本文介绍通过Python自带的email模块解析电子邮件的基本实现方法。
这里阿猪假设你已经通过pop、imap等方式获取到了一封邮件,或者有一个现成的eml文件。下边的代码着重演示解析邮件内容过程中的基本实现方法。
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83
| import imaplib from email.parser import Parser from email.header import decode_header import re import datetime imap_user = '用户名email地址' imap_object = imaplib.IMAP4_SSL(port="993",host="imap.xxx.com") imap_object.login(imap_user, '密码或授权码') imap_object.select('INBOX') typ, msg_ids = imap_object.search(None, 'ALL') ids = msg_ids[0] ret = ids.decode('utf-8') message_id_list = ret.split() int_mail_num = len(message_id_list) print('收件箱中共有%s封邮件'%int_mail_num) msg = msg_ids[0] msg_list = msg.split()
ids = msg_list[0] results, data = imap_object.fetch(ids, "(RFC822)") imap_object.close() str_source = data[0][1].decode('UTF-8')
msg_email = Parser().parsestr(str_source)
str_from = msg_email["from"]
str_from_name = re.search(r'(?<=")[\s\S]*?(?=")',str_from).group() str_from_address = re.search(r'(?<=<)[\s\S]*?(?=>)',str_from).group() value, charset = decode_header(str_from_name)[0] if charset: str_from_name = value.decode(charset) print(">>From:%s<%s>"%(str_from_name,str_from_address)) str_to = msg_email["to"] str_to_name = re.search(r'(?<=")[\s\S]*?(?=")',str_to).group() str_to_address = re.search(r'(?<=<)[\s\S]*?(?=>)',str_to).group() value, charset = decode_header(str_to_name)[0] if charset: str_to_name = value.decode(charset) print(">>To:%s<%s>"%(str_to_name,str_to_address)) str_date = msg_email["date"] str_date = str_date.replace('GMT','+0000') dtime_date = datetime.datetime.strptime(str_date, '%a, %d %b %Y %H:%M:%S %z') print('>>时间:%s'%dtime_date) str_subject = msg_email["subject"] value, charset = decode_header(str_subject)[0] if charset: str_subject = value.decode(charset) print('>>邮件主题:%s'%str_subject) def decode_mime(msg): if msg.is_multipart(): parts = msg.get_payload() for part in parts: decode_mime(part) else: str_content_type = msg.get_content_type() str_charset = msg.get_content_charset(failobj=None) if str_content_type in ('text/plain', 'text/html'): bytes_content = msg.get_payload(decode=True) str_content = bytes_content.decode(str_charset) print('>>邮件正文(%s):%s'%(str_content_type,str_content))
decode_mime(msg_email)
|
版权声明: 未经书面授权许可,任何个人和组织不得以任何形式转载、引用本站的任何内容。本站保留追究侵权者法律责任的权利。