Item archiveteam_archivebot_go_20240514133617_2c5cb5b4

Filename	Size
anti-spiegel.ru-inf-20240505-140211-a1zlh-00112.warc.gz	7648020296	download job
anti-spiegel.ru-inf-20240505-140211-a1zlh-00112.warc.os.cdx.gz	437429	download
archiveteam_archivebot_go_20240514133617_2c5cb5b4.cdx.gz	30204923	download
archiveteam_archivebot_go_20240514133617_2c5cb5b4.cdx.idx	33447	download
archiveteam_archivebot_go_20240514133617_2c5cb5b4_files.xml	0	download
archiveteam_archivebot_go_20240514133617_2c5cb5b4_meta.sqlite	180224	download
archiveteam_archivebot_go_20240514133617_2c5cb5b4_meta.xml	1047	download
buromaks.nl-inf-20240514-125707-c08kr-00000.warc.gz	340220888	download job
buromaks.nl-inf-20240514-125707-c08kr-00000.warc.os.cdx.gz	250993	download
buromaks.nl-inf-20240514-125707-c08kr-meta.warc.gz	186262	download job
buromaks.nl-inf-20240514-125707-c08kr-meta.warc.os.cdx.gz	47	download
buromaks.nl-inf-20240514-125707-c08kr.json	239	download job
chorgemeinschaftspay.de-inf-20240514-131039-b7gig-00000.warc.gz	116714729	download job
chorgemeinschaftspay.de-inf-20240514-131039-b7gig-00000.warc.os.cdx.gz	54107	download
chorgemeinschaftspay.de-inf-20240514-131039-b7gig-meta.warc.gz	36884	download job
chorgemeinschaftspay.de-inf-20240514-131039-b7gig-meta.warc.os.cdx.gz	47	download
chorgemeinschaftspay.de-inf-20240514-131039-b7gig.json	251	download job
cluesforum.info-inf-20240506-123511-asrpo-00084.warc.gz	5432962933	download job
cluesforum.info-inf-20240506-123511-asrpo-00084.warc.os.cdx.gz	375550	download
community.chocolatey.org-inf-20240505-103936-oyad1-00202.warc.gz	5416702713	download job
community.chocolatey.org-inf-20240505-103936-oyad1-00202.warc.os.cdx.gz	23725	download
deblauwetijger.com-inf-20240513-130613-64sk9-00034.warc.gz	8037386643	download job
deblauwetijger.com-inf-20240513-130613-64sk9-00034.warc.os.cdx.gz	1486	download
deblauwetijger.com-inf-20240513-130613-64sk9-00035.warc.gz	6055243220	download job
deblauwetijger.com-inf-20240513-130613-64sk9-00035.warc.os.cdx.gz	1729	download
ebiblio.feedbooks.com-inf-20240329-043352-8p6cj-00168.warc.gz	5369889866	download job
ebiblio.feedbooks.com-inf-20240329-043352-8p6cj-00168.warc.os.cdx.gz	4204261	download
europepmc.org-inf-20240212-215511-8x1ov-02655.warc.gz	5376045686	download job
europepmc.org-inf-20240212-215511-8x1ov-02655.warc.os.cdx.gz	51962	download
germaniaostheim.wordpress.com-inf-20240514-131313-125nu-00000.warc.gz	108527542	download job
germaniaostheim.wordpress.com-inf-20240514-131313-125nu-00000.warc.os.cdx.gz	210961	download
germaniaostheim.wordpress.com-inf-20240514-131313-125nu-meta.warc.gz	144686	download job
germaniaostheim.wordpress.com-inf-20240514-131313-125nu-meta.warc.os.cdx.gz	47	download
germaniaostheim.wordpress.com-inf-20240514-131313-125nu.json	257	download job
jenkins.savethechildren.es-inf-20240514-133337-7dtk6-00000.warc.gz	6987	download job
jenkins.savethechildren.es-inf-20240514-133337-7dtk6-00000.warc.os.cdx.gz	342	download
jenkins.savethechildren.es-inf-20240514-133337-7dtk6-meta.warc.gz	3499	download job
jenkins.savethechildren.es-inf-20240514-133337-7dtk6-meta.warc.os.cdx.gz	47	download
jenkins.savethechildren.es-inf-20240514-133337-7dtk6.json	257	download job
l.savethechildren.es-inf-20240514-133154-6wqeg-00000.warc.gz	8612305	download job
l.savethechildren.es-inf-20240514-133154-6wqeg-00000.warc.os.cdx.gz	12716	download
l.savethechildren.es-inf-20240514-133154-6wqeg-meta.warc.gz	11033	download job
l.savethechildren.es-inf-20240514-133154-6wqeg-meta.warc.os.cdx.gz	47	download
l.savethechildren.es-inf-20240514-133154-6wqeg.json	251	download job
market.feedbooks.com-inf-20240329-040738-7ctg7-00119.warc.gz	5368723672	download job
market.feedbooks.com-inf-20240329-040738-7ctg7-00119.warc.os.cdx.gz	1412876	download
movies.disney.com-inf-20240513-024117-drod2-00097.warc.gz	4206155313	download job
movies.disney.com-inf-20240513-024117-drod2-00097.warc.os.cdx.gz	1874783	download
movies.disney.com-inf-20240513-024117-drod2-meta.warc.gz	16444303	download job
movies.disney.com-inf-20240513-024117-drod2-meta.warc.os.cdx.gz	47	download
movies.disney.com-inf-20240513-024117-drod2.json	246	download job
neumonia.savethechildren.es-inf-20240514-133052-17mj6-00000.warc.gz	2085302	download job
neumonia.savethechildren.es-inf-20240514-133052-17mj6-00000.warc.os.cdx.gz	5181	download
neumonia.savethechildren.es-inf-20240514-133052-17mj6-meta.warc.gz	6453	download job
neumonia.savethechildren.es-inf-20240514-133052-17mj6-meta.warc.os.cdx.gz	47	download
neumonia.savethechildren.es-inf-20240514-133052-17mj6.json	258	download job
regalos.savethechildren.es-inf-20240514-132948-27ehj-00000.warc.gz	2777149	download job
regalos.savethechildren.es-inf-20240514-132948-27ehj-00000.warc.os.cdx.gz	7044	download
regalos.savethechildren.es-inf-20240514-132948-27ehj-meta.warc.gz	7836	download job
regalos.savethechildren.es-inf-20240514-132948-27ehj-meta.warc.os.cdx.gz	47	download
regalos.savethechildren.es-inf-20240514-132948-27ehj.json	257	download job
researchrepository.wvu.edu-inf-20240513-152217-1rdis-00055.warc.gz	5432314405	download job
researchrepository.wvu.edu-inf-20240513-152217-1rdis-00055.warc.os.cdx.gz	111849	download
restaurant56.nl-inf-20240514-130114-44h8g-meta.warc.gz	97776	download job
restaurant56.nl-inf-20240514-130114-44h8g-meta.warc.os.cdx.gz	47	download
restaurant56.nl-inf-20240514-130114-44h8g.json	243	download job
retos.savethechildren.es-inf-20240514-132906-5szsw-00000.warc.gz	3109649	download job
retos.savethechildren.es-inf-20240514-132906-5szsw-00000.warc.os.cdx.gz	6121	download
retos.savethechildren.es-inf-20240514-132906-5szsw-meta.warc.gz	7114	download job
retos.savethechildren.es-inf-20240514-132906-5szsw-meta.warc.os.cdx.gz	47	download
retos.savethechildren.es-inf-20240514-132906-5szsw.json	255	download job
storage.googleapis.com-inf-20240301-202801-5jgg7-08030.warc.gz	5718894962	download job
storage.googleapis.com-inf-20240301-202801-5jgg7-08030.warc.os.cdx.gz	942	download
storage.googleapis.com-inf-20240301-202801-5jgg7-08031.warc.gz	5514780525	download job
storage.googleapis.com-inf-20240301-202801-5jgg7-08031.warc.os.cdx.gz	998	download
urls-transfer.archivete.am-extras.chron.com_seed_urls.txt-inf-20240512-175410-bwkm9-00042.warc.gz	5385560611	download job
urls-transfer.archivete.am-extras.chron.com_seed_urls.txt-inf-20240512-175410-bwkm9-00042.warc.os.cdx.gz	50127	download
usprogram.gatesfoundation.org-inf-20240514-023825-791ol-00002.warc.gz	4618221692	download job
usprogram.gatesfoundation.org-inf-20240514-023825-791ol-00002.warc.os.cdx.gz	5713695	download
usprogram.gatesfoundation.org-inf-20240514-023825-791ol-meta.warc.gz	6399949	download job
usprogram.gatesfoundation.org-inf-20240514-023825-791ol-meta.warc.os.cdx.gz	47	download
usprogram.gatesfoundation.org-inf-20240514-023825-791ol.json	259	download job
vbbfw.savethechildren.es-inf-20240514-132705-e5v0u-00000.warc.gz	52416859	download job
vbbfw.savethechildren.es-inf-20240514-132705-e5v0u-00000.warc.os.cdx.gz	47665	download
vbbfw.savethechildren.es-inf-20240514-132705-e5v0u-meta.warc.gz	35697	download job
vbbfw.savethechildren.es-inf-20240514-132705-e5v0u-meta.warc.os.cdx.gz	47	download
vbbfw.savethechildren.es-inf-20240514-132705-e5v0u.json	255	download job
virtuelle-chorwelten.de-inf-20240514-130933-8ev69-00000.warc.gz	5880051938	download job
virtuelle-chorwelten.de-inf-20240514-130933-8ev69-00000.warc.os.cdx.gz	58668	download
www.buromaks.nl-inf-20240514-125732-dfot4-00000.warc.gz	15007441	download job
www.buromaks.nl-inf-20240514-125732-dfot4-00000.warc.os.cdx.gz	14398	download
www.buromaks.nl-inf-20240514-125732-dfot4-meta.warc.gz	12049	download job
www.buromaks.nl-inf-20240514-125732-dfot4-meta.warc.os.cdx.gz	47	download
www.buromaks.nl-inf-20240514-125732-dfot4.json	243	download job
www.caecilia-dielfen.de-inf-20240514-130916-5oqe6-00000.warc.gz	111198830	download job
www.caecilia-dielfen.de-inf-20240514-130916-5oqe6-00000.warc.os.cdx.gz	50567	download
www.caecilia-dielfen.de-inf-20240514-130916-5oqe6-meta.warc.gz	36343	download job
www.caecilia-dielfen.de-inf-20240514-130916-5oqe6-meta.warc.os.cdx.gz	47	download
www.caecilia-dielfen.de-inf-20240514-130916-5oqe6.json	250	download job
www.gatesfoundation.org-inf-20240513-180908-boad4-00002.warc.gz	5370080803	download job
www.gatesfoundation.org-inf-20240513-180908-boad4-00002.warc.os.cdx.gz	2948408	download
www.igmdb.org-inf-20240511-121709-71c7w-00071.warc.gz	5405816632	download job
www.igmdb.org-inf-20240511-121709-71c7w-00071.warc.os.cdx.gz	58742	download
www.mini2.info-inf-20240315-204545-25lna-00038.warc.gz	5368730649	download job
www.mini2.info-inf-20240315-204545-25lna-00038.warc.os.cdx.gz	10583588	download
www.multimarta.nl-inf-20240514-124104-1929a-00000.warc.gz	1371459739	download job
www.multimarta.nl-inf-20240514-124104-1929a-00000.warc.os.cdx.gz	709209	download
www.multimarta.nl-inf-20240514-124104-1929a-meta.warc.gz	424234	download job
www.multimarta.nl-inf-20240514-124104-1929a-meta.warc.os.cdx.gz	47	download
www.multimarta.nl-inf-20240514-124104-1929a.json	245	download job
www.netwerkevenement.ondernemersbelang.nl-inf-20240514-130458-23vnj-00000.warc.gz	6735	download job
www.netwerkevenement.ondernemersbelang.nl-inf-20240514-130458-23vnj-00000.warc.os.cdx.gz	322	download
www.netwerkevenement.ondernemersbelang.nl-inf-20240514-130458-23vnj-meta.warc.gz	3618	download job
www.netwerkevenement.ondernemersbelang.nl-inf-20240514-130458-23vnj-meta.warc.os.cdx.gz	47	download
www.netwerkevenement.ondernemersbelang.nl-inf-20240514-130458-23vnj.json	268	download job
www.new.ondernemersbelang.nl-inf-20240514-130512-5qtmu-00000.warc.gz	6574	download job
www.new.ondernemersbelang.nl-inf-20240514-130512-5qtmu-00000.warc.os.cdx.gz	308	download
www.new.ondernemersbelang.nl-inf-20240514-130512-5qtmu-meta.warc.gz	3584	download job
www.new.ondernemersbelang.nl-inf-20240514-130512-5qtmu-meta.warc.os.cdx.gz	47	download
www.new.ondernemersbelang.nl-inf-20240514-130512-5qtmu.json	255	download job
www.rainbow-gospel-voices.de-inf-20240514-131747-7zzy0-00000.warc.gz	9899996	download job
www.rainbow-gospel-voices.de-inf-20240514-131747-7zzy0-00000.warc.os.cdx.gz	26600	download
www.rainbow-gospel-voices.de-inf-20240514-131747-7zzy0-meta.warc.gz	18475	download job
www.rainbow-gospel-voices.de-inf-20240514-131747-7zzy0-meta.warc.os.cdx.gz	47	download
www.rainbow-gospel-voices.de-inf-20240514-131747-7zzy0.json	256	download job
www.sheetmusicplus.com-inf-20240512-212156-pg1ia-00004.warc.gz	5371490102	download job
www.sheetmusicplus.com-inf-20240512-212156-pg1ia-00004.warc.os.cdx.gz	1930166	download