python 字符编码

# Author:Finyaci
import chardet
# Python3 中默认Unicode ，Unicode包含utf-8
import sys

print("sysdefaultencoding: ",sys.getdefaultencoding())
print("------------------------")


str1 = "埃塞克斯大风"


utf8_ec = str1.encode("utf-8")                          # unicode-->utf-8
gbk_ec = str1.encode("gbk")                             # unicode-->gbk
gbk_to_utf8 = gbk_ec.decode("gbk").encode("utf-8")      # gbk-->unicode-->utf-8
utf8_to_gbk = utf8_ec.decode("utf-8").encode("gbk")

print("utf8_ec: ",utf8_ec,chardet.detect(utf8_ec))
print("gbk_ec: ",gbk_ec,chardet.detect(gbk_ec))
print("------------------------")
print("gbk_to_utf8",gbk_to_utf8,chardet.detect(gbk_to_utf8))
print("utf8_to_gbk",utf8_to_gbk,chardet.detect(utf8_to_gbk))

#CON: xxx-->unicode  decode()
#     unicode-->xxx  encode()
#     所有不同字符集的转换都要经过Unicode