编码变换

# utf-8与gbk互相转化需要通过Unicode作为中介 s="我爱北京天安门" # 默认编码为Unicode print(s.encode("gbk")) # Unicode可直接转化为gbk

b’\xce\xd2\xb0\xae\xb1\xb1\xbe\xa9\xcc\xec\xb0\xb2\xc3\xc5’

print(s.encode("utf-8")) # Unicode可直接转化为utf-8

b’\xe6\x88\x91\xe7\x88\xb1\xe5\x8c\x97\xe4\xba\xac\xe5\xa4\xa9\xe5\xae\x89\xe9\x97\xa8’

print(s.encode("utf-8").decode("utf-8").encode("gb2312")) # 此时s.encode("utf-8")即转为utf-8了，然后转为gb2312，则需要先告诉Unicode你原先的编码是什么，即s.encode("utf-8").decode("utf-8"),再对其进行编码为gb2312，即最终为s.encode("utf-8").decode("utf-8").encode("gb2312")

b’\xce\xd2\xb0\xae\xb1\xb1\xbe\xa9\xcc\xec\xb0\xb2\xc3\xc5’