Python只读取文本中文字符

#coding=utf-8
import re

with open('aaa.txt','r',encoding="utf-8") as f:
    #data = f.read().decode('gbk').encode('utf-8')
    data = f.read()
    print(data)
    #str = re.sub(r'(\\u\d+)',"",data)
    #data = re.sub("[A-Za-z0-9\!\%\[\]\,\。]", "", data)
    #data = re.sub('[\W_+]', "", data)
    data = re.sub('[\u4E00-\u9FA5]',"", data)
    print(data)

#过滤掉除了中文以外的字符

 

import re

"""
python 3.5版本
正则匹配中文，固定形式：\u4E00-\u9FA5
"""

text = "aqweded***中国***xsa***日本***韩国"
regStr = ".*?([\u4E00-\u9FA5]+).*?"
aa = re.findall(regStr, text)
if aa:
    print(aa)

#提取字符串里的中文，返回数组 

#coding=utf-8
import re

with open('aaa.txt','r',encoding="utf-8") as f:
    #data = f.read().decode('gbk').encode('utf-8')
    data = f.read()
    print(data)
    data = re.sub("[A-Za-z0-9\!\%\[\]\,\。\ ]", "", data)
    #data = re.sub('[\u4E00-\u9FA5]',"", data)
    print(data)

 

# -*- coding: utf-8 -*-
import re
#过滤掉除了中文以外的字符
str = "hello,world!!%[545]你好234世界。。。"
str = re.sub("[A-Za-z0-9\!\%\[\]\,\。]", "", str)
print(str)
 
#提取字符串里的中文，返回数组
pattern="[\u4e00-\u9fa5]+" 
regex = re.compile(pattern)
results =  regex.findall("adf中文adf发京东方")
print(results)