>>> import sys
>>> print("系统默认编码是：",sys.getdefaultencoding())
('\xe7\xb3\xbb\xe7\xbb\x9f\xe9\xbb\x98\xe8\xae\xa4\xe7\xbc\x96\xe7\xa0\x81\xe6\x98\xaf\xef\xbc\x9a', 'ascii')
>>> s = "你好"
>>> s_to_gbk = s.encode("gbk")
Traceback (most recent call last):File "<stdin>", line 1, in <module>
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe4 in position 0: ordinal not in range(128)
>>> s_to_gbk = s.decode().encode("gbk")
Traceback (most recent call last):File "<stdin>", line 1, in <module>
UnicodeDecodeError: 'ascii' codec can't decode byte 0xe4 in position 0: ordinal not in range(128)

>>> s = "你好"
>>> s_to_unicode = s.decode("utf-8")
>>> print(s_to_unicode)
你好
>>> s_to_gbk = s_to_unicode.encode("gbk")
>>> print(s_to_gbk)    #终端切换成GBK可以正常显示
▒▒▒
>>> gbk_to_utf8 = s_to_gbk.decode("gbk").encode("utf-8")
>>> print(gbk_to_utf8)
你好
>>>#python2.7 字符串 -> unicode -> decode(原编码) -> encode(目标编码

>>> import sys
>>> print("系统默认编码是：",sys.getdefaultencoding())
('\xe7\xb3\xbb\xe7\xbb\x9f\xe9\xbb\x98\xe8\xae\xa4\xe7\xbc\x96\xe7\xa0\x81\xe6\x98\xaf\xef\xbc\x9a', 'ascii')
>>>
>>> s = "你好"
>>> s_to_gb2312 = s.decode("utf-8").encode("gb2312")
>>> print(s_to_gb2312)  #终端编码为gb2312可以正常显示
▒▒▒
>>> s_to_gb2312_to_utf8 = s_to_gb2312.decode("gb2312").encode("utf-8")
>>> print(s_to_gb2312_to_utf8)
你好
>>> s_to_gb2312_to_utf8_to_gbk = s_to_gb2312_to_utf8.decode("utf-8").encode("gbk")
>>> print(s_to_gb2312_to_utf8_to_gbk) ##终端编码为gbk可以正常显示
▒▒▒
>>> s_to_gb2312_to_utf8_to_gbk_to_utf8 = s_to_gb2312_to_utf8_to_gbk.decode("gbk").encode("utf-8")>>> print(s_to_gb2312_to_utf8_to_gbk_to_utf8)你好>>> s_to_gb2312_to_utf8_to_gbk_to_utf8_to_gb2312 = s_to_gb2312_to_utf8_to_gbk_to_utf8.decode("utf-8").encode("gb2312")>>> print s_to_gb2312_to_utf8_to_gbk_to_utf8_to_gb2312▒▒▒

# /usr/bin/env python# -*- coding: gbk -*-# Author:jenvid.yangimport sysprint("系统默认编码是：", sys.getdefaultencoding())msg = '世界你好'# unicode程序编码，文件头部定义的是文件编码msg_unicode_to_gbk = msg.encode("gbk")# 已经是unicode，只能encode成其他编码print("unicode -> gbk: ",msg_unicode_to_gbk)

msg_unicode_to_utf8 = msg.encode("utf-8")print("unicode -> utf8: ",msg_unicode_to_utf8)

msg_unicode_to_gb2312 = msg.encode("gb2312")print("unicode -> gb2312: ",msg_unicode_to_gb2312)

msg_unicode_to_utf8_to_gbk = msg_unicode_to_utf8.decode("utf-8").encode("gbk")# 默认decode成utf-8，可以不写，显示指定print("unicode -> utf8 -> gbk: ",msg_unicode_to_utf8_to_gbk)

msg_unicode_to_utf8_to_gbk =msg_unicode_to_utf8.decode("utf-8").encode("gb2312")# 默认decode成utf-8，可以不写，但显示指定print("unicode -> utf8 -> gb2312: ",msg_unicode_to_utf8_to_gbk)# gbk兼容gb2312print(msg_unicode_to_utf8.decode("utf-8").encode("gb2312").decode("gb2312"))print(msg.encode("utf-8").decode("utf-8"))# decode的时候将字节码转换成字符串# 用str方法指定原编码也可以转换成字符串print(str(msg_unicode_to_utf8,encoding="utf-8"))print(str(msg_unicode_to_gb2312,encoding="gb2312"))

输出如下：

# 系统默认编码是： utf-8# unicode -> gbk:  b'\xca\xc0\xbd\xe7\xc4\xe3\xba\xc3'# unicode -> utf8:  b'\xe4\xb8\x96\xe7\x95\x8c\xe4\xbd\xa0\xe5\xa5\xbd'# unicode -> gb2312: b'\xca\xc0\xbd\xe7\xc4\xe3\xba\xc3'# unicode -> utf8 -> gbk: b'\xca\xc0\xbd\xe7\xc4\xe3\xba\xc3'# unicode -> utf8 -> gb2312: b'\xca\xc0\xbd\xe7\xc4\xe3\xba\xc3'# 世界你好# 世界你好# 世界你好# 世界你好