Item archiveteam_archivebot_go_20260331054858_d4c516f9

Filename	Size
archives.uslhs.org-inf-20260330-204528-bq6cd-00004.warc.gz	5368921766	download job
archives.uslhs.org-inf-20260330-204528-bq6cd-00004.warc.os.cdx.gz	1082003	download
archiveteam_archivebot_go_20260331054858_d4c516f9_files.xml	0	download
archiveteam_archivebot_go_20260331054858_d4c516f9_meta.sqlite	102400	download
archiveteam_archivebot_go_20260331054858_d4c516f9_meta.xml	881	download
ddr.densho.org-inf-20260328-213558-5eckx-00091.warc.gz	5372291142	download job
ddr.densho.org-inf-20260328-213558-5eckx-00091.warc.os.cdx.gz	314365	download
dev.lewisforleader.ca-inf-20260331-040333-cepnv-00000.warc.gz	2127788681	download job
dev.lewisforleader.ca-inf-20260331-040333-cepnv-00000.warc.os.cdx.gz	1453359	download
dev.lewisforleader.ca-inf-20260331-040333-cepnv-meta.warc.gz	961621	download job
dev.lewisforleader.ca-inf-20260331-040333-cepnv-meta.warc.os.cdx.gz	47	download
dev.lewisforleader.ca-inf-20260331-040333-cepnv.json	252	download job
fr.heathermcpherson.ca-inf-20260331-054031-d0n35-00000.warc.gz	1498874	download job
fr.heathermcpherson.ca-inf-20260331-054031-d0n35-00000.warc.os.cdx.gz	16094	download
fr.heathermcpherson.ca-inf-20260331-054031-d0n35-meta.warc.gz	11360	download job
fr.heathermcpherson.ca-inf-20260331-054031-d0n35-meta.warc.os.cdx.gz	47	download
fr.heathermcpherson.ca-inf-20260331-054031-d0n35.json	253	download job
heathermcpherson.ca-inf-20260331-054009-6ryfs-00000.warc.gz	21098	download job
heathermcpherson.ca-inf-20260331-054009-6ryfs-00000.warc.os.cdx.gz	477	download
heathermcpherson.ca-inf-20260331-054009-6ryfs-meta.warc.gz	3571	download job
heathermcpherson.ca-inf-20260331-054009-6ryfs-meta.warc.os.cdx.gz	47	download
heathermcpherson.ca-inf-20260331-054009-6ryfs.json	250	download job
howardbrown.org-inf-20260331-021726-6d4lt-00001.warc.gz	5582850406	download job
howardbrown.org-inf-20260331-021726-6d4lt-00001.warc.os.cdx.gz	595793	download
lewisforleader.ca-inf-20260331-033242-7bdnz-00000.warc.gz	2512301872	download job
lewisforleader.ca-inf-20260331-033242-7bdnz-00000.warc.os.cdx.gz	2111087	download
lewisforleader.ca-inf-20260331-033242-7bdnz.json	248	download job
lgbcouragecoalition.substack.com-inf-20260329-235312-9cgut-00004.warc.gz	5377982992	download job
lgbcouragecoalition.substack.com-inf-20260329-235312-9cgut-00004.warc.os.cdx.gz	1092630	download
mcpl.info-inf-20260331-004827-43upa-00002.warc.gz	5505456601	download job
mcpl.info-inf-20260331-004827-43upa-00002.warc.os.cdx.gz	390701	download
news.uslhs.org-inf-20260330-205816-9a1ba-00004.warc.gz	5397427932	download job
news.uslhs.org-inf-20260330-205816-9a1ba-00004.warc.os.cdx.gz	99187	download
notepad-plus-plus.org-inf-20260331-054416-aquwd-00000.warc.gz	5251	download job
notepad-plus-plus.org-inf-20260331-054416-aquwd-00000.warc.os.cdx.gz	265	download
notepad-plus-plus.org-inf-20260331-054416-aquwd-meta.warc.gz	3506	download job
notepad-plus-plus.org-inf-20260331-054416-aquwd-meta.warc.os.cdx.gz	47	download
notepad-plus-plus.org-inf-20260331-054416-aquwd.json	295	download job
novynarnia.com-inf-20260315-020904-bya0d-00119.warc.gz	5496414797	download job
novynarnia.com-inf-20260315-020904-bya0d-00119.warc.os.cdx.gz	63046	download
peq42.com-inf-20260331-022026-anepp-00001.warc.gz	5886964283	download job
peq42.com-inf-20260331-022026-anepp-00001.warc.os.cdx.gz	927963	download
radiomoldova.md-inf-20260312-193836-4zvlb-00044.warc.gz	5564903671	download job
radiomoldova.md-inf-20260312-193836-4zvlb-00044.warc.os.cdx.gz	318919	download
urls-transfer.archivete.am-dlib.nyu.edu_aco_law_high.txt-shallow-20260330-212650-cb6y0-00039.warc.gz	5627637996	download job
urls-transfer.archivete.am-dlib.nyu.edu_aco_law_high.txt-shallow-20260330-212650-cb6y0-00039.warc.os.cdx.gz	1160	download
urls-transfer.archivete.am-dlib.nyu.edu_aco_law_high.txt-shallow-20260330-212650-cb6y0-00040.warc.gz	5478913407	download job
urls-transfer.archivete.am-dlib.nyu.edu_aco_law_high.txt-shallow-20260330-212650-cb6y0-00040.warc.os.cdx.gz	909	download
urls-transfer.archivete.am-dlib.nyu.edu_aco_law_high.txt-shallow-20260330-212650-cb6y0-00041.warc.gz	5422490546	download job
urls-transfer.archivete.am-dlib.nyu.edu_aco_law_high.txt-shallow-20260330-212650-cb6y0-00041.warc.os.cdx.gz	1438	download
urls-transfer.archivete.am-old-site.uslhs.org_seed_urls.txt-inf-20260330-210611-bqzaf-00000.warc.gz	5368956070	download job
urls-transfer.archivete.am-old-site.uslhs.org_seed_urls.txt-inf-20260330-210611-bqzaf-00000.warc.os.cdx.gz	2039502	download
urls-transfer.archivete.am-s3ftp.flybase.org_psql_urls.txt-shallow-20260330-063343-7slgt-00049.warc.gz	15915637175	download job
urls-transfer.archivete.am-s3ftp.flybase.org_psql_urls.txt-shallow-20260330-063343-7slgt-00049.warc.os.cdx.gz	455	download
urls-transfer.archivete.am-waterkeeper.org_subdomains.txt-inf-20260330-204116-26all-00002.warc.gz	5379447720	download job
urls-transfer.archivete.am-waterkeeper.org_subdomains.txt-inf-20260330-204116-26all-00002.warc.os.cdx.gz	1181037	download
urls-transfer.archivete.am-www.nasa.gov_science.nasa.gov.txt-inf-20260324-233148-4cdjh-00072.warc.gz	5369067266	download job
urls-transfer.archivete.am-www.nasa.gov_science.nasa.gov.txt-inf-20260324-233148-4cdjh-00072.warc.os.cdx.gz	2114004	download
www.airforcetimes.com-inf-20260328-140114-4n8ju-00066.warc.gz	5669981825	download job
www.airforcetimes.com-inf-20260328-140114-4n8ju-00066.warc.os.cdx.gz	980442	download
www.heathermcpherson.ca-inf-20260331-054132-75bri-aborted-00000.warc.gz	519154	download job
www.heathermcpherson.ca-inf-20260331-054132-75bri-aborted-00000.warc.os.cdx.gz	5492	download
www.heathermcpherson.ca-inf-20260331-054132-75bri-aborted-wpull.log.gz	3736	download
www.heathermcpherson.ca-inf-20260331-054132-75bri-aborted.json	253	download job
www.svenskalag.se-inf-20260329-194324-30rge-00021.warc.gz	5757767653	download job
www.svenskalag.se-inf-20260329-194324-30rge-00021.warc.os.cdx.gz	666	download
www.whatsonweibo.com-inf-20260328-170053-1icsf-00015.warc.gz	5369869141	download job
www.yvesforndpleader.ca-inf-20260331-054207-41bmn-00000.warc.gz	12118837	download job
www.yvesforndpleader.ca-inf-20260331-054207-41bmn-meta.warc.gz	11545	download job
www.yvesforndpleader.ca-inf-20260331-054207-41bmn.json	254	download job