download
transfer.archivete.am-shallow-20240122-071213-36qlg-00000.warc.gz	18061	download job
transfer.archivete.am-shallow-20240122-071213-36qlg-00000.warc.os.cdx.gz	247	download
transfer.archivete.am-shallow-20240122-071213-36qlg-meta.warc.gz	3503	download job
transfer.archivete.am-shallow-20240122-071213-36qlg-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20240122-071213-36qlg.json	282	download job
transfer.archivete.am-shallow-20240122-071530-b7n9k-00000.warc.gz	5756	download job
transfer.archivete.am-shallow-20240122-071530-b7n9k-00000.warc.os.cdx.gz	251	download
transfer.archivete.am-shallow-20240122-071530-b7n9k-meta.warc.gz	3494	download job
transfer.archivete.am-shallow-20240122-071530-b7n9k-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20240122-071530-b7n9k.json	284	download job
transfer.archivete.am-shallow-20240122-075213-30ch7-00000.warc.gz	8560	download job
transfer.archivete.am-shallow-20240122-075213-30ch7-00000.warc.os.cdx.gz	251	download
transfer.archivete.am-shallow-20240122-075213-30ch7-meta.warc.gz	3429	download job
transfer.archivete.am-shallow-20240122-075213-30ch7-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20240122-075213-30ch7.json	288	download job
urls-transfer.archivete.am-archive.mozilla.org_pub_firefox_tinderbox-builds_autoland-macosx64-debug_seed_urls_from_non_debug.txt-inf-20240108-202326-eo3kd-01502.warc.gz	5377404200	download job
urls-transfer.archivete.am-archive.mozilla.org_pub_firefox_tinderbox-builds_autoland-macosx64-debug_seed_urls_from_non_debug.txt-inf-20240108-202326-eo3kd-01502.warc.os.cdx.gz	1271	download
urls-transfer.archivete.am-archive.mozilla.org_pub_firefox_tinderbox-builds_autoland-macosx64-debug_seed_urls_from_non_debug.txt-inf-20240108-202326-eo3kd-01503.warc.gz	5878364305	download job
urls-transfer.archivete.am-archive.mozilla.org_pub_firefox_tinderbox-builds_autoland-macosx64-debug_seed_urls_from_non_debug.txt-inf-20240108-202326-eo3kd-01503.warc.os.cdx.gz	1247	download
urls-transfer.archivete.am-archive.mozilla.org_pub_firefox_tinderbox-builds_autoland-macosx64-debug_seed_urls_from_non_debug.txt-inf-20240108-202326-eo3kd-01504.warc.gz	5867772251	download job
urls-transfer.archivete.am-archive.mozilla.org_pub_firefox_tinderbox-builds_autoland-macosx64-debug_seed_urls_from_non_debug.txt-inf-20240108-202326-eo3kd-01504.warc.os.cdx.gz	1350	download
urls-transfer.archivete.am-hg.osdn.net-view-all-repo-urls.txt-shallow-20240122-065414-6nb1q-00000.warc.gz	57154619	download job
urls-transfer.archivete.am-hg.osdn.net-view-all-repo-urls.txt-shallow-20240122-065414-6nb1q-00000.warc.os.cdx.gz	153712	download
urls-transfer.archivete.am-hg.osdn.net-view-all-repo-urls.txt-shallow-20240122-065414-6nb1q-meta.warc.gz	71913	download job
urls-transfer.archivete.am-hg.osdn.net-view-all-repo-urls.txt-shallow-20240122-065414-6nb1q-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-hg.osdn.net-view-all-repo-urls.txt-shallow-20240122-065414-6nb1q-urls.txt	185691	download
urls-transfer.archivete.am-hg.osdn.net-view-all-repo-urls.txt-shallow-20240122-065414-6nb1q.json	359	download job
urls-transfer.archivete.am-images.pexels.com_photos_jpeg_0M_to_1M.txt-shallow-20240118-224642-47yo8-00070.warc.gz	5368849014	download job
urls-transfer.archivete.am-images.pexels.com_photos_jpeg_0M_to_1M.txt-shallow-20240118-224642-47yo8-00070.warc.os.cdx.gz	377580	download
vds-ev.de-inf-20240121-224630-98zg7-00008.warc.gz	5490330097	download job
vds-ev.de-inf-20240121-224630-98zg7-00008.warc.os.cdx.gz	821878	download
www.bioblogia.net-inf-20240121-044959-c66p8-00006.warc.gz	200701132	download job
www.bioblogia.net-inf-20240121-044959-c66p8-00006.warc.os.cdx.gz	360003	download
www.bioblogia.net-inf-20240121-044959-c66p8-meta.warc.gz	16004631	download job
www.bioblogia.net-inf-20240121-044959-c66p8-meta.warc.os.cdx.gz	47	download
www.bioblogia.net-inf-20240121-044959-c66p8.json	249	download job
www.goethe.de-inf-20231030-110227-23lnq-00364.warc.gz	4265506706	download job
www.goethe.de-inf-20231030-110227-23lnq-00364.warc.os.cdx.gz	683355	download
www.goethe.de-inf-20231030-110227-23lnq-meta.warc.gz	297121575	download job
www.goethe.de-inf-20231030-110227-23lnq-meta.warc.os.cdx.gz	47	download
www.goethe.de-inf-20231030-110227-23lnq.json	239	download job
www.thurnundtaxis.de-inf-20240122-065256-8lcfc-00000.warc.gz	442172962	download job
www.thurnundtaxis.de-inf-20240122-065256-8lcfc-00000.warc.os.cdx.gz	227108	download
www.thurnundtaxis.de-inf-20240122-065256-8lcfc-meta.warc.gz	134381	download job
www.thurnundtaxis.de-inf-20240122-065256-8lcfc-meta.warc.os.cdx.gz	47	download
www.thurnundtaxis.de-inf-20240122-065256-8lcfc.json	247	download job