python 正则过滤中文、英文、数字、特殊字符demo

import re
# 匹配中文
CN_PATTERN = re.compile(u'[\u4e00-\u9fa5]')
# 匹配英文和数字
NUM_PATTERN = re.compile(r'[A-Za-z0-9]+')
# 匹配关键词
KEYWORDS_PATTERN = re.compile(r'新疆大学|世界|外汇|中国')
# 特殊自负
SPECIAL_CHAR_PATTERN = re.compile(r'[’!"#$%&\'()*+,-./:;<=>?@，。?★、…【】《》？“”‘’！\[\\\]^_`{|}~]+')
def regular_fun(s):
    cn = CN_PATTERN.findall(s)
    num = NUM_PATTERN.findall(s)
    words = KEYWORDS_PATTERN.findall(s)
    print(cn, num, words)

if __name__ == '__main__':
    t1 = r'this boy chincese name, NLPer, 18 years old'
    t2 = r'当前测试数据全是中文'
    t3 = r'current data is all english!'
    t4 = r'ddddddddddddddddddddddddddddddddddddddddddddddddddddddddd这是一个对用户预填垃圾信息过滤方案'
    t5 = r'新疆大学（Xinjiang University），简称“新大”，位于新疆维吾尔自治区首府乌鲁木齐，是世界一流大学建设高校（B类）'
    t6 = r'%^&&*^*(^&*(%&%$#$@#%^#'
    regular_fun(t1)
    regular_fun(t2)
    regular_fun(t3)
    regular_fun(t4)
    regular_fun(t5)
    regular_fun(t6)
    print(SPECIAL_CHAR_PATTERN.findall(t3))