Python 模块chardet安装过程(windows环境)

最新推荐文章于 2022-10-25 20:44:15 发布

weixin_30377461

最新推荐文章于 2022-10-25 20:44:15 发布

阅读量321

点赞数

文章标签： python java

原文链接：http://www.cnblogs.com/lijc1990/p/3480710.html

版权

　　最近需要一个txt文件的批量转码功能，在网上找到一段批量处理java源文件的py程序如下：

 1 #-*- coding: utf-8 -*-
 2 
 3 import codecs
 4 import os
 5 import shutil
 6 import re
 7 import chardet
 8 
 9 def convert_encoding(filename, target_encoding):
10     # Backup the origin file.
11     shutil.copyfile(filename, filename + '.bak')
12 
13     # convert file from the source encoding to target encoding
14     content = codecs.open(filename, 'r').read()
15     source_encoding = chardet.detect(content)['encoding']
16     print source_encoding, filename
17     content = content.decode(source_encoding) #.encode(source_encoding)
18     codecs.open(filename, 'w', encoding=target_encoding).write(content)
19 
20 def main():
21     for root, dirs, files in os.walk(os.getcwd()):
22         for f in files:
23             if f.lower().endswith('.txt'):
24                 filename = os.path.join(root, f)
25                 try:
26                     convert_encoding(filename, 'utf-8')
27                 except Exception, e:
28                     print filename
29 
30 def process_bak_files(action='restore'):
31     for root, dirs, files in os.walk(os.getcwd()):
32         for f in files:
33             if f.lower().endswith('.txt.bak'):
34                 source = os.path.join(root, f)
35                 target = os.path.join(root, re.sub('\.txt\.bak$', '.txt', f, flags=re.IGNORECASE))
36                 try:
37                     if action == 'restore':
38                         shutil.move(source, target)
39                     elif action == 'clear':
40                         os.remove(source)
41                 except Exception, e:
42                     print source
43 
44 if __name__ == '__main__':
45     # process_bak_files(action='clear')
46     main()