Extract Attachment which itself is of type MSG from an EMAIL in python

Question

I need to extract an msg type attachment from an email and save the MSG attachment to a location in python.

The script i wrote works for nearly all types of files other than outlook items

def parse_attachment(message_part):
    content_disposition = message_part.get("Content-Disposition", None)
    if content_disposition:
        dispositions = content_disposition.strip().split(";")
        if bool(content_disposition and (dispositions[0].lower() == "attachment" or dispositions[0].lower() == "inline")):

            file_data = message_part.get_payload(decode=True)
            debug(message_part)
            attachment = {}
            attachment['data'] = file_data
            attachment['content_type'] = message_part.get_content_type()
            attachment['size'] = len(file_data)

            for param in dispositions[1:]:
                name,value = param.split("=")
                name = name.lower().strip()
                value = value.strip().strip("\"")

                if name == "filename":
                    attachment['name'] = value
                elif name == "creation-date":
                    attachment['creation-date'] = value
                elif name == "modification-date":
                    attachment['modification-date'] = value
                elif name == "size":
                    attachment['size'] = value
            return attachment

    return None

Answer 1

We have to handle email attachments separately. However, if we use walk(), which is an all-purpose generator which can be used to iterate over all the parts and subparts of a message object tree, in depth-first traversal order, we end up parsing the attachment email as well.

So, we will have to use get_payload() for getting each individual part of the email. Here is how we can parse the email attachments -

def get_subject(msgobj) :
    subject = None
    if msgobj['Subject'] is not None:
        decodefrag = decode_header(msgobj['Subject'])
        subj_fragments = []
        for s , enc in decodefrag:
            if enc:
                s = unicode(s , enc).encode('utf8','replace')
            subj_fragments.append(s)
        subject = ''.join(subj_fragments)
        subject = re.sub('\n', '', subject)
    return subject

def get_msg_file_as_attachment(message_part):
    attachment = {}
    attachment['data'] = message_part.get_payload()[0].as_string(unixfrom=True)
    attachment['content_type'] = message_part.get_content_type()
    attachment['name'] = get_subject(message_part.get_payload()[0])
    attachment['name'] +=  '.eml'
    attachment['size'] = len(attachment['data'])

    return attachment

def parse_attachment(message_part):
    content_disposition = message_part.get("Content-Disposition", None)
    content_type = message_part.get_content_type()
    if content_disposition:
        dispositions = content_disposition.strip().split(";")
        if bool(content_disposition and (dispositions[0].lower() == "attachment" or dispositions[0].lower() == "inline")):
            if (content_type.lower().strip() == 'message/rfc822'):
                return get_msg_file_as_attachment(message_part)

            else:
                file_data = message_part.get_payload(decode=True)
                attachment = {}
                attachment['data'] = file_data
                attachment['content_type'] = content_type
                attachment['size'] = len(file_data)
                attachment['name'] = message_part.get_filename()
                return attachment

    return None