python正则-文本预处理

import re

# make English text clean
def clean_en_text(text):
# keep English,
comp = re.compile('[^A-Z^a-z^0-9^ ]')
return comp.sub('', text)

# make Chinese text clean
def clean_zh_text(text):
# keep English,
comp = re.compile('[^A-Z^a-z^0-9^\u4e00-\u9fa5]')
return comp.sub('', text)

if __name__ == '__main__':
text_en = '$How old are you?$'
text_zh = '$你好！我是个程序媛，中国新生代农民工。$'
print(clean_en_text(text_en))
print(clean_zh_text(text_zh))