Delete unwanted characters from txt files, and convert them to valid text files

convert_txt.py

import re

PATH = r"C:\Projects\Notebooks\week4\resources\alice.txt"

with open(PATH, 'rb') as f:
    text = f.read()

new_text = re.sub(br'[^a-zA-Z0-9_ ?!@#$%^&*\(\)+.,></\\[\]\n\r-]', br'', text)

with open(PATH, 'w') as f:
    f.write(new_text.decode('utf-8'))