python 编码问题（二）

>>> a = '中文'
>>> chardet.detect(a)
{'confidence': 0.7525, 'encoding': 'utf-8'}
>>> b = a.decode('utf-8')
>>> b
u'\u4e2d\u6587'
>>> c = b.encode('gb2312')
>>> c
'\xd6\xd0\xce\xc4'
>>> d = b.encode('utf-8')
>>> d
'\xe4\xb8\xad\xe6\x96\x87'
>>> e = str(a)
>>> chardet.detect(e)
{'confidence': 0.7525, 'encoding': 'utf-8'}
>>> print a
中文
>>> b
u'\u4e2d\u6587'
>>> print b
中文
>>> print c
����
>>> print d
中文
>>> print e
中文
>>> a == b
False
>>> a == c
False
>>> a == d
True
>>> a == e
True