[linux] 正则re去除标点符号等自定义特殊字符

import re
import sys

punctuation = "~!@#$%^&*()_+`{}|\[\]\:\";\-\\\='<>?,./?,。;!~"

def removePunctuation(text):
    text = re.sub(r'[{}]+'.format(punctuation), ' ', text)
    return text.strip().lower()

for line in sys.stdin:
        line = line.replace("\n", "")
        replaced_line = removePunctuation(line)
        print(replaced_line)

猜你喜欢

转载自blog.csdn.net/Trance95/article/details/130198469
今日推荐