python提取文件中的汉字

Posted 2021-06-02 骨头

读取指定目录下的文件,提取文件中的所有汉字

# -*- coding: utf-8 -*-

import os
import io
import re

fo = open("word.txt", "w")

# 遍历指定目录，显示目录下的所有文件名
def each_file(filepath):
  for root, dirs, files in os.walk(filepath):
    for file in files:
      filename = os.path.join(root, file)
      read_file(filename)

def read_file(filename):
  with io.open(filename, \'r\', encoding=\'utf-8\', errors=\'ignore\') as fn:
    lines = fn.readlines()
    han = re.compile(\'"[\\u4e00-\\u9fff]+"\').findall(str(lines))
    for val in han:
      fo.write(val + "\\n")



if __name__ == \'__main__\':
  each_file("src")