python - Descargando múltiples archivos adjuntos usando imaplib

email attachment

Question

¿Cómo puedo descargar varios archivos adjuntos de un solo correo usando imaplib ?

Digamos que tengo un correo electrónico y ese correo electrónico contiene 4 archivos adjuntos. ¿Cómo puedo descargar todos esos archivos adjuntos? El siguiente código solo descarga un archivo adjunto de un correo electrónico.

detach_dir = ''c:/downloads''
m = imaplib.IMAP4_SSL("imap.gmail.com")
m.login(''[email protected]'',''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

Para cualquier futuro viajero pitón. Aquí hay una clase que descarga cualquier archivo adjunto encontrado para un correo electrónico y lo guarda en una ubicación específica.

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'', ''[email protected]'')
        """
        return email.utils.parseaddr(email_address)

Answer 2

Reelaboré el código, dividiéndolo en funciones. Uso PEEK para no cambiar el estado de UNREAD de los mensajes de correo electrónico.

Estoy publicando mi opinión sobre el problema, similar a @John, pero solo uso funciones en lugar de clases:

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

Su código parece correcto, excepto por la return (¿quizás un error tipográfico?) Justo después de fp.close() :

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

Después de guardar el primer archivo adjunto, regresa de la función. Comente esa línea y vea si soluciona su problema.

Answer 4

* You can try following function to get mail attachment

def create_message_attachment(self,msg_str):
        count = 1
        body = ''''
        content_id = ''''
        for part in msg_str.walk():
            file_name_gl = None
            mptype = part.get_content_maintype()
            file_name_gl = part.get_filename()
            if mptype == "multipart":
                continue
            elif mptype == "text":
                if not file_name_gl: continue
            elif mptype == "image":
                content_id = part.get(''Content-ID'')
                if not file_name_gl:
                    file_name_gl = ''image_'' + str(count) + ''.'' + part.get_content_subtype()
                    count = count + 1

            body = part.get_payload(decode = True)
            if type(body) <> type(None) :
                body = body.strip()
                if body <> "":
                    body = base64.encodestring(body)