Item archiveteam_archivebot_go_20200820150002

Filename	Size
acro.ceu.edu-inf-20200820-114842-5kw1v-00000.warc.gz	5369244864	download job
acro.ceu.edu-inf-20200820-114842-5kw1v-00000.warc.os.cdx.gz	1436810	download
acro.ceu.edu-inf-20200820-114842-5kw1v-meta.warc.gz	2074193	download job
acro.ceu.edu-inf-20200820-114842-5kw1v-meta.warc.os.cdx.gz	47	download
acro.ceu.edu-inf-20200820-114842-5kw1v.json	241	download job
actjust.ceu.edu-inf-20200820-141217-1t192-00000.warc.gz	310364941	download job
actjust.ceu.edu-inf-20200820-141217-1t192-00000.warc.os.cdx.gz	413039	download
actjust.ceu.edu-inf-20200820-141217-1t192.json	244	download job
archiveteam_archivebot_go_20200820150002.cdx.gz	48427108	download
archiveteam_archivebot_go_20200820150002.cdx.idx	47794	download
archiveteam_archivebot_go_20200820150002_files.xml	0	download
archiveteam_archivebot_go_20200820150002_meta.sqlite	224256	download
archiveteam_archivebot_go_20200820150002_meta.xml	968	download
californiaglobe.com-shallow-20200820-125951-7so39-00000.warc.gz	13180119	download job
californiaglobe.com-shallow-20200820-125951-7so39-00000.warc.os.cdx.gz	16163	download
californiaglobe.com-shallow-20200820-125951-7so39-meta.warc.gz	15647	download job
californiaglobe.com-shallow-20200820-125951-7so39-meta.warc.os.cdx.gz	47	download
californiaglobe.com-shallow-20200820-125951-7so39.json	331	download job
cellohealth.com-inf-20200820-135848-d6w5d-00000.warc.gz	517704161	download job
cellohealth.com-inf-20200820-135848-d6w5d-00000.warc.os.cdx.gz	426194	download
cellohealth.com-inf-20200820-135848-d6w5d.json	244	download job
channel9.msdn.com-inf-20200804-232506-7i2a5-00820.warc.gz	5368954174	download job
channel9.msdn.com-inf-20200804-232506-7i2a5-00820.warc.os.cdx.gz	3172487	download
chowtimes.com-inf-20200819-235037-7nc9j-00001.warc.gz	5368714765	download job
chowtimes.com-inf-20200819-235037-7nc9j-00001.warc.os.cdx.gz	3526503	download
clayandmilk.com-shallow-20200820-135047-efcnt-00000.warc.gz	4635809	download job
clayandmilk.com-shallow-20200820-135047-efcnt-00000.warc.os.cdx.gz	15843	download
clayandmilk.com-shallow-20200820-135047-efcnt-meta.warc.gz	12513	download job
clayandmilk.com-shallow-20200820-135047-efcnt-meta.warc.os.cdx.gz	47	download
clayandmilk.com-shallow-20200820-135047-efcnt.json	310	download job
clutch.win-inf-20200801-220229-bxf3k-01870.warc.gz	5372043566	download job
clutch.win-inf-20200801-220229-bxf3k-01870.warc.os.cdx.gz	42310	download
ektoplazm.com-inf-20200704-233408-66i1h-00170.warc.gz	5391253212	download job
ektoplazm.com-inf-20200704-233408-66i1h-00170.warc.os.cdx.gz	10275	download
jerry-mahoney.com-inf-20200819-235828-dpezq-00006.warc.gz	2783663466	download job
jerry-mahoney.com-inf-20200819-235828-dpezq-00006.warc.os.cdx.gz	1013979	download
jerry-mahoney.com-inf-20200819-235828-dpezq-meta.warc.gz	7799420	download job
jerry-mahoney.com-inf-20200819-235828-dpezq-meta.warc.os.cdx.gz	47	download
jerry-mahoney.com-inf-20200819-235828-dpezq.json	246	download job
morningberryz48.wordpress.com-inf-20200818-210104-czfnl-00012.warc.gz	5369423799	download job
morningberryz48.wordpress.com-inf-20200818-210104-czfnl-00012.warc.os.cdx.gz	3101626	download
omnimax.com-inf-20200820-135340-cz9u0-00000.warc.gz	322606546	download job
omnimax.com-inf-20200820-135340-cz9u0-00000.warc.os.cdx.gz	540274	download
omnimax.com-inf-20200820-135340-cz9u0-meta.warc.gz	341155	download job
omnimax.com-inf-20200820-135340-cz9u0-meta.warc.os.cdx.gz	47	download
omnimax.com-inf-20200820-135340-cz9u0.json	240	download job
pharmaphorum.com-shallow-20200820-135728-9kp7f-00000.warc.gz	3170720	download job
pharmaphorum.com-shallow-20200820-135728-9kp7f-00000.warc.os.cdx.gz	18869	download
pharmaphorum.com-shallow-20200820-135728-9kp7f-meta.warc.gz	16352	download job
pharmaphorum.com-shallow-20200820-135728-9kp7f-meta.warc.os.cdx.gz	47	download
pharmaphorum.com-shallow-20200820-135728-9kp7f.json	292	download job
progressivegrocer.com-shallow-20200820-134558-6rvj6-00000.warc.gz	3211481	download job
progressivegrocer.com-shallow-20200820-134558-6rvj6-00000.warc.os.cdx.gz	15429	download
progressivegrocer.com-shallow-20200820-134558-6rvj6-meta.warc.gz	13456	download job
progressivegrocer.com-shallow-20200820-134558-6rvj6-meta.warc.os.cdx.gz	47	download
progressivegrocer.com-shallow-20200820-134558-6rvj6.json	301	download job
technical.ly-shallow-20200820-140048-4jywx-00000.warc.gz	5447454	download job
technical.ly-shallow-20200820-140048-4jywx-00000.warc.os.cdx.gz	4949	download
technical.ly-shallow-20200820-140048-4jywx-meta.warc.gz	6591	download job
technical.ly-shallow-20200820-140048-4jywx-meta.warc.os.cdx.gz	47	download
technical.ly-shallow-20200820-140048-4jywx.json	332	download job
theideagirlsays.wordpress.com-inf-20200820-044254-dtxhu-00003.warc.gz	4724373398	download job
theideagirlsays.wordpress.com-inf-20200820-044254-dtxhu-00003.warc.os.cdx.gz	2138946	download
theideagirlsays.wordpress.com-inf-20200820-044254-dtxhu-meta.warc.gz	12879740	download job
theideagirlsays.wordpress.com-inf-20200820-044254-dtxhu-meta.warc.os.cdx.gz	47	download
thevirustracker.com-inf-20200620-170113-b912c-00059.warc.gz	5368801699	download job
thevirustracker.com-inf-20200620-170113-b912c-00059.warc.os.cdx.gz	5603523	download
theyellowkid.wordpress.com-inf-20200820-032942-5v50i-00000.warc.gz	5368742849	download job
theyellowkid.wordpress.com-inf-20200820-032942-5v50i-00000.warc.os.cdx.gz	6345495	download
urls-transfer.notkiska.pw-2020-08-20-www.intomore.com-post-urls.txt-shallow-20200820-062410-dqgl1-00001.warc.gz	4046344205	download job
urls-transfer.notkiska.pw-2020-08-20-www.intomore.com-post-urls.txt-shallow-20200820-062410-dqgl1-00001.warc.os.cdx.gz	1896952	download
urls-transfer.notkiska.pw-2020-08-20-www.intomore.com-post-urls.txt-shallow-20200820-062410-dqgl1-meta.warc.gz	1897984	download job
urls-transfer.notkiska.pw-2020-08-20-www.intomore.com-post-urls.txt-shallow-20200820-062410-dqgl1-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-2020-08-20-www.intomore.com-post-urls.txt-shallow-20200820-062410-dqgl1-urls.txt	507974	download
urls-transfer.notkiska.pw-2020-08-20-www.intomore.com-post-urls.txt-shallow-20200820-062410-dqgl1.json	375	download job
urls-transfer.notkiska.pw-facebook-@TheGamerInside-shallow-20200820-062451-k0s5y-00003.warc.gz	3539844713	download job
urls-transfer.notkiska.pw-facebook-@TheGamerInside-shallow-20200820-062451-k0s5y-00003.warc.os.cdx.gz	2048231	download
urls-transfer.notkiska.pw-facebook-@TheGamerInside-shallow-20200820-062451-k0s5y-meta.warc.gz	2985468	download job
urls-transfer.notkiska.pw-facebook-@TheGamerInside-shallow-20200820-062451-k0s5y-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@TheGamerInside-shallow-20200820-062451-k0s5y-urls.txt	360541	download
urls-transfer.notkiska.pw-facebook-@TheGamerInside-shallow-20200820-062451-k0s5y.json	344	download job
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00002.warc.gz	5580021267	download job
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00002.warc.os.cdx.gz	34359	download
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00003.warc.gz	5370123730	download job
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00003.warc.os.cdx.gz	31398	download
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00004.warc.gz	5374863519	download job
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00004.warc.os.cdx.gz	31004	download
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00005.warc.gz	5372070166	download job
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00005.warc.os.cdx.gz	33872	download
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00006.warc.gz	5389685375	download job
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00006.warc.os.cdx.gz	112932	download
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00007.warc.gz	5409518371	download job
urls-transfer.notkiska.pw-facebook-@TreesWaterPeople-shallow-20200820-042814-34ldv-00007.warc.os.cdx.gz	226757	download
urls-transfer.notkiska.pw-facebook-@limelighthealth-shallow-20200820-135329-79zbl-00000.warc.gz	5385033790	download job
urls-transfer.notkiska.pw-facebook-@limelighthealth-shallow-20200820-135329-79zbl-00000.warc.os.cdx.gz	543628	download
urls-transfer.notkiska.pw-facebook-@limelighthealth-shallow-20200820-135329-79zbl-00001.warc.gz	5388005423	download job
urls-transfer.notkiska.pw-facebook-@limelighthealth-shallow-20200820-135329-79zbl-00001.warc.os.cdx.gz	32944	download
urls-transfer.notkiska.pw-facebook-@limelighthealth-shallow-20200820-135329-79zbl-00002.warc.gz	5373544085	download job
urls-transfer.notkiska.pw-facebook-@limelighthealth-shallow-20200820-135329-79zbl-00002.warc.os.cdx.gz	31480	download
urls-transfer.notkiska.pw-facebook-@waterloosparkling-shallow-20200820-134839-2ee90-00000.warc.gz	773942687	download job
urls-transfer.notkiska.pw-facebook-@waterloosparkling-shallow-20200820-134839-2ee90-00000.warc.os.cdx.gz	171533	download
urls-transfer.notkiska.pw-facebook-@waterloosparkling-shallow-20200820-134839-2ee90-meta.warc.gz	108703	download job
urls-transfer.notkiska.pw-facebook-@waterloosparkling-shallow-20200820-134839-2ee90-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00288.warc.gz	5368921651	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00288.warc.os.cdx.gz	3715798	download
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00427.warc.gz	5383328250	download job
urls-transfer.notkiska.pw-twitter-%23qanon-shallow-20200531-053932-8yw79-00427.warc.os.cdx.gz	1811536	download
urls-transfer.notkiska.pw-twitter-@CEUhungary-shallow-20200820-141421-5ey7x-meta.warc.gz	6335	download job
urls-transfer.notkiska.pw-twitter-@CEUhungary-shallow-20200820-141421-5ey7x-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@Camerai-shallow-20200820-134859-9qg50-00000.warc.gz	789629698	download job
urls-transfer.notkiska.pw-twitter-@Camerai-shallow-20200820-134859-9qg50-00000.warc.os.cdx.gz	188790	download
urls-transfer.notkiska.pw-twitter-@Camerai-shallow-20200820-134859-9qg50-meta.warc.gz	121746	download job
urls-transfer.notkiska.pw-twitter-@Camerai-shallow-20200820-134859-9qg50-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@FromKalen-shallow-20200820-130249-1bkx3-00000.warc.gz	1180545027	download job
urls-transfer.notkiska.pw-twitter-@FromKalen-shallow-20200820-130249-1bkx3-00000.warc.os.cdx.gz	1155947	download
urls-transfer.notkiska.pw-twitter-@FromKalen-shallow-20200820-130249-1bkx3-meta.warc.gz	657589	download job
urls-transfer.notkiska.pw-twitter-@FromKalen-shallow-20200820-130249-1bkx3-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@FromKalen-shallow-20200820-130249-1bkx3-urls.txt	91208	download
urls-transfer.notkiska.pw-twitter-@FromKalen-shallow-20200820-130249-1bkx3.json	330	download job
urls-transfer.notkiska.pw-twitter-@SCIENION_AG-shallow-20200820-135029-34rx6-00000.warc.gz	77532117	download job
urls-transfer.notkiska.pw-twitter-@SCIENION_AG-shallow-20200820-135029-34rx6-00000.warc.os.cdx.gz	110756	download
urls-transfer.notkiska.pw-twitter-@SCIENION_AG-shallow-20200820-135029-34rx6-meta.warc.gz	72171	download job
urls-transfer.notkiska.pw-twitter-@SCIENION_AG-shallow-20200820-135029-34rx6-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@SCIENION_AG-shallow-20200820-135029-34rx6.json	334	download job
urls-transfer.notkiska.pw-twitter-@TheManlyStanley-shallow-20200820-043618-d7jc0-00001.warc.gz	2252103456	download job
urls-transfer.notkiska.pw-twitter-@TheManlyStanley-shallow-20200820-043618-d7jc0-00001.warc.os.cdx.gz	1618842	download
urls-transfer.notkiska.pw-twitter-@TheManlyStanley-shallow-20200820-043618-d7jc0.json	342	download job
urls-transfer.notkiska.pw-twitter-@appledaily_hk-shallow-20200810-205216-ekfxh-00019.warc.gz	5370540499	download job
urls-transfer.notkiska.pw-twitter-@appledaily_hk-shallow-20200810-205216-ekfxh-00019.warc.os.cdx.gz	1455012	download
urls-transfer.notkiska.pw-twitter-@appledaily_hk-shallow-20200810-205216-ekfxh-00020.warc.gz	5377352500	download job
urls-transfer.notkiska.pw-twitter-@appledaily_hk-shallow-20200810-205216-ekfxh-00020.warc.os.cdx.gz	1323520	download
urls-transfer.notkiska.pw-twitter-@livesmattershow-shallow-20200820-130323-b686x-00000.warc.gz	877346138	download job
urls-transfer.notkiska.pw-twitter-@livesmattershow-shallow-20200820-130323-b686x-00000.warc.os.cdx.gz	792538	download
urls-transfer.notkiska.pw-twitter-@livesmattershow-shallow-20200820-130323-b686x-meta.warc.gz	448176	download job
urls-transfer.notkiska.pw-twitter-@livesmattershow-shallow-20200820-130323-b686x-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@livesmattershow-shallow-20200820-130323-b686x-urls.txt	55149	download
urls-transfer.notkiska.pw-twitter-@livesmattershow-shallow-20200820-130323-b686x.json	342	download job
urls-transfer.notkiska.pw-twitter-@momentapharma-shallow-20200820-135542-1otpl-00000.warc.gz	35461100	download job
urls-transfer.notkiska.pw-twitter-@momentapharma-shallow-20200820-135542-1otpl-00000.warc.os.cdx.gz	48174	download
urls-transfer.notkiska.pw-twitter-@momentapharma-shallow-20200820-135542-1otpl-meta.warc.gz	31477	download job
urls-transfer.notkiska.pw-twitter-@momentapharma-shallow-20200820-135542-1otpl-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@momentapharma-shallow-20200820-135542-1otpl-urls.txt	1165	download
urls-transfer.notkiska.pw-twitter-@momentapharma-shallow-20200820-135542-1otpl.json	338	download job
www.animenewsnetwork.com-shallow-20200820-131759-77ckt-00000.warc.gz	2708292	download job
www.animenewsnetwork.com-shallow-20200820-131759-77ckt-00000.warc.os.cdx.gz	7101	download
www.animenewsnetwork.com-shallow-20200820-131759-77ckt-meta.warc.gz	7853	download job
www.animenewsnetwork.com-shallow-20200820-131759-77ckt-meta.warc.os.cdx.gz	47	download
www.animenewsnetwork.com-shallow-20200820-131759-77ckt.json	366	download job
www.bizjournals.com-shallow-20200820-135414-7c793-00000.warc.gz	30372	download job
www.bizjournals.com-shallow-20200820-135414-7c793-00000.warc.os.cdx.gz	424	download
www.bizjournals.com-shallow-20200820-135414-7c793-meta.warc.gz	3677	download job
www.bizjournals.com-shallow-20200820-135414-7c793-meta.warc.os.cdx.gz	47	download
www.bizjournals.com-shallow-20200820-135414-7c793.json	326	download job
www.calcalistech.com-shallow-20200820-134819-2gghe-00000.warc.gz	3189053	download job
www.calcalistech.com-shallow-20200820-134819-2gghe-00000.warc.os.cdx.gz	17808	download
www.calcalistech.com-shallow-20200820-134819-2gghe-meta.warc.gz	13626	download job
www.calcalistech.com-shallow-20200820-134819-2gghe-meta.warc.os.cdx.gz	47	download
www.calcalistech.com-shallow-20200820-134819-2gghe.json	292	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00524.warc.gz	1074323444	download job
www.chinadaily.com.cn-inf-20190927-102302-505np-00524.warc.os.cdx.gz	540813	download
www.dailycal.org-shallow-20200820-125635-3bu4g-00000.warc.gz	1787368	download job
www.dailycal.org-shallow-20200820-125635-3bu4g-00000.warc.os.cdx.gz	8354	download
www.dailycal.org-shallow-20200820-125635-3bu4g-meta.warc.gz	8408	download job
www.dailycal.org-shallow-20200820-125635-3bu4g-meta.warc.os.cdx.gz	47	download
www.dailycal.org-shallow-20200820-125635-3bu4g.json	284	download job
www.drinkwaterloo.com-inf-20200820-134656-aa8yu.json	250	download job
www.fixt.co-inf-20200820-140948-a6rcz-00000.warc.gz	33908107	download job
www.fixt.co-inf-20200820-140948-a6rcz-00000.warc.os.cdx.gz	103083	download
www.fixt.co-inf-20200820-140948-a6rcz-meta.warc.gz	63332	download job
www.fixt.co-inf-20200820-140948-a6rcz-meta.warc.os.cdx.gz	47	download
www.flickr.com-inf-20200819-222851-f1vtc-00019.warc.gz	5372014749	download job
www.flickr.com-inf-20200819-222851-f1vtc-00019.warc.os.cdx.gz	605195	download
www.flickr.com-inf-20200819-222851-f1vtc-00020.warc.gz	5387445549	download job
www.flickr.com-inf-20200819-222851-f1vtc-00020.warc.os.cdx.gz	515474	download
www.flickr.com-inf-20200819-222851-f1vtc-00022.warc.gz	5391301492	download job
www.flickr.com-inf-20200819-222851-f1vtc-00022.warc.os.cdx.gz	572767	download
www.genomeweb.com-shallow-20200820-134924-phj2a-00000.warc.gz	1552321	download job
www.genomeweb.com-shallow-20200820-134924-phj2a-00000.warc.os.cdx.gz	10189	download
www.genomeweb.com-shallow-20200820-134924-phj2a-meta.warc.gz	9293	download job
www.genomeweb.com-shallow-20200820-134924-phj2a-meta.warc.os.cdx.gz	47	download
www.genomeweb.com-shallow-20200820-134924-phj2a.json	292	download job
www.inceptuminsurance.com-inf-20200820-135655-79hkn-00000.warc.gz	15120725	download job
www.inceptuminsurance.com-inf-20200820-135655-79hkn-00000.warc.os.cdx.gz	25276	download
www.inceptuminsurance.com-inf-20200820-135655-79hkn-meta.warc.gz	18127	download job
www.inceptuminsurance.com-inf-20200820-135655-79hkn-meta.warc.os.cdx.gz	47	download
www.inceptuminsurance.com-inf-20200820-135655-79hkn.json	253	download job
www.instagram.com-inf-20200820-134842-cfdda-00000.warc.gz	31386523	download job
www.instagram.com-inf-20200820-134842-cfdda-00000.warc.os.cdx.gz	49531	download
www.instagram.com-inf-20200820-134842-cfdda.json	264	download job
www.instagram.com-inf-20200820-140320-3x9qw-00000.warc.gz	13934759	download job
www.instagram.com-inf-20200820-140320-3x9qw-00000.warc.os.cdx.gz	27945	download
www.instagram.com-inf-20200820-140320-3x9qw.json	262	download job
www.instagram.com-inf-20200820-141232-aigj6-00000.warc.gz	16906821	download job
www.instagram.com-inf-20200820-141232-aigj6-00000.warc.os.cdx.gz	33208	download
www.instagram.com-inf-20200820-141232-aigj6-meta.warc.gz	26078	download job
www.instagram.com-inf-20200820-141232-aigj6-meta.warc.os.cdx.gz	47	download
www.insurancejournal.com-shallow-20200820-135547-37pof-00000.warc.gz	3677732	download job
www.insurancejournal.com-shallow-20200820-135547-37pof-00000.warc.os.cdx.gz	8134	download
www.insurancejournal.com-shallow-20200820-135547-37pof-meta.warc.gz	8187	download job
www.insurancejournal.com-shallow-20200820-135547-37pof-meta.warc.os.cdx.gz	47	download
www.insurancejournal.com-shallow-20200820-135547-37pof.json	297	download job
www.momentapharma.com-inf-20200820-135508-95yx3-meta.warc.gz	330800	download job
www.momentapharma.com-inf-20200820-135508-95yx3-meta.warc.os.cdx.gz	47	download
www.momentapharma.com-inf-20200820-135508-95yx3.json	250	download job
www.portlandoregon.gov-shallow-20200820-130135-bz7uw-00000.warc.gz	383046	download job
www.portlandoregon.gov-shallow-20200820-130135-bz7uw-00000.warc.os.cdx.gz	2744	download
www.portlandoregon.gov-shallow-20200820-130135-bz7uw-meta.warc.gz	5163	download job
www.portlandoregon.gov-shallow-20200820-130135-bz7uw-meta.warc.os.cdx.gz	47	download
www.portlandoregon.gov-shallow-20200820-130135-bz7uw.json	286	download job
www.prnewswire.com-shallow-20200820-135243-d1cqi-00000.warc.gz	1928396	download job
www.prnewswire.com-shallow-20200820-135243-d1cqi-00000.warc.os.cdx.gz	5309	download
www.prnewswire.com-shallow-20200820-135243-d1cqi-meta.warc.gz	6674	download job
www.prnewswire.com-shallow-20200820-135243-d1cqi-meta.warc.os.cdx.gz	47	download
www.prnewswire.com-shallow-20200820-135243-d1cqi.json	329	download job
www.turiver.com-inf-20200629-212723-6d3re-00081.warc.gz	5368722149	download job
www.turiver.com-inf-20200629-212723-6d3re-00081.warc.os.cdx.gz	2513489	download
www.yaf.org-shallow-20200820-130030-2gse0-00000.warc.gz	20422238	download job
www.yaf.org-shallow-20200820-130030-2gse0-00000.warc.os.cdx.gz	25244	download
www.yaf.org-shallow-20200820-130030-2gse0-meta.warc.gz	17274	download job
www.yaf.org-shallow-20200820-130030-2gse0-meta.warc.os.cdx.gz	47	download
www.yaf.org-shallow-20200820-130030-2gse0.json	334	download job