Item archiveteam_archivebot_go_20240602120322_24bf5b86

Filename	Size
archiveteam_archivebot_go_20240602120322_24bf5b86.cdx.gz	135376	download
archiveteam_archivebot_go_20240602120322_24bf5b86.cdx.idx	67	download
archiveteam_archivebot_go_20240602120322_24bf5b86_files.xml	0	download
archiveteam_archivebot_go_20240602120322_24bf5b86_meta.sqlite	176128	download
archiveteam_archivebot_go_20240602120322_24bf5b86_meta.xml	1045	download
developers.google.com-inf-20240601-165639-1ut8g-00017.warc.gz	5593820958	download job
developers.google.com-inf-20240601-165639-1ut8g-00017.warc.os.cdx.gz	3417	download
developers.google.com-inf-20240601-165639-1ut8g-00018.warc.gz	5559384287	download job
developers.google.com-inf-20240601-165639-1ut8g-00018.warc.os.cdx.gz	3561	download
dspace.nplg.gov.ge-inf-20240518-160308-crlmb-00717.warc.gz	5378572272	download job
dspace.nplg.gov.ge-inf-20240518-160308-crlmb-00717.warc.os.cdx.gz	132043	download
elsikatainen.fi-inf-20240602-111826-7ekak-00000.warc.gz	2867108736	download job
elsikatainen.fi-inf-20240602-111826-7ekak-00000.warc.os.cdx.gz	1316446	download
elsikatainen.fi-inf-20240602-111826-7ekak-meta.warc.gz	937430	download job
elsikatainen.fi-inf-20240602-111826-7ekak-meta.warc.os.cdx.gz	47	download
elsikatainen.fi-inf-20240602-111826-7ekak.json	248	download job
europepmc.org-inf-20240212-215511-8x1ov-03405.warc.gz	5380487940	download job
europepmc.org-inf-20240212-215511-8x1ov-03405.warc.os.cdx.gz	210272	download
forums.radioreference.com-inf-20240509-135047-rbd5j-00033.warc.gz	5368712287	download job
forums.radioreference.com-inf-20240509-135047-rbd5j-00033.warc.os.cdx.gz	1149159	download
forums.techarena.in-inf-20240601-194621-3lcx4-00002.warc.gz	6067204696	download job
forums.techarena.in-inf-20240601-194621-3lcx4-00002.warc.os.cdx.gz	4514388	download
initiativeouryjalloh.wordpress.com-inf-20240602-092720-81air-00001.warc.gz	1637977417	download job
initiativeouryjalloh.wordpress.com-inf-20240602-092720-81air-00001.warc.os.cdx.gz	1060468	download
initiativeouryjalloh.wordpress.com-inf-20240602-092720-81air-meta.warc.gz	2125393	download job
initiativeouryjalloh.wordpress.com-inf-20240602-092720-81air-meta.warc.os.cdx.gz	47	download
initiativeouryjalloh.wordpress.com-inf-20240602-092720-81air.json	262	download job
jessijokelainen.fi-inf-20240602-114109-ez2lm-00000.warc.gz	1914215753	download job
jessijokelainen.fi-inf-20240602-114109-ez2lm-00000.warc.os.cdx.gz	225087	download
jessijokelainen.fi-inf-20240602-114109-ez2lm-meta.warc.gz	149267	download job
jessijokelainen.fi-inf-20240602-114109-ez2lm-meta.warc.os.cdx.gz	47	download
jessijokelainen.fi-inf-20240602-114109-ez2lm.json	250	download job
kadler.abgeordnete.fdpbt.de-inf-20240602-114241-dp31m-00000.warc.gz	940597185	download job
kadler.abgeordnete.fdpbt.de-inf-20240602-114241-dp31m-00000.warc.os.cdx.gz	343530	download
kadler.abgeordnete.fdpbt.de-inf-20240602-114241-dp31m-meta.warc.gz	209289	download job
kadler.abgeordnete.fdpbt.de-inf-20240602-114241-dp31m-meta.warc.os.cdx.gz	47	download
kadler.abgeordnete.fdpbt.de-inf-20240602-114241-dp31m.json	255	download job
kansasfamilyvoice.com-inf-20240602-062133-ed28k-00000.warc.gz	2696341562	download job
kansasfamilyvoice.com-inf-20240602-062133-ed28k-00000.warc.os.cdx.gz	3507213	download
kansasfamilyvoice.com-inf-20240602-062133-ed28k-meta.warc.gz	2686079	download job
kansasfamilyvoice.com-inf-20240602-062133-ed28k-meta.warc.os.cdx.gz	47	download
kansasfamilyvoice.com-inf-20240602-062133-ed28k.json	252	download job
knut-abraham.de-inf-20240602-114237-7plv7-00000.warc.gz	441025783	download job
knut-abraham.de-inf-20240602-114237-7plv7-00000.warc.os.cdx.gz	60752	download
knut-abraham.de-inf-20240602-114237-7plv7-meta.warc.gz	39397	download job
knut-abraham.de-inf-20240602-114237-7plv7-meta.warc.os.cdx.gz	47	download
knut-abraham.de-inf-20240602-114237-7plv7.json	243	download job
lottatuominen.fi-inf-20240602-113014-42eqd-00000.warc.gz	388787087	download job
lottatuominen.fi-inf-20240602-113014-42eqd-00000.warc.os.cdx.gz	205368	download
lottatuominen.fi-inf-20240602-113014-42eqd-meta.warc.gz	147464	download job
lottatuominen.fi-inf-20240602-113014-42eqd-meta.warc.os.cdx.gz	47	download
lottatuominen.fi-inf-20240602-113014-42eqd.json	249	download job
opposition24.com-inf-20240530-142305-cxivf-00047.warc.gz	5831010444	download job
opposition24.com-inf-20240530-142305-cxivf-00047.warc.os.cdx.gz	88014	download
sebastiantynkkynen.com-inf-20240602-112332-b9ksp-00000.warc.gz	2615041850	download job
sebastiantynkkynen.com-inf-20240602-112332-b9ksp-00000.warc.os.cdx.gz	600649	download
sebastiantynkkynen.com-inf-20240602-112332-b9ksp-meta.warc.gz	430801	download job
sebastiantynkkynen.com-inf-20240602-112332-b9ksp-meta.warc.os.cdx.gz	47	download
sebastiantynkkynen.com-inf-20240602-112332-b9ksp.json	255	download job
thekeep.eiu.edu-inf-20240530-002558-burk8-00079.warc.gz	6591513837	download job
thekeep.eiu.edu-inf-20240530-002558-burk8-00079.warc.os.cdx.gz	2044	download
truthout.org-inf-20240408-165731-16a89-00566.warc.gz	5395723602	download job
truthout.org-inf-20240408-165731-16a89-00566.warc.os.cdx.gz	526359	download
urls-transfer.archivete.am-2024-05-31_repo.mongodb.org.txt-shallow-20240531-221208-cinrn-00184.warc.gz	5380163635	download job
urls-transfer.archivete.am-2024-05-31_repo.mongodb.org.txt-shallow-20240531-221208-cinrn-00184.warc.os.cdx.gz	20119	download
urls-transfer.archivete.am-2024-05-31_repo.mongodb.org.txt-shallow-20240531-221208-cinrn-00185.warc.gz	5371669116	download job
urls-transfer.archivete.am-2024-05-31_repo.mongodb.org.txt-shallow-20240531-221208-cinrn-00185.warc.os.cdx.gz	28938	download
www.coisacoisa.info-inf-20240602-070132-idqxw-00005.warc.gz	5194391301	download job
www.coisacoisa.info-inf-20240602-070132-idqxw-00005.warc.os.cdx.gz	201720	download
www.coisacoisa.info-inf-20240602-070132-idqxw-meta.warc.gz	1721787	download job
www.coisacoisa.info-inf-20240602-070132-idqxw-meta.warc.os.cdx.gz	47	download
www.coisacoisa.info-inf-20240602-070132-idqxw.json	244	download job
www.inkahopsu.fi-inf-20240602-112654-3s4ot-00000.warc.gz	3468575594	download job
www.inkahopsu.fi-inf-20240602-112654-3s4ot-00000.warc.os.cdx.gz	822357	download
www.inkahopsu.fi-inf-20240602-112654-3s4ot-meta.warc.gz	528560	download job
www.inkahopsu.fi-inf-20240602-112654-3s4ot-meta.warc.os.cdx.gz	47	download
www.inkahopsu.fi-inf-20240602-112654-3s4ot.json	249	download job
www.iratoppinen.fi-inf-20240602-113903-a5poa-00000.warc.gz	362598368	download job
www.iratoppinen.fi-inf-20240602-113903-a5poa-00000.warc.os.cdx.gz	41693	download
www.iratoppinen.fi-inf-20240602-113903-a5poa-meta.warc.gz	27119	download job
www.iratoppinen.fi-inf-20240602-113903-a5poa-meta.warc.os.cdx.gz	47	download
www.iratoppinen.fi-inf-20240602-113903-a5poa.json	251	download job
www.katihakkinen.fi-inf-20240602-115539-24pas-00000.warc.gz	100615063	download job
www.katihakkinen.fi-inf-20240602-115539-24pas-00000.warc.os.cdx.gz	109831	download
www.katihakkinen.fi-inf-20240602-115539-24pas-meta.warc.gz	72049	download job
www.katihakkinen.fi-inf-20240602-115539-24pas-meta.warc.os.cdx.gz	47	download
www.katihakkinen.fi-inf-20240602-115539-24pas.json	256	download job
www.mariamiala.fi-inf-20240602-115743-30r3f-00000.warc.gz	75662025	download job
www.mariamiala.fi-inf-20240602-115743-30r3f-00000.warc.os.cdx.gz	81632	download
www.mariamiala.fi-inf-20240602-115743-30r3f-meta.warc.gz	51173	download job
www.mariamiala.fi-inf-20240602-115743-30r3f-meta.warc.os.cdx.gz	47	download
www.mariamiala.fi-inf-20240602-115743-30r3f.json	250	download job
www.mariarautanen.fi-inf-20240602-114930-3f8fu-00000.warc.gz	54031472	download job
www.mariarautanen.fi-inf-20240602-114930-3f8fu-00000.warc.os.cdx.gz	65539	download
www.mariarautanen.fi-inf-20240602-114930-3f8fu-meta.warc.gz	49744	download job
www.mariarautanen.fi-inf-20240602-114930-3f8fu-meta.warc.os.cdx.gz	47	download
www.mariarautanen.fi-inf-20240602-114930-3f8fu.json	252	download job
www.mikaaaltola.eu-inf-20240602-115643-5hv31-00000.warc.gz	67689295	download job
www.mikaaaltola.eu-inf-20240602-115643-5hv31-00000.warc.os.cdx.gz	132539	download
www.oscarbyman.fi-inf-20240602-115449-dgqcj-00000.warc.gz	46834273	download job
www.oscarbyman.fi-inf-20240602-115449-dgqcj-00000.warc.os.cdx.gz	51786	download
www.oscarbyman.fi-inf-20240602-115449-dgqcj-meta.warc.gz	32773	download job
www.oscarbyman.fi-inf-20240602-115449-dgqcj-meta.warc.os.cdx.gz	47	download
www.oscarbyman.fi-inf-20240602-115449-dgqcj.json	249	download job
www.patrick-breyer.de-inf-20240530-184320-de2jt-00114.warc.gz	5616189386	download job
www.patrick-breyer.de-inf-20240530-184320-de2jt-00114.warc.os.cdx.gz	514655	download
www.patrick-breyer.de-inf-20240530-184320-de2jt-00115.warc.gz	5622603648	download job
www.patrick-breyer.de-inf-20240530-184320-de2jt-00115.warc.os.cdx.gz	51905	download
www.polskieradio.pl-inf-20231221-075717-djrf2-01829.warc.gz	5835846095	download job
www.polskieradio.pl-inf-20231221-075717-djrf2-01829.warc.os.cdx.gz	6786	download
www.tollbrothers.com-inf-20240602-044819-brcq7-00001.warc.gz	5368986169	download job
www.tollbrothers.com-inf-20240602-044819-brcq7-00001.warc.os.cdx.gz	2663699	download
www.tuulikousa.com-inf-20240602-113704-a60x3-00000.warc.gz	127435019	download job
www.tuulikousa.com-inf-20240602-113704-a60x3-00000.warc.os.cdx.gz	123790	download
www.tuulikousa.com-inf-20240602-113704-a60x3-meta.warc.gz	84819	download job
www.tuulikousa.com-inf-20240602-113704-a60x3-meta.warc.os.cdx.gz	47	download
www.tuulikousa.com-inf-20240602-113704-a60x3.json	251	download job
www.wmtv15news.com-shallow-20240602-115904-7pgn0-00000.warc.gz	14412504	download job
www.wmtv15news.com-shallow-20240602-115904-7pgn0-00000.warc.os.cdx.gz	13331	download
www.wmtv15news.com-shallow-20240602-115904-7pgn0-meta.warc.gz	11384	download job
www.wmtv15news.com-shallow-20240602-115904-7pgn0-meta.warc.os.cdx.gz	47	download
www.wmtv15news.com-shallow-20240602-115904-7pgn0.json	345	download job