clean_filename.py

# From https://gist.github.com/wassname/1393c4a57cfcbf03641dbc31886123b8

import unicodedata
import string

valid_filename_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
char_limit = 255

def convert(filename, whitelist=valid_filename_chars, replace=''):
     # replace arbitrary things with underscore (default nuffin')
    for r in replace:
        filename = filename.replace(r,'_')
    
    # keep only valid ascii chars
    cleaned_filename = unicodedata.normalize('NFKD', filename).encode('ASCII', 'ignore').decode()
    
    # keep only whitelisted chars
    cleaned_filename = ''.join(c for c in cleaned_filename if c in whitelist)
    if len(cleaned_filename)>char_limit:
        print("Warning, filename truncated because it was over {}. Filenames may no longer be unique".format(char_limit))
    return cleaned_filename[:char_limit]