邮件转为html格式,poplib获取邮件内容转化为Html格式

import poplib

import email

from email.parser import Parser

from email.header import decode_header

from email.utils import parseaddr

from bs4 import BeautifulSoup

def decode_str(s):

return 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):

headers = {}

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

value = msg.get(header, '')

if value:

if header == 'Date':

headers['date'] = value

if header == 'Subject':

subject = decode_str(value)

headers['subject'] = subject

else:

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

return headers

# indent用于缩进显示:

def get_email_cntent(message):

j = 0

content = ''

for part in message.walk():

j = j + 1

file_name = part.get_filename()

contentType = part.get_content_type()

if file_name: # 保存附件

pass

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

data = part.get_payload(decode=True)

charset = guess_charset(part)

if charset:

charset = charset.strip().split(';')[0]

# data = data.decode(charset)

content = data

return content

if __name__ == '__main__':

emailaddress = ''

password = ''

pop3_server = ''

server = poplib.POP3(pop3_server)

print(server.getwelcome())

server.user(emailaddress)

server.pass_(password)

messagesCount, messagesSize = server.stat()

print('邮件数量:', messagesCount)

print('占用空间:', messagesSize)

resp, mails, octets = server.list()

print('------ resp ------')

print(resp)

print('------ mails ------')

print(mails)

print('------ octets ------')

print(octets)

print("****************要第几篇就传几*******************************************************************")

resp, lines, octets = server.retr(423)

msg_content = "" ;

for le in lines:

msg_content = msg_content + str(le, encoding = "utf-8")

msg_content = msg_content + "\n"

msg = Parser().parsestr(msg_content)

msg_headers = get_email_headers(msg)

content = get_email_cntent(msg)

print('subject:', msg_headers['subject'])

print('from_address:', msg_headers['from'])

print('to_address:', msg_headers['to'])

print('date:', msg_headers['date'])

bs = BeautifulSoup(content, "lxml")

print(bs.prettify())

server.quit()