Downloading multiple attachments using imaplib

Question

How can I download multiple attachments from a single mail using imaplib?

Let's say I have an e-mail and that e-mail contains 4 attachments. How can I download all of those attachments? The code below only downloads a single attachment from an e-mail.

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')

Your reliance on the existence of an explicit `Content-Disposition:` header is wrong on multiple counts. Unfortunately, several of the answers here simply blindly inherit this flaw. Perhaps see https://stackoverflow.com/questions/48562935/what-are-the-parts-in-a-multipart-email/48563281#48563281 — tripleee, Sep 22 '20 at 11:21

John Paul Hayes · Answer 1 · 2018-09-07T16:18:22.767

For any future python travellers. Here is a class that downloads any attachment found for an email and saves it to a specific location.

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)

For Python 3 use `msg = email.message_from_bytes(data[0][1])` instead of `msg = email.message_from_string(data[0][1])`. Else `for part in msg.walk()` is not working as expected. — a.Dippel, Sep 04 '18 at 16:06
I'm wondering what is this search by 'UnSeen'? In my case this search returns 0 messages. — sequence, Feb 26 '19 at 01:23
where do we pass through the specific location we want to save the attachments to? — BrianBeing, May 15 '19 at 15:31
@BrianBeing you can pass this in via the download_folder parameter in the def save_attachment — John Paul Hayes, May 21 '19 at 12:18
I recommend you do it like below. It's more straightforward and works with octet-stream attachments. filename = part.get_filename() if filename: att_path = os.path.join(download_folder, filename) fp = open(att_path, 'wb') fp.write(part.get_payload(decode=True)) fp.close() — BenSabo, Nov 15 '19 at 20:29
My E-Mail server stores PDF attachments with Content-Disposition as None, recommend @BenSabo solution. — ROJI, Oct 13 '21 at 21:44

score 16 · Answer 2 · answered Nov 12 '15 at 17:01

I reworked the code, breaking it up into functions. I use PEEK so I don't change the UNREAD status of the email messages.

I'm posting my take on the problem, similar to @John, but I use only functions instead of classes:

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)

For `emailid`, look at how `downloadAllAttachmentsInInbox()` calls `downloaAttachmentsInEmail()`. For outputdir, it is the directory where the attachments are downloaded. — sashoalm, May 15 '19 at 06:45
ok. So I only need to fill in values for the variables: server, user, password, and outputdir? — BrianBeing, May 15 '19 at 14:52
This one really works. In my case, I had to change message_from_string to message_from_bytes and it worked perfectly. — Mujeeb Ishaque, Sep 12 '20 at 21:50
Hmm, it downloads dat-file that contains message itself, not attachements. — Okloks, Feb 25 '22 at 07:18

score 7 · Answer 3 · answered Jun 03 '11 at 12:28

You code appears okay except for the return (perhaps a typo?) right after the fp.close():

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

After saving the first attachment it returns from the function. Comment out that line and see if it fixes your issue.

Vladimir · Answer 4 · 2020-04-11T11:39:18.677

You may use imap_tools package: https://pypi.org/project/imap-tools/

from imap_tools import MailBox
with MailBox('imap.mail.com').login('test@mail.com', 'password', 'INBOX') as mailbox:
    for message in mailbox.fetch():
        for att in message.attachments:  # list: [Attachment objects]
            att.filename         # str: 'cat.jpg'
            att.content_type     # str: 'image/jpeg'
            att.payload          # bytes: b'\xff\xd8\xff\xe0\'

score 2 · Answer 5 · answered Jun 03 '11 at 12:28

* 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)

R.F. · Answer 6 · 2020-01-08T17:27:50.433

@sashoalm 's code worked for me with a minor change:

change mail = email.message_from_string(email_body) in downloaAttachmentsInEmail to mail = email.message_from_bytes(email_body)

I was getting an error when trying to read bytes (the attachment) as a string. Now it works perfectly for me.

Heres a full example of the code:

server = 'outlook.office365.com'
user = 'YOUR USERNAME'
password = 'YOUR PASSWORD'
outputdir = 'DIRECTORY THAT YOU WANT FILES DOWNLOADED TO'
subject = 'Data Exports' #subject line of the emails you want to download attachments from

def connect(server, user, password):
    m = imaplib.IMAP4_SSL(server)
    m.login(user, password)
    m.select()
    return m

def downloaAttachmentsInEmail(m, emailid, outputdir):
    resp, data = m.fetch(emailid, "(BODY.PEEK[])")
    email_body = data[0][1]
    mail = email.message_from_bytes(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 attachments from all emails with a specified subject line
def downloadAttachments(subject):
    m = connect(server, user, password)
    m.select("Inbox")
    typ, msgs = m.search(None, '(SUBJECT "' + subject + '")')
    msgs = msgs[0].split()
    for emailid in msgs:
        downloaAttachmentsInEmail(m, emailid, outputdir)

downloadAttachments(subject)

score 1 · Answer 7 · answered Feb 21 '21 at 10:33

import re

def get_valid_filename(s):
    s = str(s).strip().replace(' ', '_')
    return re.sub(r'(?u)[^-\w.]', '', s)

            fileName = get_valid_filename(part.get_filename())

Clean up the file name if it contains invalid characters. e.g: : on Windows.

Downloading multiple attachments using imaplib

7 Answers7

Linked