使用Python编写提取日志中的中文的脚本的方法

# -*- coding: utf-8 -*-
#!/usr/bin/python
# filename: picktools.py
# codedtime:2015-3-25

import os
import configparser

# 遍历一个目录，输出所有文件名
def itemsbrowse(path):
  for home, dirs, files in os.walk(path):
    for filename in files:
      yield os.path.join(home, filename)

# 给的文件中查找对应的字符串所在行      
def findchars(filename, chars):
  file = open(filename, 'r')
  for eachline in file:
    if eachline.find(chars) >= 0:
      yield eachline
  file.close()

# 添加到指定的文件
def addtofile(filename, mygenerator):
  file = open(filename, 'a')   # 追加方式打开
  for line in mygenerator:
    file.write(line)
  file.close()

# 过滤重复的字符行
def filter(filename):
  mylist = []
  file = open(filename, 'r')
  for eachline in file:
    mylist.append(eachline.strip())
  file.close()
  
  file2 = open(os.path.splitext(filename)[0] + '_filter.txt', 'w')
  for line in list(set(mylist)):
    print(line, file = file2)
    #file2.write(line) 
  file2.close()
  

def excute():
  iniconf = configparser.ConfigParser()
  iniconf.read('config.ini')
  ifile = iniconf.get('setting', 'ifilepath')
  ofile = iniconf.get('setting', 'ofilepath')
  chars = iniconf.get('setting', 'searchstr')
  
  for fullname in itemsbrowse(ifile):
    mygenerator = findchars(fullname, chars)
    addtofile(ofile, mygenerator)
    
  filter(ofile)
      
      
if __name__ == '__main__':
  excute()