您可以将http://spambayes.sourceforge.net/和http://www.cs.cmu.edu/~biglou/resources/bad-words.txt结合在一起。

arrBad = [
'2g1c',
'2 girls 1 cup',
'acrotomophilia',
'anal',
'anilingus',
'anus',
'arsehole',
'ass',
'asshole',
'assmunch',
'auto erotic',
'autoerotic',
'babeland',
'baby batter',
'ball gag',
'ball gravy',
'ball kicking',
'ball licking',
'ball sack',
'ball sucking',
'bangbros',
'bareback',
'barely legal',
'barenaked',
'bastardo',
'bastinado',
'bbw',
'bdsm',
'beaver cleaver',
'beaver lips',
'bestiality',
'bi curious',
'big black',
'big breasts',
'big knockers',
'big tits',
'bimbos',
'birdlock',
'bitch',
'black cock',
'blonde action',
'blonde on blonde action',
'blow j',
'blow your l',
'blue waffle',
'blumpkin',
'bollocks',
'bondage',
'boner',
'boob',
'boobs',
'booty call',
'brown showers',
'brunette action',
'bukkake',
'bulldyke',
'bullet vibe',
'bung hole',
'bunghole',
'busty',
'butt',
'buttcheeks',
'butthole',
'camel toe',
'camgirl',
'camslut',
'camwhore',
'carpet muncher',
'carpetmuncher',
'chocolate rosebuds',
'circlejerk',
'cleveland steamer',
'clit',
'clitoris',
'clover clamps',
'clusterfuck',
'cock',
'cocks',
'coprolagnia',
'coprophilia',
'cornhole',
'cum',
'cumming',
'cunnilingus',
'cunt',
'darkie',
'date rape',
'daterape',
'deep throat',
'deepthroat',
'dick',
'dildo',
'dirty pillows',
'dirty sanchez',
'dog style',
'doggie style',
'doggiestyle',
'doggy style',
'doggystyle',
'dolcett',
'domination',
'dominatrix',
'dommes',
'donkey punch',
'double dong',
'double penetration',
'dp action',
'eat my ass',
'ecchi',
'ejaculation',
'erotic',
'erotism',
'escort',
'ethical slut',
'eunuch',
'faggot',
'fecal',
'felch',
'fellatio',
'feltch',
'female squirting',
'femdom',
'figging',
'fingering',
'fisting',
'foot fetish',
'footjob',
'frotting',
'fuck',
'fucking',
'fuck buttons',
'fudge packer',
'fudgepacker',
'futanari',
'g-spot',
'gang bang',
'gay sex',
'genitals',
'giant cock',
'girl on',
'girl on top',
'girls gone wild',
'goatcx',
'goatse',
'gokkun',
'golden shower',
'goo girl',
'goodpoop',
'goregasm',
'grope',
'group sex',
'guro',
'hand job',
'handjob',
'hard core',
'hardcore',
'hentai',
'homoerotic',
'honkey',
'hooker',
'hot chick',
'how to kill',
'how to murder',
'huge fat',
'humping',
'incest',
'intercourse',
'jack off',
'jail bait',
'jailbait',
'jerk off',
'jigaboo',
'jiggaboo',
'jiggerboo',
'jizz',
'juggs',
'kike',
'kinbaku',
'kinkster',
'kinky',
'knobbing',
'leather restraint',
'leather straight jacket',
'lemon party',
'lolita',
'lovemaking',
'make me come',
'male squirting',
'masturbate',
'menage a trois',
'milf',
'missionary position',
'motherfucker',
'mound of venus',
'mr hands',
'muff diver',
'muffdiving',
'nambla',
'nawashi',
'negro',
'neonazi',
'nig nog',
'nigga',
'nigger',
'nimphomania',
'nipple',
'nipples',
'nsfw images',
'nude',
'nudity',
'nympho',
'nymphomania',
'octopussy',
'omorashi',
'one cup two girls',
'one guy one jar',
'orgasm',
'orgy',
'paedophile',
'panties',
'panty',
'pedobear',
'pedophile',
'pegging',
'penis',
'phone sex',
'piece of shit',
'piss pig',
'pissing',
'pisspig',
'playboy',
'pleasure chest',
'pole smoker',
'ponyplay',
'poof',
'poop chute',
'poopchute',
'porn',
'porno',
'pornography',
'prince albert piercing',
'pthc',
'pubes',
'pussy',
'queaf',
'raghead',
'raging boner',
'rape',
'raping',
'rapist',
'rectum',
'reverse cowgirl',
'rimjob',
'rimming',
'rosy palm',
'rosy palm and her 5 sisters',
'rusty trombone',
's&m',
'sadism',
'scat',
'schlong',
'scissoring',
'semen',
'sex',
'sexo',
'sexy',
'shaved beaver',
'shaved pussy',
'shemale',
'shibari',
'shit',
'shota',
'shrimping',
'slanteye',
'slut',
'smut',
'snatch',
'snowballing',
'sodomize',
'sodomy',
'spic',
'spooge',
'spread legs',
'strap on',
'strapon',
'strappado',
'strip club',
'style doggy',
'suck',
'sucks',
'suicide girls',
'sultry women',
'swastika',
'swinger',
'tainted love',
'taste my',
'tea bagging',
'threesome',
'throating',
'tied up',
'tight white',
'tit',
'tits',
'titties',
'titty',
'tongue in a',
'topless',
'tosser',
'towelhead',
'tranny',
'tribadism',
'tub girl',
'tubgirl',
'tushy',
'twat',
'twink',
'twinkie',
'two girls one cup',
'undressing',
'upskirt',
'urethra play',
'urophilia',
'vagina',
'venus mound',
'vibrator',
'violet blue',
'violet wand',
'vorarephilia',
'voyeur',
'vulva',
'wank',
'wet dream',
'wetback',
'white power',
'women rapping',
'wrapping men',
'wrinkled starfish',
'xx',
'xxx',
'yaoi',
'yellow showers',
'yiffy',
'zoophilia']

def profanityFilter(text):
brokenStr1 = text.split()
badWordMask = '!@#$%!@#$%^~!@%^~@#$%!@#$%^~!'
new = ''
for word in brokenStr1:
    if word in arrBad:
        print word + ' <--Bad word!'
        text = text.replace(word,badWordMask[:len(word)])
        #print new

return text

print profanityFilter("this thing sucks sucks sucks fucking stuff")

您可以根据需要添加或删除不良词列表arrBad。

WebPurify是Python的亵渎过滤器库

我没有找到任何Python亵渎库，所以我自己做了一个。

参量

filterlist

与禁止字匹配的正则表达式列表。请不要使用\b ，它会根据inside_words插入。

例如： ['bad', 'un\w+']

ignore_case

默认值： True

不言自明。

replacements

默认值： "$@%-?!"

一个带有字符的字符串，将从中随机生成替换字符串。

示例： "%&$?!"或"-"等

complete

默认值： True

控制是否将替换整个字符串，或者是否保留第一个和最后一个字符。

inside_words

默认值： False

控制是否也在其他单词中搜索单词。禁用此

模块来源

（最后的例子）

"""
Module that provides a class that filters profanities

"""

__author__ = "leoluk"
__version__ = '0.0.1'

import random
import re

class ProfanitiesFilter(object):
    def __init__(self, filterlist, ignore_case=True, replacements="$@%-?!", 
                 complete=True, inside_words=False):
        """
        Inits the profanity filter.

        filterlist -- a list of regular expressions that
        matches words that are forbidden
        ignore_case -- ignore capitalization
        replacements -- string with characters to replace the forbidden word
        complete -- completely remove the word or keep the first and last char?
        inside_words -- search inside other words?

        """

        self.badwords = filterlist
        self.ignore_case = ignore_case
        self.replacements = replacements
        self.complete = complete
        self.inside_words = inside_words

    def _make_clean_word(self, length):
        """
        Generates a random replacement string of a given length
        using the chars in self.replacements.

        """
        return ''.join([random.choice(self.replacements) for i in
                  range(length)])

    def __replacer(self, match):
        value = match.group()
        if self.complete:
            return self._make_clean_word(len(value))
        else:
            return value[0]+self._make_clean_word(len(value)-2)+value[-1]

    def clean(self, text):
        """Cleans a string from profanity."""

        regexp_insidewords = {
            True: r'(%s)',
            False: r'\b(%s)\b',
            }

        regexp = (regexp_insidewords[self.inside_words] % 
                  '|'.join(self.badwords))

        r = re.compile(regexp, re.IGNORECASE if self.ignore_case else 0)

        return r.sub(self.__replacer, text)


if __name__ == '__main__':

    f = ProfanitiesFilter(['bad', 'un\w+'], replacements="-")    
    example = "I am doing bad ungood badlike things."

    print f.clean(example)
    # Returns "I am doing --- ------ badlike things."

    f.inside_words = True    
    print f.clean(example)
    # Returns "I am doing --- ------ ---like things."

    f.complete = False    
    print f.clean(example)
    # Returns "I am doing b-d u----d b-dlike things."