使用IMAP提取扭曲的電子郵件

Question

我想用扭曲的方式獲取gmail帳戶上的電子郵件，並且至少說這是一種痛苦，看着電子郵件是他們的一個清晰的解釋和結構（它似乎最好一起被黑客攻擊）。我試圖抓取附件，但附件並不在任何地方。

我使用示例IMAP客戶端從扭曲和修改它，我使用fetchAll（'1：'）來獲取電子郵件，然後獲取第一封電子郵件，但我無法找到電子郵件附件該電子郵件（我檢查了它在谷歌）。另外什麼是1：，我似乎無法找到任何實際解釋電子郵件的東西（好像沒有人理解它）

所以Stackoverflow，我錯過了什麼？

代碼

#!/usr/bin/env python 

# Copyright (c) Twisted Matrix Laboratories. 
# See LICENSE for details. 


""" 
    Simple IMAP4 client which displays the subjects of all messages in a 
    particular mailbox. 
    """ 

import sys 

from twisted.internet import protocol 
from twisted.internet import ssl 
from twisted.internet import defer 
from twisted.internet import stdio 
from twisted.mail import imap4 
from twisted.protocols import basic 
from twisted.python import util 
from twisted.python import log 



class TrivialPrompter(basic.LineReceiver): 
    from os import linesep as delimiter 

    promptDeferred = None 

    def prompt(self, msg): 
     assert self.promptDeferred is None 
     self.display(msg) 
     self.promptDeferred = defer.Deferred() 
     return self.promptDeferred 

    def display(self, msg): 
     self.transport.write(msg) 

    def lineReceived(self, line): 
     if self.promptDeferred is None: 
      return 
     d, self.promptDeferred = self.promptDeferred, None 
     d.callback(line) 



class SimpleIMAP4Client(imap4.IMAP4Client): 
    """ 
     A client with callbacks for greeting messages from an IMAP server. 
     """ 
    greetDeferred = None 

    def serverGreeting(self, caps): 
     self.serverCapabilities = caps 
     if self.greetDeferred is not None: 
      d, self.greetDeferred = self.greetDeferred, None 
      d.callback(self) 



class SimpleIMAP4ClientFactory(protocol.ClientFactory): 
    usedUp = False 

    protocol = SimpleIMAP4Client 


    def __init__(self, username, onConn): 
     self.ctx = ssl.ClientContextFactory() 

     self.username = username 
     self.onConn = onConn 


    def buildProtocol(self, addr): 
     """ 
      Initiate the protocol instance. Since we are building a simple IMAP 
      client, we don't bother checking what capabilities the server has. We 
      just add all the authenticators twisted.mail has. Note: Gmail no 
      longer uses any of the methods below, it's been using XOAUTH since 
      2010. 
      """ 
     assert not self.usedUp 
     self.usedUp = True 

     p = self.protocol(self.ctx) 
     p.factory = self 
     p.greetDeferred = self.onConn 

     p.registerAuthenticator(imap4.PLAINAuthenticator(self.username)) 
     p.registerAuthenticator(imap4.LOGINAuthenticator(self.username)) 
     p.registerAuthenticator(
           imap4.CramMD5ClientAuthenticator(self.username)) 

     return p 


    def clientConnectionFailed(self, connector, reason): 
     d, self.onConn = self.onConn, None 
     d.errback(reason) 



def cbServerGreeting(proto, username, password): 
    """ 
     Initial callback - invoked after the server sends us its greet message. 
     """ 
    # Hook up stdio 
    tp = TrivialPrompter() 
    stdio.StandardIO(tp) 

    # And make it easily accessible 
    proto.prompt = tp.prompt 
    proto.display = tp.display 

    # Try to authenticate securely 
    return proto.authenticate(password 
          ).addCallback(cbAuthentication, proto 
              ).addErrback(ebAuthentication, proto, username, password 
                 ) 


def ebConnection(reason): 
    """ 
     Fallback error-handler. If anything goes wrong, log it and quit. 
     """ 
    log.startLogging(sys.stdout) 
    log.err(reason) 
    return reason 


def cbAuthentication(result, proto): 
    """ 
     Callback after authentication has succeeded. 

     Lists a bunch of mailboxes. 
     """ 
    return proto.list("", "*" 
        ).addCallback(cbMailboxList, proto 
            ) 


def ebAuthentication(failure, proto, username, password): 
    """ 
     Errback invoked when authentication fails. 

     If it failed because no SASL mechanisms match, offer the user the choice 
     of logging in insecurely. 

     If you are trying to connect to your Gmail account, you will be here! 
     """ 
    failure.trap(imap4.NoSupportedAuthentication) 
    return proto.prompt(
         "No secure authentication available. Login insecurely? (y/N) " 
         ).addCallback(cbInsecureLogin, proto, username, password 
            ) 


def cbInsecureLogin(result, proto, username, password): 
    """ 
     Callback for "insecure-login" prompt. 
     """ 
    if result.lower() == "y": 
     # If they said yes, do it. 
     return proto.login(username, password 
          ).addCallback(cbAuthentication, proto 
             ) 
    return defer.fail(Exception("Login failed for security reasons.")) 


def cbMailboxList(result, proto): 
    """ 
     Callback invoked when a list of mailboxes has been retrieved. 
     """ 
    result = [e[2] for e in result] 
    s = '\n'.join(['%d. %s' % (n + 1, m) for (n, m) in zip(range(len(result)), result)]) 
    if not s: 
     return defer.fail(Exception("No mailboxes exist on server!")) 
    return proto.prompt(s + "\nWhich mailbox? [1] " 
         ).addCallback(cbPickMailbox, proto, result 
            ) 


def cbPickMailbox(result, proto, mboxes): 
    """ 
     When the user selects a mailbox, "examine" it. 
     """ 
    mbox = mboxes[int(result or '1') - 1] 
    return proto.examine(mbox 
         ).addCallback(cbExamineMbox, proto 
             ) 


def cbExamineMbox(result, proto): 
    """ 
     Callback invoked when examine command completes. 

     Retrieve the subject header of every message in the mailbox. 
     """ 
    # FETCH ALL HEADERS? WHERE IS A ONE FOR AN ATTACHMENT 
    return proto.fetchAll('1:*').addCallback(cbFetch, proto) 


def cbFetch(result, proto): 
    """ 
     Finally, display headers. 
     """ 
    if result: 
     keys = result.keys() 
     keys.sort() 
     k = keys[-1] 
     proto.display('%s %s' % (k, result[k])) 
    else: 
     print "Hey, an empty mailbox!" 

    return proto.logout() 


def cbClose(result): 
    """ 
     Close the connection when we finish everything. 
     """ 
    from twisted.internet import reactor 
    reactor.stop() 


def main(): 
    hostname = raw_input('IMAP4 Server Hostname: ') 
    port = raw_input('IMAP4 Server Port (the default is 143, 993 uses SSL): ') 
    username = raw_input('IMAP4 Username: ') 
    password = util.getPassword('IMAP4 Password: ') 

    onConn = defer.Deferred(
    ).addCallback(cbServerGreeting, username, password 
       ).addErrback(ebConnection 
           ).addBoth(cbClose) 

    factory = SimpleIMAP4ClientFactory(username, onConn) 

    from twisted.internet import reactor 
    if port == '993': 
     reactor.connectSSL(hostname, int(port), factory, ssl.ClientContextFactory()) 
    else: 
     if not port: 
      port = 143 
     reactor.connectTCP(hostname, int(port), factory) 
    reactor.run() 


if __name__ == '__main__': 
    main() 

Answer 1

首先，IMAP4是郵件處理一個（也許是不必要的）複雜的協議，並扭曲的客戶端實現的（必須的）複雜的全力支持該協議。爲了獲得更多的地方，你應該考慮花一些時間閱讀解釋協議的標準：rfc3501和twisted's api的相關部分。

也就是說，它看起來像你使用IMAP4Client.fetchAll()，矛盾的是，它獲取「信封」數據，有關郵件的標題和元數據。返回電子郵件正文的可比通話實際上是fetchFull()。