Python 检索目录下所有文件中包含指定字符串的文件

http://blog.youkuaiyun.com/authorzhh/article/details/8933758

#!/usr/bin/env python
# 1.py
# use UTF-8
# Python 3.3.0

# 检索目录下所有文件中包含指定字符串的文件
import os
import re

# 枚举dirPath目录下的所有文件
def ListFiles(dirPath):
#begin
	fileList = []
	for root, dirs, files in os.walk(dirPath):			# 注意os.walk的功能
	#begin
		for fileObj in files:
		#begin
			fileList.append(os.path.join(root, fileObj))
		#end
	#end
	return fileList
#end

def FindString(filePath, regex):
#begin
	fileObj = open(filePath, 'r')
	for eachLine in fileObj:
	#begin
		if re.search(regex, eachLine, re.I):
		#begin
			print(fileObj)		#打印文件对象
			break
		#end
	#end
#end


def main():
#begin
	fileDir = "F:" + os.sep + "aaa"		# 查找F:\aaa 目录下
	regex = 'include'					# 包含include 的文件
	fileList = ListFiles(fileDir)
	print(fileList)
	for fileObj in fileList:
	#begin
		FindString(fileObj, regex)
	#end
	os.system("pause")
#end

if __name__ == '__main__':
#begin
	main()
#end

# 输出:
# <_io.TextIOWrapper name='F:\\aaa\\1.cpp' mode='r' encoding='cp936'>
# <_io.TextIOWrapper name='F:\\aaa\\2.h' mode='r' encoding='cp936'>
# <_io.TextIOWrapper name='F:\\aaa\\3.c' mode='r' encoding='cp936'>
# <_io.TextIOWrapper name='F:\\aaa\\4.h' mode='r' encoding='cp936'>
# <_io.TextIOWrapper name='F:\\aaa\\5.cpp' mode='r' encoding='cp936'>
# <_io.TextIOWrapper name='F:\\aaa\\6.h' mode='r' encoding='cp936'>
# <_io.TextIOWrapper name='F:\\aaa\\我.cpp' mode='r' encoding='cp936'>

# 遇到的问题有
# 如果做枚举到的文件不是文本文件, 例如rar文件, 就会有异常产生