使用python接收imap邮件

r囧r小猫 2022-02-28 04:58 446阅读 0赞

最近研究邮件透明加密技术，需要测试imap服务，然而邮件客户端不好用所以需要自己编写代码，这里使用python编写。这里关于邮件透明加密技术，推荐天御云安的隐密邮，部署简单，不影响用户使用习惯，非常好的一款产品。网址：[https://mail.tyyunan.com/][https_mail.tyyunan.com]

import getpass, imaplib
    import time
    import pickle
    import email,string,sys,os
    from email.header import Header
    from email.header import decode_header
    from time import strptime, strftime
    from email.parser import Parser
    import hashlib
    
    ISOTIMEFORMAT="%Y-%m-%d %X"
    #定义邮件服务器常量
    IMAPSever='192.168.61.4'
    IMAPPort='143'
    IMAPUser='laoww@163.com'
    IMAPPassword='123456'
    tmp_dir='E:\\python\\'
    def GetFileMd5(filename):
        
        try:
            if not os.path.isfile(filename):
                return None
            myhash = hashlib.md5()
            f = open(filename, 'rb')
            while True:
                b = f.read(8096)
                if not b: break
                myhash.update(b)
            f.close()
            return myhash.hexdigest()
        except :
            return None
    #def writelog(log):
    #    fn = tmp_dir + 'log.txt'
    #    f = open(fn, 'a+')
    #    f.write(log+'\n')
    #    f.close
    def writelog(log):
        f = open('E:\\log.txt', 'a+')
        f.write(log+'\n')
        f.close
    def test_log(log):
        fn = tmp_dir + 'test_log.txt'
        f = open(fn, 'a+')
        f.write(log)
        f.close    
    ##附件MD5映射表
    #attr_md5_dic = {'c:\\tmp1\imap\\1_python.eml':'db38f30bf46982b51998acf7878586ed',
    #                'c:\\tmp1\imap\\2_python.eml':'f6865b3e0e0d5592dc94c0db2c397c0c',
    #                'c:\\tmp1\\imap\\3_python.eml':'a51e1fca402febe65e7a097cea299a43',
    #                'c:\\tmp1\\imap\\4_python.eml':'2ecd56ec0dac8fd0742763be9c756a5f',
    #                'c:\\tmp1\\imap\\5_python.eml':'9218a63c8bce5b1ff57d02deb8ba03b5',
    #                'c:\\tmp1\\imap\\6_python.eml':'36e1ae8414a39f3af757a1b47d669191',
    #                'c:\\tmp1\\imap\\7_python.eml':'2f34d001116515b35e2edbb79e4c229c',
    #                'c:\\tmp1\\imap\\8_python.eml':'8c12c98b9062b2a1c16bedb21d554135',
    #                'c:\\tmp1\\imap\\9_python.eml':'0b8ffc79c11a0dfb2f75291dfd75f29b',
    #                'c:\\tmp1\\imap\\10_python.eml':'b5451f68d6cb9cec7403affd2b5157ed',
    #                'c:\\tmp1\\imap\\11_python.eml':'895c22a04d6d574bbf6cdd050b9e0162',
    #                'c:\\tmp1\\imap\\12_python.eml':'42bacecc8c6746a3878bfb0157e48440',
    #                'c:\\tmp1\\imap\\13_python.eml':'2f7847fb47c3f94add85dcf71eebb89b',
    #                'c:\\tmp1\\imap\\14_python.eml':'db3b78eae3146fb5b7c858849fb93084'
    #                }
    #附件MD5映射表
    attr_md5_dic = {'1.jpg':'7C6426E4F8CD8B12D6CDE3DFDB8F2E9F',
                    '1M-good.txt':'D1240F099E53AF249541AC95B7B0FA95',
                    '2.jpg':'B167F5EE9B7F12E615106D0DE5A194C6',
                    '3.jpg':'622E1A2410C21667F731FD2D5C67596F',
                    '4.pdf':'DCB7434FCA1034EBA641EBFEE23C7283',
                    '5.pdf':'5DBC1699C1C0CABE08E571654885693E',
                    '6.rar':'0031E302AEABD0262B0F38FA537DF0BE',
                    '7.docx':'3F471FC456F1917AE282022ECD6DDB5D',
                    '8.docx':'4684DFA7FE8B87B0181855AA095D9C9D',
                    '9.7z':'08C9CE615196E95475DA832E2A7C43AF',
                    '10.xlsx':'24895653E8D04D2F3E756964A44A274E',
                    '11.txt':'4973E43DB511BA94A4A4F96DC0AD161A',
                    '12.txt':'2F0670DA4398CFC7E04DC6D7F77F8411',
                    '13.txt':'D51BEB408B4829BA895B2A5F7AF10894',
                    '14.txt':'066F8F57FBC8F77698CDA4B72B45C129',
                    '15.txt':'14F4A15ABF92BF4866BE9FD8A4A00338',
                    '16.pdf':'451B25E4AD13B671192F4E6548C1B632',
                    '17.rar':'F63CEC86FF2877FAA6383C28C6F3B7EF',
                    '18.rar':'57555CC3B82EDD8734558372CBB50BC9',
                    '20180911.txt':'9B7C71319B104F5DD30545C1B1C711E4'
                    }                
    
    def save_file(fn, data, msdir="inbox"):
        filename = tmp_dir + fn + '_' + msdir + '_python.eml'
        f = open(filename, '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
        f.write(data)
        f.close()
        #
        fileMd5 = GetFileMd5(filename)
        ret_str = ''
        ret_str = 'FAIL'
        if fileMd5 is None:
            writelog("file md5 get fail    =>filename:%s"%filename)
        else:
            #filename 是bytes类型  需要解码 才能变为字符串
            if  filename not in attr_md5_dic:
                writelog("file not in attr_md5_dic  =>filename:%s"%filename)
            else:
                if fileMd5 in attr_md5_dic[ filename]:
                    ret_str = 'OK'
        #输出md5 list
        f = open('E:\\imap-client\\tmp\\python\\md5_list', 'a')  
        t=time.strftime( ISOTIMEFORMAT, time.localtime())   
        #f.write("Md5 of"+ filename +"is " + fileMd5+ "\r\n")
        f.write("%s Md5 of %s is %s result is %s\n"%(t, filename, fileMd5, ret_str))
        #md5content = t + " Md5 of " + filename + "is" + (fileMd5) 
        #f.write( md5content )
        f.close()
        return None
    #取信息编码
    def get_charset(message, default="ascii"):
        #Get the message charset
        return message.get_charset()
        return default
    #解析邮件
    def ParseMail(mail):
    
        try:
            textplain = ''
            texthtml = ''
            atta = {}
            fileMd5= ''
            
            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
                        name = par.get_filename()
                        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
                            #print("filename:" + filename)
                            h = email.header.Header(name)
                            dh = email.header.decode_header(h)
                            fname = dh[0][0]
                            #print(dh)
                            print("fname:" + fname.decode())
                            # 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' + fname.decode())
                                f = open('aaaa', 'wb')
                            f.write(data)
                            f.close()
                            
                            fileMd5 = GetFileMd5(fname)
                            os.remove(fname) #del attr
                            if fileMd5 is None:
                                writelog("file md5 get fail    =>fname:%s"%fname)
                                return (None, None, None)
                            else:
                                #fname 是bytes类型  需要解码 才能变为字符串
                                if  fname.decode() not in attr_md5_dic:
                                    writelog("file not in attr_md5_dic  =>fname:%s"%fname.decode())
                                    return (None, None, None)
                                #writelog("md5:%s   md5:%s"%(fileMd5.upper() ,attr_md5_dic[ fname.decode()]) )
                                if fileMd5.upper() not in attr_md5_dic[ fname.decode()]:
                                    return (None, None, None)
                            
                        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:
                    content_type = mail.get_content_type()
                    charset = get_charset(mail)
                    if content_type in ['text/plain']:
                        if charset == None:
                            textplain = mail.get_payload(decode=True)
                        else:
                            textplain = mail.get_payload(decode=True).decode(charset)
            
            return (textplain, texthtml, atta)
        except Exception as e:
            writelog("error parse mail=>"+str(e))
            
            return (None, None, None)    
    
    def imap_get_mail_body(IMAPSever,IMAPPort,IMAPUser,IMAPPassword,BaseNum,StepNum):
        #M = imaplib.IMAP4_SSL(IMAPSever, IMAPPort) 
        M = imaplib.IMAP4(IMAPSever, IMAPPort)
        M.login(IMAPUser, IMAPPassword)
        result, msg = M.select('inbox')
    
        #print('result %s msg is %s\n' %(result, msg))
    
        #typ, data = M.search(None, 'ALL')
    
        #print('search result is [%s]--type is [%s]\n' %(data,typ))
        #typ, maildata = M.fetch('13', '(RFC822)')
        #save_file(str(int('13')), maildata[0][1])
        #print('Message %s\n%s\n' %('1', maildata[0][1]))
        #exit(0)
        success_num = 0
        fail_num = 0
    
        #for num in data[0].split():
        for num in range(BaseNum,BaseNum+StepNum):
            #if( int(num) > 3 ):
            #    exit(0)
            print('Message [%s]\n' %(str(num)))
            typ, maildata = M.fetch(str(num), '(UID BODY[1])')
            #print(maildata)
            #save_file(str(int(num)), maildata[0][1])
            mail = Parser().parsestr(maildata[0][1].decode('utf-8'))
            TextContent,HTMLContent,MailAtta = ParseMail(mail)
            
            if MailAtta != None and TextContent != None and HTMLContent != None:
                success_num += 1
                
            else:
                fail_num += 1
                
            writelog('success:%d  fail:%d'% (success_num, fail_num) )    
            #print('Message [%s]\n[%s]\n' %(num, maildata[0][1]))
        #writelog('success:%d  fail:%d'% (success_num, fail_num) )
        t=time.strftime( ISOTIMEFORMAT, time.localtime()) 
        writelog('----------------imapClient.quit---------------------now time is[%s]'%t)    
        M.close()
        M.logout()
    
    
    BaseNum=1
    for num in range(1,30):
        imap_get_mail_body(IMAPSever,IMAPPort,IMAPUser,IMAPPassword,BaseNum,160000)
        BaseNum+=5000

[https_mail.tyyunan.com]: https://mail.tyyunan.com/