In [8]: name = u‘张三‘
 
In [9]: name
Out[9]: u‘\u5f20\u4e09‘     #Unicode编码   表现形式
 
In [10]: print name
张三
 
In [11]: print name[0:1]
张
 
In [12]: name[0:1]
Out[12]: u‘\u5f20‘
 
In [13]:  len(name)
Out[13]: 2
 
In [15]: type(name)
Out[15]: unicode     #类型是一个unicode
 

In [37]: name = u‘张三‘
 
In [38]: b_name = name.encode(‘utf-8‘)     #编码为不同的存储形式，既可以编码为utf-8
 
In [39]: b_name
Out[39]: ‘\xe5\xbc\xa0\xe4\xb8\x89‘
 
In [47]: type(b_name)     #类型为str
Out[47]: str
 
In [40]: b_name2 = name.encode(‘utf-16‘)     #也可以编码为utf-16
 
In [41]: b_name2
Out[41]: ‘\xff\xfe _\tN‘
 
In [42]: b_name3 = name.encode(‘utf-32‘)     #还可以编码为utf-32
 
In [43]: b_name3
Out[43]: ‘\xff\xfe\x00\x00 _\x00\x00\tN\x00\x00‘
 
In [44]: j_name = b_name.decode(‘utf-8‘)     #把utf-8解码为Unicode
 
In [45]: j_name
Out[45]: u‘\u5f20\u4e09‘
 
In [46]: type(j_name)     #类型为Unicode
Out[46]: unicode
 

In [47]: name = u‘张三‘
 
In [50]: with open(‘/tmp/test‘, ‘w‘) as f:
    ...:     f.write(name)
    ...:
---------------------------------------------------------------------------
UnicodeEncodeError                        Traceback (most recent call last)
<ipython-input-4-0d87fa01de83> in <module>()
      1 with open(‘/tmp/test‘, ‘w‘) as f:
----> 2     f.write(name)
 
UnicodeEncodeError: ‘ascii‘ codec can‘t encode characters in position 0-1: ordinal not in range(128)
 
 

In [51]: with open(‘/tmp/test‘, ‘w‘) as f:
    ...:     f.write(name.encode(‘utf-8‘))     #编码为utf-8形式写入到文件里面
    ...:
 
 
In [52]: with open(‘/tmp/test‘, ‘r‘) as f:
    ...:     new_name=f.read()
    ...:
 
In [53]: new_name.decode(‘utf-8‘)     #把utf-8解码为Unicode
Out[53]: u‘\u5f20\u4e09‘
 

In [15]: name = u‘张三‘
 
In [16]: type(name)
Out[16]: unicode

In [55]: import codecs
 
In [56]: name = u‘张三‘
 
In [57]: with open(‘/tmp/test‘, ‘w‘, encoding=‘utf-8‘) as f:
    ...:     f.write(name)
    ...:
 
In [58]: with open(‘/tmp/test‘, ‘r‘, encoding=‘utf-8‘) as f:
    ...:     new_name=f.read()
    ...:
 
In [59]: new_name
Out[59]: u‘\u5f20\u4e09‘
 

>>> name = ‘张三‘
>>> name
‘张三‘
>>> with open(‘/tmp/test‘, ‘w‘, encoding=‘utf-8‘) as f:
... f.write(name)
...
 

#在Python3中，我们需要编写接受str或bytes，并总是返回str的方法：
def to_str(bytes_or_str):
  if isinstance(bytes_or_str, bytes):
    value = bytes_or_str.decode(‘utf-8‘)
  else:
    value = bytes_or_str
  return value # Instance of str


#另外，还需要编写接受str或bytes，并总是返回bytes的方法：
def to_bytes(bytes_or_str):
  if isinstance(bytes_or_str, str):
    value = bytes_or_str.encode(‘utf-8)
  else:
    value = bytes_or_str
  return value # Instance of bytes

#在Python2中，需要编写接受str或unicode，并总是返回unicode的方法：
#python2
def to_unicode(unicode_or_str):
  if isinstance(unicode_or_str, str):
    value = unicode_or_str.decode(‘utf-8‘)
  else:
    value = unicode_or_str
  return value # Instance of unicode


#另外，还需要编写接受str或unicode，并总是返回str的方法：
#Python2
def to_str(unicode_or_str):
  if isinstance(unicode_or_str, unicode):
    value = unicode_or_str.encode(‘utf-8‘)
  else:
    value = unicode_or_str
  reutrn vlaue # Instance of str