python 字符编码练习

# \x00 - \xff 256个字符
>>> a = range(256)
>>> b = bytes(a)      # 不用参数encoding
>>> b
b'\x00\x01\x02 ... \xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff'
>>> b.decode('utf-8') # 报错
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 128: invalid start byte
>>> b.decode('unicode-escape') #正常
'\x00\x01\x02 ... \xf6÷\xf8ùú\xfbü\xfd\xfe\xff'

# 题外：上面几句等价于下面一句
>>> ''.join(list(map(chr, range(256))))
'\x00\x01\x02 ... \xf6÷\xf8ùú\xfbü\xfd\xfe\xff'

>>> a = 'abc'
>>> a
'abc'
>>> b = bytes(a, encoding='utf-8')  # 方式一：把 'abc' 变为字节数据
>>> b
b'abc'
>>> c = a.encode('utf-8')           # 方式二：把 'abc' 变为字节数据，与一等价
>>> c
b'abc'



# \x00 - \xff 256个字符，bytearray方式
>>> a = range(256)
>>> b = bytearray(a)
>>> b
bytearray(b'\x00\x01\x02 ... \xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff')
>>> b.decode('unicode-escape')
'\x00\x01\x02 ... \xf6÷\xf8ùú\xfbü\xfd\xfe\xff'



# 中文编码
>>> a = '中'
>>> a
'中'
>>> b = a.encode('gbk')
>>> b
b'\xd6\xd0'
>>> c = a.encode('utf-8')
>>> c
b'\xe4\xb8\xad'
>>> d = a.encode('unicode-escape')
>>> d
b'\\u4e2d'
>>> e = a.encode('cp936')
>>> e
b'\xd6\xd0'

# 中文解码
>>> a.decode('utf-8')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
AttributeError: 'str' object has no attribute 'decode'

>>> b.decode()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd6 in position 0: invalid continuation byte

>>> b.decode('utf-8')
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd6 in position 0: invalid continuation byte

>>> b.decode('gbk')
'中'
>>> b.decode('cp936') # gbk编码的可以cp936解码，反之不行。因为gbk是cp936的一个子集
'中'