コード例 #1
0
def get_raw_body_text(
    msg: email.message.Message
) -> typing.List[typing.Tuple[typing.Any, typing.Any, typing.Any]]:
    """This method recursively retrieves all e-mail body parts and returns them as a list.

    Args:
        msg (email.message.Message): The actual e-mail message or sub-message.

    Returns:
        list: Returns a list of sets which are in the form of "set(encoding, raw_body_string, message field headers)"
    """
    raw_body = [
    ]  # type: typing.List[typing.Tuple[typing.Any, typing.Any,typing.Any]]

    if msg.is_multipart():
        for part in msg.get_payload():  # type: ignore
            raw_body.extend(get_raw_body_text(part))  # type: ignore
    else:
        # Treat text document attachments as belonging to the body of the mail.
        # Attachments with a file-extension of .htm/.html are implicitely treated
        # as text as well in order not to escape later checks (e.g. URL scan).

        try:
            filename = msg.get_filename('').lower()
        except (binascii.Error, AssertionError):
            logger.exception(
                'Exception occured while trying to parse the content-disposition header. Collected data will not be complete.'
            )
            filename = ''

        if ('content-disposition' not in msg and msg.get_content_maintype() == 'text') \
            or (filename.endswith('.html') or filename.endswith('.htm')):
            encoding = msg.get('content-transfer-encoding', '').lower()

            charset = msg.get_content_charset()
            if charset is None:
                raw_body_str = msg.get_payload(decode=True)
                raw_body_str = eml_parser.decode.decode_string(
                    raw_body_str, None)
            else:
                try:
                    raw_body_str = msg.get_payload(decode=True).decode(
                        charset, 'ignore')
                except Exception:
                    logger.debug(
                        'An exception occured while decoding the payload!',
                        exc_info=True)
                    raw_body_str = msg.get_payload(decode=True).decode(
                        'ascii', 'ignore')

            # In case we hit bug 27257, try to downgrade the used policy
            try:
                raw_body.append((encoding, raw_body_str, msg.items()))
            except AttributeError:
                former_policy = msg.policy
                msg.policy = email.policy.compat32
                raw_body.append((encoding, raw_body_str, msg.items()))
                msg.policy = former_policy

    return raw_body
コード例 #2
0
ファイル: eml_parser.py プロジェクト: sim0nx/eml_parser
def get_raw_body_text(msg: email.message.Message) -> typing.List[typing.Tuple[typing.Any, typing.Any, typing.Any]]:
    """This method recursively retrieves all e-mail body parts and returns them as a list.

    Args:
        msg (email.message.Message): The actual e-mail message or sub-message.

    Returns:
        list: Returns a list of sets which are in the form of "set(encoding, raw_body_string, message field headers)"
    """
    raw_body = []  # type: typing.List[typing.Tuple[typing.Any, typing.Any,typing.Any]]

    if msg.is_multipart():
        for part in msg.get_payload():  # type: ignore
            raw_body.extend(get_raw_body_text(part))  # type: ignore
    else:
        # Treat text document attachments as belonging to the body of the mail.
        # Attachments with a file-extension of .htm/.html are implicitely treated
        # as text as well in order not to escape later checks (e.g. URL scan).

        try:
            filename = msg.get_filename('').lower()
        except (binascii.Error, AssertionError):
            logger.exception(
                'Exception occured while trying to parse the content-disposition header. Collected data will not be complete.')
            filename = ''

        if ('content-disposition' not in msg and msg.get_content_maintype() == 'text') or (
                filename.endswith('.html') or filename.endswith('.htm')):
            encoding = msg.get('content-transfer-encoding', '').lower()

            charset = msg.get_content_charset()
            if charset is None:
                raw_body_str = msg.get_payload(decode=True)
                raw_body_str = eml_parser.decode.decode_string(raw_body_str, None)
            else:
                try:
                    raw_body_str = msg.get_payload(decode=True).decode(charset, 'ignore')
                except Exception:
                    logger.debug('An exception occured while decoding the payload!', exc_info=True)
                    raw_body_str = msg.get_payload(decode=True).decode('ascii', 'ignore')

            # In case we hit bug 27257, try to downgrade the used policy
            try:
                raw_body.append((encoding, raw_body_str, msg.items()))
            except AttributeError:
                former_policy = msg.policy
                msg.policy = email.policy.compat32
                raw_body.append((encoding, raw_body_str, msg.items()))
                msg.policy = former_policy

    return raw_body
コード例 #3
0
    def decode_body(message: email.message.Message):
        # If the message comes in multiple portions (i.e. there are attachments)
        if message.is_multipart():
            for part in message.get_payload():
                # Throw away attachments
                if part.get_filename():
                    continue

                # Return an html object or plaintext
                charset = part.get_content_charset()
                if part.get_content_type() == 'text/plain':
                    return part.get_payload(
                        decode=True).decode(charset).strip()
                if part.get_content_type() == 'text/html':
                    return html(part.get_payload(decode=True).decode(charset))
                # Note that we can just return because even though it's multipart, the only usual suspects for the multiple parts are extra attachments, which we're avoiding.
        else:
            return message.get_payload(decode=True).decode(
                message.get_content_charset()).strip()