Item archiveteam_archivebot_go_20190515060001

View on Internet Archive

Filename	Size
americanlibrariesmagazine.org-inf-20190510-043106-d4sz7-00008.warc.gz	5473385960	download   job
americanlibrariesmagazine.org-inf-20190510-043106-d4sz7-00008.warc.os.cdx.gz	2496086	download
americanlibrariesmagazine.org-inf-20190510-043106-d4sz7-00009.warc.gz	5378201099	download   job
americanlibrariesmagazine.org-inf-20190510-043106-d4sz7-00009.warc.os.cdx.gz	272525	download
archiveteam_archivebot_go_20190515060001.cdx.gz	129834685	download
archiveteam_archivebot_go_20190515060001.cdx.idx	122429	download
archiveteam_archivebot_go_20190515060001_archive.torrent	822531	download
archiveteam_archivebot_go_20190515060001_files.xml	0	download
archiveteam_archivebot_go_20190515060001_meta.sqlite	164864	download
archiveteam_archivebot_go_20190515060001_meta.xml	973	download
attika.christogenea.org-shallow-20190515-011459-adxoh-00000.warc.gz	98053	download   job
attika.christogenea.org-shallow-20190515-011459-adxoh-00000.warc.os.cdx.gz	866	download
blog.jim.com-inf-20190514-173559-e31bt-00001.warc.gz	5368725547	download   job
blog.jim.com-inf-20190514-173559-e31bt-00001.warc.os.cdx.gz	3482583	download
blog.jim.com-inf-20190514-173559-e31bt-00002.warc.gz	5518836117	download   job
blog.jim.com-inf-20190514-173559-e31bt-00002.warc.os.cdx.gz	2669118	download
blog.livedoor.jp-inf-20190509-175024-3djk2-00017.warc.gz	2668028197	download   job
blog.livedoor.jp-inf-20190509-175024-3djk2-00017.warc.os.cdx.gz	3657935	download
blog.livedoor.jp-inf-20190509-175024-3djk2-meta.warc.gz	53735435	download   job
blog.livedoor.jp-inf-20190509-175024-3djk2-meta.warc.os.cdx.gz	47	download
blog.livedoor.jp-inf-20190509-175024-3djk2.json	251	download   job
camerondugmore.co.za-inf-20190515-010547-9m872-00000.warc.gz	322972931	download   job
camerondugmore.co.za-inf-20190515-010547-9m872-00000.warc.os.cdx.gz	887143	download
camerondugmore.co.za-inf-20190515-010547-9m872-meta.warc.gz	455766	download   job
camerondugmore.co.za-inf-20190515-010547-9m872-meta.warc.os.cdx.gz	47	download
camerondugmore.co.za-inf-20190515-010547-9m872.json	250	download   job
ccgi.vortexion.plus.com-inf-20190515-023043-eqli4-00000.warc.gz	73964634	download   job
ccgi.vortexion.plus.com-inf-20190515-023043-eqli4-00000.warc.os.cdx.gz	91800	download
ccgi.vortexion.plus.com-inf-20190515-023043-eqli4-meta.warc.gz	58245	download   job
ccgi.vortexion.plus.com-inf-20190515-023043-eqli4-meta.warc.os.cdx.gz	47	download
ccgi.vortexion.plus.com-inf-20190515-023043-eqli4.json	247	download   job
chat.codoh.com-shallow-20190515-025504-7ymdv-meta.warc.gz	64994	download   job
chat.codoh.com-shallow-20190515-025504-7ymdv-meta.warc.os.cdx.gz	47	download
chat.codoh.com-shallow-20190515-025504-7ymdv.json	248	download   job
club.myce.com-inf-20190513-081128-46rna-00002.warc.gz	5369044689	download   job
club.myce.com-inf-20190513-081128-46rna-00002.warc.os.cdx.gz	6231132	download
clubseodeverdade.com-inf-20190515-001800-coii7-00000.warc.gz	249082795	download   job
clubseodeverdade.com-inf-20190515-001800-coii7-00000.warc.os.cdx.gz	410641	download
clubseodeverdade.com-inf-20190515-001800-coii7-meta.warc.gz	296754	download   job
clubseodeverdade.com-inf-20190515-001800-coii7-meta.warc.os.cdx.gz	47	download
community.ubnt.com-inf-20190214-041029-4vxgd-00098.warc.gz	5368716440	download   job
community.ubnt.com-inf-20190214-041029-4vxgd-00098.warc.os.cdx.gz	5631542	download
dabun.net-inf-20190512-053851-10ecw-00005.warc.gz	5368821500	download   job
dabun.net-inf-20190512-053851-10ecw-00005.warc.os.cdx.gz	7892411	download
disboard.org-inf-20190501-170853-cul77-00009.warc.gz	5368719500	download   job
disboard.org-inf-20190501-170853-cul77-00009.warc.os.cdx.gz	25022657	download
dissenter.com-inf-20190416-164130-5k22c-00132.warc.gz	5369295290	download   job
dissenter.com-inf-20190416-164130-5k22c-00132.warc.os.cdx.gz	843793	download
forum.codoh.com-inf-20190512-200721-1a4ug-00018.warc.gz	5369222514	download   job
forum.codoh.com-inf-20190512-200721-1a4ug-00018.warc.os.cdx.gz	1730626	download
gamefaqs.gamespot.com-inf-20181124-172703-7phhd-00120.warc.gz	5368730231	download   job
gamefaqs.gamespot.com-inf-20181124-172703-7phhd-00120.warc.os.cdx.gz	6396010	download
golden.com-inf-20190501-042518-asreq-00081.warc.gz	5368926587	download   job
golden.com-inf-20190501-042518-asreq-00081.warc.os.cdx.gz	1219915	download
isdb.pw-inf-20190513-161528-e2ymx-00017.warc.gz	5372177104	download   job
isdb.pw-inf-20190513-161528-e2ymx-00017.warc.os.cdx.gz	2101292	download
isdb.pw-inf-20190513-161528-e2ymx-00018.warc.gz	5368890263	download   job
isdb.pw-inf-20190513-161528-e2ymx-00018.warc.os.cdx.gz	1967401	download
jim.jim.com-shallow-20190515-045139-cvsl9-00000.warc.gz	27305	download   job
jim.jim.com-shallow-20190515-045139-cvsl9-00000.warc.os.cdx.gz	459	download
jim.jim.com-shallow-20190515-045139-cvsl9-meta.warc.gz	3590	download   job
jim.jim.com-shallow-20190515-045139-cvsl9-meta.warc.os.cdx.gz	47	download
jim.jim.com-shallow-20190515-045139-cvsl9.json	245	download   job
philosophyofscienceportal.blogspot.com-inf-20190513-025012-6oce3-00003.warc.gz	3001031621	download   job
philosophyofscienceportal.blogspot.com-inf-20190513-025012-6oce3-00003.warc.os.cdx.gz	10482034	download
philosophyofscienceportal.blogspot.com-inf-20190513-025012-6oce3-meta.warc.gz	17284314	download   job
philosophyofscienceportal.blogspot.com-inf-20190513-025012-6oce3-meta.warc.os.cdx.gz	47	download
philosophyofscienceportal.blogspot.com-inf-20190513-025012-6oce3.json	263	download   job
phoenix.christogenea.org-shallow-20190515-012108-di406-00000.warc.gz	3824	download   job
phoenix.christogenea.org-shallow-20190515-012108-di406-00000.warc.os.cdx.gz	220	download
phoenix.christogenea.org-shallow-20190515-012108-di406.json	257	download   job
radio5.christogenea.org-shallow-20190515-032239-ba7w1-00000.warc.gz	3959	download   job
radio5.christogenea.org-shallow-20190515-032239-ba7w1-00000.warc.os.cdx.gz	218	download
radio5.christogenea.org-shallow-20190515-032239-ba7w1-meta.warc.gz	3392	download   job
radio5.christogenea.org-shallow-20190515-032239-ba7w1-meta.warc.os.cdx.gz	47	download
radio5.christogenea.org-shallow-20190515-032239-ba7w1.json	256	download   job
radio6.christogenea.org-inf-20190515-034307-yqpji-00000.warc.gz	5436825132	download   job
radio6.christogenea.org-inf-20190515-034307-yqpji-00000.warc.os.cdx.gz	92788	download
radio6.christogenea.org-inf-20190515-034307-yqpji-00001.warc.gz	5566457318	download   job
radio6.christogenea.org-inf-20190515-034307-yqpji-00001.warc.os.cdx.gz	33053	download
radio6.christogenea.org-inf-20190515-034307-yqpji-00002.warc.gz	5377339263	download   job
radio6.christogenea.org-inf-20190515-034307-yqpji-00002.warc.os.cdx.gz	30852	download
radio6.christogenea.org-inf-20190515-034307-yqpji-00003.warc.gz	5370043144	download   job
radio6.christogenea.org-inf-20190515-034307-yqpji-00003.warc.os.cdx.gz	81667	download
rahyabmohsaver.com-inf-20190515-034151-3nsgp-00000.warc.gz	2478	download   job
rahyabmohsaver.com-inf-20190515-034151-3nsgp-00000.warc.os.cdx.gz	47	download
rahyabmohsaver.com-inf-20190515-034151-3nsgp-meta.warc.gz	3486	download   job
rahyabmohsaver.com-inf-20190515-034151-3nsgp-meta.warc.os.cdx.gz	47	download
rahyabmohsaver.com-inf-20190515-034151-3nsgp.json	249	download   job
russiatweets.com-inf-20190507-010513-exgtv-00081.warc.gz	5368907000	download   job
russiatweets.com-inf-20190507-010513-exgtv-00081.warc.os.cdx.gz	9846098	download
sites.google.com-inf-20190510-080639-464hf-00019.warc.gz	5368713837	download   job
sites.google.com-inf-20190510-080639-464hf-00019.warc.os.cdx.gz	5074524	download
sjsuspartans.com-inf-20190513-221305-2amk9-00004.warc.gz	5370004883	download   job
sjsuspartans.com-inf-20190513-221305-2amk9-00004.warc.os.cdx.gz	1027182	download
sputniknews.com-inf-20190505-084431-an2l7-00080.warc.gz	5499303089	download   job
sputniknews.com-inf-20190505-084431-an2l7-00080.warc.os.cdx.gz	1575504	download
sputniknews.com-inf-20190505-084431-an2l7-00081.warc.gz	5369468087	download   job
sputniknews.com-inf-20190505-084431-an2l7-00081.warc.os.cdx.gz	335183	download
sputniknews.com-inf-20190505-084431-an2l7-00082.warc.gz	5430963019	download   job
sputniknews.com-inf-20190505-084431-an2l7-00082.warc.os.cdx.gz	1314926	download
testing.christogenea.org-shallow-20190515-011257-15ttl-00000.warc.gz	4021	download   job
testing.christogenea.org-shallow-20190515-011257-15ttl-00000.warc.os.cdx.gz	219	download
testing.christogenea.org-shallow-20190515-011257-15ttl-meta.warc.gz	3515	download   job
testing.christogenea.org-shallow-20190515-011257-15ttl-meta.warc.os.cdx.gz	47	download
testing.christogenea.org-shallow-20190515-011257-15ttl.json	257	download   job
urls-transfer.notkiska.pw-facebook-user-ParliamentofRSA.txt-shallow-20190515-010656-ey6cb-00000.warc.gz	142662909	download   job
urls-transfer.notkiska.pw-facebook-user-ParliamentofRSA.txt-shallow-20190515-010656-ey6cb-00000.warc.os.cdx.gz	251687	download
urls-transfer.notkiska.pw-facebook-user-ParliamentofRSA.txt-shallow-20190515-010656-ey6cb-meta.warc.gz	122645	download   job
urls-transfer.notkiska.pw-facebook-user-ParliamentofRSA.txt-shallow-20190515-010656-ey6cb-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-user-ParliamentofRSA.txt-shallow-20190515-010656-ey6cb.json	359	download   job
urls-transfer.notkiska.pw-twitter-user-CapeTimesSA.txt-shallow-20190515-004048-17lhu-00000.warc.gz	889771882	download   job
urls-transfer.notkiska.pw-twitter-user-CapeTimesSA.txt-shallow-20190515-004048-17lhu-00000.warc.os.cdx.gz	1207669	download
urls-transfer.notkiska.pw-twitter-user-CapeTimesSA.txt-shallow-20190515-004048-17lhu-meta.warc.gz	641092	download   job
urls-transfer.notkiska.pw-twitter-user-CapeTimesSA.txt-shallow-20190515-004048-17lhu-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-user-CapeTimesSA.txt-shallow-20190515-004048-17lhu-urls.txt	615271	download
urls-transfer.notkiska.pw-twitter-user-CapeTimesSA.txt-shallow-20190515-004048-17lhu.json	349	download   job
urls-transfer.notkiska.pw-twitter-user-ParliamentofRSA.txt-shallow-20190515-030749-8985c-00000.warc.gz	2377092026	download   job
urls-transfer.notkiska.pw-twitter-user-ParliamentofRSA.txt-shallow-20190515-030749-8985c-00000.warc.os.cdx.gz	4362803	download
urls-transfer.notkiska.pw-twitter-user-ParliamentofRSA.txt-shallow-20190515-030749-8985c-meta.warc.gz	2255037	download   job
urls-transfer.notkiska.pw-twitter-user-ParliamentofRSA.txt-shallow-20190515-030749-8985c-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-user-ParliamentofRSA.txt-shallow-20190515-030749-8985c-urls.txt	1381707	download
urls-transfer.notkiska.pw-twitter-user-ParliamentofRSA.txt-shallow-20190515-030749-8985c.json	357	download   job
urls-transfer.notkiska.pw-twitter-user-WesternCapeGov.txt-shallow-20190515-003625-7pu7j-00000.warc.gz	1886524813	download   job
urls-transfer.notkiska.pw-twitter-user-WesternCapeGov.txt-shallow-20190515-003625-7pu7j-00000.warc.os.cdx.gz	2144754	download
urls-transfer.notkiska.pw-twitter-user-WesternCapeGov.txt-shallow-20190515-003625-7pu7j-meta.warc.gz	1143590	download   job
urls-transfer.notkiska.pw-twitter-user-WesternCapeGov.txt-shallow-20190515-003625-7pu7j-meta.warc.os.cdx.gz	47	download
urls-transfer.sh-blog.lemonde.fre-additional-urls.txt-inf-20190409-113141-bn7kh-00090.warc.gz	5369513994	download   job
urls-transfer.sh-blog.lemonde.fre-additional-urls.txt-inf-20190409-113141-bn7kh-00090.warc.os.cdx.gz	297816	download
wp.me-inf-20190515-014819-2xpzm-00000.warc.gz	277394326	download   job
wp.me-inf-20190515-014819-2xpzm-00000.warc.os.cdx.gz	242497	download
wp.me-inf-20190515-014819-2xpzm-meta.warc.gz	172229	download   job
wp.me-inf-20190515-014819-2xpzm-meta.warc.os.cdx.gz	47	download
wp.me-inf-20190515-014819-2xpzm.json	245	download   job
www.boogle.plus.com-inf-20190515-025703-tv7ax-00000.warc.gz	2318531	download   job
www.boogle.plus.com-inf-20190515-025703-tv7ax-00000.warc.os.cdx.gz	1834	download
www.boogle.plus.com-inf-20190515-025703-tv7ax-meta.warc.gz	4343	download   job
www.boogle.plus.com-inf-20190515-025703-tv7ax-meta.warc.os.cdx.gz	47	download
www.boogle.plus.com-inf-20190515-025703-tv7ax.json	243	download   job
www.cnn.com-shallow-20190515-031439-zhyw7-00000.warc.gz	64869930	download   job
www.cnn.com-shallow-20190515-031439-zhyw7-00000.warc.os.cdx.gz	40014	download
www.cnn.com-shallow-20190515-031439-zhyw7.json	305	download   job
www.flickr.com-shallow-20190515-031222-5psfh.json	267	download   job
www.joelbenford.plus.com-inf-20190515-024216-ctz5i-00000.warc.gz	65694695	download   job
www.joelbenford.plus.com-inf-20190515-024216-ctz5i-00000.warc.os.cdx.gz	115657	download
www.joelbenford.plus.com-inf-20190515-024216-ctz5i-meta.warc.gz	67824	download   job
www.joelbenford.plus.com-inf-20190515-024216-ctz5i-meta.warc.os.cdx.gz	47	download
www.joelbenford.plus.com-inf-20190515-024216-ctz5i.json	248	download   job
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-00001.warc.gz	1073791111	download   job
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-00001.warc.os.cdx.gz	672607	download
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-00002.warc.gz	1073983840	download   job
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-00002.warc.os.cdx.gz	666311	download
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-00003.warc.gz	1073744937	download   job
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-00003.warc.os.cdx.gz	1301910	download
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-meta.warc.gz	2721629	download   job
www.le-grenier-informatique.fr-inf-20190514-180143-7htf5-meta.warc.os.cdx.gz	47	download
www.minedminds.org-inf-20190515-034223-9qtsq-00000.warc.gz	7718286	download   job
www.minedminds.org-inf-20190515-034223-9qtsq-00000.warc.os.cdx.gz	3789	download
www.minedminds.org-inf-20190515-034223-9qtsq-meta.warc.gz	5788	download   job
www.minedminds.org-inf-20190515-034223-9qtsq-meta.warc.os.cdx.gz	47	download
www.minedminds.org-inf-20190515-034223-9qtsq.json	247	download   job
www.puposet.plus.com-inf-20190515-031006-1mtyy-00000.warc.gz	42886268	download   job
www.puposet.plus.com-inf-20190515-031006-1mtyy-00000.warc.os.cdx.gz	64227	download
www.puposet.plus.com-inf-20190515-031006-1mtyy-meta.warc.gz	37815	download   job
www.puposet.plus.com-inf-20190515-031006-1mtyy-meta.warc.os.cdx.gz	47	download
www.puposet.plus.com-inf-20190515-031006-1mtyy.json	244	download   job
www.sinemia.com-inf-20190427-214134-6u3nh-00028.warc.gz	5376838979	download   job
www.sinemia.com-inf-20190427-214134-6u3nh-00028.warc.os.cdx.gz	11056391	download
www.soap.com.au-inf-20190515-044146-cczon-00000.warc.gz	29353414	download   job
www.soap.com.au-inf-20190515-044146-cczon-00000.warc.os.cdx.gz	51785	download
www.soap.com.au-inf-20190515-044146-cczon-meta.warc.gz	35488	download   job
www.soap.com.au-inf-20190515-044146-cczon-meta.warc.os.cdx.gz	47	download
www.soap.com.au-inf-20190515-044146-cczon.json	245	download   job
www.unnecessaryquotes.com-inf-20190514-154828-4gypz-00000.warc.gz	5416081396	download   job
www.unnecessaryquotes.com-inf-20190514-154828-4gypz-00000.warc.os.cdx.gz	8041055	download