Item archiveteam_archivebot_go_20260416161020_dc7bcf74

Filename	Size
archiveteam_archivebot_go_20260416161020_dc7bcf74.cdx.gz	34619062	download
archiveteam_archivebot_go_20260416161020_dc7bcf74.cdx.idx	44891	download
archiveteam_archivebot_go_20260416161020_dc7bcf74_files.xml	0	download
archiveteam_archivebot_go_20260416161020_dc7bcf74_meta.sqlite	49152	download
archiveteam_archivebot_go_20260416161020_dc7bcf74_meta.xml	881	download
das.sdss.org-inf-20250226-051304-5s39o-07432.warc.gz	5369082034	download job
das.sdss.org-inf-20250226-051304-5s39o-07432.warc.os.cdx.gz	1179181	download
diariodistrito.sapo.pt-inf-20260414-020513-4gga5-00014.warc.gz	5368830338	download job
diariodistrito.sapo.pt-inf-20260414-020513-4gga5-00014.warc.os.cdx.gz	4742891	download
dunamsz.hu-inf-20260416-143339-75viu-00000.warc.gz	2428431019	download job
dunamsz.hu-inf-20260416-143339-75viu-00000.warc.os.cdx.gz	1233609	download
dunamsz.hu-inf-20260416-143339-75viu-meta.warc.gz	755346	download job
dunamsz.hu-inf-20260416-143339-75viu-meta.warc.os.cdx.gz	47	download
dunamsz.hu-inf-20260416-143339-75viu.json	238	download job
heartland.org-inf-20260410-012410-6kgjd-00074.warc.gz	5385116888	download job
heartland.org-inf-20260410-012410-6kgjd-00074.warc.os.cdx.gz	847854	download
honestlyconcerned.info-inf-20260409-152919-cgbw5-00023.warc.gz	5452118016	download job
honestlyconcerned.info-inf-20260409-152919-cgbw5-00023.warc.os.cdx.gz	1452211	download
kolyanray.github.io-inf-20260416-160118-5tlu2-00000.warc.gz	93752956	download job
kolyanray.github.io-inf-20260416-160118-5tlu2-00000.warc.os.cdx.gz	91724	download
kolyanray.github.io-inf-20260416-160118-5tlu2-meta.warc.gz	64947	download job
kolyanray.github.io-inf-20260416-160118-5tlu2-meta.warc.os.cdx.gz	47	download
kolyanray.github.io-inf-20260416-160118-5tlu2.json	247	download job
league-uat.livgolf.com-inf-20260416-012454-a1q5c-00027.warc.gz	6088107713	download job
league-uat.livgolf.com-inf-20260416-012454-a1q5c-00027.warc.os.cdx.gz	627	download
mike-ochmann.de-inf-20260416-152935-eag8u-meta.warc.gz	449300	download job
mike-ochmann.de-inf-20260416-152935-eag8u-meta.warc.os.cdx.gz	47	download
mike-ochmann.de-inf-20260416-152935-eag8u.json	243	download job
nowiny24.pl-inf-20260310-123849-19bim-00237.warc.gz	5369082433	download job
nowiny24.pl-inf-20260310-123849-19bim-00237.warc.os.cdx.gz	3329608	download
skane.dexter-ist.com-inf-20260416-160657-4sxd2-00000.warc.gz	1377101	download job
skane.dexter-ist.com-inf-20260416-160657-4sxd2-00000.warc.os.cdx.gz	2033	download
skane.dexter-ist.com-inf-20260416-160657-4sxd2-meta.warc.gz	4664	download job
skane.dexter-ist.com-inf-20260416-160657-4sxd2-meta.warc.os.cdx.gz	47	download
skane.dexter-ist.com-inf-20260416-160657-4sxd2.json	245	download job
socialsecurityworks.org-inf-20260416-045030-4tfqt-00028.warc.gz	5369034057	download job
socialsecurityworks.org-inf-20260416-045030-4tfqt-00028.warc.os.cdx.gz	1454142	download
telex.hu-shallow-20260416-153429-36g94-00000.warc.gz	80352591	download job
telex.hu-shallow-20260416-153429-36g94-00000.warc.os.cdx.gz	181973	download
telex.hu-shallow-20260416-153429-36g94-meta.warc.gz	92222	download job
telex.hu-shallow-20260416-153429-36g94-meta.warc.os.cdx.gz	47	download
telex.hu-shallow-20260416-153429-36g94.json	340	download job
urls-nue2.nulldata.foo-github.com_ONLYOFFICE-20260415211048-links.txt-shallow-20260415-211915-biszp-00057.warc.gz	5549815662	download job
urls-nue2.nulldata.foo-github.com_ONLYOFFICE-20260415211048-links.txt-shallow-20260415-211915-biszp-00057.warc.os.cdx.gz	8949	download
urls-nue2.nulldata.foo-github.com_ONLYOFFICE-20260415211048-links.txt-shallow-20260415-211915-biszp-00058.warc.gz	5612285429	download job
urls-nue2.nulldata.foo-github.com_ONLYOFFICE-20260415211048-links.txt-shallow-20260415-211915-biszp-00058.warc.os.cdx.gz	5468	download
urls-nue2.nulldata.foo-github.com_ONLYOFFICE-20260415211048-links.txt-shallow-20260415-211915-biszp-00059.warc.gz	5525704744	download job
urls-nue2.nulldata.foo-github.com_ONLYOFFICE-20260415211048-links.txt-shallow-20260415-211915-biszp-00059.warc.os.cdx.gz	6165	download
urls-transfer.archivete.am-counterextremism.com_subdomains.txt-inf-20260409-105821-1ziun-00156.warc.gz	4261749123	download job
urls-transfer.archivete.am-counterextremism.com_subdomains.txt-inf-20260409-105821-1ziun-00156.warc.os.cdx.gz	872518	download
urls-transfer.archivete.am-counterextremism.com_subdomains.txt-inf-20260409-105821-1ziun-meta.warc.gz	105794691	download job
urls-transfer.archivete.am-counterextremism.com_subdomains.txt-inf-20260409-105821-1ziun-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-counterextremism.com_subdomains.txt-inf-20260409-105821-1ziun-urls.txt	208	download
urls-transfer.archivete.am-counterextremism.com_subdomains.txt-inf-20260409-105821-1ziun.json	362	download job
urls-transfer.archivete.am-mines.edu_subdomains.txt-inf-20260410-044120-30y9i-00068.warc.gz	5740896704	download job
urls-transfer.archivete.am-mines.edu_subdomains.txt-inf-20260410-044120-30y9i-00068.warc.os.cdx.gz	2227649	download
www.animated-smileys.com-inf-20260416-095143-701pg-00000.warc.gz	1025993235	download job
www.animated-smileys.com-inf-20260416-095143-701pg-00000.warc.os.cdx.gz	3855841	download
www.animated-smileys.com-inf-20260416-095143-701pg-meta.warc.gz	2532564	download job
www.animated-smileys.com-inf-20260416-095143-701pg-meta.warc.os.cdx.gz	47	download
www.animated-smileys.com-inf-20260416-095143-701pg.json	255	download job
www.asriran.com-inf-20260131-055905-eawh4-00200.warc.gz	5373902097	download job
www.asriran.com-inf-20260131-055905-eawh4-00200.warc.os.cdx.gz	4694953	download
www.bernoullisociety.org-shallow-20260416-154256-as7gc-00000.warc.gz	322578	download job
www.bernoullisociety.org-shallow-20260416-154256-as7gc-00000.warc.os.cdx.gz	1218	download
www.bernoullisociety.org-shallow-20260416-154256-as7gc-meta.warc.gz	4093	download job
www.bernoullisociety.org-shallow-20260416-154256-as7gc-meta.warc.os.cdx.gz	47	download
www.bernoullisociety.org-shallow-20260416-154256-as7gc.json	256	download job
www.bollerwagen-ol.de-inf-20260416-154220-ej7qi-00000.warc.gz	25167678	download job
www.bollerwagen-ol.de-inf-20260416-154220-ej7qi-00000.warc.os.cdx.gz	38758	download
www.bollerwagen-ol.de-inf-20260416-154220-ej7qi-meta.warc.gz	24544	download job
www.bollerwagen-ol.de-inf-20260416-154220-ej7qi-meta.warc.os.cdx.gz	47	download
www.bollerwagen-ol.de-inf-20260416-154220-ej7qi.json	249	download job
www.buemmersteder-krug.de-inf-20260416-153025-f3up5-00000.warc.gz	1022845986	download job
www.buemmersteder-krug.de-inf-20260416-153025-f3up5-00000.warc.os.cdx.gz	620341	download
www.buemmersteder-krug.de-inf-20260416-153025-f3up5-meta.warc.gz	375622	download job
www.buemmersteder-krug.de-inf-20260416-153025-f3up5-meta.warc.os.cdx.gz	47	download
www.buemmersteder-krug.de-inf-20260416-153025-f3up5.json	253	download job
www.cs.umd.edu-inf-20260416-153027-ahmce-00000.warc.gz	134113656	download job
www.cs.umd.edu-inf-20260416-153027-ahmce-00000.warc.os.cdx.gz	157172	download
www.cs.umd.edu-inf-20260416-153027-ahmce-meta.warc.gz	108746	download job
www.cs.umd.edu-inf-20260416-153027-ahmce-meta.warc.os.cdx.gz	47	download
www.cs.umd.edu-inf-20260416-153027-ahmce.json	251	download job
www.docip.org-inf-20260416-021723-633la-00003.warc.gz	6383873927	download job
www.docip.org-inf-20260416-021723-633la-00003.warc.os.cdx.gz	2720898	download
www.docip.org-inf-20260416-021723-633la-00004.warc.gz	155470933	download job
www.docip.org-inf-20260416-021723-633la-00004.warc.os.cdx.gz	80114	download
www.docip.org-inf-20260416-021723-633la-meta.warc.gz	4957357	download job
www.docip.org-inf-20260416-021723-633la-meta.warc.os.cdx.gz	47	download
www.docip.org-inf-20260416-021723-633la.json	244	download job
www.grasset.fr-inf-20260416-060538-au8zt-00001.warc.gz	5368813638	download job
www.grasset.fr-inf-20260416-060538-au8zt-00001.warc.os.cdx.gz	3344303	download
www.hogskoleprov.nu-inf-20260416-160628-9tusf-00000.warc.gz	20315788	download job
www.hogskoleprov.nu-inf-20260416-160628-9tusf-00000.warc.os.cdx.gz	11268	download
www.hogskoleprov.nu-inf-20260416-160628-9tusf-meta.warc.gz	10910	download job
www.hogskoleprov.nu-inf-20260416-160628-9tusf-meta.warc.os.cdx.gz	47	download
www.hogskoleprov.nu-inf-20260416-160628-9tusf.json	244	download job
www.loverslab.com-inf-20260413-151753-a9t2m-00058.warc.gz	5368938880	download job
www.loverslab.com-inf-20260413-151753-a9t2m-00058.warc.os.cdx.gz	563819	download
www.newnation.news-inf-20260414-102406-5mhes-00072.warc.gz	5454373284	download job
www.newnation.news-inf-20260414-102406-5mhes-00072.warc.os.cdx.gz	180610	download
www.newnation.news-inf-20260414-102406-5mhes-00073.warc.gz	5621342357	download job
www.newnation.news-inf-20260414-102406-5mhes-00073.warc.os.cdx.gz	54227	download
www.rcaland.ax-inf-20260416-093337-dxpfd-00002.warc.gz	4680634150	download job
www.rcaland.ax-inf-20260416-093337-dxpfd-00002.warc.os.cdx.gz	989693	download
www.rcaland.ax-inf-20260416-093337-dxpfd-meta.warc.gz	653009	download job
www.rcaland.ax-inf-20260416-093337-dxpfd-meta.warc.os.cdx.gz	47	download
www.rcaland.ax-inf-20260416-093337-dxpfd.json	244	download job
www.softwarelode.com-inf-20260415-080412-e0u0o-00006.warc.gz	5371644323	download job
www.softwarelode.com-inf-20260415-080412-e0u0o-00006.warc.os.cdx.gz	689308	download
www.swissmem.ch-inf-20260416-063054-f4gq2-00004.warc.gz	5386786965	download job
www.swissmem.ch-inf-20260416-063054-f4gq2-00004.warc.os.cdx.gz	423087	download