Python encoding processing: The difference and use of str and Unicode

Traceback (most recent call last): File "<stdin>", line 1, in <module> UnicodeDecodeError: ‘ascii‘ codec can‘t decode byte 0xe6 in position 0: ordinal

Traceback (most recent call last): File "<stdin>", line 1, in <module> File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/encodings/utf_8.py", line 16, in decode     return codecs.utf_8_decode(input, errors, True) UnicodeEncodeError: ‘ascii‘ codec can‘t encode characters in position 0-1: ordinal not in range(128)

>>> s = ‘中文‘ s = u‘中文‘.encode(‘utf-8‘)  
>>> type(‘中文‘) <type ‘str‘>

>>> u‘中文‘.encode(‘utf-8‘) ‘\xe4\xb8\xad\xe6\x96\x87‘ 
>>> len(u‘中文‘.encode(‘utf-8‘)) 
6

>>> s = u‘中文‘ 
>>> s = ‘中文‘.decode(‘utf-8‘) 
>>> s = unicode(‘中文‘, ‘utf-8‘)  
>>> type(u‘中文‘) <type ‘unicode‘>

>>> u‘中文‘ u‘\u4e2d\u6587‘ 
>>> len(u‘中文‘) 
2

>>> isinstance(u‘中文‘, unicode) True 
>>> isinstance(‘中文‘, unicode) False  
>>> isinstance(‘中文‘, str) True 
>>> isinstance(u‘中文‘, str) False

>>> ‘中文‘.encode(‘utf-8‘) 
Traceback (most recent call last): File "", line 1, in  UnicodeDecodeError: ‘ascii‘ codec can‘t decode byte 0xe4 in position 0: ordinal not in range(128)  
>>> u‘中文‘.decode(‘utf-8‘) 
Traceback (most recent call last): File "<stdin>", line 1, in <module> File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/encodings/utf_8.py", line 16, in decode     return codecs.utf_8_decode(input, errors, True) UnicodeEncodeError: ‘ascii‘ codec can‘t encode characters in position 0-1: ordinal not in range(128)

#s是code_A的str s.decode(‘code_A‘).encode(‘code_B‘)

>>> print u‘中文‘.encode(‘gbk‘) ???? 
>>> print u‘中文‘.encode(‘utf-8‘) 中文

File "XXX.py", line 3 SyntaxError: Non-ASCII character ‘\xd6‘ in file c.py on line 3, but no encoding declared; see http://www.python.org/peps/pep-0263.html for details

# -*- coding: utf-8 -*- 或者 #coding=utf-8

if s == u‘中文‘:  #而不是 s == ‘中文‘     pass #注意这里 s到这里时，确保转为unicode

>>> import sys 
>>> sys.getdefaultencoding() ‘ascii‘  
>>> reload(sys) <module ‘sys‘ (built-in)> 
>>> sys.setdefaultencoding(‘utf-8‘) 
>>> sys.getdefaultencoding() ‘utf-8‘ 
>>> str.encode(‘other_coding‘)

>>> import chardet 
>>> f = open(‘test.txt‘,‘r‘) 
>>> result = chardet.detect(f.read()) 
>>> result {‘confidence‘: 0.99, ‘encoding‘: ‘utf-8‘}

>>> u‘中‘ u‘\u4e2d‘  
>>> s = ‘\u4e2d‘ 
>>> print s.decode(‘unicode_escape‘) 中  
>>> a = ‘\\u4fee\\u6539\\u8282\\u70b9\\u72b6\\u6001\\u6210\\u529f‘ 
>>> a.decode(‘unicode_escape‘) u‘\u4fee\u6539\u8282\u70b9\u72b6\u6001\u6210\u529f‘