Item archiveteam_archivebot_go_20250421004153_eb723d1d

Filename	Size
archiveteam_archivebot_go_20250421004153_eb723d1d.cdx.gz	1515282	download
archiveteam_archivebot_go_20250421004153_eb723d1d.cdx.idx	1498	download
archiveteam_archivebot_go_20250421004153_eb723d1d_files.xml	0	download
archiveteam_archivebot_go_20250421004153_eb723d1d_meta.sqlite	98304	download
archiveteam_archivebot_go_20250421004153_eb723d1d_meta.xml	1046	download
beta.powerpoetry.org-inf-20250421-002444-b4d8s-00000.warc.gz	13685606	download job
beta.powerpoetry.org-inf-20250421-002444-b4d8s-00000.warc.os.cdx.gz	39402	download
beta.powerpoetry.org-inf-20250421-002444-b4d8s-meta.warc.gz	27830	download job
beta.powerpoetry.org-inf-20250421-002444-b4d8s-meta.warc.os.cdx.gz	47	download
beta.powerpoetry.org-inf-20250421-002444-b4d8s.json	251	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-07097.warc.gz	6302673511	download job
cirrus.ucsd.edu-inf-20250204-222623-178n0-07097.warc.os.cdx.gz	1650	download
ec.crypton.co.jp-inf-20250420-065532-mped3-00019.warc.gz	5368718706	download job
ec.crypton.co.jp-inf-20250420-065532-mped3-00019.warc.os.cdx.gz	233092	download
hmi.org-inf-20250420-225040-2cdm5-00000.warc.gz	5369604799	download job
hmi.org-inf-20250420-225040-2cdm5-00000.warc.os.cdx.gz	1277924	download
lemmy.zip-inf-20250312-165238-aa83x-00269.warc.gz	5368734392	download job
lemmy.zip-inf-20250312-165238-aa83x-00269.warc.os.cdx.gz	1122592	download
ospo.noaa.gov-inf-20250404-151509-euinz-00412.warc.gz	5369157914	download job
ospo.noaa.gov-inf-20250404-151509-euinz-00412.warc.os.cdx.gz	325159	download
pdos.csail.mit.edu-inf-20250420-173816-eifrm-00003.warc.gz	5441286919	download job
pdos.csail.mit.edu-inf-20250420-173816-eifrm-00003.warc.os.cdx.gz	1718301	download
portal.nersc.gov-inf-20250411-235739-duomw-00369.warc.gz	5454256133	download job
portal.nersc.gov-inf-20250411-235739-duomw-00369.warc.os.cdx.gz	1609	download
public.dhe.ibm.com-inf-20250416-120237-a9nyc-00068.warc.gz	7314564487	download job
public.dhe.ibm.com-inf-20250416-120237-a9nyc-00068.warc.os.cdx.gz	689	download
pubs.usgs.gov-inf-20250404-060456-32bnb-00097.warc.gz	5389449291	download job
pubs.usgs.gov-inf-20250404-060456-32bnb-00097.warc.os.cdx.gz	10925	download
urls-transfer.archivete.am-data.nber.org_conference.nber.org_back.nber.org_users.nber.org_taxsim.nber.org_seed_urls.txt-inf-20250420-200407-beeo4-00002.warc.gz	5402947199	download job
urls-transfer.archivete.am-data.nber.org_conference.nber.org_back.nber.org_users.nber.org_taxsim.nber.org_seed_urls.txt-inf-20250420-200407-beeo4-00002.warc.os.cdx.gz	319912	download
urls-transfer.archivete.am-rubberslug.s3.amazonaws.com_marker_urls.txt-shallow-20250420-211844-5qhyk-00001.warc.gz	919379551	download job
urls-transfer.archivete.am-rubberslug.s3.amazonaws.com_marker_urls.txt-shallow-20250420-211844-5qhyk-meta.warc.gz	4488939	download job
urls-transfer.archivete.am-rubberslug.s3.amazonaws.com_marker_urls.txt-shallow-20250420-211844-5qhyk-urls.txt	12431099	download
urls-transfer.archivete.am-rubberslug.s3.amazonaws.com_marker_urls.txt-shallow-20250420-211844-5qhyk.json	382	download job
urls-transfer.archivete.am-s3.amazonaws.com_pastperfectonline_bulk.txt-shallow-20250409-225214-ec8sy-00544.warc.gz	5379714489	download job
urls-transfer.archivete.am-sigfig.com_subdomains.txt-inf-20250420-213324-chgvf-00000.warc.gz	3050021076	download job
urls-transfer.archivete.am-sigfig.com_subdomains.txt-inf-20250420-213324-chgvf-meta.warc.gz	1326955	download job
urls-transfer.archivete.am-sigfig.com_subdomains.txt-inf-20250420-213324-chgvf-urls.txt	5730	download
urls-transfer.archivete.am-sigfig.com_subdomains.txt-inf-20250420-213324-chgvf.json	342	download job
urls-transfer.archivete.am-www.biblioteca-digitala.ro.txt-inf-20250414-185922-8dp4c-00266.warc.gz	5390213352	download job
urls-transfer.archivete.am-www.documented.info_urls.txt-shallow-20250420-230817-4yji8-00000.warc.gz	5430090725	download job
urls-transfer.archivete.am-zenefits.com_subdomains.txt-inf-20250420-210336-522dq-00000.warc.gz	1921719330	download job
urls-transfer.archivete.am-zenefits.com_subdomains.txt-inf-20250420-210336-522dq-meta.warc.gz	1786887	download job
urls-transfer.archivete.am-zenefits.com_subdomains.txt-inf-20250420-210336-522dq-urls.txt	5067	download
urls-transfer.archivete.am-zenefits.com_subdomains.txt-inf-20250420-210336-522dq.json	346	download job
videocast.nih.gov-inf-20250411-131031-4l9c9-00616.warc.gz	6207829850	download job
webdav.dandiarchive.org-inf-20250411-130303-4ylae-00250.warc.gz	7476171438	download job
www.artisticfreedominitiative.org-inf-20250421-002746-c7wjq-00000.warc.gz	27814967	download job
www.artisticfreedominitiative.org-inf-20250421-002746-c7wjq-meta.warc.gz	17004	download job
www.artisticfreedominitiative.org-inf-20250421-002746-c7wjq.json	264	download job
www.flickr.com-inf-20250416-203114-2njgm-00038.warc.gz	5370569347	download job
www.npr.org-inf-20250330-091933-craqr-00487.warc.gz	5369934619	download job
www.pbs.org-inf-20250330-092508-bykmh-02347.warc.gz	5682788216	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-05300.warc.gz	5373593609	download job
www.sciencebase.gov-inf-20250204-024621-3gyep-05301.warc.gz	5378181554	download job