Python接收邮件并保存至MySQL

转自:http://www.360doc.com/content/14/0103/13/11789990_342303735.shtml

参考了一些网络上的资料，做了个简单程序，使用python接收邮件并保存到mysql中。

#-------------------------------------------------------------------------------
# Name:        接收邮件模块
# Purpose:
#
# Author:      garfield
#
# Created:     15-02-2011
# Copyright:   (c) garfield 2011
# Licence:     <your licence>
#-------------------------------------------------------------------------------
 #_*_encoding:utf-8_*_
####源代码用来接收邮件
import MySQLdb
import time
import poplib
import pickle
import email,string,sys,os
from email.Header import Header
from email.Header import decode_header
from time import strptime, strftime

ISOTIMEFORMAT="%Y-%m-%d %X"

#定义数据库常量
MySQL_Server="localhost"
MySQL_User="root"
MySQL_Password="****"
MySQL_Database="Python"

#定义邮件服务器常量
POP3Sever='pop3.sina.com'
POP3User='mailuser'
POP3Password='*****'

CurMailID=-1

#取信息编码
def get_charset(message, default="ascii"):
    #Get the message charset
    return message.get_charset()
    return default

def SaveMail(Sender,Receiver,Subject,SendDate,ReceiveDate,TextContent,HTMLContent,OriginalMailinfo):
    #save mail info to mysql
    Sender=MySQLdb.escape_string(Sender)
    Receiver=MySQLdb.escape_string(Receiver)
    Subject=MySQLdb.escape_string(Subject)
    TextContent=MySQLdb.escape_string(TextContent)
    HTMLContent=MySQLdb.escape_string(HTMLContent)
    OriginalMailinfo=MySQLdb.escape_string(OriginalMailinfo)
    conn = MySQLdb.connect(MySQL_Server,MySQL_User,MySQL_Password,MySQL_Database,port=3306,connect_timeout=10,compress=True,charset='utf8',use_unicode=True)
    cursor=conn.cursor()
    vsql="insert into mail(Sender,Receiver,Subject,SendDate,ReceiveDate,TextContent,HTMLContent,OriginalMailinfo) values('%s','%s','%s','%s','%s','%s','%s','%s')" % (Sender,Receiver,Subject,SendDate,ReceiveDate,TextContent,HTMLContent,OriginalMailinfo) ;
    vsql = vsql.encode('utf8')
    cursor.execute(vsql)#一条SQL语句

    vsql = "SELECT max(id) from mail"
    cursor.execute(vsql)
    CurMailID=cursor.fetchone()[0]

    conn.commit()
    cursor.close()
    conn.close()

def SaveMailAtta(vMailID,vFileName,Content,IsInline):
    vFileName=MySQLdb.escape_string(vFileName)
    Content=MySQLdb.escape_string(Content)
    conn = MySQLdb.connect(MySQL_Server,MySQL_User,MySQL_Password,MySQL_Database,port=3306,connect_timeout=10,compress=True,charset='utf8',use_unicode=True)
    cursor=conn.cursor()
    vsql="insert into mailatta(mailid,filename,content,isinline) values('%s','%s','%s','%s')" % (vMailID,vFileName,Content,IsInline) ;
    vsql = vsql.encode('utf8')
    cursor.execute(vsql)#一条SQL语句

    conn.commit()
    cursor.close()
    conn.close()

#解析邮件
def ParseMail(mail):
  textplain=''
  texthtml=''
  atta={}
  if mail.is_multipart():
      for par in mail.walk():
        if not par.is_multipart(): # 这里要判断是否是multipart，是的话，里面的数据是无用的，至于为什么可以了解mime相关知识。
            name = par.get_param("name") #如果是附件，这里就会取出附件的文件名

            if name:
                #有附件
                # 下面的三行代码只是为了解码象=?gbk?Q?=CF=E0=C6=AC.rar?=这样的文件名
                h = email.Header.Header(name)
                dh = email.Header.decode_header(h)
                fname = dh[0][0]

                #print '有附件'+fname
                data = par.get_payload(decode=True) #　解码出附件数据，然后存储到文件中
                atta[fname]=data
                """
                try:
                    f = open(fname, 'wb') #注意一定要用wb来打开文件，因为附件一般都是二进制文件
                except:
                    print '附件名有非法字符，自动换一个'
                    f = open('aaaa', 'wb')
                f.write(data)
                f.close()
                """
            else:
                #不是附件，是文本内容
                content_type=par.get_content_type()
                charset = get_charset(par)
                if content_type in ['text/plain']:
                    if charset==None:
                        textplain=par.get_payload(decode=True)
                    else:
                        textplain=par.get_payload(decode=True).decode(charset)
                if content_type in ['text/html']:
                    if charset==None:
                        texthtml=par.get_payload(decode=True)
                    else:
                        texthtml=par.get_payload(decode=True).decode(charset)
  else:
    type=mail.get_content_charset()
    if type==None:
        textplain=mail.get_payload()
    else:
        try:
            textplain=unicode(mail.get_payload('base64'),type)
        except UnicodeDecodeError:
            textplain='Error'

  return (textplain,texthtml,atta)

def main():
    t=time.strftime( ISOTIMEFORMAT, time.localtime())

    popClient=poplib.POP3(POP3Sever)
    popClient.set_debuglevel(1)
    popClient.user(POP3User)
    popClient.pass_(POP3Password)

    numMsgs,mboxSize=popClient.stat()

    for id in range (numMsgs):
      hdr,message,octet=popClient.retr(id+1)
      mail=email.message_from_string(string.join(message, '\n'))
      subject=mail.get("subject")
      h = email.Header.Header(subject)
      dh = email.Header.decode_header(h)
      subject = dh[0][0]

      FromAddr=email.utils.parseaddr(mail['from'])[1]
      ToAddr=email.utils.parseaddr(mail['To'])[1]
      mdate=mail.get('date')  #'Wed, 16 Feb 2011 14:34:44 +0800'
      mdate=mdate[0:len(mdate)-6]
      #:取邮件中的时间进行处理
      md= mktime(strptime(mdate,"%a, %d %b %Y %H:%M:%S"))
      MailDate=time.strftime(ISOTIMEFORMAT,time.localtime(md))
      originalmailinfo=mail.as_string()
      TextContent,HTMLContent,MailAtta=ParseMail(mail)
      #保存邮件
      SaveMail(FromAddr,ToAddr,subject,MailDate,MailDate,TextContent,HTMLContent,originalmailinfo)
      #保存邮件附件
      #for fk in MailAtta.keys():
      #  SaveMailAtta(CurMailID,fk,MailAtta[fk],False)
    popClient.quit()

if __name__=='__main__':
    main()

但附件因为是二进制文件，所以保存到数据库中时需要序列化或进行其他处理，所以以上程序中的附件还不能这么简单地进行保存，需要进一步修改。

MySQL数据库脚本：

--
-- 表的结构 `mail`
--

CREATE TABLE IF NOT EXISTS `mail` (
  `ID` int(10) NOT NULL auto_increment,
  `Sender` text,
  `Receiver` text,
  `SendDate` datetime default NULL,
  `ReceiveDate` datetime default NULL,
  `Subject` varchar(500) default NULL,
  `TextContent` text,
  `HTMLContent` text,
  `OriginalMailInfo` text,
  PRIMARY KEY  (`ID`)
) ENGINE=MyISAM  DEFAULT CHARSET=utf8 AUTO_INCREMENT=546 ;

--

--
-- 表的结构 `mailatta`
--

CREATE TABLE IF NOT EXISTS `mailatta` (
  `ID` int(11) NOT NULL auto_increment,
  `MailID` int(11) NOT NULL,
  `filename` varchar(200) NOT NULL,
  `isinline` tinyint(1) NOT NULL,
  `conent` blob NOT NULL,
  PRIMARY KEY  (`ID`)
) ENGINE=MyISAM DEFAULT CHARSET=utf8 AUTO_INCREMENT=1 ;