Item archiveteam_archivebot_go_20250401043136_535a8719

Filename	Size
aprilfoolsdayontheweb.com-shallow-20250401-041044-6fgdc-00000.warc.gz	7741	download job
aprilfoolsdayontheweb.com-shallow-20250401-041044-6fgdc-00000.warc.os.cdx.gz	272	download
aprilfoolsdayontheweb.com-shallow-20250401-041044-6fgdc-meta.warc.gz	3392	download job
aprilfoolsdayontheweb.com-shallow-20250401-041044-6fgdc-meta.warc.os.cdx.gz	47	download
aprilfoolsdayontheweb.com-shallow-20250401-041044-6fgdc.json	270	download job
archiveteam_archivebot_go_20250401043136_535a8719.cdx.gz	272	download
archiveteam_archivebot_go_20250401043136_535a8719.cdx.idx	64	download
archiveteam_archivebot_go_20250401043136_535a8719_files.xml	0	download
archiveteam_archivebot_go_20250401043136_535a8719_meta.sqlite	28672	download
archiveteam_archivebot_go_20250401043136_535a8719_meta.xml	1042	download
cirrus.ucsd.edu-inf-20250204-222623-178n0-05076.warc.gz	5576568904	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-05076.warc.os.cdx.gz	582	download
cirrus.ucsd.edu-inf-20250204-222623-178n0-05077.warc.gz	6992750802	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-05077.warc.os.cdx.gz	727	download
code.groupe-genes.fr-shallow-20250401-042319-9fiep-00000.warc.gz	698548	download job
code.groupe-genes.fr-shallow-20250401-042319-9fiep-00000.warc.os.cdx.gz	4012	download
code.groupe-genes.fr-shallow-20250401-042319-9fiep-meta.warc.gz	7320	download job
code.groupe-genes.fr-shallow-20250401-042319-9fiep-meta.warc.os.cdx.gz	47	download
code.groupe-genes.fr-shallow-20250401-042319-9fiep.json	263	download job
code.groupe-genes.fr-shallow-20250401-042328-3umnd-00000.warc.gz	696348	download job
code.groupe-genes.fr-shallow-20250401-042328-3umnd-00000.warc.os.cdx.gz	4014	download
code.groupe-genes.fr-shallow-20250401-042328-3umnd-meta.warc.gz	7261	download job
code.groupe-genes.fr-shallow-20250401-042328-3umnd-meta.warc.os.cdx.gz	47	download
code.groupe-genes.fr-shallow-20250401-042328-3umnd.json	250	download job
digitallibrary.un.org-inf-20250216-081652-th9ph-00100.warc.gz	5392884935	download job
digitallibrary.un.org-inf-20250216-081652-th9ph-00100.warc.os.cdx.gz	635869	download
flibusta.is-inf-20240924-060021-7gpwv-01239.warc.gz	5386986568	download job
flibusta.is-inf-20240924-060021-7gpwv-01239.warc.os.cdx.gz	1639363	download
ginniemae.gov-inf-20250401-040758-574hy-00000.warc.gz	8272389	download job
ginniemae.gov-inf-20250401-040758-574hy-00000.warc.os.cdx.gz	22945	download
ginniemae.gov-inf-20250401-040758-574hy-meta.warc.gz	19038	download job
ginniemae.gov-inf-20250401-040758-574hy-meta.warc.os.cdx.gz	47	download
ginniemae.gov-inf-20250401-040758-574hy.json	244	download job
git.wut.ee-shallow-20250401-041830-d1i16-00000.warc.gz	608998	download job
git.wut.ee-shallow-20250401-041830-d1i16-00000.warc.os.cdx.gz	3904	download
git.wut.ee-shallow-20250401-041830-d1i16-meta.warc.gz	7146	download job
git.wut.ee-shallow-20250401-041830-d1i16-meta.warc.os.cdx.gz	47	download
git.wut.ee-shallow-20250401-041830-d1i16.json	253	download job
git.wut.ee-shallow-20250401-041901-cn2ku-00000.warc.gz	611572	download job
git.wut.ee-shallow-20250401-041901-cn2ku-00000.warc.os.cdx.gz	4019	download
git.wut.ee-shallow-20250401-041901-cn2ku-meta.warc.gz	7177	download job
git.wut.ee-shallow-20250401-041901-cn2ku-meta.warc.os.cdx.gz	47	download
git.wut.ee-shallow-20250401-041901-cn2ku.json	240	download job
groupe-genes.fr-shallow-20250401-042356-2b8p4-00000.warc.gz	1288571	download job
groupe-genes.fr-shallow-20250401-042356-2b8p4-00000.warc.os.cdx.gz	4571	download
groupe-genes.fr-shallow-20250401-042356-2b8p4-meta.warc.gz	5858	download job
groupe-genes.fr-shallow-20250401-042356-2b8p4-meta.warc.os.cdx.gz	47	download
groupe-genes.fr-shallow-20250401-042356-2b8p4.json	245	download job
groupe-genes.fr-shallow-20250401-042425-4i8a7-00000.warc.gz	2983163	download job
groupe-genes.fr-shallow-20250401-042425-4i8a7-00000.warc.os.cdx.gz	5166	download
groupe-genes.fr-shallow-20250401-042425-4i8a7-meta.warc.gz	6204	download job
groupe-genes.fr-shallow-20250401-042425-4i8a7-meta.warc.os.cdx.gz	47	download
groupe-genes.fr-shallow-20250401-042425-4i8a7.json	256	download job
groupe-genes.fr-shallow-20250401-042432-einfj-00000.warc.gz	1286566	download job
groupe-genes.fr-shallow-20250401-042432-einfj-00000.warc.os.cdx.gz	4593	download
groupe-genes.fr-shallow-20250401-042432-einfj-meta.warc.gz	5891	download job
groupe-genes.fr-shallow-20250401-042432-einfj-meta.warc.os.cdx.gz	47	download
groupe-genes.fr-shallow-20250401-042432-einfj.json	265	download job
home.web.cern.ch-shallow-20250401-041422-br5g0-00000.warc.gz	3464670	download job
home.web.cern.ch-shallow-20250401-041422-br5g0-00000.warc.os.cdx.gz	11215	download
home.web.cern.ch-shallow-20250401-041422-br5g0-meta.warc.gz	9926	download job
home.web.cern.ch-shallow-20250401-041422-br5g0-meta.warc.os.cdx.gz	47	download
home.web.cern.ch-shallow-20250401-041422-br5g0.json	358	download job
indico.cern.ch-inf-20250401-041451-2z3jt-00000.warc.gz	47732646	download job
indico.cern.ch-inf-20250401-041451-2z3jt-00000.warc.os.cdx.gz	54539	download
indico.cern.ch-inf-20250401-041451-2z3jt-meta.warc.gz	36732	download job
indico.cern.ch-inf-20250401-041451-2z3jt-meta.warc.os.cdx.gz	47	download
indico.cern.ch-inf-20250401-041451-2z3jt.json	270	download job
ipsw.me-inf-20241201-145231-9lrev-06617.warc.gz	6333560431	download job
ipsw.me-inf-20241201-145231-9lrev-06617.warc.os.cdx.gz	698	download
jdeploy.pasteur-lille.fr-shallow-20250401-042216-7r4qa-00000.warc.gz	2386	download job
jdeploy.pasteur-lille.fr-shallow-20250401-042216-7r4qa-00000.warc.os.cdx.gz	47	download
jdeploy.pasteur-lille.fr-shallow-20250401-042216-7r4qa-meta.warc.gz	3442	download job
jdeploy.pasteur-lille.fr-shallow-20250401-042216-7r4qa-meta.warc.os.cdx.gz	47	download
jdeploy.pasteur-lille.fr-shallow-20250401-042216-7r4qa.json	253	download job
jurassictime.wixsite.com-inf-20250401-034157-cul15-00000.warc.gz	5411236126	download job
jurassictime.wixsite.com-inf-20250401-034157-cul15-00000.warc.os.cdx.gz	720284	download
michiganross.umich.edu-inf-20250331-110945-6gmxi-00004.warc.gz	5448816450	download job
michiganross.umich.edu-inf-20250331-110945-6gmxi-00004.warc.os.cdx.gz	345536	download
osseu2023.sched.com-inf-20250331-114759-9vv31-00000.warc.gz	1975719472	download job
osseu2023.sched.com-inf-20250331-114759-9vv31-00000.warc.os.cdx.gz	1871433	download
osseu2023.sched.com-inf-20250331-114759-9vv31-meta.warc.gz	1474969	download job
osseu2023.sched.com-inf-20250331-114759-9vv31-meta.warc.os.cdx.gz	47	download
osseu2023.sched.com-inf-20250331-114759-9vv31.json	247	download job
panamabiota.org-inf-20250328-200457-6r9ab-00040.warc.gz	5369566887	download job
panamabiota.org-inf-20250328-200457-6r9ab-00040.warc.os.cdx.gz	724404	download
photocontest.smithsonianmag.com-inf-20250328-131056-9s5ca-00290.warc.gz	5369725720	download job
photocontest.smithsonianmag.com-inf-20250328-131056-9s5ca-00290.warc.os.cdx.gz	128207	download
socds.huduser.gov-inf-20250401-040327-b6ob2-00000.warc.gz	265409255	download job
socds.huduser.gov-inf-20250401-040327-b6ob2-00000.warc.os.cdx.gz	188112	download
socds.huduser.gov-inf-20250401-040327-b6ob2-meta.warc.gz	105973	download job
socds.huduser.gov-inf-20250401-040327-b6ob2-meta.warc.os.cdx.gz	47	download
socds.huduser.gov-inf-20250401-040327-b6ob2.json	255	download job
transfer.archivete.am-shallow-20250401-042206-ybi5u-00000.warc.gz	84795	download job
transfer.archivete.am-shallow-20250401-042206-ybi5u-00000.warc.os.cdx.gz	243	download
transfer.archivete.am-shallow-20250401-042206-ybi5u-meta.warc.gz	3502	download job
transfer.archivete.am-shallow-20250401-042206-ybi5u-meta.warc.os.cdx.gz	47	download
transfer.archivete.am-shallow-20250401-042206-ybi5u.json	294	download job
urls-transfer.archivete.am-plala.jp_seed_urls.txt-inf-20250330-064232-1z311-00022.warc.gz	5440123639	download job
urls-transfer.archivete.am-plala.jp_seed_urls.txt-inf-20250330-064232-1z311-00022.warc.os.cdx.gz	36872	download
urls-transfer.archivete.am-www.gsa.gov_origin-www.gsa.gov_seed_urls.txt-inf-20250331-181743-8o21j-00005.warc.gz	5444858542	download job
urls-transfer.archivete.am-www.gsa.gov_origin-www.gsa.gov_seed_urls.txt-inf-20250331-181743-8o21j-00005.warc.os.cdx.gz	1632981	download
urls-transfer.archivete.am-www.radio4all.net-unlinked-contributor-outlinks.txt-shallow-20250401-034119-264bk-00000.warc.gz	5396357282	download job
urls-transfer.archivete.am-www.radio4all.net-unlinked-contributor-outlinks.txt-shallow-20250401-034119-264bk-00000.warc.os.cdx.gz	728365	download
wut.ee-inf-20250401-041817-cxpjz-00000.warc.gz	5440608	download job
wut.ee-inf-20250401-041817-cxpjz-00000.warc.os.cdx.gz	14895	download
wut.ee-inf-20250401-041817-cxpjz-meta.warc.gz	11066	download job
wut.ee-inf-20250401-041817-cxpjz-meta.warc.os.cdx.gz	47	download
wut.ee-inf-20250401-041817-cxpjz.json	232	download job
www.centrepompidou.fr-inf-20250331-112126-b22je-00006.warc.gz	5474392744	download job
www.centrepompidou.fr-inf-20250331-112126-b22je-00006.warc.os.cdx.gz	403383	download
www.centrepompidou.fr-inf-20250331-112126-b22je-00007.warc.gz	5490887653	download job
www.centrepompidou.fr-inf-20250331-112126-b22je-00007.warc.os.cdx.gz	7414	download
www.gameinformer.com-inf-20250325-204828-42tjw-00033.warc.gz	5368716116	download job
www.gameinformer.com-inf-20250325-204828-42tjw-00033.warc.os.cdx.gz	3779044	download
www.jbs.org-inf-20250401-041545-3g1b2-00000.warc.gz	7615306	download job
www.jbs.org-inf-20250401-041545-3g1b2-00000.warc.os.cdx.gz	19764	download
www.jbs.org-inf-20250401-041545-3g1b2-meta.warc.gz	13821	download job
www.jbs.org-inf-20250401-041545-3g1b2-meta.warc.os.cdx.gz	47	download
www.jbs.org-inf-20250401-041545-3g1b2.json	242	download job
www.new.differencegames.com-inf-20250401-040735-9rufc-00000.warc.gz	204962475	download job
www.new.differencegames.com-inf-20250401-040735-9rufc-00000.warc.os.cdx.gz	238749	download
www.new.differencegames.com-inf-20250401-040735-9rufc-meta.warc.gz	164425	download job
www.new.differencegames.com-inf-20250401-040735-9rufc-meta.warc.os.cdx.gz	47	download
www.new.differencegames.com-inf-20250401-040735-9rufc.json	252	download job
www.ntt.com-inf-20250330-051935-292az-00007.warc.gz	2134221725	download job
www.ntt.com-inf-20250330-051935-292az-00007.warc.os.cdx.gz	784624	download
www.ntt.com-inf-20250330-051935-292az-meta.warc.gz	15979010	download job
www.ntt.com-inf-20250330-051935-292az-meta.warc.os.cdx.gz	47	download
www.ntt.com-inf-20250330-051935-292az.json	242	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-02244.warc.gz	5383077349	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-02244.warc.os.cdx.gz	527025	download
www.usmcu.edu-inf-20250331-184701-14gw3-00036.warc.gz	5527166766	download job
www.usmcu.edu-inf-20250331-184701-14gw3-00036.warc.os.cdx.gz	4246	download
www.voaafrica.com-inf-20250318-081912-1fye9-01514.warc.gz	5377867784	download job
www.voaafrica.com-inf-20250318-081912-1fye9-01514.warc.os.cdx.gz	59317	download
www.voadeewanews.com-inf-20250318-081603-6w6oc-00832.warc.gz	5586955231	download job
www.voadeewanews.com-inf-20250318-081603-6w6oc-00832.warc.os.cdx.gz	4216	download
www.voanews.com-inf-20250317-033633-biyl5-00923.warc.gz	5550223332	download job
www.voanews.com-inf-20250317-033633-biyl5-00923.warc.os.cdx.gz	37822	download
www.voanews.com-inf-20250317-033633-biyl5-00924.warc.gz	5949589866	download job
www.voanews.com-inf-20250317-033633-biyl5-00924.warc.os.cdx.gz	19045	download
yalis.fr-shallow-20250401-041642-4m4w0-00000.warc.gz	5959	download job
yalis.fr-shallow-20250401-041642-4m4w0-00000.warc.os.cdx.gz	228	download
yalis.fr-shallow-20250401-041642-4m4w0-meta.warc.gz	3384	download job
yalis.fr-shallow-20250401-041642-4m4w0-meta.warc.os.cdx.gz	47	download
yalis.fr-shallow-20250401-041642-4m4w0.json	242	download job
yalis.fr-shallow-20250401-041736-bd8ib-00000.warc.gz	6228	download job
yalis.fr-shallow-20250401-041736-bd8ib-00000.warc.os.cdx.gz	311	download
yalis.fr-shallow-20250401-041736-bd8ib-meta.warc.gz	3444	download job
yalis.fr-shallow-20250401-041736-bd8ib-meta.warc.os.cdx.gz	47	download
yalis.fr-shallow-20250401-041736-bd8ib.json	238	download job