Function _parseBurpLog

lib/core/common.py:5317–5465

Parses Burp logs

(content)

                yield (url, method, None, cookie, tuple())

    def _parseBurpLog(content):
        """
        Parses Burp logs
        """

        if not re.search(BURP_REQUEST_REGEX, content, re.I | re.S):
            if re.search(BURP_XML_HISTORY_REGEX, content, re.I | re.S):
                reqResList = []
                for match in re.finditer(BURP_XML_HISTORY_REGEX, content, re.I | re.S):
                    port, request = match.groups()
                    try:
                        request = decodeBase64(request, binary=False)
                    except (binascii.Error, TypeError):
                        continue
                    _ = re.search(r"%s:.+" % re.escape(HTTP_HEADER.HOST), request)
                    if _:
                        host = _.group(0).strip()
                        if not re.search(r":\d+\Z", host) and int(port) != 80:
                            request = request.replace(host, "%s:%d" % (host, int(port)))
                    reqResList.append(request)
            else:
                reqResList = [content]
        else:
            reqResList = re.finditer(BURP_REQUEST_REGEX, content, re.I | re.S)

        for match in reqResList:
            request = match if isinstance(match, six.string_types) else match.group(1)
            request = re.sub(r"\A[^\w]+", "", request)
            schemePort = re.search(r"(http[\w]*)\:\/\/.*?\:([\d]+).+?={10,}", request, re.I | re.S)

            if schemePort:
                scheme = schemePort.group(1)
                port = schemePort.group(2)
                request = re.sub(r"\n=+\Z", "", request.split(schemePort.group(0))[-1].lstrip())
            else:
                scheme, port = None, None

            if "HTTP/" not in request:
                continue

            if re.search(r"^[\n]*%s[^?]*?\.(%s)\sHTTP\/" % (HTTPMETHOD.GET, "|".join(CRAWL_EXCLUDE_EXTENSIONS)), request, re.I | re.M):
                if not re.search(r"^[\n]*%s[^\n]*\*[^\n]*\sHTTP\/" % HTTPMETHOD.GET, request, re.I | re.M):
                    continue

            getPostReq = False
            forceBody = False
            url = None
            host = None
            method = None
            data = None
            cookie = None
            params = False
            newline = None
            lines = request.split('\n')
            headers = []

            for index in xrange(len(lines)):
                line = lines[index]