Item archiveteam_archivebot_go_20201015230003

Filename	Size
archiveteam_archivebot_go_20201015230003.cdx.gz	29743583	download
archiveteam_archivebot_go_20201015230003.cdx.idx	32221	download
archiveteam_archivebot_go_20201015230003_files.xml	0	download
archiveteam_archivebot_go_20201015230003_meta.sqlite	248832	download
archiveteam_archivebot_go_20201015230003_meta.xml	968	download
bidenforum.org-inf-20201015-195821-dk835.json	244	download job
bidenfoundation.org-inf-20201015-191146-2a9bg-00000.warc.gz	1867740430	download job
bidenfoundation.org-inf-20201015-191146-2a9bg-00000.warc.os.cdx.gz	559738	download
big5.xinhuanet.com-inf-20200804-144727-f0ved-00116.warc.gz	5563911226	download job
big5.xinhuanet.com-inf-20200804-144727-f0ved-00116.warc.os.cdx.gz	2851	download
coronadashboard.rijksoverheid.nl-inf-20201015-221454-1i7fr-meta.warc.gz	83818	download job
coronadashboard.rijksoverheid.nl-inf-20201015-221454-1i7fr-meta.warc.os.cdx.gz	47	download
coronadashboard.rijksoverheid.nl-inf-20201015-221454-1i7fr.json	264	download job
coronamelder.nl-inf-20201015-200001-759tf.json	247	download job
debates.ndi.org-inf-20201015-133603-2f1pv-00002.warc.gz	5379337424	download job
debates.ndi.org-inf-20201015-133603-2f1pv-00002.warc.os.cdx.gz	1064416	download
diplomatie.belgium.be-shallow-20201015-223815-cfc5w-00000.warc.gz	2267737	download job
diplomatie.belgium.be-shallow-20201015-223815-cfc5w-00000.warc.os.cdx.gz	10669	download
diplomatie.belgium.be-shallow-20201015-223815-cfc5w-meta.warc.gz	9402	download job
diplomatie.belgium.be-shallow-20201015-223815-cfc5w-meta.warc.os.cdx.gz	47	download
freedomhouse.org-inf-20201014-032605-1txne-00028.warc.gz	5461736704	download job
freedomhouse.org-inf-20201014-032605-1txne-00028.warc.os.cdx.gz	2686588	download
global.upenn.edu-inf-20201015-210503-58e4m-00000.warc.gz	1955006318	download job
global.upenn.edu-inf-20201015-210503-58e4m-00000.warc.os.cdx.gz	939255	download
global.upenn.edu-inf-20201015-210503-58e4m-meta.warc.gz	603417	download job
global.upenn.edu-inf-20201015-210503-58e4m-meta.warc.os.cdx.gz	47	download
global.upenn.edu-inf-20201015-210503-58e4m.json	268	download job
hcrepublicans.org-inf-20201015-140839-74hfh-00000.warc.gz	29389055	download job
hcrepublicans.org-inf-20201015-140839-74hfh-00000.warc.os.cdx.gz	73391	download
hcrepublicans.org-inf-20201015-140839-74hfh-meta.warc.gz	50106	download job
hcrepublicans.org-inf-20201015-140839-74hfh-meta.warc.os.cdx.gz	47	download
hcrepublicans.org-inf-20201015-140839-74hfh.json	246	download job
linktr.ee-inf-20201015-203142-bt3rj-00000.warc.gz	60771377	download job
linktr.ee-inf-20201015-203142-bt3rj-00000.warc.os.cdx.gz	55690	download
mailchi.mp-shallow-20201015-201036-eozwp-00000.warc.gz	367420	download job
mailchi.mp-shallow-20201015-201036-eozwp-00000.warc.os.cdx.gz	1270	download
naftogaz-europe.com-inf-20201015-155328-4etvd-00000.warc.gz	5378081488	download job
naftogaz-europe.com-inf-20201015-155328-4etvd-00000.warc.os.cdx.gz	2740074	download
noonprop21.vote-inf-20201015-194258-9jkz1-00000.warc.gz	2327180028	download job
noonprop21.vote-inf-20201015-194258-9jkz1-00000.warc.os.cdx.gz	863361	download
noonprop21.vote-inf-20201015-194258-9jkz1-meta.warc.gz	584707	download job
noonprop21.vote-inf-20201015-194258-9jkz1-meta.warc.os.cdx.gz	47	download
noonprop21.vote-inf-20201015-194258-9jkz1.json	246	download job
pbc.upenn.edu-inf-20201015-214805-87d37-00000.warc.gz	79689409	download job
pbc.upenn.edu-inf-20201015-214805-87d37-00000.warc.os.cdx.gz	98467	download
pbc.upenn.edu-inf-20201015-214805-87d37-meta.warc.gz	63536	download job
pbc.upenn.edu-inf-20201015-214805-87d37-meta.warc.os.cdx.gz	47	download
pbc.upenn.edu-inf-20201015-214805-87d37.json	243	download job
shifti.org-shallow-20201015-205519-9zndd-00000.warc.gz	227997	download job
shifti.org-shallow-20201015-205519-9zndd-00000.warc.os.cdx.gz	4177	download
shifti.org-shallow-20201015-205519-9zndd.json	275	download job
stopprop16.org-inf-20201015-194326-7vlx4-00000.warc.gz	6258431626	download job
stopprop16.org-inf-20201015-194326-7vlx4-00000.warc.os.cdx.gz	686349	download
transfer.notkiska.pw-shallow-20201015-203605-4z4px-meta.warc.gz	3510	download job
transfer.notkiska.pw-shallow-20201015-203605-4z4px-meta.warc.os.cdx.gz	47	download
transfer.notkiska.pw-shallow-20201015-203612-alygb-00000.warc.gz	2476	download job
transfer.notkiska.pw-shallow-20201015-203612-alygb-00000.warc.os.cdx.gz	47	download
transfer.notkiska.pw-shallow-20201015-203612-alygb-meta.warc.gz	3615	download job
transfer.notkiska.pw-shallow-20201015-203612-alygb-meta.warc.os.cdx.gz	47	download
transfer.notkiska.pw-shallow-20201015-203714-alygb-00000.warc.gz	887144	download job
transfer.notkiska.pw-shallow-20201015-203714-alygb-00000.warc.os.cdx.gz	236	download
transfer.notkiska.pw-shallow-20201015-203714-alygb-meta.warc.gz	3520	download job
transfer.notkiska.pw-shallow-20201015-203714-alygb-meta.warc.os.cdx.gz	47	download
upgnet.com-inf-20201015-213943-dcqso-00000.warc.gz	13880864	download job
upgnet.com-inf-20201015-213943-dcqso-00000.warc.os.cdx.gz	29125	download
upgnet.com-inf-20201015-213943-dcqso-meta.warc.gz	21753	download job
upgnet.com-inf-20201015-213943-dcqso-meta.warc.os.cdx.gz	47	download
upgnet.com-inf-20201015-213943-dcqso.json	318	download job
urls-transfer.notkiska.pw-docs.microsoft.com-duspk-remaining-offsite-shallow-20200920-040417-7e2ub-00229.warc.gz	5520118631	download job
urls-transfer.notkiska.pw-docs.microsoft.com-duspk-remaining-offsite-shallow-20200920-040417-7e2ub-00229.warc.os.cdx.gz	136726	download
urls-transfer.notkiska.pw-docs.microsoft.com-duspk-remaining-offsite-shallow-20200920-040417-7e2ub-00230.warc.gz	5640538267	download job
urls-transfer.notkiska.pw-docs.microsoft.com-duspk-remaining-offsite-shallow-20200920-040417-7e2ub-00230.warc.os.cdx.gz	223871	download
urls-transfer.notkiska.pw-twitter-@BeauBidenFdn-shallow-20201015-173954-nsxsw-00000.warc.gz	5316809057	download job
urls-transfer.notkiska.pw-twitter-@BeauBidenFdn-shallow-20201015-173954-nsxsw-00000.warc.os.cdx.gz	2149912	download
urls-transfer.notkiska.pw-twitter-@BidenCancer-shallow-20201015-193547-5s9os-00000.warc.gz	3231809978	download job
urls-transfer.notkiska.pw-twitter-@BidenCancer-shallow-20201015-193547-5s9os-00000.warc.os.cdx.gz	977272	download
urls-transfer.notkiska.pw-twitter-@BidenCancer-shallow-20201015-193547-5s9os-meta.warc.gz	600048	download job
urls-transfer.notkiska.pw-twitter-@BidenCancer-shallow-20201015-193547-5s9os-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@DrBiden-shallow-20201015-195556-daifl-00000.warc.gz	1293709219	download job
urls-transfer.notkiska.pw-twitter-@DrBiden-shallow-20201015-195556-daifl-00000.warc.os.cdx.gz	1243114	download
urls-transfer.notkiska.pw-twitter-@DrBiden-shallow-20201015-195556-daifl-meta.warc.gz	731222	download job
urls-transfer.notkiska.pw-twitter-@DrBiden-shallow-20201015-195556-daifl-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@DrBiden-shallow-20201015-195556-daifl-urls.txt	50937	download
urls-transfer.notkiska.pw-twitter-@DrBiden-shallow-20201015-195556-daifl.json	326	download job
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00050.warc.gz	7048437578	download job
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00050.warc.os.cdx.gz	101594	download
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00051.warc.gz	5475084332	download job
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00051.warc.os.cdx.gz	109009	download
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00052.warc.gz	6396481001	download job
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00052.warc.os.cdx.gz	96063	download
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00053.warc.gz	5677304096	download job
urls-transfer.notkiska.pw-twitter-@GameSpot-btivf-remaining-shallow-20201014-210802-dofi2-00053.warc.os.cdx.gz	54688	download
urls-transfer.notkiska.pw-twitter-@IBMRedbooks-shallow-20201015-011333-icemm-00006.warc.gz	5371720578	download job
urls-transfer.notkiska.pw-twitter-@IBMRedbooks-shallow-20201015-011333-icemm-00006.warc.os.cdx.gz	3361697	download
urls-transfer.notkiska.pw-twitter-@PennBiden-shallow-20201015-210334-4vv4v-00000.warc.gz	5407522299	download job
urls-transfer.notkiska.pw-twitter-@PennBiden-shallow-20201015-210334-4vv4v-00000.warc.os.cdx.gz	392275	download
urls-transfer.notkiska.pw-twitter-@SteveScully-shallow-20201015-214925-7m6ug-00000.warc.gz	4859255	download job
urls-transfer.notkiska.pw-twitter-@SteveScully-shallow-20201015-214925-7m6ug-00000.warc.os.cdx.gz	9959	download
urls-transfer.notkiska.pw-twitter-@SteveScully-shallow-20201015-214925-7m6ug-meta.warc.gz	9475	download job
urls-transfer.notkiska.pw-twitter-@SteveScully-shallow-20201015-214925-7m6ug-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@SteveScully-shallow-20201015-214925-7m6ug-urls.txt	327	download
urls-transfer.notkiska.pw-twitter-@SteveScully-shallow-20201015-214925-7m6ug.json	334	download job
urls-transfer.notkiska.pw-twitter-@TransEquality-shallow-20201014-214554-9yj9d-00017.warc.gz	5423958000	download job
urls-transfer.notkiska.pw-twitter-@TransEquality-shallow-20201014-214554-9yj9d-00017.warc.os.cdx.gz	735315	download
urls-transfer.notkiska.pw-twitter-@UDBidenInst-shallow-20201015-200959-c7371-00000.warc.gz	479693944	download job
urls-transfer.notkiska.pw-twitter-@UDBidenInst-shallow-20201015-200959-c7371-00000.warc.os.cdx.gz	581295	download
urls-transfer.notkiska.pw-twitter-@UDBidenInst-shallow-20201015-200959-c7371-meta.warc.gz	378325	download job
urls-transfer.notkiska.pw-twitter-@UDBidenInst-shallow-20201015-200959-c7371-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@UDBidenInst-shallow-20201015-200959-c7371.json	334	download job
urls-transfer.notkiska.pw-twitter-@Ultrasyd1-shallow-20201015-203639-bjuyy-00000.warc.gz	1848400962	download job
urls-transfer.notkiska.pw-twitter-@Ultrasyd1-shallow-20201015-203639-bjuyy-00000.warc.os.cdx.gz	827931	download
urls-transfer.notkiska.pw-twitter-@Ultrasyd1-shallow-20201015-203639-bjuyy-meta.warc.gz	461710	download job
urls-transfer.notkiska.pw-twitter-@Ultrasyd1-shallow-20201015-203639-bjuyy-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@Ultrasyd1-shallow-20201015-203639-bjuyy-urls.txt	49362	download
urls-transfer.notkiska.pw-twitter-@Ultrasyd1-shallow-20201015-203639-bjuyy.json	332	download job
urls-transfer.notkiska.pw-twitter-@bidenfoundation-shallow-20201015-191441-aduyx-00001.warc.gz	4757632153	download job
urls-transfer.notkiska.pw-twitter-@bidenfoundation-shallow-20201015-191441-aduyx-00001.warc.os.cdx.gz	1577398	download
urls-transfer.notkiska.pw-twitter-@bidenfoundation-shallow-20201015-191441-aduyx-meta.warc.gz	1413246	download job
urls-transfer.notkiska.pw-twitter-@bidenfoundation-shallow-20201015-191441-aduyx-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@bidenfoundation-shallow-20201015-191441-aduyx-urls.txt	75529	download
urls-transfer.notkiska.pw-twitter-@bidenfoundation-shallow-20201015-191441-aduyx.json	342	download job
urls-transfer.notkiska.pw-twitter-@mikercarpenter-shallow-20201015-214928-7ml9u-00000.warc.gz	39538273	download job
urls-transfer.notkiska.pw-twitter-@mikercarpenter-shallow-20201015-214928-7ml9u-00000.warc.os.cdx.gz	73168	download
urls-transfer.notkiska.pw-twitter-@mikercarpenter-shallow-20201015-214928-7ml9u-meta.warc.gz	49778	download job
urls-transfer.notkiska.pw-twitter-@mikercarpenter-shallow-20201015-214928-7ml9u-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@mikercarpenter-shallow-20201015-214928-7ml9u-urls.txt	2264	download
urls-transfer.notkiska.pw-twitter-@mikercarpenter-shallow-20201015-214928-7ml9u.json	340	download job
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv-00000.warc.gz	5734471778	download job
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv-00000.warc.os.cdx.gz	146569	download
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv-00001.warc.gz	2528	download job
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv-00001.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv-meta.warc.gz	88939	download job
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv-urls.txt	20697	download
urls-transfer.notkiska.pw-www-mkb-nl-corona.txt-shallow-20201015-203045-2issv.json	339	download job
urls-transfer.notkiska.pw-www-rivm-nl-corona.txt-shallow-20201015-215800-dtivk-00000.warc.gz	1185623726	download job
urls-transfer.notkiska.pw-www-rivm-nl-corona.txt-shallow-20201015-215800-dtivk-00000.warc.os.cdx.gz	126692	download
urls-transfer.notkiska.pw-www-rivm-nl-corona.txt-shallow-20201015-215800-dtivk-meta.warc.gz	74821	download job
urls-transfer.notkiska.pw-www-rivm-nl-corona.txt-shallow-20201015-215800-dtivk-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-www-rivm-nl-corona.txt-shallow-20201015-215800-dtivk-urls.txt	163408	download
urls-transfer.notkiska.pw-www-rivm-nl-corona.txt-shallow-20201015-215800-dtivk.json	341	download job
voteyeson110.org-inf-20201015-192152-e1oer.json	247	download job
voteyesonr.org-inf-20201015-193325-e7w8p-00002.warc.gz	4015802926	download job
voteyesonr.org-inf-20201015-193325-e7w8p-00002.warc.os.cdx.gz	582632	download
vpn.pbc.upenn.edu-inf-20201015-210351-7f9hg-00000.warc.gz	671797	download job
vpn.pbc.upenn.edu-inf-20201015-210351-7f9hg-00000.warc.os.cdx.gz	2363	download
vpn.pbc.upenn.edu-inf-20201015-210351-7f9hg-meta.warc.gz	5832	download job
vpn.pbc.upenn.edu-inf-20201015-210351-7f9hg-meta.warc.os.cdx.gz	47	download
vpn.pbc.upenn.edu-inf-20201015-210351-7f9hg-wpull.log.gz	3125	download
vpn.pbc.upenn.edu-inf-20201015-210351-7f9hg.json	247	download job
winecellarmedia.com-inf-20201015-164631-8dwt8-00009.warc.gz	5373229476	download job
winecellarmedia.com-inf-20201015-164631-8dwt8-00009.warc.os.cdx.gz	220196	download
winecellarmedia.com-inf-20201015-164631-8dwt8-00010.warc.gz	5432372030	download job
winecellarmedia.com-inf-20201015-164631-8dwt8-00010.warc.os.cdx.gz	396656	download
winecellarmedia.com-inf-20201015-164631-8dwt8-00011.warc.gz	5370171639	download job
winecellarmedia.com-inf-20201015-164631-8dwt8-00011.warc.os.cdx.gz	278743	download
winecellarmedia.com-inf-20201015-164631-8dwt8-00012.warc.gz	5427810698	download job
winecellarmedia.com-inf-20201015-164631-8dwt8-00012.warc.os.cdx.gz	706603	download
winecellarmedia.com-inf-20201015-164631-8dwt8-00013.warc.gz	5372115964	download job
winecellarmedia.com-inf-20201015-164631-8dwt8-00013.warc.os.cdx.gz	565066	download
www.bideninstitute.udel.edu-inf-20201015-202449-1hp67-00000.warc.gz	191673474	download job
www.bideninstitute.udel.edu-inf-20201015-202449-1hp67-00000.warc.os.cdx.gz	215378	download
www.bideninstitute.udel.edu-inf-20201015-202449-1hp67-meta.warc.gz	140624	download job
www.bideninstitute.udel.edu-inf-20201015-202449-1hp67-meta.warc.os.cdx.gz	47	download
www.bideninstitute.udel.edu-inf-20201015-202449-1hp67.json	256	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00638.warc.gz	1073762437	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00638.warc.os.cdx.gz	343929	download
www.christianpost.com-shallow-20201015-212416-6qxa9-00000.warc.gz	11654324	download job
www.christianpost.com-shallow-20201015-212416-6qxa9-00000.warc.os.cdx.gz	17736	download
www.christianpost.com-shallow-20201015-212416-6qxa9-meta.warc.gz	13687	download job
www.christianpost.com-shallow-20201015-212416-6qxa9-meta.warc.os.cdx.gz	47	download
www.christianpost.com-shallow-20201015-212416-6qxa9.json	324	download job
www.cleanmissouri.org-inf-20201015-194427-7thje-meta.warc.gz	442925	download job
www.cleanmissouri.org-inf-20201015-194427-7thje-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20201015-192406-49xiu-meta.warc.gz	125016	download job
www.flickr.com-inf-20201015-192406-49xiu-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20201015-192459-9iotj-00000.warc.gz	409628823	download job
www.flickr.com-inf-20201015-192459-9iotj-00000.warc.os.cdx.gz	234681	download
www.independent.org-shallow-20201015-200501-1ip4d-00000.warc.gz	5527691	download job
www.independent.org-shallow-20201015-200501-1ip4d-00000.warc.os.cdx.gz	17461	download
www.independent.org-shallow-20201015-200501-1ip4d.json	278	download job
www.mykitlog.com-inf-20201011-074655-9r8lq-00004.warc.gz	5368769325	download job
www.mykitlog.com-inf-20201011-074655-9r8lq-00004.warc.os.cdx.gz	3422142	download
www.rijkshuisstijl.nl-shallow-20201015-222449-6nw6o-00000.warc.gz	1232113	download job
www.rijkshuisstijl.nl-shallow-20201015-222449-6nw6o-00000.warc.os.cdx.gz	1960	download
www.rijkshuisstijl.nl-shallow-20201015-222449-6nw6o-meta.warc.gz	4616	download job
www.rijkshuisstijl.nl-shallow-20201015-222449-6nw6o-meta.warc.os.cdx.gz	47	download
www.rijkshuisstijl.nl-shallow-20201015-222449-6nw6o.json	293	download job
www.rijkshuisstijl.nl-shallow-20201015-222517-7xzdg-00000.warc.gz	1244860	download job
www.rijkshuisstijl.nl-shallow-20201015-222517-7xzdg-00000.warc.os.cdx.gz	2045	download
www.rijkshuisstijl.nl-shallow-20201015-222517-7xzdg.json	307	download job
www.rijkshuisstijl.nl-shallow-20201015-222539-b4tno-00000.warc.gz	20693021	download job
www.rijkshuisstijl.nl-shallow-20201015-222539-b4tno-00000.warc.os.cdx.gz	19279	download
www.rijkshuisstijl.nl-shallow-20201015-222539-b4tno-meta.warc.gz	18183	download job
www.rijkshuisstijl.nl-shallow-20201015-222539-b4tno-meta.warc.os.cdx.gz	47	download
www.rijkshuisstijl.nl-shallow-20201015-222539-b4tno.json	303	download job
www.rijkshuisstijl.nl-shallow-20201015-222730-f04ho-00000.warc.gz	1231719	download job
www.rijkshuisstijl.nl-shallow-20201015-222730-f04ho-00000.warc.os.cdx.gz	2013	download
www.rijkshuisstijl.nl-shallow-20201015-222730-f04ho-meta.warc.gz	4735	download job
www.rijkshuisstijl.nl-shallow-20201015-222730-f04ho-meta.warc.os.cdx.gz	47	download
www.rijkshuisstijl.nl-shallow-20201015-222730-f04ho.json	377	download job
www.rijkshuisstijl.nl-shallow-20201015-222832-9zi4e-00000.warc.gz	1661431	download job
www.rijkshuisstijl.nl-shallow-20201015-222832-9zi4e-00000.warc.os.cdx.gz	8205	download
www.rijkshuisstijl.nl-shallow-20201015-222913-7mkxm-00000.warc.gz	1239727	download job
www.rijkshuisstijl.nl-shallow-20201015-222913-7mkxm-00000.warc.os.cdx.gz	2158	download
www.rijkshuisstijl.nl-shallow-20201015-222913-7mkxm.json	301	download job
www.rijkshuisstijl.nl-shallow-20201015-222941-ah9ys-00000.warc.gz	1231894	download job
www.rijkshuisstijl.nl-shallow-20201015-222941-ah9ys-00000.warc.os.cdx.gz	2020	download
www.rijkshuisstijl.nl-shallow-20201015-222941-ah9ys.json	374	download job
www.rijkshuisstijl.nl-shallow-20201015-223020-a26m5-00000.warc.gz	1475213	download job
www.rijkshuisstijl.nl-shallow-20201015-223020-a26m5-00000.warc.os.cdx.gz	2269	download
www.rijkshuisstijl.nl-shallow-20201015-223020-a26m5-meta.warc.gz	4812	download job
www.rijkshuisstijl.nl-shallow-20201015-223020-a26m5-meta.warc.os.cdx.gz	47	download
www.rijkshuisstijl.nl-shallow-20201015-223020-a26m5.json	304	download job
www.rijkshuisstijl.nl-shallow-20201015-223059-csc1l-00000.warc.gz	1249084	download job
www.rijkshuisstijl.nl-shallow-20201015-223059-csc1l-00000.warc.os.cdx.gz	2068	download
www.rijkshuisstijl.nl-shallow-20201015-223059-csc1l-meta.warc.gz	4727	download job
www.rijkshuisstijl.nl-shallow-20201015-223059-csc1l-meta.warc.os.cdx.gz	47	download
www.rijkshuisstijl.nl-shallow-20201015-223122-edbyk-00000.warc.gz	1247926	download job
www.rijkshuisstijl.nl-shallow-20201015-223122-edbyk-00000.warc.os.cdx.gz	2063	download
www.rijkshuisstijl.nl-shallow-20201015-223122-edbyk-meta.warc.gz	4734	download job
www.rijkshuisstijl.nl-shallow-20201015-223122-edbyk-meta.warc.os.cdx.gz	47	download
www.rijkshuisstijl.nl-shallow-20201015-223122-edbyk.json	317	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00167.warc.gz	5376457271	download job
www.teenvogue.com-inf-20200928-163823-6ac7g-00167.warc.os.cdx.gz	996151	download
www.theblaze.com-shallow-20201015-211701-6qkur-00000.warc.gz	3789	download job
www.theblaze.com-shallow-20201015-211701-6qkur-00000.warc.os.cdx.gz	241	download
www.theblaze.com-shallow-20201015-211701-6qkur-meta.warc.gz	3530	download job
www.theblaze.com-shallow-20201015-211701-6qkur-meta.warc.os.cdx.gz	47	download
www.theblaze.com-shallow-20201015-211701-6qkur.json	297	download job
www.theblaze.com-shallow-20201015-224226-6qkur-meta.warc.gz	11484	download job
www.theblaze.com-shallow-20201015-224226-6qkur-meta.warc.os.cdx.gz	47	download
www.thegatewaypundit.com-inf-20201002-220654-4zoku-00090.warc.gz	5530687497	download job
www.thegatewaypundit.com-inf-20201002-220654-4zoku-00090.warc.os.cdx.gz	1717121	download
www.vforsanjacinto.com-inf-20201015-193439-6jpju.json	252	download job
yesmeasureb.com-inf-20201015-194151-7zkwu.json	245	download job
yeson108.org-inf-20201015-193150-80dj6-meta.warc.gz	100573	download job
yeson108.org-inf-20201015-193150-80dj6-meta.warc.os.cdx.gz	47	download
yesonmeasuren.org-inf-20201015-192830-229wg-00000.warc.gz	36377119	download job
yesonmeasuren.org-inf-20201015-192830-229wg-00000.warc.os.cdx.gz	120755	download
yesonmeasuren.org-inf-20201015-192830-229wg.json	248	download job