Item archiveteam_archivebot_go_20250707180033_642aa8b2

Filename	Size
archiveteam_archivebot_go_20250707180033_642aa8b2.cdx.gz	20209495	download
archiveteam_archivebot_go_20250707180033_642aa8b2.cdx.idx	22788	download
archiveteam_archivebot_go_20250707180033_642aa8b2_files.xml	0	download
archiveteam_archivebot_go_20250707180033_642aa8b2_meta.sqlite	188416	download
archiveteam_archivebot_go_20250707180033_642aa8b2_meta.xml	1047	download
cdsarc.cds.unistra.fr-inf-20250316-091614-2ddo1-01556.warc.gz	6570477024	download job
cdsarc.cds.unistra.fr-inf-20250316-091614-2ddo1-01556.warc.os.cdx.gz	7904	download
ecfr.eu-inf-20250704-125115-3axt8-00180.warc.gz	5378335694	download job
ecfr.eu-inf-20250704-125115-3axt8-00180.warc.os.cdx.gz	891562	download
evangelicaldarkweb.org-inf-20250705-215547-6pvc4-00034.warc.gz	6107549999	download job
evangelicaldarkweb.org-inf-20250705-215547-6pvc4-00034.warc.os.cdx.gz	115423	download
ibn.aachen.ihk.de-inf-20250707-173539-9116b-00000.warc.gz	2469	download job
ibn.aachen.ihk.de-inf-20250707-173539-9116b-00000.warc.os.cdx.gz	47	download
ibn.aachen.ihk.de-inf-20250707-173539-9116b-meta.warc.gz	3630	download job
ibn.aachen.ihk.de-inf-20250707-173539-9116b-meta.warc.os.cdx.gz	47	download
ibn.aachen.ihk.de-inf-20250707-173539-9116b.json	245	download job
ihkschwaben.limequery.com-inf-20250707-173724-6830n-00000.warc.gz	19897538	download job
ihkschwaben.limequery.com-inf-20250707-173724-6830n-00000.warc.os.cdx.gz	23199	download
ihkschwaben.limequery.com-inf-20250707-173724-6830n-meta.warc.gz	18162	download job
ihkschwaben.limequery.com-inf-20250707-173724-6830n-meta.warc.os.cdx.gz	47	download
ihkschwaben.limequery.com-inf-20250707-173724-6830n.json	253	download job
jerseyjackpinball.com-inf-20250707-043018-339xm-00014.warc.gz	4669820237	download job
jerseyjackpinball.com-inf-20250707-043018-339xm-00014.warc.os.cdx.gz	2412854	download
jerseyjackpinball.com-inf-20250707-043018-339xm-meta.warc.gz	2062047	download job
jerseyjackpinball.com-inf-20250707-043018-339xm-meta.warc.os.cdx.gz	47	download
jerseyjackpinball.com-inf-20250707-043018-339xm.json	252	download job
karriere.abnahme.services.ihk.de-inf-20250707-173531-6e3we-00000.warc.gz	12655461	download job
karriere.abnahme.services.ihk.de-inf-20250707-173531-6e3we-00000.warc.os.cdx.gz	24901	download
karriere.abnahme.services.ihk.de-inf-20250707-173531-6e3we-meta.warc.gz	22193	download job
karriere.abnahme.services.ihk.de-inf-20250707-173531-6e3we-meta.warc.os.cdx.gz	47	download
karriere.abnahme.services.ihk.de-inf-20250707-173531-6e3we.json	260	download job
karriere.integration.services.ihk.de-inf-20250707-173145-7t7p8-00000.warc.gz	216817498	download job
karriere.integration.services.ihk.de-inf-20250707-173145-7t7p8-00000.warc.os.cdx.gz	247281	download
karriere.integration.services.ihk.de-inf-20250707-173145-7t7p8-meta.warc.gz	162699	download job
karriere.integration.services.ihk.de-inf-20250707-173145-7t7p8-meta.warc.os.cdx.gz	47	download
karriere.integration.services.ihk.de-inf-20250707-173145-7t7p8.json	264	download job
karriere.stuttgart.ihk.de-inf-20250707-172929-54f0x-00000.warc.gz	121906360	download job
karriere.stuttgart.ihk.de-inf-20250707-172929-54f0x-00000.warc.os.cdx.gz	151781	download
karriere.stuttgart.ihk.de-inf-20250707-172929-54f0x-meta.warc.gz	90677	download job
karriere.stuttgart.ihk.de-inf-20250707-172929-54f0x-meta.warc.os.cdx.gz	47	download
karriere.stuttgart.ihk.de-inf-20250707-172929-54f0x.json	253	download job
level4.ihk.de-inf-20250707-172445-dqe6q-00000.warc.gz	166986499	download job
level4.ihk.de-inf-20250707-172445-dqe6q-00000.warc.os.cdx.gz	326736	download
level4.ihk.de-inf-20250707-172445-dqe6q-meta.warc.gz	199781	download job
level4.ihk.de-inf-20250707-172445-dqe6q-meta.warc.os.cdx.gz	47	download
level4.ihk.de-inf-20250707-172445-dqe6q.json	241	download job
mpgu.su-inf-20250630-174942-5vqda-00051.warc.gz	5369116912	download job
mpgu.su-inf-20250630-174942-5vqda-00051.warc.os.cdx.gz	1969178	download
onlineanmeldung.schwaben.ihk.de-inf-20250707-172911-d0cp1-00000.warc.gz	168483621	download job
onlineanmeldung.schwaben.ihk.de-inf-20250707-172911-d0cp1-00000.warc.os.cdx.gz	271789	download
onlineanmeldung.schwaben.ihk.de-inf-20250707-172911-d0cp1-meta.warc.gz	160097	download job
onlineanmeldung.schwaben.ihk.de-inf-20250707-172911-d0cp1-meta.warc.os.cdx.gz	47	download
onlineanmeldung.schwaben.ihk.de-inf-20250707-172911-d0cp1.json	259	download job
real-life.echochurchmt.com-inf-20250707-165531-7alwe-00000.warc.gz	670547795	download job
real-life.echochurchmt.com-inf-20250707-165531-7alwe-00000.warc.os.cdx.gz	935096	download
real-life.echochurchmt.com-inf-20250707-165531-7alwe-meta.warc.gz	602050	download job
real-life.echochurchmt.com-inf-20250707-165531-7alwe-meta.warc.os.cdx.gz	47	download
real-life.echochurchmt.com-inf-20250707-165531-7alwe.json	251	download job
swscan.apple.com-shallow-20250707-173355-5f4wx-00000.warc.gz	161818	download job
swscan.apple.com-shallow-20250707-173355-5f4wx-00000.warc.os.cdx.gz	270	download
test.amtliches-verzeichnis.ihk.de-inf-20250707-174457-60yc9-00000.warc.gz	362532	download job
test.amtliches-verzeichnis.ihk.de-inf-20250707-174457-60yc9-00000.warc.os.cdx.gz	2750	download
test.amtliches-verzeichnis.ihk.de-inf-20250707-174457-60yc9-meta.warc.gz	5038	download job
test.amtliches-verzeichnis.ihk.de-inf-20250707-174457-60yc9-meta.warc.os.cdx.gz	47	download
test.amtliches-verzeichnis.ihk.de-inf-20250707-174457-60yc9.json	261	download job
texas.forums.rivals.com-inf-20250703-134408-4m682-00031.warc.gz	4096570857	download job
texas.forums.rivals.com-inf-20250703-134408-4m682-00031.warc.os.cdx.gz	3686357	download
texas.forums.rivals.com-inf-20250703-134408-4m682-meta.warc.gz	410860054	download job
texas.forums.rivals.com-inf-20250703-134408-4m682-meta.warc.os.cdx.gz	47	download
texas.forums.rivals.com-inf-20250703-134408-4m682.json	253	download job
trieuphong.quangtri.gov.vn-inf-20250707-150118-1378k-00000.warc.gz	5368837221	download job
trieuphong.quangtri.gov.vn-inf-20250707-150118-1378k-00000.warc.os.cdx.gz	1724116	download
umfrage.rostock.ihk.de-inf-20250707-173543-pg399-00000.warc.gz	16535379	download job
umfrage.rostock.ihk.de-inf-20250707-173543-pg399-00000.warc.os.cdx.gz	17046	download
umfrage.rostock.ihk.de-inf-20250707-173543-pg399-meta.warc.gz	13390	download job
umfrage.rostock.ihk.de-inf-20250707-173543-pg399-meta.warc.os.cdx.gz	47	download
umfrage.rostock.ihk.de-inf-20250707-173543-pg399.json	250	download job
unternehmen.gfi.ihk.de-inf-20250707-173733-bavjj-00000.warc.gz	14004968	download job
unternehmen.gfi.ihk.de-inf-20250707-173733-bavjj-00000.warc.os.cdx.gz	72255	download
unternehmen.gfi.ihk.de-inf-20250707-173733-bavjj-meta.warc.gz	53896	download job
unternehmen.gfi.ihk.de-inf-20250707-173733-bavjj-meta.warc.os.cdx.gz	47	download
unternehmen.gfi.ihk.de-inf-20250707-173733-bavjj.json	250	download job
urls-transfer.archivete.am-4dnucleome.org_subdomains.txt-inf-20250411-044610-9dhhx-01179.warc.gz	12536634390	download job
urls-transfer.archivete.am-4dnucleome.org_subdomains.txt-inf-20250411-044610-9dhhx-01179.warc.os.cdx.gz	826	download
urls-transfer.archivete.am-cap.gov_gocivilairpatrol.com_cap.news_subdomains.txt-inf-20250426-065415-yy94g-00685.warc.gz	5369972155	download job
urls-transfer.archivete.am-cap.gov_gocivilairpatrol.com_cap.news_subdomains.txt-inf-20250426-065415-yy94g-00685.warc.os.cdx.gz	597792	download
urls-transfer.archivete.am-dkvine.com_seed_urls.txt-inf-20250702-233434-7iacz-00016.warc.gz	5368865264	download job
urls-transfer.archivete.am-dkvine.com_seed_urls.txt-inf-20250702-233434-7iacz-00016.warc.os.cdx.gz	2570426	download
urls-transfer.archivete.am-ortapinc.com-non-www-and-www-inf-20250707-172420-14erg-00000.warc.gz	358393152	download job
urls-transfer.archivete.am-ortapinc.com-non-www-and-www-inf-20250707-172420-14erg-00000.warc.os.cdx.gz	249093	download
urls-transfer.archivete.am-ortapinc.com-non-www-and-www-inf-20250707-172420-14erg-meta.warc.gz	161413	download job
urls-transfer.archivete.am-ortapinc.com-non-www-and-www-inf-20250707-172420-14erg-meta.warc.os.cdx.gz	47	download
urls-transfer.archivete.am-ortapinc.com-non-www-and-www-inf-20250707-172420-14erg-urls.txt	50	download
urls-transfer.archivete.am-ortapinc.com-non-www-and-www-inf-20250707-172420-14erg.json	342	download job
urls-transfer.archivete.am-sternpinball.com_subdomains.txt-inf-20250707-033103-7cs9u-00025.warc.gz	5774698325	download job
urls-transfer.archivete.am-sternpinball.com_subdomains.txt-inf-20250707-033103-7cs9u-00025.warc.os.cdx.gz	551	download
urls-transfer.archivete.am-sternpinball.com_subdomains.txt-inf-20250707-033103-7cs9u-00026.warc.gz	6905999046	download job
urls-transfer.archivete.am-sternpinball.com_subdomains.txt-inf-20250707-033103-7cs9u-00026.warc.os.cdx.gz	432	download
usatoday.tumblr.com-inf-20250628-071652-9p1l8-00123.warc.gz	5369724836	download job
usatoday.tumblr.com-inf-20250628-071652-9p1l8-00123.warc.os.cdx.gz	1521407	download
vdi.hannover.ihk.de-inf-20250707-173809-dyyp3-00000.warc.gz	2390	download job
vdi.hannover.ihk.de-inf-20250707-173809-dyyp3-00000.warc.os.cdx.gz	47	download
vdi.hannover.ihk.de-inf-20250707-173809-dyyp3-meta.warc.gz	3551	download job
vdi.hannover.ihk.de-inf-20250707-173809-dyyp3-meta.warc.os.cdx.gz	47	download
vdi.hannover.ihk.de-inf-20250707-173809-dyyp3.json	247	download job
vdi.lueneburg.ihk.de-inf-20250707-173920-axihx-00000.warc.gz	2459	download job
vdi.lueneburg.ihk.de-inf-20250707-173920-axihx-00000.warc.os.cdx.gz	47	download
vdi.lueneburg.ihk.de-inf-20250707-173920-axihx-meta.warc.gz	3617	download job
vdi.lueneburg.ihk.de-inf-20250707-173920-axihx-meta.warc.os.cdx.gz	47	download
vdi.lueneburg.ihk.de-inf-20250707-173920-axihx.json	248	download job
vdigw.erfurt.ihk.de-inf-20250707-173924-ep296-00000.warc.gz	2462	download job
vdigw.erfurt.ihk.de-inf-20250707-173924-ep296-00000.warc.os.cdx.gz	47	download
vdigw.erfurt.ihk.de-inf-20250707-173924-ep296-meta.warc.gz	3605	download job
vdigw.erfurt.ihk.de-inf-20250707-173924-ep296-meta.warc.os.cdx.gz	47	download
vdigw.erfurt.ihk.de-inf-20250707-173924-ep296.json	247	download job
whatisproject2025.net-inf-20250706-203505-916h9-00021.warc.gz	5533732500	download job
whatisproject2025.net-inf-20250706-203505-916h9-00021.warc.os.cdx.gz	100060	download
www.assnat.qc.ca-inf-20250628-184306-cmlix-00345.warc.gz	6442911533	download job
www.assnat.qc.ca-inf-20250628-184306-cmlix-00345.warc.os.cdx.gz	5722	download
www.hellogyor.hu-inf-20250707-171554-7r39w-00000.warc.gz	600691332	download job
www.hellogyor.hu-inf-20250707-171554-7r39w-00000.warc.os.cdx.gz	609758	download
www.hellogyor.hu-inf-20250707-171554-7r39w-meta.warc.gz	355811	download job
www.hellogyor.hu-inf-20250707-171554-7r39w-meta.warc.os.cdx.gz	47	download
www.hellogyor.hu-inf-20250707-171554-7r39w.json	241	download job
www.npr.org-inf-20250330-091933-craqr-01429.warc.gz	5407953855	download job
www.npr.org-inf-20250330-091933-craqr-01429.warc.os.cdx.gz	598377	download
www.pbs.org-inf-20250330-092508-bykmh-08386.warc.gz	5585471888	download job
www.pbs.org-inf-20250330-092508-bykmh-08386.warc.os.cdx.gz	6076	download
www.pbs.org-inf-20250330-092508-bykmh-08387.warc.gz	5775216605	download job
www.pbs.org-inf-20250330-092508-bykmh-08387.warc.os.cdx.gz	10479	download
www.telepolis.de-inf-20241207-091925-2j219-00273.warc.gz	5513653716	download job
www.telepolis.de-inf-20241207-091925-2j219-00273.warc.os.cdx.gz	1069420	download
www.vaterland.li-inf-20250707-094405-dylw9-00004.warc.gz	5368802270	download job
www.vaterland.li-inf-20250707-094405-dylw9-00004.warc.os.cdx.gz	805268	download