使用imaplib下载多个附件

Question

我怎样才能用 imaplib 从一封邮件中下载多个附件呢？

假设我有一封邮件，这封邮件里有4个附件。我该怎么才能把这些附件都下载下来呢？下面的代码只下载了一封邮件中的一个附件。

detach_dir = 'c:/downloads'
m = imaplib.IMAP4_SSL("imap.gmail.com")
m.login('hello@gmail.com','3323434')
m.select("[Gmail]/All Mail")

resp, items = m.search(None, "(UNSEEN)")
items = items[0].split()

for emailid in items:
    resp, data = m.fetch(emailid, "(RFC822)") 
    email_body = data[0][1] 
    mail = email.message_from_string(email_body) 
    temp = m.store(emailid,'+FLAGS', '\\Seen')
    m.expunge()

    if mail.get_content_maintype() != 'multipart':
        continue

    print "["+mail["From"]+"] :" + mail["Subject"]

    for part in mail.walk():
        if part.get_content_maintype() == 'multipart':
            continue
        if part.get('Content-Disposition') is None:
            continue

        filename = part.get_filename()
        att_path = os.path.join(detach_dir, filename)

        if not os.path.isfile(att_path) :
            fp = open(att_path, 'wb')
            fp.write(part.get_payload(decode=True))
            fp.close()
            return HttpResponse('check folder')

Answer 1

你的代码看起来没什么问题，除了在 fp.close() 后面有个 return（可能是个打错的地方？）:

...
fp.write(part.get_payload(decode=True))
fp.close()
return HttpResponse('check folder')

在保存第一个附件后，它就从这个函数返回了。把那一行注释掉，看看这样是否能解决你的问题。

Answer 2

我重新整理了代码，把它分成了几个函数。我使用了 PEEK，这样就不会改变邮件的未读状态。

我在这里分享我对这个问题的看法，和 @John 的方法类似，不过我只用了函数，没有使用类：

import imaplib
import email

# Connect to an IMAP server
def connect(server, user, password):
    m = imaplib.IMAP4_SSL(server)
    m.login(user, password)
    m.select()
    return m

# Download all attachment files for a given email
def downloaAttachmentsInEmail(m, emailid, outputdir):
    resp, data = m.fetch(emailid, "(BODY.PEEK[])")
    email_body = data[0][1]
    mail = email.message_from_string(email_body)
    if mail.get_content_maintype() != 'multipart':
        return
    for part in mail.walk():
        if part.get_content_maintype() != 'multipart' and part.get('Content-Disposition') is not None:
            open(outputdir + '/' + part.get_filename(), 'wb').write(part.get_payload(decode=True))

# Download all the attachment files for all emails in the inbox.
def downloadAllAttachmentsInInbox(server, user, password, outputdir):
    m = connect(server, user, password)
    resp, items = m.search(None, "(ALL)")
    items = items[0].split()
    for emailid in items:
        downloaAttachmentsInEmail(m, emailid, outputdir)

Answer 3

给未来的Python学习者们。这里有一个类，它可以下载电子邮件中的任何附件，并将其保存到指定的位置。

import email
import imaplib
import os

class FetchEmail():

    connection = None
    error = None

    def __init__(self, mail_server, username, password):
        self.connection = imaplib.IMAP4_SSL(mail_server)
        self.connection.login(username, password)
        self.connection.select(readonly=False) # so we can mark mails as read

    def close_connection(self):
        """
        Close the connection to the IMAP server
        """
        self.connection.close()

    def save_attachment(self, msg, download_folder="/tmp"):
        """
        Given a message, save its attachments to the specified
        download folder (default is /tmp)

        return: file path to attachment
        """
        att_path = "No attachment found."
        for part in msg.walk():
            if part.get_content_maintype() == 'multipart':
                continue
            if part.get('Content-Disposition') is None:
                continue

            filename = part.get_filename()
            att_path = os.path.join(download_folder, filename)

            if not os.path.isfile(att_path):
                fp = open(att_path, 'wb')
                fp.write(part.get_payload(decode=True))
                fp.close()
        return att_path

    def fetch_unread_messages(self):
        """
        Retrieve unread messages
        """
        emails = []
        (result, messages) = self.connection.search(None, 'UnSeen')
        if result == "OK":
            for message in messages[0].split(' '):
                try: 
                    ret, data = self.connection.fetch(message,'(RFC822)')
                except:
                    print "No new emails to read."
                    self.close_connection()
                    exit()

                msg = email.message_from_bytes(data[0][1])
                if isinstance(msg, str) == False:
                    emails.append(msg)
                response, data = self.connection.store(message, '+FLAGS','\\Seen')

            return emails

        self.error = "Failed to retreive emails."
        return emails

    def parse_email_address(self, email_address):
        """
        Helper function to parse out the email address from the message

        return: tuple (name, address). Eg. ('John Doe', 'jdoe@example.com')
        """
        return email.utils.parseaddr(email_address)