python解析邮件的时候编码问题

import sys

import base64

import os

import re

s1 = '"=?UTF-8?B?56mG6Zi/5rWpKOWnnOW8iyk=?=" <ahao.mah@ffff.com>, "=?UTF-8?B?56mG6Zi/5rWpKOWnnOW8iyk=?=" <ahao.mah@ffff.com>'

s2 = '"=?UTF-8?B?56mG6Zi/5rWpKOWnnOW8iyk=?=" <ahao.mah@ffff.com>'

s3 = "=?GBK?B?wfXWvrvUKLPLu8Yp?="

s4 = "hello"

def encoded_words_to_text(encoded_words):

    aa = ""

    bb = ""

    if "UTF-8" in encoded_words or "GBK" in encoded_words:

        list02 = encoded_words.split()

        for k in list02:

            if "UTF-8" in k or "GBK" in k:

                encoded_word_regex = r'=\?{1}(.+)\?{1}([B|Q])\?{1}(.+)\?{1}='

                k = k.strip("\"")

                charset, encoding, encoded_text = re.match(encoded_word_regex, k).groups()

                if encoding is 'B':

                    byte_string = base64.b64decode(encoded_text)

                elif encoding is 'Q':

                    byte_string = quopri.decodestring(encoded_text)

                aa = byte_string.decode(charset)

            else:

                bb = k

        cc = aa+' '+bb

        return cc

    else:

        return encoded_words

list01 = s4.split(",")

for i in list01:

    ff=encoded_words_to_text(i)

    print ff
巴特西

python解析邮件的时候编码问题

最新文章

热门文章
