email_utils.py 文件源码

def _find_attachments_in_email(mesg, expand_attachment, atts):

    # MHTML detection
    if mesg.get_content_maintype() == "multipart" and mesg.get_content_subtype() == "related":
        for part in mesg.walk():
            if part.is_multipart():
                continue
            payload = part.get_payload(decode=True)
            if isinstance(payload, str) and payload.startswith('ActiveMime'):
                return

    for part in mesg.walk():
        content_type = part.get_content_type()
        if part.is_multipart():
            continue
        payload = part.get_payload(decode=True)

        if content_type.startswith('text/') and expand_attachment:
            normalized = payload.lstrip(" \t\r\n")
            if any(normalized.startswith(m) for m in EMAIL_MAGIC):
                new_mesg = email.message_from_string(normalized)
                _find_attachments_in_email(new_mesg, expand_attachment, atts)
                continue

        if content_type in SAFE_MEDIA_TYPE:
            continue

        filename = part.get_filename()
        if filename is None:
            ext = mimetypes.guess_extension(content_type) or ''
            filename = '<unknown>' + ext
        else:
            # Sanitize the header value
            filename = _decode_header(filename)
            filename = utils.get_filename_from_path(filename)
        tempfile_path = utils.store_temp_file(payload, filename)
        atts.append((tempfile_path, filename, content_type))