Item archiveteam_archivebot_go_20260410054747_fd07fd22

Filename	Size
archiveteam_archivebot_go_20260410054747_fd07fd22.cdx.gz	2332442	download
archiveteam_archivebot_go_20260410054747_fd07fd22.cdx.idx	2362	download
archiveteam_archivebot_go_20260410054747_fd07fd22_files.xml	0	download
archiveteam_archivebot_go_20260410054747_fd07fd22_meta.sqlite	217088	download
archiveteam_archivebot_go_20260410054747_fd07fd22_meta.xml	1046	download
assets.philzcoffee.com-inf-20260410-053158-3edg7-00000.warc.gz	7771	download job
assets.philzcoffee.com-inf-20260410-053158-3edg7-00000.warc.os.cdx.gz	345	download
assets.philzcoffee.com-inf-20260410-053158-3edg7-meta.warc.gz	3578	download job
assets.philzcoffee.com-inf-20260410-053158-3edg7-meta.warc.os.cdx.gz	47	download
assets.philzcoffee.com-inf-20260410-053158-3edg7.json	253	download job
barmiriam.com-inf-20260410-051329-dhuns.json	244	download job
budapestsummit.mcc.hu-inf-20260410-032934-ar8ci-meta.warc.gz	97591	download job
budapestsummit.mcc.hu-inf-20260410-032934-ar8ci-meta.warc.os.cdx.gz	47	download
budapestsummit.mcc.hu-inf-20260410-032934-ar8ci.json	251	download job
cms.freemanspogli.com-inf-20260410-053314-7czyk-00000.warc.gz	889284217	download job
cms.freemanspogli.com-inf-20260410-053314-7czyk-00000.warc.os.cdx.gz	121259	download
cms.freemanspogli.com-inf-20260410-053314-7czyk-meta.warc.gz	86630	download job
cms.freemanspogli.com-inf-20260410-053314-7czyk-meta.warc.os.cdx.gz	47	download
cms.freemanspogli.com-inf-20260410-053314-7czyk.json	252	download job
corporate.arcelormittal.com-inf-20260410-054409-4w40v-00000.warc.gz	13877	download job
corporate.arcelormittal.com-inf-20260410-054409-4w40v-00000.warc.os.cdx.gz	342	download
corporate.arcelormittal.com-inf-20260410-054409-4w40v-meta.warc.gz	3526	download job
corporate.arcelormittal.com-inf-20260410-054409-4w40v-meta.warc.os.cdx.gz	47	download
corporate.arcelormittal.com-inf-20260410-054409-4w40v.json	258	download job
corporate.arcelormittal.com-inf-20260410-054628-4w40v-00000.warc.gz	9275	download job
corporate.arcelormittal.com-inf-20260410-054628-4w40v-00000.warc.os.cdx.gz	340	download
corporate.arcelormittal.com-inf-20260410-054628-4w40v-meta.warc.gz	3414	download job
corporate.arcelormittal.com-inf-20260410-054628-4w40v-meta.warc.os.cdx.gz	47	download
csn.cancer.org-inf-20260407-130734-3k5td-00013.warc.gz	5368747458	download job
csn.cancer.org-inf-20260407-130734-3k5td-00013.warc.os.cdx.gz	2284316	download
ddr.densho.org-inf-20260328-213558-5eckx-00352.warc.gz	5416793098	download job
dsigateway.philzcoffee.com-inf-20260410-053132-ehc66-00000.warc.gz	2487	download job
dsigateway.philzcoffee.com-inf-20260410-053132-ehc66-meta.warc.gz	3631	download job
dsigateway.philzcoffee.com-inf-20260410-053132-ehc66.json	257	download job
focus-pt.com-inf-20260410-052239-6aid7-00000.warc.gz	1795279	download job
focus-pt.com-inf-20260410-052239-6aid7-meta.warc.gz	7359	download job
focus-pt.com-inf-20260410-052239-6aid7.json	243	download job
foto.patriarchia.ru-inf-20260406-025907-d1vgb-00133.warc.gz	5384897895	download job
foto.patriarchia.ru-inf-20260406-025907-d1vgb-00134.warc.gz	5391943321	download job
globalnews.ca-inf-20250821-223546-ejnq1-03077.warc.gz	5437189639	download job
gopher.viste.fr-inf-20260410-054605-4h4e3-00000.warc.gz	6127	download job
gopher.viste.fr-inf-20260410-054605-4h4e3-meta.warc.gz	3397	download job
gopher.viste.fr-inf-20260410-054605-4h4e3.json	240	download job
hotnews.ro-inf-20260126-105436-8in5a-00704.warc.gz	6104781856	download job
knowledge.breatheforchange.com-inf-20260410-045046-axyt8-00000.warc.gz	1646650267	download job
knowledge.breatheforchange.com-inf-20260410-045046-axyt8-meta.warc.gz	616115	download job
knowledge.breatheforchange.com-inf-20260410-045046-axyt8.json	261	download job
lemadforumlibre.free.fr-inf-20260409-232557-bu4g5-00001.warc.gz	5376956694	download job
liveingreatness.com-inf-20260410-050413-a7c1r-00000.warc.gz	1357713444	download job
liveingreatness.com-inf-20260410-050413-a7c1r-meta.warc.gz	278283	download job
liveingreatness.com-inf-20260410-050413-a7c1r.json	250	download job
physiquechimie.forum.free.fr-inf-20260409-214909-5u283-00001.warc.gz	5368845355	download job
qnotescarolinas.com-inf-20260406-005409-7cvy5-00043.warc.gz	5368857229	download job
socioforum.su-inf-20260228-195352-axh5n-00055.warc.gz	5509007209	download job
staging.hillside.net-inf-20260410-045747-dpux6-00000.warc.gz	188501341	download job
staging.hillside.net-inf-20260410-045747-dpux6-meta.warc.gz	84301	download job
staging.hillside.net-inf-20260410-045747-dpux6.json	251	download job
store.philzcoffee.com-inf-20260410-053114-a75f1-00000.warc.gz	18436241	download job
store.philzcoffee.com-inf-20260410-053114-a75f1-meta.warc.gz	46122	download job
store.philzcoffee.com-inf-20260410-053114-a75f1.json	252	download job
svn.mateusz.fr-inf-20260410-054507-a5kal-00000.warc.gz	6127	download job
svn.mateusz.fr-inf-20260410-054507-a5kal-meta.warc.gz	3466	download job
svn.mateusz.fr-inf-20260410-054507-a5kal.json	239	download job
tdosea.com-inf-20260410-051345-cpkid-00000.warc.gz	4828424	download job
tdosea.com-inf-20260410-051345-cpkid-meta.warc.gz	9507	download job
tdosea.com-inf-20260410-051345-cpkid.json	241	download job
urls-nue2.nulldata.foo-github.com_NVIDIA-RTX-20260410015507-links.txt-shallow-20260410-020016-6f1zs-00004.warc.gz	2453447460	download job
urls-nue2.nulldata.foo-github.com_NVIDIA-RTX-20260410015507-links.txt-shallow-20260410-020016-6f1zs-meta.warc.gz	273346	download job
urls-nue2.nulldata.foo-github.com_NVIDIA-RTX-20260410015507-links.txt-shallow-20260410-020016-6f1zs-urls.txt	139373	download
urls-nue2.nulldata.foo-github.com_NVIDIA-RTX-20260410015507-links.txt-shallow-20260410-020016-6f1zs.json	386	download job
urls-nue2.nulldata.foo-github.com_cirruslabs-20260409030036-links.txt-shallow-20260409-030327-14a70-00053.warc.gz	5382961897	download job
urls-transfer.archivete.am-counterextremism.com_subdomains.txt-inf-20260409-105821-1ziun-00016.warc.gz	5564308554	download job
urls-transfer.archivete.am-www.hcipatterns.org.txt-inf-20260410-050709-bg0tp-00000.warc.gz	111713254	download job
urls-transfer.archivete.am-www.hcipatterns.org.txt-inf-20260410-050709-bg0tp-meta.warc.gz	104120	download job
urls-transfer.archivete.am-www.hcipatterns.org.txt-inf-20260410-050709-bg0tp-urls.txt	54	download
urls-transfer.archivete.am-www.hcipatterns.org.txt-inf-20260410-050709-bg0tp.json	338	download job
urls-transfer.archivete.am-www.palantirfoundation.org.txt-inf-20260409-193736-8ie38-00002.warc.gz	5377374864	download job
urls-transfer.archivete.am-www.sikhnet.com.txt-inf-20260404-062338-2mo2a-00424.warc.gz	5375177584	download job
usgovernmentofficial.tumblr.com-inf-20251222-061339-b1lo1-02292.warc.gz	5374859381	download job
windward.ai-inf-20260409-190919-enn70-00005.warc.gz	5369055801	download job
worker.philzcoffee.com-inf-20260410-053058-1kk9l-00000.warc.gz	7845	download job
worker.philzcoffee.com-inf-20260410-053058-1kk9l-meta.warc.gz	3601	download job
worker.philzcoffee.com-inf-20260410-053058-1kk9l.json	253	download job
www.arcelormittal.com-inf-20260410-054311-90426-00000.warc.gz	14373	download job
www.arcelormittal.com-inf-20260410-054311-90426-meta.warc.gz	3495	download job
www.arcelormittal.com-inf-20260410-054311-90426.json	252	download job
www.barmiriam.com-inf-20260410-051341-esyby-00000.warc.gz	76254120	download job
www.barmiriam.com-inf-20260410-051341-esyby-meta.warc.gz	56869	download job
www.barmiriam.com-inf-20260410-051341-esyby.json	248	download job
www.idahofamilyphysicians.org-inf-20260410-051924-cl0df-00000.warc.gz	6861044	download job
www.idahofamilyphysicians.org-inf-20260410-051924-cl0df-meta.warc.gz	9898	download job
www.idahofamilyphysicians.org-inf-20260410-051924-cl0df.json	260	download job
www.ilna.ir-inf-20260130-213111-e3fs1-00194.warc.gz	5431250090	download job
www.palantir.com-inf-20260409-180335-6ey6q-00003.warc.gz	5410230843	download job
www.philzcoffee.com-inf-20260410-052811-efnwf-00000.warc.gz	18471444	download job
www.philzcoffee.com-inf-20260410-052811-efnwf-meta.warc.gz	46506	download job
www.philzcoffee.com-inf-20260410-052811-efnwf.json	250	download job
www.seattlemet.com-inf-20260406-221417-1r9ds-00029.warc.gz	5447699322	download job
www.tabnak.ir-inf-20260130-213526-8r7zi-00505.warc.gz	5389745229	download job
www.tdosea.com-inf-20260410-051426-3dpwr-00000.warc.gz	146567689	download job
www.tdosea.com-inf-20260410-051426-3dpwr-meta.warc.gz	66842	download job
www.tdosea.com-inf-20260410-051426-3dpwr.json	245	download job
www.womenpeacesecurity.org-inf-20260410-014515-32ceg-00000.warc.gz	5368870792	download job