Item archiveteam_archivebot_go_20200724050002

Filename	Size
all4humor.com-inf-20200724-034909-b0ho0.json	238	download job
anders-steuerkanzlei.de-inf-20200724-021233-93aaq-00000.warc.gz	2304088	download job
anders-steuerkanzlei.de-inf-20200724-021233-93aaq-00000.warc.os.cdx.gz	8524	download
anders-steuerkanzlei.de-inf-20200724-021233-93aaq-meta.warc.gz	8490	download job
anders-steuerkanzlei.de-inf-20200724-021233-93aaq-meta.warc.os.cdx.gz	47	download
anders-steuerkanzlei.de-inf-20200724-021233-93aaq.json	248	download job
apnewton.blogspot.com-inf-20200724-001631-3tmod-meta.warc.gz	468579	download job
apnewton.blogspot.com-inf-20200724-001631-3tmod-meta.warc.os.cdx.gz	47	download
archiveteam_archivebot_go_20200724050002.cdx.gz	65236703	download
archiveteam_archivebot_go_20200724050002.cdx.idx	60299	download
archiveteam_archivebot_go_20200724050002_files.xml	0	download
archiveteam_archivebot_go_20200724050002_meta.sqlite	256000	download
archiveteam_archivebot_go_20200724050002_meta.xml	969	download
atifco.ro-inf-20200724-002159-1wa2y-aborted-wpull.log.gz	30128	download
barackobama.tumblr.com-inf-20200723-015409-xo18b-meta.warc.gz	93753098	download job
barackobama.tumblr.com-inf-20200723-015409-xo18b-meta.warc.os.cdx.gz	47	download
baxterit.net-inf-20200724-035501-6wbsw-00000.warc.gz	39392322	download job
baxterit.net-inf-20200724-035501-6wbsw-00000.warc.os.cdx.gz	32129	download
baxterit.net-inf-20200724-035501-6wbsw-meta.warc.gz	22560	download job
baxterit.net-inf-20200724-035501-6wbsw-meta.warc.os.cdx.gz	47	download
baxterit.net-inf-20200724-035501-6wbsw.json	237	download job
big5.cri.cn-inf-20200719-230814-2nxf5-00028.warc.gz	5456999676	download job
big5.cri.cn-inf-20200719-230814-2nxf5-00028.warc.os.cdx.gz	1498025	download
captionbot.ai-inf-20200724-014256-fo90m-00000.warc.gz	49090174	download job
captionbot.ai-inf-20200724-014256-fo90m-00000.warc.os.cdx.gz	58549	download
captionbot.ai-inf-20200724-014256-fo90m-wpull.log.gz	42943	download
crowbarmassage.com-inf-20200724-035208-119up-00000.warc.gz	57204861	download job
crowbarmassage.com-inf-20200724-035208-119up-00000.warc.os.cdx.gz	49276	download
crowbarmassage.com-inf-20200724-035208-119up-meta.warc.gz	33311	download job
crowbarmassage.com-inf-20200724-035208-119up-meta.warc.os.cdx.gz	47	download
crowbarmassage.com-inf-20200724-035208-119up.json	243	download job
disrn.com-inf-20200723-180526-3ovz8-00012.warc.gz	5368741386	download job
disrn.com-inf-20200723-180526-3ovz8-00012.warc.os.cdx.gz	1061998	download
disrn.com-inf-20200723-180526-3ovz8-00013.warc.gz	5431572448	download job
disrn.com-inf-20200723-180526-3ovz8-00013.warc.os.cdx.gz	1732342	download
disrn.com-inf-20200723-180526-3ovz8-00015.warc.gz	5380154888	download job
disrn.com-inf-20200723-180526-3ovz8-00015.warc.os.cdx.gz	30127	download
docs.microsoft.com-inf-20200719-173331-ex56m-00025.warc.gz	5368724529	download job
docs.microsoft.com-inf-20200719-173331-ex56m-00025.warc.os.cdx.gz	2946787	download
ektoplazm.com-inf-20200704-233408-66i1h-00070.warc.gz	5453971998	download job
ektoplazm.com-inf-20200704-233408-66i1h-00070.warc.os.cdx.gz	10372	download
getcobra.io-inf-20200724-035709-epbvx-meta.warc.gz	109420	download job
getcobra.io-inf-20200724-035709-epbvx-meta.warc.os.cdx.gz	47	download
help.nearlyweds.com-inf-20200724-015656-a7dbl-00000.warc.gz	1375376	download job
help.nearlyweds.com-inf-20200724-015656-a7dbl-00000.warc.os.cdx.gz	3152	download
help.nearlyweds.com-inf-20200724-015656-a7dbl.json	243	download job
hordehero.com-inf-20200724-025330-1hazt-00000.warc.gz	825388949	download job
hordehero.com-inf-20200724-025330-1hazt-00000.warc.os.cdx.gz	387411	download
hordehero.com-inf-20200724-025330-1hazt-meta.warc.gz	239092	download job
hordehero.com-inf-20200724-025330-1hazt-meta.warc.os.cdx.gz	47	download
hordehero.com-inf-20200724-025330-1hazt.json	238	download job
logoease.com-inf-20200724-020539-6m7js-00000.warc.gz	36083889	download job
logoease.com-inf-20200724-020539-6m7js-00000.warc.os.cdx.gz	24959	download
logoease.com-inf-20200724-020539-6m7js-meta.warc.gz	18329	download job
logoease.com-inf-20200724-020539-6m7js-meta.warc.os.cdx.gz	47	download
logoease.com-inf-20200724-020539-6m7js.json	237	download job
luc.devroye.org-inf-20200629-195003-6kmq5-00101.warc.gz	5370320828	download job
luc.devroye.org-inf-20200629-195003-6kmq5-00101.warc.os.cdx.gz	2614742	download
maximumcompression.com-inf-20200724-021627-f5asp-00000.warc.gz	82588763	download job
maximumcompression.com-inf-20200724-021627-f5asp-00000.warc.os.cdx.gz	150254	download
maximumcompression.com-inf-20200724-021627-f5asp-meta.warc.gz	95135	download job
maximumcompression.com-inf-20200724-021627-f5asp-meta.warc.os.cdx.gz	47	download
maximumcompression.com-inf-20200724-021627-f5asp.json	247	download job
mousai.org-inf-20200724-041122-cfgns-00000.warc.gz	87992327	download job
mousai.org-inf-20200724-041122-cfgns-00000.warc.os.cdx.gz	45513	download
myskin.com-inf-20200724-031852-1n12c-00000.warc.gz	373086885	download job
myskin.com-inf-20200724-031852-1n12c-00000.warc.os.cdx.gz	567968	download
myskin.com-inf-20200724-031852-1n12c-meta.warc.gz	368021	download job
myskin.com-inf-20200724-031852-1n12c-meta.warc.os.cdx.gz	47	download
myskin.com-inf-20200724-031852-1n12c.json	235	download job
nearlyweds.com-inf-20200724-015508-7dam5-00000.warc.gz	4658551	download job
nearlyweds.com-inf-20200724-015508-7dam5-00000.warc.os.cdx.gz	9981	download
negativespace-videoproduction.com-inf-20200724-013556-25s06.json	258	download job
newtonairlines.blogspot.com-inf-20200724-001729-9qlj8-00000.warc.gz	1074146787	download job
newtonairlines.blogspot.com-inf-20200724-001729-9qlj8-00000.warc.os.cdx.gz	1112765	download
newtonairlines.blogspot.com-inf-20200724-001729-9qlj8-meta.warc.gz	706323	download job
newtonairlines.blogspot.com-inf-20200724-001729-9qlj8-meta.warc.os.cdx.gz	47	download
obavintage.com.br-inf-20200724-032418-65clc-00000.warc.gz	50603738	download job
obavintage.com.br-inf-20200724-032418-65clc-00000.warc.os.cdx.gz	90477	download
obavintage.com.br-inf-20200724-032418-65clc-meta.warc.gz	56025	download job
obavintage.com.br-inf-20200724-032418-65clc-meta.warc.os.cdx.gz	47	download
obavintage.com.br-inf-20200724-032418-65clc.json	242	download job
planetoftheapps.com-inf-20200724-023403-1zaqz-00000.warc.gz	198198285	download job
planetoftheapps.com-inf-20200724-023403-1zaqz-00000.warc.os.cdx.gz	177037	download
planetoftheapps.com-inf-20200724-023403-1zaqz-meta.warc.gz	101690	download job
planetoftheapps.com-inf-20200724-023403-1zaqz-meta.warc.os.cdx.gz	47	download
planetoftheapps.com-inf-20200724-023403-1zaqz.json	244	download job
plus.im-inf-20200724-031904-b6amx-00000.warc.gz	50714319	download job
plus.im-inf-20200724-031904-b6amx-00000.warc.os.cdx.gz	44292	download
plus.im-inf-20200724-031904-b6amx-meta.warc.gz	30049	download job
plus.im-inf-20200724-031904-b6amx-meta.warc.os.cdx.gz	47	download
plus.im-inf-20200724-031904-b6amx.json	232	download job
pola-retradio.org-inf-20200723-124007-ei3bl-00015.warc.gz	2817054386	download job
pola-retradio.org-inf-20200723-124007-ei3bl-00015.warc.os.cdx.gz	11786	download
pola-retradio.org-inf-20200723-124007-ei3bl.json	247	download job
prueba.escarabajario.com-inf-20200724-024923-e8x49-00000.warc.gz	40498414	download job
prueba.escarabajario.com-inf-20200724-024923-e8x49-00000.warc.os.cdx.gz	79650	download
prueba.escarabajario.com-inf-20200724-024923-e8x49-meta.warc.gz	50001	download job
prueba.escarabajario.com-inf-20200724-024923-e8x49-meta.warc.os.cdx.gz	47	download
prueba.escarabajario.com-inf-20200724-024923-e8x49.json	254	download job
scarecrowink.ca-inf-20200724-010031-e0z55-meta.warc.gz	88886	download job
scarecrowink.ca-inf-20200724-010031-e0z55-meta.warc.os.cdx.gz	47	download
simeondimitriou.gr-inf-20200724-013335-ffddj.json	243	download job
social.technet.microsoft.com-inf-20200719-173750-1vqe0-00020.warc.gz	5432232995	download job
social.technet.microsoft.com-inf-20200719-173750-1vqe0-00020.warc.os.cdx.gz	2760539	download
social.technet.microsoft.com-inf-20200719-173750-1vqe0-00021.warc.gz	5380976927	download job
social.technet.microsoft.com-inf-20200719-173750-1vqe0-00021.warc.os.cdx.gz	630024	download
tienda.escarabajario.com-inf-20200724-025825-5z1ec-00000.warc.gz	36967289	download job
tienda.escarabajario.com-inf-20200724-025825-5z1ec-00000.warc.os.cdx.gz	103561	download
tienda.escarabajario.com-inf-20200724-025825-5z1ec-meta.warc.gz	59820	download job
tienda.escarabajario.com-inf-20200724-025825-5z1ec-meta.warc.os.cdx.gz	47	download
tienda.escarabajario.com-inf-20200724-025825-5z1ec.json	263	download job
uif.hu-inf-20200724-040713-50tgf-meta.warc.gz	70816	download job
uif.hu-inf-20200724-040713-50tgf-meta.warc.os.cdx.gz	47	download
unclesunshine.comicgenesis.com-inf-20200724-030521-birlw-00000.warc.gz	7496277	download job
unclesunshine.comicgenesis.com-inf-20200724-030521-birlw-00000.warc.os.cdx.gz	16474	download
unclesunshine.comicgenesis.com-inf-20200724-030521-birlw-meta.warc.gz	13029	download job
unclesunshine.comicgenesis.com-inf-20200724-030521-birlw-meta.warc.os.cdx.gz	47	download
unclesunshine.comicgenesis.com-inf-20200724-030521-birlw.json	254	download job
urls-archive.max.fan-twitter-@PrimerImpacto-20200716.txt-shallow-20200723-183434-e1m55-00001.warc.gz	5368767770	download job
urls-archive.max.fan-twitter-@PrimerImpacto-20200716.txt-shallow-20200723-183434-e1m55-00001.warc.os.cdx.gz	6383068	download
urls-archive.max.fan-twitter-@PublicWelfare-20200716.txt-shallow-20200723-213610-7is3p.json	359	download job
urls-archive.max.fan-twitter-@presstelegram-20200716.txt-shallow-20200723-170524-4d6fg-00001.warc.gz	3807878225	download job
urls-archive.max.fan-twitter-@presstelegram-20200716.txt-shallow-20200723-170524-4d6fg-00001.warc.os.cdx.gz	3568380	download
urls-archive.max.fan-twitter-@presstelegram-20200716.txt-shallow-20200723-170524-4d6fg-urls.txt	5799199	download
urls-transfer.notkiska.pw-facebook-@Prothoma.org-shallow-20200724-041553-32daf.json	338	download job
urls-transfer.notkiska.pw-facebook-@concepter-shallow-20200724-040948-5lvtx.json	332	download job
urls-transfer.notkiska.pw-facebook-@escarabajario-shallow-20200724-030215-cp2yb-00000.warc.gz	104692450	download job
urls-transfer.notkiska.pw-facebook-@escarabajario-shallow-20200724-030215-cp2yb-00000.warc.os.cdx.gz	195709	download
urls-transfer.notkiska.pw-facebook-@escarabajario-shallow-20200724-030215-cp2yb-meta.warc.gz	118255	download job
urls-transfer.notkiska.pw-facebook-@escarabajario-shallow-20200724-030215-cp2yb-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@escarabajario-shallow-20200724-030215-cp2yb-urls.txt	43502	download
urls-transfer.notkiska.pw-facebook-@escarabajario-shallow-20200724-030215-cp2yb.json	340	download job
urls-transfer.notkiska.pw-facebook-@linuxvoice-shallow-20200724-013039-1a701-meta.warc.gz	219014	download job
urls-transfer.notkiska.pw-facebook-@linuxvoice-shallow-20200724-013039-1a701-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@linuxvoice-shallow-20200724-013039-1a701-urls.txt	50349	download
urls-transfer.notkiska.pw-facebook-@myskin-shallow-20200724-031906-b4kl8-00000.warc.gz	12913182	download job
urls-transfer.notkiska.pw-facebook-@myskin-shallow-20200724-031906-b4kl8-00000.warc.os.cdx.gz	39173	download
urls-transfer.notkiska.pw-facebook-@myskin-shallow-20200724-031906-b4kl8-meta.warc.gz	28010	download job
urls-transfer.notkiska.pw-facebook-@myskin-shallow-20200724-031906-b4kl8-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@myskin-shallow-20200724-031906-b4kl8-urls.txt	2669	download
urls-transfer.notkiska.pw-facebook-@myskin-shallow-20200724-031906-b4kl8.json	326	download job
urls-transfer.notkiska.pw-facebook-@nearlyweds-shallow-20200724-015759-2nv1o-00000.warc.gz	566138829	download job
urls-transfer.notkiska.pw-facebook-@nearlyweds-shallow-20200724-015759-2nv1o-00000.warc.os.cdx.gz	881219	download
urls-transfer.notkiska.pw-facebook-@nearlyweds-shallow-20200724-015759-2nv1o-meta.warc.gz	498963	download job
urls-transfer.notkiska.pw-facebook-@nearlyweds-shallow-20200724-015759-2nv1o-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@nearlyweds-shallow-20200724-015759-2nv1o-urls.txt	115360	download
urls-transfer.notkiska.pw-facebook-@nearlyweds-shallow-20200724-015759-2nv1o.json	334	download job
urls-transfer.notkiska.pw-facebook-@planetoftheapps-shallow-20200724-023503-esine-00000.warc.gz	3816386858	download job
urls-transfer.notkiska.pw-facebook-@planetoftheapps-shallow-20200724-023503-esine-00000.warc.os.cdx.gz	260951	download
urls-transfer.notkiska.pw-facebook-@planetoftheapps-shallow-20200724-023503-esine-meta.warc.gz	156928	download job
urls-transfer.notkiska.pw-facebook-@planetoftheapps-shallow-20200724-023503-esine-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-facebook-@planetoftheapps-shallow-20200724-023503-esine-urls.txt	8542	download
urls-transfer.notkiska.pw-facebook-@planetoftheapps-shallow-20200724-023503-esine.json	344	download job
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00290.warc.gz	5372886177	download job
urls-transfer.notkiska.pw-twitter-%23BlackHistoryMonth-shallow-20200610-132545-46qdq-00290.warc.os.cdx.gz	1480316	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00032.warc.gz	5693675141	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00032.warc.os.cdx.gz	3640726	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00033.warc.gz	5522818639	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00033.warc.os.cdx.gz	15217	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00034.warc.gz	5540024065	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00034.warc.os.cdx.gz	20136	download
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00035.warc.gz	5470894403	download job
urls-transfer.notkiska.pw-twitter-%23BlackTwitter-shallow-20200710-163004-dpwry-00035.warc.os.cdx.gz	21495	download
urls-transfer.notkiska.pw-twitter-%23eclipse2017-shallow-20200717-124458-9ofq2-00033.warc.gz	5369836908	download job
urls-transfer.notkiska.pw-twitter-%23eclipse2017-shallow-20200717-124458-9ofq2-00033.warc.os.cdx.gz	6382691	download
urls-transfer.notkiska.pw-twitter-%23fireball-shallow-20200717-130157-zc0mx-00029.warc.gz	5368747069	download job
urls-transfer.notkiska.pw-twitter-%23fireball-shallow-20200717-130157-zc0mx-00029.warc.os.cdx.gz	6496427	download
urls-transfer.notkiska.pw-twitter-%23memorabilia-shallow-20200717-110135-cs9fk-00012.warc.gz	5368712231	download job
urls-transfer.notkiska.pw-twitter-%23memorabilia-shallow-20200717-110135-cs9fk-00012.warc.os.cdx.gz	2192990	download
urls-transfer.notkiska.pw-twitter-%23volcano-shallow-20200717-182336-akgvn-00074.warc.gz	5391055411	download job
urls-transfer.notkiska.pw-twitter-%23volcano-shallow-20200717-182336-akgvn-00074.warc.os.cdx.gz	3670799	download
urls-transfer.notkiska.pw-twitter-@LinuxVoice-shallow-20200724-023534-ccb8r-00000.warc.gz	5374505762	download job
urls-transfer.notkiska.pw-twitter-@LinuxVoice-shallow-20200724-023534-ccb8r-00000.warc.os.cdx.gz	341821	download
urls-transfer.notkiska.pw-twitter-@LinuxVoice-shallow-20200724-023534-ccb8r-00001.warc.gz	5373505476	download job
urls-transfer.notkiska.pw-twitter-@LinuxVoice-shallow-20200724-023534-ccb8r-00001.warc.os.cdx.gz	345784	download
urls-transfer.notkiska.pw-twitter-@LinuxVoice-shallow-20200724-023534-ccb8r-urls.txt	116285	download
urls-transfer.notkiska.pw-twitter-@LinuxVoice-shallow-20200724-023534-ccb8r.json	332	download job
urls-transfer.notkiska.pw-twitter-@MIHistoryCenter-shallow-20200724-020148-985bw-urls.txt	206957	download
urls-transfer.notkiska.pw-twitter-@MIHistoryCenter-shallow-20200724-020148-985bw.json	342	download job
urls-transfer.notkiska.pw-twitter-@QueeringEDU-shallow-20200722-190254-7fmhm-00025.warc.gz	4393304759	download job
urls-transfer.notkiska.pw-twitter-@QueeringEDU-shallow-20200722-190254-7fmhm-00025.warc.os.cdx.gz	168453	download
urls-transfer.notkiska.pw-twitter-@Raptor_Toons-shallow-20200724-023723-bw95w-00001.warc.gz	5376360339	download job
urls-transfer.notkiska.pw-twitter-@Raptor_Toons-shallow-20200724-023723-bw95w-00001.warc.os.cdx.gz	31911	download
urls-transfer.notkiska.pw-twitter-@immelmann42-shallow-20200724-023643-8sfio-00000.warc.gz	917010	download job
urls-transfer.notkiska.pw-twitter-@immelmann42-shallow-20200724-023643-8sfio-00000.warc.os.cdx.gz	3967	download
urls-transfer.notkiska.pw-twitter-@immelmann42-shallow-20200724-023643-8sfio-meta.warc.gz	6097	download job
urls-transfer.notkiska.pw-twitter-@immelmann42-shallow-20200724-023643-8sfio-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@immelmann42-shallow-20200724-023643-8sfio-urls.txt	91	download
urls-transfer.notkiska.pw-twitter-@immelmann42-shallow-20200724-023643-8sfio.json	334	download job
urls-transfer.notkiska.pw-twitter-@nearlyweds-shallow-20200724-023533-c7ccy-00000.warc.gz	87580284	download job
urls-transfer.notkiska.pw-twitter-@nearlyweds-shallow-20200724-023533-c7ccy-00000.warc.os.cdx.gz	66512	download
urls-transfer.notkiska.pw-twitter-@nearlyweds-shallow-20200724-023533-c7ccy-meta.warc.gz	45887	download job
urls-transfer.notkiska.pw-twitter-@nearlyweds-shallow-20200724-023533-c7ccy-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@nearlyweds-shallow-20200724-023533-c7ccy-urls.txt	7763	download
urls-transfer.notkiska.pw-twitter-@nearlyweds-shallow-20200724-023533-c7ccy.json	332	download job
urls-transfer.notkiska.pw-twitter-@planetoftheapps-shallow-20200724-023454-d17qe-00000.warc.gz	794389147	download job
urls-transfer.notkiska.pw-twitter-@planetoftheapps-shallow-20200724-023454-d17qe-00000.warc.os.cdx.gz	317848	download
urls-transfer.notkiska.pw-twitter-@planetoftheapps-shallow-20200724-023454-d17qe-meta.warc.gz	185611	download job
urls-transfer.notkiska.pw-twitter-@planetoftheapps-shallow-20200724-023454-d17qe-meta.warc.os.cdx.gz	47	download
urls-transfer.notkiska.pw-twitter-@planetoftheapps-shallow-20200724-023454-d17qe-urls.txt	35454	download
urls-transfer.notkiska.pw-twitter-@planetoftheapps-shallow-20200724-023454-d17qe.json	342	download job
users.ncable.net.au-inf-20200724-000919-b7oue-00000.warc.gz	890873048	download job
users.ncable.net.au-inf-20200724-000919-b7oue-00000.warc.os.cdx.gz	1138157	download
users.ncable.net.au-inf-20200724-000919-b7oue-meta.warc.gz	691164	download job
users.ncable.net.au-inf-20200724-000919-b7oue-meta.warc.os.cdx.gz	47	download
vio-pov.com-inf-20200724-035552-8eh2z-00000.warc.gz	95625283	download job
vio-pov.com-inf-20200724-035552-8eh2z-00000.warc.os.cdx.gz	148358	download
www.crysis.com-inf-20200724-003146-1rr9r-meta.warc.gz	135650	download job
www.crysis.com-inf-20200724-003146-1rr9r-meta.warc.os.cdx.gz	47	download
www.museunacional.ufrj.br-inf-20200724-022531-4149z-00000.warc.gz	80316254	download job
www.museunacional.ufrj.br-inf-20200724-022531-4149z-00000.warc.os.cdx.gz	86703	download
www.museunacional.ufrj.br-inf-20200724-022531-4149z-meta.warc.gz	56342	download job
www.museunacional.ufrj.br-inf-20200724-022531-4149z-meta.warc.os.cdx.gz	47	download
www.museunacional.ufrj.br-inf-20200724-022531-4149z.json	266	download job
www.refinery29.com-inf-20191002-211042-3symg-00685.warc.gz	5393745458	download job
www.refinery29.com-inf-20191002-211042-3symg-00685.warc.os.cdx.gz	1233181	download
www.taringa.net-inf-20190927-205127-2a0h7-00732.warc.gz	5368958225	download job
www.taringa.net-inf-20190927-205127-2a0h7-00732.warc.os.cdx.gz	2684503	download
www.thefleshfarm.com-inf-20200724-002548-aojxw-00000.warc.gz	3741081906	download job
www.thefleshfarm.com-inf-20200724-002548-aojxw-00000.warc.os.cdx.gz	1831148	download
www.thefleshfarm.com-inf-20200724-002548-aojxw-meta.warc.gz	968619	download job
www.thefleshfarm.com-inf-20200724-002548-aojxw-meta.warc.os.cdx.gz	47	download
www.thefleshfarm.com-inf-20200724-002548-aojxw.json	244	download job
xansons4cod.com-inf-20200714-080018-2r93t-00004.warc.gz	401364023	download job
xansons4cod.com-inf-20200714-080018-2r93t-00004.warc.os.cdx.gz	6087495	download
xansons4cod.com-inf-20200714-080018-2r93t.json	239	download job
youknowumsayin.wordpress.com-inf-20200724-022707-15z7l-00000.warc.gz	849000396	download job
youknowumsayin.wordpress.com-inf-20200724-022707-15z7l-00000.warc.os.cdx.gz	667204	download
youknowumsayin.wordpress.com-inf-20200724-022707-15z7l-meta.warc.gz	454633	download job
youknowumsayin.wordpress.com-inf-20200724-022707-15z7l-meta.warc.os.cdx.gz	47	download
youknowumsayin.wordpress.com-inf-20200724-022707-15z7l.json	253	download job
zangramarsh.wordpress.com-inf-20200724-022807-11zvu-00000.warc.gz	1264267124	download job
zangramarsh.wordpress.com-inf-20200724-022807-11zvu-00000.warc.os.cdx.gz	303159	download
zangramarsh.wordpress.com-inf-20200724-022807-11zvu-meta.warc.gz	225986	download job
zangramarsh.wordpress.com-inf-20200724-022807-11zvu-meta.warc.os.cdx.gz	47	download
zangramarsh.wordpress.com-inf-20200724-022807-11zvu.json	250	download job
zombiecrawler.wordpress.com-inf-20200724-023107-cj1rw-00000.warc.gz	688638272	download job
zombiecrawler.wordpress.com-inf-20200724-023107-cj1rw-00000.warc.os.cdx.gz	233682	download
zombiecrawler.wordpress.com-inf-20200724-023107-cj1rw-meta.warc.gz	174849	download job
zombiecrawler.wordpress.com-inf-20200724-023107-cj1rw-meta.warc.os.cdx.gz	47	download
zombiecrawler.wordpress.com-inf-20200724-023107-cj1rw.json	252	download job