Item archiveteam_archivebot_go_20261001013445_5f2122d7

Filename	Size
advocacy.consumerreports.org-inf-20260925-003939-3qq5g-00007.warc.gz	5370059410	download job
advocacy.consumerreports.org-inf-20260925-003939-3qq5g-00007.warc.os.cdx.gz	1802066	download
archiveteam_archivebot_go_20261001013445_5f2122d7.cdx.gz	2107602	download
archiveteam_archivebot_go_20261001013445_5f2122d7.cdx.idx	2354	download
archiveteam_archivebot_go_20261001013445_5f2122d7_files.xml	0	download
archiveteam_archivebot_go_20261001013445_5f2122d7_meta.sqlite	102400	download
archiveteam_archivebot_go_20261001013445_5f2122d7_meta.xml	1046	download
christophermathias.com-inf-20261001-001359-an453.json	248	download job
das.sdss.org-inf-20250226-051304-5s39o-09918.warc.gz	5373359402	download job
das.sdss.org-inf-20250226-051304-5s39o-09918.warc.os.cdx.gz	357292	download
deliberateexcellence.wordpress.com-inf-20260930-225211-4u333-00001.warc.gz	3431409174	download job
deliberateexcellence.wordpress.com-inf-20260930-225211-4u333-meta.warc.gz	1404789	download job
deliberateexcellence.wordpress.com-inf-20260930-225211-4u333.json	265	download job
discord.com-inf-20260927-220325-dc6fw-00072.warc.gz	5368936149	download job
filtonactionists.com-inf-20260930-235844-7p0a2-00000.warc.gz	1559804379	download job
filtonactionists.com-inf-20260930-235844-7p0a2-meta.warc.gz	1059178	download job
filtonactionists.com-inf-20260930-235844-7p0a2.json	246	download job
forms.sflhidta.org-inf-20261001-013341-8hvdi-meta.warc.gz	4436	download job
forms.sflhidta.org-inf-20261001-013341-8hvdi.json	249	download job
fpf.org-inf-20260929-204206-7vauh-00008.warc.gz	5368783577	download job
news.cornell.edu-inf-20260930-170620-41jwf-00003.warc.gz	5369253665	download job
sflhidta.org-inf-20261001-013303-6vrd8-00000.warc.gz	2464	download job
sflhidta.org-inf-20261001-013303-6vrd8-meta.warc.gz	3600	download job
sflhidta.org-inf-20261001-013303-6vrd8.json	247	download job
sflhidta.org-inf-20261001-013303-7wym9-00000.warc.gz	2467	download job
sflhidta.org-inf-20261001-013303-7wym9.json	248	download job
sites.google.com-inf-20261001-001030-1r7af-00000.warc.gz	5494260758	download job
studyfinds.com-inf-20260922-030220-8q9yf-00115.warc.gz	6058558331	download job
texasfarmbureau.org-inf-20260929-191555-c1f47-00007.warc.gz	5468063983	download job
thefinalstrawradio.mayfirst.info-inf-20260930-235129-5fvq4-00000.warc.gz	5389805588	download job
transfer.archivete.am-shallow-20261001-011051-5m99u.json	303	download job
urls-nue2.nulldata.foo-github.com_CHOMPI-Club-20261001005148-links.txt-shallow-20261001-005215-c132z-00000.warc.gz	965780241	download job
urls-nue2.nulldata.foo-github.com_CHOMPI-Club-20261001005148-links.txt-shallow-20261001-005215-c132z-meta.warc.gz	49150	download job
urls-nue2.nulldata.foo-github.com_CHOMPI-Club-20261001005148-links.txt-shallow-20261001-005215-c132z-urls.txt	6688	download
urls-nue2.nulldata.foo-github.com_CHOMPI-Club-20261001005148-links.txt-shallow-20261001-005215-c132z.json	383	download job
urls-transfer.archivete.am-21styles.com_style-21.com_etc_403_retry_1.txt-inf-20261001-012304-a7593-aborted-00000.warc.gz	22696	download job
urls-transfer.archivete.am-21styles.com_style-21.com_etc_403_retry_1.txt-inf-20261001-012304-a7593-aborted-wpull.log.gz	1119	download
urls-transfer.archivete.am-21styles.com_style-21.com_etc_403_retry_1.txt-inf-20261001-012304-a7593-aborted.json	381	download job
urls-transfer.archivete.am-21styles.com_style-21.com_etc_403_retry_1.txt-inf-20261001-012304-a7593-urls.txt	450	download
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20260930-233343-eufv5-aborted-00000.warc.gz	17370088	download job
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20260930-233343-eufv5-aborted-wpull.log.gz	187131	download
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20260930-233343-eufv5-aborted.json	389	download job
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20260930-233343-eufv5-urls.txt	444	download
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20261001-012239-eufv5-aborted-00000.warc.gz	52405	download job
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20261001-012239-eufv5-aborted-wpull.log.gz	1692	download
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20261001-012239-eufv5-aborted.json	389	download job
urls-transfer.archivete.am-21styles.com_style-21.com_etc_extra_seed_urls.txt-inf-20261001-012239-eufv5-urls.txt	444	download
urls-transfer.archivete.am-ldpr.ru_known-subdomains.txt-inf-20260918-144114-9n004-00327.warc.gz	5381518989	download job
urls-transfer.archivete.am-nynjhidta.org_subdomains.txt-inf-20261001-001822-85o0u-00000.warc.gz	2336921082	download job
urls-transfer.archivete.am-nynjhidta.org_subdomains.txt-inf-20261001-001822-85o0u-meta.warc.gz	415237	download job
urls-transfer.archivete.am-nynjhidta.org_subdomains.txt-inf-20261001-001822-85o0u-urls.txt	4096	download
urls-transfer.archivete.am-nynjhidta.org_subdomains.txt-inf-20261001-001822-85o0u.json	348	download job
www.ca1.uscourts.gov-inf-20260930-231255-acvzh-00007.warc.gz	5407044304	download job
www.ca1.uscourts.gov-inf-20260930-231255-acvzh-00008.warc.gz	5372340732	download job
www.ca1.uscourts.gov-inf-20260930-231255-acvzh-00009.warc.gz	5390308245	download job
www.chompiclub.com-inf-20261001-005059-dm780-00000.warc.gz	912771842	download job
www.chompiclub.com-inf-20261001-005059-dm780-meta.warc.gz	299148	download job
www.chompiclub.com-inf-20261001-005059-dm780.json	244	download job
www.doe.mass.edu-inf-20260930-061818-4wwe2-00004.warc.gz	5333904095	download job
www.doe.mass.edu-inf-20260930-061818-4wwe2-meta.warc.gz	12970615	download job
www.doe.mass.edu-inf-20260930-061818-4wwe2.json	247	download job
www.edg.com-inf-20261001-004352-c1y6c-00000.warc.gz	912917567	download job
www.edg.com-inf-20261001-004352-c1y6c-meta.warc.gz	376070	download job
www.edg.com-inf-20261001-004352-c1y6c.json	237	download job
www.glerl.noaa.gov-inf-20260902-014202-3ci2l-00387.warc.gz	5375188421	download job
www.hidta.org-inf-20260930-212613-5j3cl-00000.warc.gz	5050340032	download job
www.hidta.org-inf-20260930-212613-5j3cl-meta.warc.gz	2069787	download job
www.hidta.org-inf-20260930-212613-5j3cl.json	244	download job
www.new.stxhidta.org-inf-20261001-013427-2ibn1-00000.warc.gz	9485	download job
www.new.stxhidta.org-inf-20261001-013427-2ibn1-meta.warc.gz	3527	download job
www.rafcf.org.uk-inf-20260930-232542-1hfs0-00000.warc.gz	2608221002	download job
www.sflhidta.org-inf-20261001-013300-5b77t-00000.warc.gz	2471	download job
www.sflhidta.org-inf-20261001-013300-5b77t-meta.warc.gz	3480	download job
www.sflhidta.org-inf-20261001-013300-5b77t.json	251	download job
www.sflhidta.org-inf-20261001-013303-13hqu-00000.warc.gz	2475	download job
www.sflhidta.org-inf-20261001-013303-13hqu-meta.warc.gz	3546	download job
www.sflhidta.org-inf-20261001-013303-13hqu.json	252	download job
www.stxhidta.org-inf-20261001-013357-7kxip-00000.warc.gz	9333	download job
www.stxhidta.org-inf-20261001-013357-7kxip-meta.warc.gz	3528	download job
www.stxhidta.org-inf-20261001-013357-7kxip.json	247	download job
www.theraf.org-inf-20260930-232729-5dwc1-00000.warc.gz	5368824234	download job
www.thermofisher.com-inf-20260722-041853-ezatg-00171.warc.gz	5368759469	download job
www.wired.it-inf-20260919-083035-8dnvv-00345.warc.gz	5372350467	download job
zentralwerk.de-inf-20260930-161818-5u2s2-00001.warc.gz	3407439755	download job
zentralwerk.de-inf-20260930-161818-5u2s2-meta.warc.gz	2681754	download job
zentralwerk.de-inf-20260930-161818-5u2s2.json	242	download job