From b1a69d3e0546fa0a3b99559489e3548857e04015 Mon Sep 17 00:00:00 2001 From: Khoi Date: Wed, 14 Jun 2023 13:52:08 -0700 Subject: [PATCH] Updated parser code for CryptBB --- .../crawler_selenium.cpython-311.pyc | Bin 13348 -> 13378 bytes .../Read/showthreadphptid15446.html | 28 ++++ .../Read/showthreadphptid16545.html | 28 ++++ ...4e2bis5tebidonionforumdisplayphpfid88.html | 8 + ...s5tebidonionforumdisplayphpfid88page2.html | 8 + .../crawler_selenium.cpython-311.pyc | Bin 13783 -> 13571 bytes .../__pycache__/parser.cpython-311.pyc | Bin 10494 -> 10494 bytes Forums/CryptBB/crawler_selenium.py | 26 ++-- Forums/CryptBB/parser.py | 2 +- .../prepare_parser.cpython-311.pyc | Bin 15419 -> 14692 bytes Forums/Initialization/forums_mining.py | 13 +- Forums/Initialization/geckodriver.log | 139 ++++++++++++++++++ Forums/Initialization/prepare_parser.py | 4 +- 13 files changed, 228 insertions(+), 28 deletions(-) create mode 100644 Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid15446.html create mode 100644 Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid16545.html create mode 100644 Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88.html create mode 100644 Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88page2.html diff --git a/Forums/BestCardingWorld/__pycache__/crawler_selenium.cpython-311.pyc b/Forums/BestCardingWorld/__pycache__/crawler_selenium.cpython-311.pyc index 3a99d1f88bbfa771c05ed5ff810cbba8a6a58885..d87e3b62d8dd883cab504eeb70455304e341ed4a 100644 GIT binary patch delta 565 zcmZ3IaVUd#IWI340}yz%x2N=NUHB}GO+*5npp z4b>_jqu2*XG%(!d67AIO(QRfDZ%*wcWa+T5preiFV8=3VcS2OWXo~fM2%vkhiGnYy^v#Po>Lx~R1G$>GE zD3Yq>En$T585n9*C~-0-JFe=?uO7eR~o{pKb&r=VWocdalVpgN1-DDVi{OfnK9xJCJ*er8vK|pqL5BR8S}q0a8WfFhY8= zlYTGjbRbu8^A-I+jK(0x6@`NckVz1QAn76v5FrL4Kqma+u*uC&Da}c>D_XXh*+`C& epNCQ50|T5;nrvX~!_UDe_JILTNKEcFo(TZs{hVO{ delta 562 zcmX? z>nQv2<3}+EP|rLuQ--ZfR-3IwE-^B;Z{`z|Vqu)PSyO5+6XT-E&t)nZ7i>Q#?7uO<;?0j$_ynsKvSVWg`r5k zmbZiv#%ExtVXfiK5}%x}DmMAOx;HD+2F4P@$@Usw7$qm0Xx`?$#h#m5T%4GmI+bD!UqO8Avf92*oU8+QS1W)oRFKm(s(8S@GzY> diff --git a/Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid15446.html b/Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid15446.html new file mode 100644 index 0000000..4258f94 --- /dev/null +++ b/Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid15446.html @@ -0,0 +1,28 @@ + CryptBB Status About Recent Drama And Scam Claims + +
CryptBB › Public › Darknet Discussions › [Official] CryptBB Status About Recent Drama And Scam Claims

New Reply 
[Official] CryptBB Status About Recent Drama And Scam Claims
LongPig •
CryptBB Admin
Administrator

Posts:
499

Joined:
May 2017

#1
05-03-2023, 01:03 AM
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA512

Recently there is been a lot of drama about me scamming users anyway most of that its just bullshit made up from haters and people like NSA admin of Kickass forum to get new members while he was ddosing other forums and using this made up drama to throw shit on CryptBB

#1 Im the legit owner of the forum and not @Power which was the co-admin this is why ive main admin account, server access and official PGP key while he had only admin panel access and Darkindex server access because he was helping me with it but ever Darkindex was a project ran by be and soon i will gonna put it back online as ive the backup of it but at the moment im focusing on the forum new updates.

#2 I do not scammed any member of the forum if there been problems with stuff i sold i always fixed the problems and if you still have a problem with what you bought from me please PM me and we gonna work on fixing the issue, the only real thing that happened was that i wasnt able to give the money i had to give to @cyberjagu because while i was converting the bitcoins to monero i had to give him Elude exit scammed taking the money.

#3 i never ran honeypots or tried to sell forum database like NSA tried to do with his forum database trying to give me the Kickass database for getting staff rank on CryptBB even because i had no reason to share such stuff also for free even if i ran such thing and the number of users in what was shared isnt even close to the number of registered users here so i think it could be someone who ran a CryptBB phishing site shared that.

#4 We are now building a new staff team and we are working on many big updates to the forum also old staff did not quit because the drama about the scam just @cyberjagu did and other 2 staff members followed him as they were friends and all other staff in last year want offline and never came back without any warning and noone seen em online or some got personal in real life problems etc...

i hope this will explain the current situation CryptBB is going through and the drama that happend.
-----BEGIN PGP SIGNATURE-----
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=Aort
-----END PGP SIGNATURE-----
Contacts:

XMPP: longpig@jabber.calyxinstitute.org
XMPP: longpig@cryptbbsfmzv6dq4ec2iv6ravrw5ohgmklfagqhtvkgiaknvte5fylqd.onion
PM Website Find Rep
Reply Report



+ // + + $(".author_avatar img").error(function () { + $(this).unbind("error").closest('.author_avatar').remove(); + }); +
\ No newline at end of file diff --git a/Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid16545.html b/Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid16545.html new file mode 100644 index 0000000..080409c --- /dev/null +++ b/Forums/CryptBB/HTML_Pages/06142023/Description/Read/showthreadphptid16545.html @@ -0,0 +1,28 @@ + Index & Forums thread + +
CryptBB › Public › Darknet Discussions › Index & Forums thread

New Reply 
Index & Forums thread
nazcarnazcar •
Newbie
Registered

Posts:
3

Joined:
Jun 2023

Reputation:
0

#1
06-11-2023, 07:45 PM
I am looking for new Tor indexes such as darkweb.wtf tor.taxi and dark.fail, in order to find new forums and possibly markets(looking for a focus on fraud). I hope to break ground here on Cryptbb but im not skilled in programming or hacking so in the meantime while I network here. Is there any new index or forum one of you could reccommend?
PM Find Rep
Reply Report
elPROf3ss0r •
Junior
Registered

Posts:
10

Joined:
Nov 2022

Reputation:
0

#2
Yesterday, 01:27 PM
(06-11-2023, 07:45 PM)nazcarnazcar Wrote: I am looking for new Tor indexes such as darkweb.wtf tor.taxi and dark.fail, in order to find new forums and possibly markets(looking for a focus on fraud). I hope to break ground here on Cryptbb but im not skilled in programming or hacking so in the meantime while I network here. Is there any new index or forum one of you could reccommend?

This is a nice project I found recently
http://s36ex53mi4m6chlwqg6zabu2gxtiwvgap...6yd.onion/
PM Find Rep
Reply Report



+ // + + $(".author_avatar img").error(function () { + $(this).unbind("error").closest('.author_avatar').remove(); + }); +
\ No newline at end of file diff --git a/Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88.html b/Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88.html new file mode 100644 index 0000000..fbc714e --- /dev/null +++ b/Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88.html @@ -0,0 +1,8 @@ + CryptBB - Darknet Discussions + +
CryptBB › Public › Darknet Discussions


Rules
1. Read sticky before posting.
2. Ensure links are verified before sharing.
3. All content on websites linked must adhere to general forum rules.

Post Thread
Darknet Discussions
Thread / Author Replies Views Last Post [asc]
Important Threads
  0 839 05-03-2023, 01:03 AM
Last Post: LongPig
  3 1,468 04-28-2023, 06:41 AM
Last Post: aaaaaaaaaaaaaa
  0 2,039 02-16-2023, 08:46 PM
Last Post: squidPR
  0 16,105 12-24-2019, 03:20 PM
Last Post: Power
Normal Threads
  0 9 4 hours ago
Last Post: vikinlord
  1 60 10 hours ago
Last Post: Username 1
  1 42 10 hours ago
Last Post: Username 1
  0 27 10 hours ago
Last Post: seniridjdaci
  0 23 10 hours ago
Last Post: seniridjdaci
  0 24 10 hours ago
Last Post: seniridjdaci
  0 22 10 hours ago
Last Post: seniridjdaci
  0 28 Today, 04:33 AM
Last Post: Fialine
  0 29 Today, 03:27 AM
Last Post: DONTADA
  0 33 Yesterday, 11:08 PM
Last Post: Realitydocs
  0 34 Yesterday, 11:07 PM
Last Post: Realitydocs
  0 38 Yesterday, 05:07 PM
Last Post: sutrale.samartha
  2 1,181 Yesterday, 03:19 PM
Last Post: johndoe8765
  1 94 Yesterday, 01:34 PM
Last Post: selluk
  1 74 Yesterday, 01:33 PM
Last Post: selluk
  1 90 Yesterday, 01:31 PM
Last Post: selluk




\ No newline at end of file diff --git a/Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88page2.html b/Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88page2.html new file mode 100644 index 0000000..a413460 --- /dev/null +++ b/Forums/CryptBB/HTML_Pages/06142023/Listing/httpcryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebidonionforumdisplayphpfid88page2.html @@ -0,0 +1,8 @@ + CryptBB - Darknet Discussions + +
CryptBB › Public › Darknet Discussions


Rules
1. Read sticky before posting.
2. Ensure links are verified before sharing.
3. All content on websites linked must adhere to general forum rules.

Post Thread
Darknet Discussions
Thread / Author Replies Views Last Post [asc]
  1 93 Yesterday, 01:27 PM
Last Post: elPROf3ss0r
  0 54 06-12-2023, 08:23 AM
Last Post: ninjamand
  2 601 06-11-2023, 09:43 PM
Last Post: AgingBurrito
  0 61 06-11-2023, 05:58 PM
Last Post: nazcarnazcar
  0 65 06-11-2023, 09:56 AM
Last Post: kimberlju
  1 118 06-11-2023, 04:47 AM
Last Post: slumber5830
  0 71 06-11-2023, 04:44 AM
Last Post: slumber5830
  2 918 06-09-2023, 10:53 PM
Last Post: untergrund
  0 107 06-09-2023, 08:07 AM
Last Post: ergo888
  2 462 06-09-2023, 07:59 AM
Last Post: nOIkjPXas3
  0 127 06-08-2023, 08:05 PM
Last Post: 33Meatyballz
  1 227 06-08-2023, 05:14 PM
Last Post: Username 1
  0 146 06-07-2023, 10:35 PM
Last Post: Meack
  13 14,270 06-06-2023, 09:11 PM
Last Post: passerini
  5 508 06-06-2023, 05:34 PM
Last Post: AlphaBravoCharlieDelta
  0 171 06-06-2023, 02:43 PM
Last Post: GL1TcH
  4 693 06-06-2023, 02:09 AM
Last Post: Mephistopheles_ANK
  2 331 06-05-2023, 10:25 AM
Last Post: Username 1
  0 222 06-04-2023, 03:01 PM
Last Post: Hades
  2 634 06-03-2023, 03:59 AM
Last Post: lookingfor help




\ No newline at end of file diff --git a/Forums/CryptBB/__pycache__/crawler_selenium.cpython-311.pyc b/Forums/CryptBB/__pycache__/crawler_selenium.cpython-311.pyc index 5bfd08b0077e658b651a70f58b517556bddebf66..007df710eb5eed504718c01be0974c3a120fa8d3 100644 GIT binary patch delta 2010 zcmZ8iYitx%6rMXXyWMVgrdvw4-As@RcCg85sMxndsf`gsUtO+?lp!kep?7MD_{=`t6=HQxyT;~pi3P9?GS1SRMWd3j#eJFk;CcB=v z7>hWqoXcC_y^Fkee(jfv^Y>A1J{TJr>QOnNs~A_pEJOyZ6Ua?sMefuC>pL7OBbvRz zW>}+G8Iv)&Vh`n*UY58zq$KbT@Y$YvV9!C|q&lidg`=>H8sNM&G6Ia|0Fq>uvNk4L zm$I^xyD+s5z0?Te%gEqHaa=>d`>+{2i>_FikfZy1yKx)HHTtf`u=gfgma@d;%Mjzf z!_DdpIaKQBCz*?gpvqEFw}A2L80N^ge8JFaIk}$WVoO}rl*Ev4pNfOQ;GY~A26$Wq ze}*LjIvLXn;!-L{cpLn!Pt0bT&|-Cg=5?yA2a;r-*cgkQREgEdo$41K^GHhV%I!s{ zBXwb8KXQ4%$jHQUI2u-MXl4S1L^JZ$!)FfN(3DSb#Srk0U z_GQ*$aV^=z_wA?2-)?6m%ciG}(~cSOj5sYWW#>(gO^>attZ11K<$`M~bKTV>rhJ7* z&?bXbHN!R%j>%C4Yq%T?j0|8C6!jkRnIxfB@{{Cunh>#R;W2qncu2+yc_h67Wsenk zIIx)U`m#&_9)_S&F3 zPeJ$iAvq@IlJk5Kd9U;o5=l9dsx>vklrp&RgrKkc)TDJ%AU7*tK3y){E=`ZhU=&^-8xKRZ`fP9oBH|=^)$WG zhPO~DJ$goF+eAb@sw-*&m%%(B;%(&Ts@Jw0hlwTvNrQZironEH;P80dY;*WL*gT@f zx5@s^$KWWN`^Pb@rMt-*#YLs$P)#7p4BYl6*&!=Lh2p(#WDTLUL*@ZI+f9 zl$j>?962A9o<;)G6tJ%lh*wiF-mNPeB%xiVBx3UrN zx16rlO3SVC7l8l8+vM+bGP7)6M*%aNk0@W@>IiYO!D8U&OoutAqtnaH6|vwjw+T_+ zYo&a-z01zcg`8a$?pKQi_@|&C-v{fYMp!Lwp-ZM4m_B?sPK9y8*7|u0BXTtu3R=vz zzpouPQspxqhM;KOil#$yxiOznPichY>YJM~w{iLB3q%J7ii z>k3J6ePziEjTfde7N=XRVT(d@(-k<}0#*7*yngKD3Cg}piJ1YtlFU0MeVv%Ci+0|0 z|Dr7kE0i3j#5|uA%qD=+<-16y<|1j*&#dSl+x8JPIvSUE;vYZ@D@uj8gi*GDe9O#J Y;wK9Y2eWO+wah#v1!Viyv*xb+2f35$KmY&$ delta 2187 zcmZuyYitx%6rQ^?yEEJFbo*ep?Q9>zZj0SMc8ffO@=&C-U2PF)#Xw0m%j^K#ZfEPA z?E{2#)f!tVTD(6%C4_`%;fFtDV@T9Q11SANvL#I*lQiicV@QnDG@1rA@!VNkOLVgH z^}FYsdvEVO-#PPk&x2lZN)&S#c;?@EH`@7y__?Kkg%N!huK`?Ol8CI$D3`u(|oU6_8MF?F{Jse2A}9xwPXSt_Ty@Dm!hb; zZdl`q<1x+1QE+4^-jcureTJaK6S@j<*O6h1;@F^yNsv9LRKlM0)w=*v%p8~dW@t2& z3jHX$$Ga!GQ!VqnIO)F67iak5IYAsdHZD$xW8$1pIJtR7kY)ubBS>>X{-k?GD47*X zGRwaOo&m}iFES+TElp?G+sIi#4_Lem4dgTHFp|@iwks^EC*RpOT5&lz$)EPdY-lMB zrLZ-^a}$^cd!411`N!XS0* z21qf#*_a|LKN`y9)y{Brvs_(Xi%W%5 zU|1=E>XHK^hoAyFnPK)2GlZ}Uynfcqg*g>BQG*4C;7@i#3otpGKU_ks6h4Jle;xpI zoZ}jAm}p4to)bMYV)?9Co@!a(c&mF}$onAYy`0Gn;_0qw+KF$U1~$N!75anv#gB ze$L?fBga)7A`6l?-xQjlM+Vh>)EFmT&l_+RmA2CKO%KPS5c#G;&Nb^J3QOZ?`lpIc zWRrm_i2Pc-Cfz0HBUC}uwLLqj6&C{dS%d3I#5CLw1A|u*16oqW%NMl=jQZ+}(&#*m zh~E9Mb=Z3kmTT~ppi$D|YxKzAd`j*#(Nubi^W?nm2I5I`)jf1LU0A&Xp|8olb*-q7 z%;dSqP2QQFU1vxB!&<$MNm4of^Hedo@{G8;PEOlSi#=|lRl7-HO^1_D2A5+QCh8yw z$wl6-If5F=e2vSt0epCv{87_ZR$?k1kAlTup^cfMH`utU;U*IHODIlG`Rk9E*T5Z( zD82YOI+>Oq-a;oy$6{JEtj5(oXqMrlC&NlSqU&KZds}G~lrG48&#CPNEI^$7hJql^9zqZM@z#w}T<{Sl+RTt4E`;5ao>+oj&^8&3b^z?1?e~o$))LR(=l_!{hkcl%mXwEy$iRFMr%osCKm-*8K_-4s{2_SkH2%TFsm)bDf<`)S>r4579;v~qIMi+ z%zT72kd_dV$e--8V@6HCR|fJrLr%bnz6`)i$iTC3JanLd?|f zTH~hGHc4vCLIy8OF?r$ug|E7*QUz$#-J>S(H|cBWHa_-G0HWllI6FD1fx8{+{s5kq zWx+E0r`la@;R$8gj;r3N$8mHk<2=^9A$%#&g@WvNRSN&$6H@QM;~-&=$Bn-R9tIOs zPPI&uqn4AFNiq+5OU*L-1cjIB4XBoCkX}W1j8f(^SPki+dW0hQA%$my39jc1(L-t) zKM5vjgKh@f#opj%vZ}Z8C`w8(F}7(kqvd8qWqgb00X(e)Et&VTctJ@CyPLksWB8+z z!s9_dW$y7^ju0SQs_Jf3HNuN*SP$2eCPPo(+qAQnHoL1nh>M|Z?GKrQYcf!C&3B{C z{f+V62<4&!jq%+(deH12E9=(!_6CC&TbCe*On6QnGXJh_<4I+@S;wIrxELPr4F8)0 zE{C6w?))G5M$CLzZM$+0{8np?U9g)wX&KffT$Gf?Hg3Rg>=NA%w-lh;$S&;Lm^*z< z>Yz!wvmRLP#_3+X;)-G*1w-`R@{ zJ4Rhaqu%=g2xZ{MnCro|v%A(A5vMX)>zzC6R^#W)B`ds!ujYDRF4!J-GCw%;{DjQ@ z6wV7%NoG08%y8`Tj=XI;YrU2Ms$9$Foihx#LRhM-xRW!3%*tTCv(&-fh@_wKTYvEv z63-Ft*06F=v92lk$RWbrR{V$4%7R|Rysq!PzIK1;)^;se+KsgxZVbD1AS}~GS;jV?%)Dg-x=vr; zgy^eiBu33X6mFuRChh~_Pf#-Rz8Fn3F@7ON(=AI_3M0gz1`?8C{6PF*yszzBfkfiV z{d4Z`oO93bo^#$E>Dv=E7cG`5fWI@Dlj3OPbd3X^I^B}kNv2HufCxo0WiIbk#hpr3 zPj49A0D(xK0;3kufY%z)h*zs%640;Sr3N6}p~eiKL)eF| z8$Td^=hatC{YH3Py=wh~unsFgY&u40Jfw~C4%E%NjJ9+fqs_>~d#$$g7A$*o3)IEe zGqyB~F>e{O%DtKwX%l@YZ|y?=*m&52xY{AB|1&}{E45wt?i?|<8GXmNU;q`EA>-yZ zFs4{higVVCXv)`5kR#wYl((Rpc4u7z>X6 za`Xm<*CEZCuUN<N>$;6*zfxfAm^!EIZh`m}w7)A%` z)u%+LqjL1z-eSkc(FwjzYg0?`L{#OV2hZAFEIo z`xH?0-K9~W!OI}9TTL{MLAXbq-!uq?f+;b)Yet%#&J^f`G%+p~49`!bj?7N0Ywk-B z{)x^tpNG5DZchTjsQRwA37TEv@sbBR?Xw#kqUNQEMq#SxiRFPPuNx&(M>6t}^knkY zaVaw)73@X(CsDTKs{Z2p8CHLS`R~IsW3#Fk{B^W3O!pEGKv=yNya=Hay%vfN=ExO> zJG*&_@#GoLD%ZN;S>$5NTr5YHG%ZVvJI}aRxviJvMXr6BYu7dYC8jCQG_7)>1!|Ft zEOU_@xmJZPhw`R=g6_wG`qg*BUqXuv&Hcn}q2c|#YXpxv+afRJdRAEH*`rIWKhOGC zh46xXQHU-J(OgeSGr7ci^Q?DO2woBwg>B2iHeEBd#QO5AZ&lFf2<^*4d#>ldipOvR(q-0W>z?qhk0GNQJ{rS?HXeE~H>>>>>> 57f679ee7770f9425fa2725f80f96b9c7e0d0794 print("Scraping process completed successfully!") diff --git a/Forums/Initialization/geckodriver.log b/Forums/Initialization/geckodriver.log index 4a84b00..4653d45 100644 --- a/Forums/Initialization/geckodriver.log +++ b/Forums/Initialization/geckodriver.log @@ -1630,3 +1630,142 @@ JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't fin 1686603752801 Marionette INFO Stopped listening on port 52208 JavaScript error: resource://gre/modules/AsyncShutdown.jsm, line 575: uncaught exception: SessionFileInternal.getWriter() called too early! Please read the session file from disk first. JavaScript error: resource://gre/modules/PageThumbs.jsm, line 718: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished +1686700263325 geckodriver INFO Listening on 127.0.0.1:53021 +1686700267125 mozrunner::runner INFO Running command: "C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "53022" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\MINHKH~1\\AppData\\Local\\Temp\\rust_mozprofilew7iA4s" +console.info: SecurityLevel: Listening for messages from NoScript. +console.info: SecurityLevel: Initializing security-prefs.js +console.info: SecurityLevel: security-prefs.js initialization complete +console.info: TorProtocolService: SOCKS port type: TCP +console.info: TorProtocolService: SOCKS host: 127.0.0.1 +console.info: TorProtocolService: SOCKS port: 9150 +1686700267942 Marionette INFO Marionette enabled +1686700267951 Marionette INFO Listening on port 53029 +WebDriver BiDi listening on ws://localhost:53022 +console.debug: TorProtocolService: + TorProtocolService initialized +Read port: 53029 +console.debug: TorMonitorService: + TorMonitorService initialized +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.error: "getTorFile: cannot get torrc-defaults" (new Error("torrc-defaults file not found: C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\TorBrowser\\Tor\\torrc-defaults", "resource://gre/modules/TorLauncherUtil.jsm", 245)) +console.error: TorProcess: + startTor error: + Message: TypeError: torrcDefaultsFile is null + Stack: + _makeArgs@resource://gre/modules/TorProcess.jsm:296:23 +start@resource://gre/modules/TorProcess.jsm:81:12 + +console.error: TorMonitorService: + Tor not running, not starting to monitor it. +1686700268118 RemoteAgent WARN TLS certificate errors will be ignored for this session +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:53022/devtools/browser/c673c878-2958-4481-8950-4fd6f5d3b948 +1686700272178 Marionette WARN Ignoring event 'pageshow' because document has an invalid readyState of 'uninitialized'. +1686700272375 Marionette INFO Stopped listening on port 53029 +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/AsyncShutdown.jsm, line 575: uncaught exception: SessionFileInternal.getWriter() called too early! Please read the session file from disk first. +JavaScript error: resource://gre/modules/PromiseWorker.jsm, line 106: Error: Could not get children of file(C:\Users\MINHKH~1\AppData\Local\Temp\rust_mozprofilew7iA4s\thumbnails) because it does not exist +1686700398479 geckodriver INFO Listening on 127.0.0.1:53150 +1686700409460 mozrunner::runner INFO Running command: "C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "53151" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\MINHKH~1\\AppData\\Local\\Temp\\rust_mozprofileUkq06Y" +console.info: SecurityLevel: Listening for messages from NoScript. +console.info: SecurityLevel: Initializing security-prefs.js +console.info: SecurityLevel: security-prefs.js initialization complete +console.info: TorProtocolService: SOCKS port type: TCP +console.info: TorProtocolService: SOCKS host: 127.0.0.1 +console.info: TorProtocolService: SOCKS port: 9150 +1686700410130 Marionette INFO Marionette enabled +1686700410138 Marionette INFO Listening on port 53161 +WebDriver BiDi listening on ws://localhost:53151 +Read port: 53161 +console.debug: TorProtocolService: + TorProtocolService initialized +console.debug: TorMonitorService: + TorMonitorService initialized +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.error: "getTorFile: cannot get torrc-defaults" (new Error("torrc-defaults file not found: C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\TorBrowser\\Tor\\torrc-defaults", "resource://gre/modules/TorLauncherUtil.jsm", 245)) +console.error: TorProcess: + startTor error: + Message: TypeError: torrcDefaultsFile is null + Stack: + _makeArgs@resource://gre/modules/TorProcess.jsm:296:23 +start@resource://gre/modules/TorProcess.jsm:81:12 + +console.error: TorMonitorService: + Tor not running, not starting to monitor it. +1686700410307 RemoteAgent WARN TLS certificate errors will be ignored for this session +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:53151/devtools/browser/2c2722d3-4863-403d-a64a-f78e13ef52f4 +console.warn: LoginRecipes: "getRecipes: falling back to a synchronous message for:" "http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion" +console.warn: LoginRecipes: "getRecipes: falling back to a synchronous message for:" "http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion" +JavaScript error: resource://gre/modules/LoginManagerParent.jsm, line 136: TypeError: gRecipeManager is null +console.warn: LoginRecipes: "getRecipes: falling back to a synchronous message for:" "http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion" +JavaScript error: resource://gre/modules/LoginManagerParent.jsm, line 136: TypeError: gRecipeManager is null +console.warn: LoginRecipes: "getRecipes: falling back to a synchronous message for:" "http://cryptbbtg65gibadeeo2awe3j7s6evg7eklserehqr4w4e2bis5tebid.onion" +JavaScript error: resource://gre/modules/LoginManagerParent.jsm, line 136: TypeError: gRecipeManager is null +1686700505593 Marionette INFO Stopped listening on port 53161 +JavaScript error: resource://gre/modules/AsyncShutdown.jsm, line 575: uncaught exception: SessionFileInternal.getWriter() called too early! Please read the session file from disk first. +JavaScript error: resource://gre/modules/PageThumbs.jsm, line 718: AbortError: IOUtils.profileBeforeChange getter: IOUtils: profileBeforeChange phase has already finished +[Parent 5020, IPC I/O Parent] WARNING: pipe error: 232: file /var/tmp/build/firefox-cc1bd3d61c87/ipc/chromium/src/chrome/common/ipc_channel_win.cc:554 +1686700833340 geckodriver INFO Listening on 127.0.0.1:53267 +1686700837481 mozrunner::runner INFO Running command: "C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\firefox.exe" "--marionette" "--remote-debugging-port" "53268" "--remote-allow-hosts" "localhost" "-no-remote" "-profile" "C:\\Users\\MINHKH~1\\AppData\\Local\\Temp\\rust_mozprofileVl5ZBn" +console.info: SecurityLevel: Listening for messages from NoScript. +console.info: SecurityLevel: Initializing security-prefs.js +console.info: SecurityLevel: security-prefs.js initialization complete +console.info: TorProtocolService: SOCKS port type: TCP +console.info: TorProtocolService: SOCKS host: 127.0.0.1 +console.info: TorProtocolService: SOCKS port: 9150 +1686700838381 Marionette INFO Marionette enabled +1686700838388 Marionette INFO Listening on port 53275 +WebDriver BiDi listening on ws://localhost:53268 +console.debug: TorProtocolService: + TorProtocolService initialized +console.debug: TorMonitorService: + TorMonitorService initialized +console.log: "TorSettings: loadFromPrefs()" +console.log: "TorConnect: init()" +console.log: "TorConnect: Entering Initial state" +console.log: "TorConnect: Observing topic 'TorProcessExited'" +console.log: "TorConnect: Observing topic 'TorLogHasWarnOrErr'" +console.log: "TorConnect: Observing topic 'torsettings:ready'" +console.error: "getTorFile: cannot get torrc-defaults" (new Error("torrc-defaults file not found: C:\\Users\\minhkhoitran\\Desktop\\Tor Browser\\Browser\\TorBrowser\\Tor\\torrc-defaults", "resource://gre/modules/TorLauncherUtil.jsm", 245)) +console.error: TorProcess: + startTor error: + Message: TypeError: torrcDefaultsFile is null + Stack: + _makeArgs@resource://gre/modules/TorProcess.jsm:296:23 +start@resource://gre/modules/TorProcess.jsm:81:12 + +console.error: TorMonitorService: + Tor not running, not starting to monitor it. +Read port: 53275 +1686700838658 RemoteAgent WARN TLS certificate errors will be ignored for this session +console.log: "TorConnect: Will load after bootstrap => [about:blank]" +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XULStore.jsm, line 66: Error: Can't find profile directory. +JavaScript error: resource://gre/modules/XPCOMUtils.jsm, line 161: TypeError: Cc[aContract] is undefined +DevTools listening on ws://localhost:53268/devtools/browser/87406a4b-45a9-4dde-be46-ed420afc3449 diff --git a/Forums/Initialization/prepare_parser.py b/Forums/Initialization/prepare_parser.py index 5896bc5..ec1e86a 100644 --- a/Forums/Initialization/prepare_parser.py +++ b/Forums/Initialization/prepare_parser.py @@ -112,11 +112,11 @@ def new_parse(forum, createLog): raise SystemExit # Reading the Listing Html Pages - for fileListing in glob.glob(os.path.join (os.getcwd().replace("Initialization","") + forum + "\\HTML_Pages\\" + str("%02d" %crawlerDate.month) + str("%02d" %crawlerDate.day) + str("%04d" %crawlerDate.year) + "\\Listing" ,'*.html')): + for fileListing in glob.glob(os.path.join (os.getcwd().replace("initialization","") + forum + "\\HTML_Pages\\" + str("%02d" %crawlerDate.month) + str("%02d" %crawlerDate.day) + str("%04d" %crawlerDate.year) + "\\Listing" ,'*.html')): lines.append(fileListing) # Reading the Description Html Pages - for fileDescription in glob.glob(os.path.join (os.getcwd().replace("Initialization","") + forum + "\\HTML_Pages\\" + str("%02d" %crawlerDate.month) + str("%02d" %crawlerDate.day) + str("%04d" %crawlerDate.year) + "\\Description" ,'*.html')): + for fileDescription in glob.glob(os.path.join (os.getcwd().replace("initialization","") + forum + "\\HTML_Pages\\" + str("%02d" %crawlerDate.month) + str("%02d" %crawlerDate.day) + str("%04d" %crawlerDate.year) + "\\Description" ,'*.html')): lns.append(fileDescription) # Parsing the Description Pages and put the tag's content into a dictionary (Hash table)