python eml解析_提取邮件（eml格式）保存为html-python | 学步园

# -*- coding: utf-8 -*-

__author__ = 'fremcode@gmail.com'

import os

import sys

import email

import errno

import mimetypes

PATH = os.path.abspath(os.path.dirname(sys.argv[0]))

ITEM_PATH = PATH + "\item"

PATH_DATA = os.path.abspath(os.path.dirname(sys.argv[0]))+"\data"

def item(eml_file,eml_name):

fp = open(eml_file)

html_name = eml_name.split('.')

html = html_name[0]+html_name[1]

msg = email.message_from_file(fp)

fp.close()

counter = 1

for part in msg.walk():

if part.get_content_maintype() == 'multipart':

continue

filename = part.get_filename()

#print filename

if not filename:

ext = mimetypes.guess_extension(part.get_content_type())

if not ext:

ext = '.bin'

filename = html+'part-%03d%s' % (counter, ext)

counter += 1

try:

fp = open(os.path.join(ITEM_PATH, filename), 'wb')

fp.write(part.get_payload(decode=True))

fp.close()

except IOError:

pass

except TypeError:

pass

def main():

for root,dirs,files in os.walk(PATH_DATA):

for _dir in dirs:

if os.path.isdir("item"):

pass

else:

os.mkdir("_dir\html")

for _file in files:

eml_file = os.path.join(root, _file)

item(eml_file, _file)

if __name__ == '__main__':

main()