2.15.0-Beta3 - Many Bug Fixes

- Fixed log file path not being recognized with quotes around it #571
- Fixed crash when unable to encode certain unicode characters #568
- Fixed crash when writing JSON log #563
- Improve Filters #556
- Update default included spam lists
- Change default log format from rtf to plaintext

Scripts/files.py

@@ -851,6 +851,7 @@ def parse_comment_list(config, recovery=False, removal=False, returnFileName=Fal
     if str(listFileName).lower() == "x":
       return "MainMenu", None
 
+    listFileName = listFileName.strip("\"").strip("'") # Remove quotes, if added by dragging and dropping or pasting path
     if len(listFileName) > 0:
       if os.path.exists(listFileName):
         pass

Scripts/logging.py

@@ -4,6 +4,7 @@ from Scripts.shared_imports import *
 import Scripts.utils as utils
 import Scripts.auth as auth
 from Scripts.utils import choice
+from unicodedata import category as unicode_category
 
 import rtfunicode
 import os
@@ -287,7 +288,14 @@ def print_prepared_comments(current, commentsContents, scanVideoID, comments, j,
 # Takes in a string that contains unicode, and returns a string with properly escaped unicode format for use in rtf files
 # Uses 'rtfunicode' module to encode with proper rtf-compatible unicode escapes, then decode back to utf-8 so it can be written to file and read by wordpad or whatever
 def make_rtf_compatible(text):
-  return text.encode('rtfunicode').decode('utf-8')
+  try:
+    return text.encode('rtfunicode').decode('utf-8')
+  except:
+    intermediate = "".join(char for char in text if unicode_category(char) not in ["Mn", "Cc", "Cf", "Cs", "Co", "Cn"])
+    try:
+      return intermediate.encode('rtfunicode').decode('utf-8')
+    except:
+      return intermediate
 
 # Writes properly to rtf file, also can prepare with necessary header information and formatting settings
 def write_rtf(fileName, newText=None, firstWrite=False, fullWrite=False):
@@ -512,7 +520,7 @@ def get_extra_json_data(channelIDs, jsonSettingsDict):
     remainder = total % 50
     numDivisions = int((total-remainder)/50)
     for i in range(numDivisions):
-      fetch_data(channelIDs[i*50:i*50+50])         
+      fetch_data(channelIDs[i*50:i*50+50])
     if remainder > 0:
       fetch_data(channelIDs[numDivisions*50:])
   else:

Scripts/prepare_modes.py

@@ -315,7 +315,7 @@ def prepare_filter_mode_smart(scanMode, config, miscData, sensitive=False):
   # General Spammer Criteria
   #usernameBlackChars = ""
   spamGenEmoji_Raw = b'@Sl-~@Sl-};+UQApOJ|0pOJ~;q_yw3kMN(AyyC2e@3@cRnVj&SlB@'
-  usernameBlackWords_Raw = [b'aA|ICWn^M`', b'aA|ICWn>^?c>', b'Z*CxTWo%_<a$#)', b'c4=WCbY*O1XL4a}', b'Z*CxIZgX^DXL4a}', b'Z*CxIX8', b'V`yb#YanfTAY*7@', b'b7f^9ZFwMLXkh', b'c4>2IbRcbcAY*7@', b'X>N0LVP|q-Z8`', b'Z*CxIZgX^D', b'Z*CxIZgX^DAZK!6Z2', b'c4=WCX>N0LVP|q-Z2', b'b9G`gb9G_', b'b9G`MG$3<zVg', b'Z*CxMc_3qGVE', b'XKx^MZy;@XAY*7@']
+  usernameBlackWords_Raw = [b'aA|ICWn^M`', b'aA|ICWn>^?c>', b'Z*CxTWo%_<a$#)', b'c4=WCbY*O1XL4a}', b'Z*CxIZgX^DXL4a}', b'Z*CxIX8', b'V`yb#YanfTAY*7@', b'b7f^9ZFwMLXkh', b'c4>2IbRcbcAY*7@', b'X>N0LVP|q-Z8`', b'Z*CxIZgX^D', b'Z*CxIZgX^DAZK!6Z2', b'c4=WCX>N0LVP|q-Z2', b'b9G`gb9G_', b'b9G`MG$3<zVg', b'Z*CxMc_3qGVE', b'XKx^MZy;@XAY*7@', b'X(w$UY-ML@bRcteVq$4-X8', b'W^!d^AZKZ2bN']
   usernameNovidBlackWords_Raw = [b'cWHEJATS_yX=D', b'cWHEJAZ~9Uc4=e', b'cWHEJZ*_DaVQzUKc4=e']
   usernameObfuBlackWords_Raw = [b'c4Bp7YjX', b'b|7MPV{3B', b'a&KaFcm', b'a&KaFV{3B']
   usernameRedWords = ["whatsapp", "telegram"]

YTSpammerPurge.py

@@ -36,7 +36,7 @@
 ### IMPORTANT:  I OFFER NO WARRANTY OR GUARANTEE FOR THIS SCRIPT. USE AT YOUR OWN RISK.
 ###             I tested it on my own and implemented some failsafes as best as I could,
 ###             but there could always be some kind of bug. You should inspect the code yourself.
-version = "2.15.0-Beta2"
+version = "2.15.0-Beta3"
 configVersion = 26
 #~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~#
 
@@ -1513,8 +1513,8 @@ def main():
         print("\nWriting JSON log file...")
         if config['json_extra_data'] == True:
           if current.errorOccurred == False:
-            jsonDataDict = logging.get_extra_json_data(list(combinedCommentDict.keys()), jsonSettingsDict)
-            logging.write_json_log(jsonSettingsDict, combinedCommentDict.keys(), jsonDataDict)
+            jsonDataDict = logging.get_extra_json_data(list(current.matchSamplesDict.keys()), jsonSettingsDict)
+            logging.write_json_log(jsonSettingsDict, combinedCommentDict, jsonDataDict)
           else:
             print(f"\n{F.LIGHTRED_EX}NOTE:{S.R} Extra JSON data collection disabled due to error during scanning")
         else:
@@ -1524,10 +1524,10 @@ def main():
     ### ---------------- Reporting / Deletion Begin  ----------------
     if returnToMenu == False:
       if proceedWithDeletion == True:
-        operations.delete_found_comments(list(combinedCommentDict.keys()), banChoice, deletionMode)
+        operations.delete_found_comments(list(combinedCommentDict), banChoice, deletionMode)
         if deletionMode != "reportSpam":
           if config['check_deletion_success'] == True:
-            operations.check_deleted_comments(list(combinedCommentDict.keys()))
+            operations.check_deleted_comments(list(combinedCommentDict))
           elif config['check_deletion_success'] == False:
             print("\nSkipped checking if deletion was successful.\n")
 

assets/SpamDomainsList.txt

@@ -1,5 +1,5 @@
 #!! NOTE: THESE ARE SCAM / MALICIOUS DOMAINS - DO NOT VISIT THEM
-#version=[2022.1.24]
+#version=[2022.2.6]
 diva.bond
 vbucks22.com
 snapgirls.today
@@ -108,3 +108,17 @@ trojanarticle.com
 astratech.pro
 smarthackerstech.org
 universehackworld.org
+netpayjob.com
+cashend.me
+dollarbrite.com
+xbritclone.net
+247hacks.net
+orxhacks.com
+everyday.cf
+beautygirls.online
+younggirls.today
+bestdate.top
+youtuuu.tokyo
+bigbooty.online
+vum.ngo
+nmnm.lol

assets/SpamThreadsList.txt

@@ -1,6 +1,6 @@
 #!! NOTE: ALL OF THESE USERNAMES ARE BELIEVED TO BE USED BY SCAMMERS - DO NOT CONTACT THEM
 # ANY NAMES OF PEOPLE ARE PRESUMED TO BE FICTITIOUS OR MISAPPROPRIATED: ANY REFERENCE TO A REAL PERSON IS COMPLETELY COINCIDENTAL AND THE EXISTENCE OF SUCH NAMES IN THIS LIST IS ONLY BECAUSE THOSE NAMES ARE USED IN SPAM COMMENTS, AND NOT TO IMPLY THAT EVERYONE WITH THAT NAME IS MALICIOUS
-#version=[2022.1.20]
+#version=[2022.2.6]
 mr williams charles
 mr patrick smith
 mr dieter schwartz
@@ -38,3 +38,5 @@ alexandera davis
 mrs gladys wood
 mrs gladys fx
 mr charles r schwab
+mr lawrence tom
+mr steve miley

assets/default_config.ini

@@ -228,8 +228,8 @@ enable_logging = Ask
 log_path = logs
 
 	# Set whether to create log files as plain text, or Rich Text Format with colors
-	# Default = rtf  |  Possible Values: rtf | plaintext
-log_mode = rtf
+	# Default = plaintext  |  Possible Values: rtf | plaintext
+log_mode = plaintext
 
 	# Allows you to ALSO create a json version of the logged match data (in addition to normal log file)
 	# Note: If enable_logging is False, that also disables json logging regardless of this setting