Item archiveteam_archivebot_go_20250121204455_37404b52

Filename	Size
algorithmwatch.org-inf-20250121-131912-be1kf-00003.warc.gz	5369059008	download job
algorithmwatch.org-inf-20250121-131912-be1kf-00003.warc.os.cdx.gz	1937583	download
apidocs.arity.com-inf-20250121-202142-a6p9x-00000.warc.gz	210087882	download job
apidocs.arity.com-inf-20250121-202142-a6p9x-00000.warc.os.cdx.gz	59963	download
apidocs.arity.com-inf-20250121-202142-a6p9x-meta.warc.gz	40139	download job
apidocs.arity.com-inf-20250121-202142-a6p9x-meta.warc.os.cdx.gz	47	download
apidocs.arity.com-inf-20250121-202142-a6p9x-wpull.log.gz	37437	download
apidocs.arity.com-inf-20250121-202142-a6p9x.json	248	download job
archiveteam_archivebot_go_20250121204455_37404b52.cdx.gz	3905347	download
archiveteam_archivebot_go_20250121204455_37404b52.cdx.idx	3269	download
archiveteam_archivebot_go_20250121204455_37404b52_files.xml	0	download
archiveteam_archivebot_go_20250121204455_37404b52_meta.sqlite	61440	download
archiveteam_archivebot_go_20250121204455_37404b52_meta.xml	1046	download
awakenvideo.org-inf-20250120-151023-8lkap-00045.warc.gz	6197570303	download job
awakenvideo.org-inf-20250120-151023-8lkap-00045.warc.os.cdx.gz	656	download
centerforinquiry.org-inf-20250103-233800-as6k5-00057.warc.gz	5725801386	download job
centerforinquiry.org-inf-20250103-233800-as6k5-00057.warc.os.cdx.gz	493219	download
digg.tumblr.com-inf-20250119-225825-32kz8-00036.warc.gz	5422911546	download job
digg.tumblr.com-inf-20250119-225825-32kz8-00036.warc.os.cdx.gz	1461523	download
digg.tumblr.com-inf-20250119-225825-32kz8-00037.warc.gz	5415068184	download job
digg.tumblr.com-inf-20250119-225825-32kz8-00037.warc.os.cdx.gz	19350	download
download.kiwix.org-inf-20250102-121105-ee83e-00646.warc.gz	10101439046	download job
download.kiwix.org-inf-20250102-121105-ee83e-00646.warc.os.cdx.gz	512	download
downloads.dbpedia.org-inf-20241213-105718-8lci4-00871.warc.gz	5440786086	download job
downloads.dbpedia.org-inf-20241213-105718-8lci4-00871.warc.os.cdx.gz	7433	download
go.arity.com-inf-20250121-202344-3y3uc-00000.warc.gz	8642914	download job
go.arity.com-inf-20250121-202344-3y3uc-00000.warc.os.cdx.gz	7044	download
go.arity.com-inf-20250121-202344-3y3uc.json	243	download job
gwern.net-inf-20241225-012748-f08ks-00306.warc.gz	5766549798	download job
gwern.net-inf-20241225-012748-f08ks-00306.warc.os.cdx.gz	5119322	download
hypendium.com-inf-20250115-204708-53yki-00318.warc.gz	5461662700	download job
hypendium.com-inf-20250115-204708-53yki-00318.warc.os.cdx.gz	1345	download
ipsw.me-inf-20241201-145231-9lrev-02807.warc.gz	8110980523	download job
ipsw.me-inf-20241201-145231-9lrev-02807.warc.os.cdx.gz	350	download
ministryofprivacy.eu-inf-20250121-201120-74l7h-aborted-00000.warc.gz	105783015	download job
ministryofprivacy.eu-inf-20250121-201120-74l7h-aborted-00000.warc.os.cdx.gz	86381	download
ministryofprivacy.eu-inf-20250121-201120-74l7h-aborted-wpull.log.gz	50618	download
ministryofprivacy.eu-inf-20250121-201120-74l7h-aborted.json	247	download job
nedhamsonsecondlineviewofthenews.com-inf-20250112-100214-6cn6z-00117.warc.gz	5372763249	download job
nedhamsonsecondlineviewofthenews.com-inf-20250112-100214-6cn6z-00117.warc.os.cdx.gz	2185590	download
ni.bsw-vg.de-inf-20250121-194914-2cn9j-00000.warc.gz	315084345	download job
ni.bsw-vg.de-inf-20250121-194914-2cn9j-00000.warc.os.cdx.gz	380108	download
ni.bsw-vg.de-inf-20250121-194914-2cn9j-meta.warc.gz	232928	download job
ni.bsw-vg.de-inf-20250121-194914-2cn9j-meta.warc.os.cdx.gz	47	download
ni.bsw-vg.de-inf-20250121-194914-2cn9j.json	240	download job
rrpicturearchives.net-inf-20241216-220659-58ivs-00223.warc.gz	5368800162	download job
rrpicturearchives.net-inf-20241216-220659-58ivs-00223.warc.os.cdx.gz	3210684	download
rubio.senate.gov-inf-20250121-204348-b58iw-00000.warc.gz	6016	download job
rubio.senate.gov-inf-20250121-204348-b58iw-00000.warc.os.cdx.gz	257	download
rubio.senate.gov-inf-20250121-204348-b58iw-meta.warc.gz	3567	download job
rubio.senate.gov-inf-20250121-204348-b58iw-meta.warc.os.cdx.gz	47	download
rubio.senate.gov-inf-20250121-204348-b58iw.json	247	download job
sales.arity.com-inf-20250121-202506-7p9hx-00000.warc.gz	5974	download job
sales.arity.com-inf-20250121-202506-7p9hx-00000.warc.os.cdx.gz	254	download
sales.arity.com-inf-20250121-202506-7p9hx-meta.warc.gz	3432	download job
sales.arity.com-inf-20250121-202506-7p9hx-meta.warc.os.cdx.gz	47	download
sales.arity.com-inf-20250121-202506-7p9hx.json	246	download job
sciencebasedmedicine.org-inf-20250120-210703-c9oax-00009.warc.gz	5386780216	download job
sciencebasedmedicine.org-inf-20250120-210703-c9oax-00009.warc.os.cdx.gz	746334	download
sh.bsw-vg.de-inf-20250121-202930-czac4-00000.warc.gz	2454682	download job
sh.bsw-vg.de-inf-20250121-202930-czac4-00000.warc.os.cdx.gz	6471	download
sh.bsw-vg.de-inf-20250121-202930-czac4-meta.warc.gz	7353	download job
sh.bsw-vg.de-inf-20250121-202930-czac4-meta.warc.os.cdx.gz	47	download
sh.bsw-vg.de-inf-20250121-202930-czac4.json	240	download job
st.bsw-vg.de-inf-20250121-203002-dvaix-00000.warc.gz	2556103	download job
st.bsw-vg.de-inf-20250121-203002-dvaix-00000.warc.os.cdx.gz	6478	download
st.bsw-vg.de-inf-20250121-203002-dvaix-meta.warc.gz	7374	download job
st.bsw-vg.de-inf-20250121-203002-dvaix-meta.warc.os.cdx.gz	47	download
st.bsw-vg.de-inf-20250121-203002-dvaix.json	240	download job
stage2024.cducsu.de-inf-20250121-202229-6bia1.json	247	download job
steamladder.com-inf-20250115-024915-2fiop-00077.warc.gz	5371551975	download job
steamladder.com-inf-20250115-024915-2fiop-00077.warc.os.cdx.gz	4300024	download
urls-transfer.archivete.am-cdn-prod.playfirst.com_urls_part_01.txt-shallow-20250120-210508-7jwqp-00097.warc.gz	5369801557	download job
urls-transfer.archivete.am-cdn-prod.playfirst.com_urls_part_01.txt-shallow-20250120-210508-7jwqp-00097.warc.os.cdx.gz	680082	download
urls-transfer.archivete.am-download.opencontent.netflix.com.s3.amazonaws.com_under_1GB.txt-shallow-20250116-052616-l2cdn-00841.warc.gz	5369867240	download job
urls-transfer.archivete.am-download.opencontent.netflix.com.s3.amazonaws.com_under_1GB.txt-shallow-20250116-052616-l2cdn-00841.warc.os.cdx.gz	7386	download
urls-transfer.archivete.am-download.opencontent.netflix.com.s3.amazonaws.com_under_1GB.txt-shallow-20250116-052616-l2cdn-00842.warc.gz	5402155005	download job
urls-transfer.archivete.am-download.opencontent.netflix.com.s3.amazonaws.com_under_1GB.txt-shallow-20250116-052616-l2cdn-00842.warc.os.cdx.gz	6999	download
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-202622-4r14w-00000.warc.gz	27094	download job
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-202622-4r14w-00000.warc.os.cdx.gz	695	download
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-202622-4r14w-meta.warc.gz	3717	download job
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-202622-4r14w-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-202622-4r14w-urls.txt	382	download
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-202622-4r14w.json	342	download job
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-203203-4r14w-00000.warc.gz	26290	download job
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-203203-4r14w-00000.warc.os.cdx.gz	706	download
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-203203-4r14w-meta.warc.gz	3738	download job
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-203203-4r14w-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-203203-4r14w-urls.txt	382	download
urls-transfer.archivete.am-events.arity.com_urls.txt-inf-20250121-203203-4r14w.json	342	download job
usa.gov-inf-20250121-204143-1b8i8-00000.warc.gz	5265103	download job
usa.gov-inf-20250121-204143-1b8i8-00000.warc.os.cdx.gz	11249	download
usa.gov-inf-20250121-204143-1b8i8-meta.warc.gz	9775	download job
usa.gov-inf-20250121-204143-1b8i8-meta.warc.os.cdx.gz	47	download
usa.gov-inf-20250121-204143-1b8i8.json	238	download job
veranstaltungen.cducsu.de-inf-20250121-202549-7kezy-00000.warc.gz	869021	download job
veranstaltungen.cducsu.de-inf-20250121-202549-7kezy-00000.warc.os.cdx.gz	6748	download
veranstaltungen.cducsu.de-inf-20250121-202549-7kezy.json	253	download job
webstat.cducsu.de-inf-20250121-202553-1j6lz-00000.warc.gz	6728	download job
webstat.cducsu.de-inf-20250121-202553-1j6lz-00000.warc.os.cdx.gz	305	download
www.81.cn-inf-20250115-085108-45we7-00057.warc.gz	5491095676	download job
www.81.cn-inf-20250115-085108-45we7-00057.warc.os.cdx.gz	2127620	download
www.info.cducsu.de-inf-20250121-202618-7vwcu-00000.warc.gz	13121	download job
www.info.cducsu.de-inf-20250121-202618-7vwcu-00000.warc.os.cdx.gz	309	download
www.info.cducsu.de-inf-20250121-202618-7vwcu-meta.warc.gz	3608	download job
www.info.cducsu.de-inf-20250121-202618-7vwcu-meta.warc.os.cdx.gz	47	download
www.info.cducsu.de-inf-20250121-202618-7vwcu.json	246	download job
www.praktikum.cducsu.de-inf-20250121-202619-9u7qy-00000.warc.gz	407963	download job
www.praktikum.cducsu.de-inf-20250121-202619-9u7qy-00000.warc.os.cdx.gz	1793	download
www.praktikum.cducsu.de-inf-20250121-202619-9u7qy-meta.warc.gz	4460	download job
www.praktikum.cducsu.de-inf-20250121-202619-9u7qy-meta.warc.os.cdx.gz	47	download
www.praktikum.cducsu.de-inf-20250121-202619-9u7qy.json	251	download job
www.previewsworld.com-inf-20250114-173604-oylly-00048.warc.gz	5368839913	download job
www.previewsworld.com-inf-20250114-173604-oylly-00048.warc.os.cdx.gz	307719	download
www.veranstaltungen.cducsu.de-inf-20250121-202633-5dzst-00000.warc.gz	12757	download job
www.veranstaltungen.cducsu.de-inf-20250121-202633-5dzst-00000.warc.os.cdx.gz	334	download
www.veranstaltungen.cducsu.de-inf-20250121-202633-5dzst-meta.warc.gz	3564	download job
www.veranstaltungen.cducsu.de-inf-20250121-202633-5dzst-meta.warc.os.cdx.gz	47	download
www.veranstaltungen.cducsu.de-inf-20250121-202633-5dzst.json	257	download job