Using Cursor to write some code ot download YT as Mp3. Then I wanted to parse the transcript file I had it create for inappropriate language.
Here's what it gave me. I found the last two weird.
# Define patterns to check for
PATTERNS = {
'strong_language': [
r'\b(fuck|shit|damn|hell|bitch|ass|nigga|niggas)\b',
r'\b(bloody|bastard|crap|piss)\b'
],
'violence': [
r'\b(kill|murder|die|death|dead|stab|shoot|hurt|harm|attack|fight|war)\b',
r'\b(blood|violence|weapon|gun|knife|sword)\b'
],
'dark_themes': [
r'\b(hell|demon|devil|evil|dark|curse|witch|ghost|haunt)\b',
r'\b(terror|fear|scare|horror|nightmare)\b'
],
'adult_content': [
r'\b(sex|naked|nude|drunk|drug|alcohol|beer|wine|whiskey)\b',
r'\b(kiss|love|romance|relationship|marriage)\b'
],
'death_references': [
r'\b(die|death|dead|grave|tomb|coffin|bury|kill)\b',
r'\b(murder|suicide|execution|slaughter)\b'
],
'rebellious': [
r'\b(rebel|defy|disobey|break rules|against authority)\b',
r'\b(revolution|riot|protest|anarchy)\b'
],
'religious': [
r'\b(god|jesus|christ|heaven|hell|devil|satan|pray|church)\b',
r'\b(religion|faith|belief|worship|sacred|holy)\b'
]
}
