}

    /**
     * Gets the crawl delay value for the specified user agent from robots.txt.
     * The crawl delay specifies the time (in seconds) to wait between successive requests.
     *
     * @param userAgent The user agent string to match against robots.txt directives
     * @return The crawl delay value in seconds. Returns 0 if no matching directive is found
     *         or no crawl delay is specified for the matching directive.
     */

        return stripInvalidXMLCharacters(//
                value//
                        .replace("&", "&") //
                        .replace("<", "&lt;")//
                        .replace(">", "&gt;")//
                        .replace("\"", "&quot;")//
                        .replace("\'", "&apos;")//
        );
    }

    /**
     * Strips invalid XML characters from the input string.

    int NO_URL_IN_QUEUE = 4;

    /** Constant indicating that the crawler is waiting for new URLs. */
    int WAIT_NEW_URL = 8;

    /**
     * Introduces a delay based on the specified type.
     *
     * @param type the type of delay to be introduced
     */
    void delay(int type);

    /** Delay in milliseconds after processing a URL */
    protected long delayMillisAfterProcessing = 0L;

    /** Delay in milliseconds when no URL is in the queue */
    protected long delayMillisAtNoUrlInQueue = 500L;

    /** Delay in milliseconds before processing a URL */
    protected long delayMillisBeforeProcessing = 0L;

    /** Delay in milliseconds for waiting for new URLs */

 *
 * <p>
 * Subclasses are responsible for implementing the abstract methods to define the actual delay
 * mechanism for each of these stages.
 * </p>
 *
 * <p>
 * The class also provides a mechanism to ignore exceptions that may occur during the delay process.
 * If {@link #ignoreException} is set to true, any exceptions thrown during the delay will be caught
 * and ignored. Otherwise, they will be re-thrown as {@link CrawlerSystemException}.

     */
    protected String path;

    /**
     * A string to replace ?.
     */
    protected String questionStr = "_QUEST_";

    /**
     * A string to replace :.
     */
    protected String colonStr = "_CLN_";

    /**
     * A string to replace ;.
     */
    protected String semicolonStr = "_SCLN_";

    /**
     * A string to replace &.
     */
    protected String ampersandStr = "_AMP_";

 * The delayBeforeProcessing method is overridden to introduce a delay before processing a URL,
 * ensuring that requests to the same host are not made too frequently.
 * The delay is calculated based on the configured delayMillisBeforeProcessing parameter.
 * If the time since the last request to the host is less than the configured delay,
 * the thread waits until the delay has elapsed.
 * This class is thread-safe.
 */

    }

    public void test_doGet_dir() {
        final File file = ResourceUtil.getResourceAsFile("test");
        String path = file.getAbsolutePath();
        if (!path.startsWith("/")) {
            path = "/" + path.replace('\\', '/');
        }
        try {
            fsClient.doGet("file://" + path);
            fail();
        } catch (final ChildUrlsException e) {
            final Set<RequestData> urlSet = e.getChildUrlList();

        String input = content.replaceAll("[\\r\\n]", " ");
        if (ignoreCommentTag) {
            input = input.replaceAll("<!--[^>]+-->", "");
        } else {
            input = input.replace("<!--", "").replace("-->", "");
        }
        final Matcher matcher = getTagPattern().matcher(input);
        final StringBuffer sb = new StringBuffer();
        final Pattern attrPattern = Pattern.compile("\\s[^ ]+=\"([^\"]*)\"");

    protected static final Pattern ALLOW_RECORD = Pattern.compile("^allow:\\s*([^\\s]*)\\s*$", Pattern.CASE_INSENSITIVE);

    /** Pattern for parsing crawl-delay records. */
    protected static final Pattern CRAWL_DELAY_RECORD = Pattern.compile("^crawl-delay:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for Sitemap record.
     */