slugify.py

import random
import re
import unicodedata


def slugify(string, randlen=10):
    string_out = ''
    for char in string:
        if char.isspace():
            string_out += '-'
        elif re.match('[A-Za-z0-9-_]', char):
            string_out += char.lower()
        else:
            norm = unicodedata.normalize('NFKD', char)[0].encode('ascii',
                'ignore')
            if re.match('[A-Za-z0-9-_]', norm):
                string_out += norm.lower()
    string_out = remove_duplicates(string_out.strip('-_'), '-_')
    if not re.match(r'[A-Za-z0-9-_]+', string_out):
        return ''.join(
            random.choice(string.ascii_letters + '-_')
            for i in range(randlen)).strip('-_')
    return string_out


def remove_duplicates(string, characters):
    for char in characters:
        string = re.sub('(%s)+' % re.escape(char), char, string)
    return string