Python--编码转换

# -*- coding:gbk -*-
# 即使设置文件编码为gbk，下方定义的字符串s1依旧为unicode

# 获取默认编码格式
import sys
print(sys.getdefaultencoding())
# >>> utf-8

# 编码转换
# --------------python 2----------------
# utf-8  -->   decode  -->  unicode
# unicode --> encode --> gbk

s = "你好"
# 无decode方法，由于python3默认unicode, utf-8为原本的字符集，传给decode识别
s_unicode = s.decode("utf-8")
# gbk为目标字符集，指定给encode进行转换
s_gbk = s_unicode.encode("gbk")

# 示例
s1 = "大家好"
s1_to_utf8 = s1.encode("utf-8")
print(s1_to_utf8) # >>> b'xe5xa4xa7xe5xaexb6xe5xa5xbd'
s1_to_gbk = s1_to_utf8.decode("utf-8").encode("gbk")
s1_to_gb2312 = s1_to_utf8.decode("utf-8").encode("gb2312")
s1_to_gb2312_chinese = s1_to_gb2312.decode("gb2312")  
# decode转换为unicode后可以输出中文，所以证明默认为unicode
print(s1_to_gb2312_chinese) # >>> 大家好
print(s1_to_gb2312) # >>> b'xb4xf3xbcxd2xbaxc3'
print(s1_to_gbk) # >>> b'xb4xf3xbcxd2xbaxc3'
print(s1) # >>> 大家好