python编码转换(unicode / utf8 / gbk / 内部编码)

点击(此处)折叠或打开

1. #-*- coding: utf-8 -*-
   

2. import sys
   

3.                         
   

4.                         
   

5. print sys.getfilesystemencoding()
   

6.                         
   

7. # s 是 utf8 编码
   

8. s = "hi,你就要成功了."
   

9.                         
   

10.                         
    

11. # 用decode转成python内部的unicode编码,用repr输出内部形式
    

12. s_unicode = s.decode("utf8")
    

13. print repr(s_unicode)
    

14.                         
    

15. # 用ecode转成gbk编码输出
    

16. s_gbk = s_unicode.encode("gbk")
    

17. print s_gbk
    

18.                         
    

19.                         
    

20. # 用ecode转成标准的uincode编码 \u****\u****
    

21. s_unicode_output = s_unicode.encode("unicode_escape")
    

22. print s_unicode_output
    

23.                         
    

24. # 从标准的unicode编码转成 gbk 编码
    

25. s_red_gbk = s_unicode_output.decode("unicode_escape").encode("gbk")
    

26. print s_red_gbk
    

27.                         
    

28. #按照单个字输出 s 的内容
    

29. for i in s_unicode:
    

30.     print i.encode("gbk")