Python實(shí)現(xiàn)獲取郵箱內(nèi)容并解析的方法示例

# -*- coding: utf-8 -*-
from email.parser import Parser
from email.header import decode_header
from email.utils import parseaddr
import poplib
#輸入郵件地址, 口令和POP3服務(wù)器地址:
email = input('Email: ')
password = input('Password: ')
pop3_server = input('POP3 server: ')
def guess_charset(msg):
  charset = msg.get_charset()
  if charset is None:
    content_type = msg.get('Content-Type', '').lower()
    pos = content_type.find('charset=')
    if pos >= 0:
      charset = content_type[pos + 8:].strip()
  return charset
def decode_str(s):
  value, charset = decode_header(s)[0]
  if charset:
    value = value.decode(charset)
  return value
def print_info(msg, indent=0):
  if indent == 0:
    for header in ['From', 'To', 'Subject']:
      value = msg.get(header, '')
      if value:
        if header=='Subject':
          value = decode_str(value)
        else:
          hdr, addr = parseaddr(value)
          name = decode_str(hdr)
          value = u'%s <%s>' % (name, addr)
      print('%s%s: %s' % (' ' * indent, header, value))
  if (msg.is_multipart()):
    parts = msg.get_payload()
    for n, part in enumerate(parts):
      print('%spart %s' % (' ' * indent, n))
      print('%s--------------------' % (' ' * indent))
      print_info(part, indent + 1)
  else:
    content_type = msg.get_content_type()
    if content_type=='text/plain' or content_type=='text/html':
      content = msg.get_payload(decode=True)
      charset = guess_charset(msg)
      if charset:
        content = content.decode(charset)
      print('%sText: %s' % (' ' * indent, content + '...'))
    else:
      print('%sAttachment: %s' % (' ' * indent, content_type))
# 連接到POP3服務(wù)器:
server = poplib.POP3_SSL(pop3_server, 995)
# 可以打開或關(guān)閉調(diào)試信息:
server.set_debuglevel(1)
# 可選:打印POP3服務(wù)器的歡迎文字:
print(server.getwelcome().decode('utf-8'))
# 身份認(rèn)證:
server.user(email)
server.pass_(password)
# stat()返回郵件數(shù)量和占用空間:
print('Messages: %s. Size: %s' % server.stat())
# list()返回所有郵件的編號(hào):
resp, mails, octets = server.list()
# 可以查看返回的列表類似[b'1 82923', b'2 2184', ...]
print(mails)
# 獲取最新一封郵件, 注意索引號(hào)從1開始:
index = len(mails)
resp, lines, octets = server.retr(index)
# lines存儲(chǔ)了郵件的原始文本的每一行,
# 可以獲得整個(gè)郵件的原始文本:
msg_content = b'\r\n'.join(lines).decode('utf-8')
# 稍后解析出郵件:
msg = Parser().parsestr(msg_content)
print_info(msg)
# 可以根據(jù)郵件索引號(hào)直接從服務(wù)器刪除郵件:
# server.dele(index)
# 關(guān)閉連接:
server.quit()