Item archiveteam_archivebot_go_20260815102333_5d6f2b10

Filename	Size
archiveteam_archivebot_go_20260815102333_5d6f2b10.cdx.gz	23933330	download
archiveteam_archivebot_go_20260815102333_5d6f2b10.cdx.idx	33241	download
archiveteam_archivebot_go_20260815102333_5d6f2b10_files.xml	0	download
archiveteam_archivebot_go_20260815102333_5d6f2b10_meta.sqlite	188416	download
archiveteam_archivebot_go_20260815102333_5d6f2b10_meta.xml	1047	download
blogs.sw.siemens.com-inf-20260812-152856-fqtyk-00079.warc.gz	5586886108	download job
blogs.sw.siemens.com-inf-20260812-152856-fqtyk-00079.warc.os.cdx.gz	10086	download
campushistorycollection.omeka.net-inf-20260814-221743-3pfeg-00000.warc.gz	2425129090	download job
campushistorycollection.omeka.net-inf-20260814-221743-3pfeg-00000.warc.os.cdx.gz	6835574	download
campushistorycollection.omeka.net-inf-20260814-221743-3pfeg-meta.warc.gz	3661985	download job
campushistorycollection.omeka.net-inf-20260814-221743-3pfeg-meta.warc.os.cdx.gz	47	download
chinesemedicinehka.com-inf-20260815-092229-pkz5q-00000.warc.gz	695965418	download job
chinesemedicinehka.com-inf-20260815-092229-pkz5q-00000.warc.os.cdx.gz	433438	download
chinesemedicinehka.com-inf-20260815-092229-pkz5q-meta.warc.gz	392622	download job
chinesemedicinehka.com-inf-20260815-092229-pkz5q-meta.warc.os.cdx.gz	47	download
chinesemedicinehka.com-inf-20260815-092229-pkz5q.json	250	download job
cs50.tamnd.com-inf-20260812-032922-cckf3-00208.warc.gz	6338720600	download job
cs50.tamnd.com-inf-20260812-032922-cckf3-00208.warc.os.cdx.gz	2199	download
cs50.tamnd.com-inf-20260812-032922-cckf3-00209.warc.gz	5626108133	download job
cs50.tamnd.com-inf-20260812-032922-cckf3-00209.warc.os.cdx.gz	1331	download
cs50.tamnd.com-inf-20260812-032922-cckf3-00210.warc.gz	6080588357	download job
cs50.tamnd.com-inf-20260812-032922-cckf3-00210.warc.os.cdx.gz	1791	download
dannng.github.io-inf-20260815-094408-47pw8-00000.warc.gz	1284963415	download job
dannng.github.io-inf-20260815-094408-47pw8-00000.warc.os.cdx.gz	301393	download
dannng.github.io-inf-20260815-094408-47pw8-meta.warc.gz	184540	download job
dannng.github.io-inf-20260815-094408-47pw8-meta.warc.os.cdx.gz	47	download
dannng.github.io-inf-20260815-094408-47pw8.json	244	download job
encounternatomas.org-inf-20260815-003025-21q3x-00044.warc.gz	5999533086	download job
encounternatomas.org-inf-20260815-003025-21q3x-00044.warc.os.cdx.gz	1729	download
fotolubgens.lubgens.eu-inf-20260624-210047-648sl-00073.warc.gz	5368948986	download job
fotolubgens.lubgens.eu-inf-20260624-210047-648sl-00073.warc.os.cdx.gz	1055313	download
ftp.ncbi.nlm.nih.gov-inf-20260730-135633-ryrps-01104.warc.gz	5385086303	download job
ftp.ncbi.nlm.nih.gov-inf-20260730-135633-ryrps-01104.warc.os.cdx.gz	44360	download
ftp.ncbi.nlm.nih.gov-inf-20260730-135633-ryrps-01105.warc.gz	7742366549	download job
ftp.ncbi.nlm.nih.gov-inf-20260730-135633-ryrps-01105.warc.os.cdx.gz	49506	download
ftp.ncbi.nlm.nih.gov-inf-20260730-135633-ryrps-01106.warc.gz	5391325832	download job
ftp.ncbi.nlm.nih.gov-inf-20260730-135633-ryrps-01106.warc.os.cdx.gz	47627	download
gamewire.belloflostsouls.net-inf-20260815-102056-7dqrt-00000.warc.gz	17696	download job
gamewire.belloflostsouls.net-inf-20260815-102056-7dqrt-00000.warc.os.cdx.gz	334	download
gamewire.belloflostsouls.net-inf-20260815-102056-7dqrt-meta.warc.gz	3509	download job
gamewire.belloflostsouls.net-inf-20260815-102056-7dqrt-meta.warc.os.cdx.gz	47	download
gamewire.belloflostsouls.net-inf-20260815-102056-7dqrt.json	256	download job
havelland.bb.bsw-vg.de-inf-20260815-092631-b1ryn-00000.warc.gz	426426887	download job
havelland.bb.bsw-vg.de-inf-20260815-092631-b1ryn-00000.warc.os.cdx.gz	547703	download
havelland.bb.bsw-vg.de-inf-20260815-092631-b1ryn-meta.warc.gz	374212	download job
havelland.bb.bsw-vg.de-inf-20260815-092631-b1ryn-meta.warc.os.cdx.gz	47	download
havelland.bb.bsw-vg.de-inf-20260815-092631-b1ryn.json	250	download job
nik-rech.narod.ru-inf-20260815-100428-2z1hy-aborted-00000.warc.gz	2468	download job
nik-rech.narod.ru-inf-20260815-100428-2z1hy-aborted-00000.warc.os.cdx.gz	47	download
nik-rech.narod.ru-inf-20260815-100428-2z1hy-aborted-wpull.log.gz	894	download
nik-rech.narod.ru-inf-20260815-100428-2z1hy-aborted.json	244	download job
psd.org.br-inf-20260815-062319-ldudw-00000.warc.gz	5368756997	download job
psd.org.br-inf-20260815-062319-ldudw-00000.warc.os.cdx.gz	2669761	download
rhein-neckar-kreis.bw.bsw-vg.de-inf-20260815-101636-8grv7-00000.warc.gz	92555946	download job
rhein-neckar-kreis.bw.bsw-vg.de-inf-20260815-101636-8grv7-00000.warc.os.cdx.gz	90919	download
rhein-neckar-kreis.bw.bsw-vg.de-inf-20260815-101636-8grv7-meta.warc.gz	68101	download job
rhein-neckar-kreis.bw.bsw-vg.de-inf-20260815-101636-8grv7-meta.warc.os.cdx.gz	47	download
rhein-neckar-kreis.bw.bsw-vg.de-inf-20260815-101636-8grv7.json	259	download job
sachsen.buendnis-c.de-inf-20260815-092337-dqfzg-00000.warc.gz	702517323	download job
sachsen.buendnis-c.de-inf-20260815-092337-dqfzg-00000.warc.os.cdx.gz	534658	download
sachsen.buendnis-c.de-inf-20260815-092337-dqfzg-meta.warc.gz	383138	download job
sachsen.buendnis-c.de-inf-20260815-092337-dqfzg-meta.warc.os.cdx.gz	47	download
sachsen.buendnis-c.de-inf-20260815-092337-dqfzg.json	249	download job
sandzakpress.net-inf-20260815-101333-876vs-00000.warc.gz	3768355	download job
sandzakpress.net-inf-20260815-101333-876vs-00000.warc.os.cdx.gz	11680	download
sandzakpress.net-inf-20260815-101333-876vs-meta.warc.gz	9963	download job
sandzakpress.net-inf-20260815-101333-876vs-meta.warc.os.cdx.gz	47	download
sandzakpress.net-inf-20260815-101333-876vs.json	244	download job
spirit.bsw-vg.de-inf-20260815-092647-6ou85-00000.warc.gz	854685799	download job
spirit.bsw-vg.de-inf-20260815-092647-6ou85-00000.warc.os.cdx.gz	700904	download
spirit.bsw-vg.de-inf-20260815-092647-6ou85-meta.warc.gz	443048	download job
spirit.bsw-vg.de-inf-20260815-092647-6ou85-meta.warc.os.cdx.gz	47	download
spirit.bsw-vg.de-inf-20260815-092647-6ou85.json	244	download job
theukrainians.org-inf-20260814-063823-3obwe-00006.warc.gz	5489010791	download job
theukrainians.org-inf-20260814-063823-3obwe-00006.warc.os.cdx.gz	439263	download
ulf-lange.de-inf-20260815-093554-ads7z-00000.warc.gz	538731406	download job
ulf-lange.de-inf-20260815-093554-ads7z-00000.warc.os.cdx.gz	475476	download
ulf-lange.de-inf-20260815-093554-ads7z-meta.warc.gz	337771	download job
ulf-lange.de-inf-20260815-093554-ads7z-meta.warc.os.cdx.gz	47	download
ulf-lange.de-inf-20260815-093554-ads7z.json	240	download job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260815-100214-6izn3-00000.warc.gz	5284932	download job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260815-100214-6izn3-00000.warc.os.cdx.gz	18402	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260815-100214-6izn3-meta.warc.gz	13436	download job
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260815-100214-6izn3-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260815-100214-6izn3-urls.txt	29124	download
urls-transfer.archivete.am-dcas.dmdc.osd.mil_urls_v3.txt-shallow-20260815-100214-6izn3.json	368	download job
www.cas.cn-inf-20260813-133543-3wauo-00021.warc.gz	6616150180	download job
www.cas.cn-inf-20260813-133543-3wauo-00021.warc.os.cdx.gz	20682	download
www.dazeddigital.com-inf-20260727-160540-4m99k-00134.warc.gz	5375500471	download job
www.dazeddigital.com-inf-20260727-160540-4m99k-00134.warc.os.cdx.gz	1802782	download
www.ejtech.ai-inf-20260808-140927-8g1bd-00037.warc.gz	5371153561	download job
www.ejtech.ai-inf-20260808-140927-8g1bd-00037.warc.os.cdx.gz	1189078	download
www.factcheck.org-inf-20260807-124337-5pyrn-00205.warc.gz	5582044284	download job
www.factcheck.org-inf-20260807-124337-5pyrn-00205.warc.os.cdx.gz	2823925	download
www.fashiongonerogue.com-inf-20260806-131525-7j64d-00075.warc.gz	5369141214	download job
www.fashiongonerogue.com-inf-20260806-131525-7j64d-00075.warc.os.cdx.gz	1634090	download
www.jugend-oberbayern.de-inf-20260815-101403-1kiev-00000.warc.gz	10364305	download job
www.jugend-oberbayern.de-inf-20260815-101403-1kiev-00000.warc.os.cdx.gz	21687	download
www.jugend-oberbayern.de-inf-20260815-101403-1kiev-meta.warc.gz	17027	download job
www.jugend-oberbayern.de-inf-20260815-101403-1kiev-meta.warc.os.cdx.gz	47	download
www.jugend-oberbayern.de-inf-20260815-101403-1kiev.json	252	download job
www.mkultra.monster-shallow-20260815-101412-49lq1-00000.warc.gz	17253426	download job
www.mkultra.monster-shallow-20260815-101412-49lq1-00000.warc.os.cdx.gz	13085	download
www.mkultra.monster-shallow-20260815-101412-49lq1-meta.warc.gz	10898	download job
www.mkultra.monster-shallow-20260815-101412-49lq1-meta.warc.os.cdx.gz	47	download
www.mkultra.monster-shallow-20260815-101412-49lq1.json	251	download job
www.newcity.com-inf-20260811-161658-1yq17-00066.warc.gz	5380484493	download job
www.newcity.com-inf-20260811-161658-1yq17-00066.warc.os.cdx.gz	612804	download
www.sandzakpress.net-inf-20260815-101206-79ulg-aborted-00000.warc.gz	7545293	download job
www.sandzakpress.net-inf-20260815-101206-79ulg-aborted-00000.warc.os.cdx.gz	15226	download
www.sandzakpress.net-inf-20260815-101206-79ulg-aborted-wpull.log.gz	10119	download
www.sandzakpress.net-inf-20260815-101206-79ulg-aborted.json	247	download job
www.schlawe.de-inf-20260815-092902-1lwz5-00000.warc.gz	655761744	download job
www.schlawe.de-inf-20260815-092902-1lwz5-00000.warc.os.cdx.gz	579434	download
www.schlawe.de-inf-20260815-092902-1lwz5-meta.warc.gz	371840	download job
www.schlawe.de-inf-20260815-092902-1lwz5-meta.warc.os.cdx.gz	47	download
www.schlawe.de-inf-20260815-092902-1lwz5.json	242	download job
www.tfps.cn-inf-20260805-222849-4lafv-00011.warc.gz	1485691208	download job
www.tfps.cn-inf-20260805-222849-4lafv-00011.warc.os.cdx.gz	344127	download
www.tfps.cn-inf-20260805-222849-4lafv-meta.warc.gz	5396781	download job
www.tfps.cn-inf-20260805-222849-4lafv-meta.warc.os.cdx.gz	47	download
www.tfps.cn-inf-20260805-222849-4lafv.json	241	download job
www.wertebuendnis-bayern.de-inf-20260815-073618-cfnrb-00001.warc.gz	6010771020	download job
www.wertebuendnis-bayern.de-inf-20260815-073618-cfnrb-00001.warc.os.cdx.gz	1447074	download
www.xn--b1agacl3aeas4a.xn--p1ai-inf-20260815-101659-cye6y-00000.warc.gz	2610320	download job
www.xn--b1agacl3aeas4a.xn--p1ai-inf-20260815-101659-cye6y-00000.warc.os.cdx.gz	6762	download
www.xn--b1agacl3aeas4a.xn--p1ai-inf-20260815-101659-cye6y-meta.warc.gz	7769	download job
www.xn--b1agacl3aeas4a.xn--p1ai-inf-20260815-101659-cye6y-meta.warc.os.cdx.gz	47	download
www.xn--b1agacl3aeas4a.xn--p1ai-inf-20260815-101659-cye6y.json	259	download job
zermattflora.net-inf-20260814-191930-5o6vn-00030.warc.gz	5369319751	download job
zermattflora.net-inf-20260814-191930-5o6vn-00030.warc.os.cdx.gz	434184	download