python自动获取邮件数据_详解python实现读取邮件数据并下载附件的实例

#!/usr/bin/python2.7

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

"""

@Author: MarkLiu

"""

import poplib

import email

from email.parser import Parser

from email.header import decode_header

from email.utils import parseaddr

def decode_str(s):

value, charset = decode_header(s)[0] if charset:

value = value.decode(charset)

return value

def guess_charset(msg):

# 先从msg对象获取编码:

charset = msg.get_charset()

if charset is None:

# 如果获取不到，再从Content-Type字段获取:

content_type = msg.get('Content-Type', '').lower()

pos = content_type.find('charset=')

if pos >= 0:

charset = content_type[pos + 8:].strip()

return charset

def get_email_headers(msg):

# 邮件的From, To, Subject存在于根对象上:

headers = {}

for header in ['From', 'To', 'Subject', 'Date']:

value = msg.get(header, '')

if value:

if header == 'Date':

headers['date'] = value

if header == 'Subject':

# 需要解码Subject字符串:

subject = decode_str(value)

headers['subject'] = subject

else:

# 需要解码Email地址:

hdr, addr = parseaddr(value)

name = decode_str(hdr)

value = u'%s ' % (name, addr)

if header == 'From':

from_address = value

headers['from'] = from_address

else:

to_address = value

headers['to'] = to_address

content_type = msg.get_content_type()

print 'head content_type: ', content_type

return headers

# indent用于缩进显示:

def get_email_cntent(message, base_save_path):

j = 0

content = ''

attachment_files = [] for part in message.walk():

j = j + 1

file_name = part.get_filename()

contentType = part.get_content_type()

# 保存附件

if file_name: # Attachment

# Decode filename

h = email.Header.Header(file_name)

dh = email.Header.decode_header(h)

filename = dh[0][0] if dh[0][1]: # 如果包含编码的格式，则按照该格式解码

filename = unicode(filename, dh[0][1])

filename = filename.encode("utf-8")

data = part.get_payload(decode=True)

att_file = open(base_save_path + filename, 'wb')

attachment_files.append(filename)

att_file.write(data)

att_file.close()

elif contentType == 'text/plain' or contentType == 'text/html':

# 保存正文

data = part.get_payload(decode=True)

charset = guess_charset(part)