编码 decode & encode

Posted 2020-11-01 PAYNE1Z

 

 

import sys
 
# python3 中字符编码默认为 utf-8
s = \'你好\'
print(s)

# utf-8 转为 gbk (s 默认为 unicode 所以可以直接 encode 成 gbk)
s_to_gbk = s.encode(\'gbk\')
print(\'gbk\', s_to_gbk)
print(\'default\', s.encode())
print(\'bytes type\', type(s))
print(\'system default\', sys.getdefaultencoding())

# 将 gbk 再转为 utf-8 , 因为默认是 utf-8
# 所以需要先将 gbk encode 成 gbk 才能 encode 为 utf-8
gbk_to_utf8 = s_to_gbk.decode(\'gbk\').encode(\'utf-8\')
print(\'utf-8\', gbk_to_utf8)