utils.py 文件源码

def remove_emoticons(text):
    # build regexp with imported emoticon list
    smileys = '|'.join(map(re.escape, emoticons))
    emoticonsPattern = re.compile('({})'.format(smileys), flags=re.IGNORECASE)
    removed = re.sub(emoticonsPattern, '', text)
    # remove unnecessary white spaces utilizing the TweetTokenizer
    removed = tokenize(removed)
    return " ".join(sum(removed, []))