def parse_attachment(part):
"""
Get attachments of an email
:param `Message` part: A `Message`
:rtype: list
:returns: The list of attachments
"""
attachment = {}
attachment['content_type'] = part.get_content_type()
if attachment['content_type'].lower() in ['message/rfc822', 'message/delivery-status']:
attachment['content'] = str(part)
else:
attachment['content'] = part.get_payload(decode=True)
filename = part.get_filename()
if not filename:
filename = hashlib.sha1(attachment['content']).hexdigest()
if attachment['content_type']:
extension = mimetypes.guess_extension(attachment['content_type'])
if extension:
filename += extension
attachment['filename'] = utils.decode_every_charset_in_the_world(filename)
return attachment
def get_received_from_headers(headers):
"""
Parse 'received from' from headers
:param `Message` headers: The SMTP headers of the email
:rtype: list
:returns: The list of received emails
"""
result = []
if headers.get('Received'):
for current in headers.get_all('Received'):
if re.search('^from', current):
# Only keep dns and ip once
current = utils.decode_every_charset_in_the_world(current)
final = current.splitlines()[0].split(";")[0].replace("from ", "").replace("localhost", "").replace("by", "")
result.append(final)
return result
def get_subject_from_headers(headers):
"""
Get the subject of an email
:param `Message` headers: The SMTP headers of the email
:rtype: str
:returns: The subject of the email
"""
subject = ''
subject_part = []
if 'Subject' in headers and headers['Subject'] is not None:
try:
decodefrag = decode_header(headers['Subject'])
except HeaderParseError:
return subject
for line, encoding in decodefrag:
enc = 'utf-8' if encoding is None or encoding == 'unknown' else encoding
subject_part.append(utils.decode_every_charset_in_the_world(line, enc))
subject = ''.join(subject_part)[:1023]
return subject
def get_body_and_attachments(self, raw):
"""
Get the body of the mail and retreive attachments
:param str raw: The raw email
:rtype: tuple
:returns: The decoded body and a list of attachments
"""
messages = self._parser.parsestr(raw)
attachments = []
body = ''
for message in messages.walk():
content_type = message.get_content_type().lower()
if message.is_multipart() and content_type != 'message/rfc822':
continue
content_disposition = message.get('Content-Disposition')
if content_disposition:
content_disposition = content_disposition.decode('utf-8').encode('utf-8')
if content_disposition:
disposition = content_disposition.decode('utf-8').strip().split(';')[0].lower()
if disposition == 'attachment':
attachments.append(parse_attachment(message))
continue
elif disposition == 'inline' and content_type not in ['text/html', 'text/plain']:
attachments.append(parse_attachment(message))
continue
content = message.get_payload(decode=True)
if not content:
content = message.as_string()
if content:
body += utils.decode_every_charset_in_the_world(content, message.get_content_charset())
return body, attachments
