/**
     * Constructs a new ExtractException with the specified message and cause.
     *
     * @param message the detail message. The detail message is saved for later retrieval by the {@link #getMessage()} method.
     * @param cause the cause (which is saved for later retrieval by the {@link #getCause()} method).
     *              (A {@code null} value is permitted, and indicates that the cause is nonexistent or unknown.)
     */

     * @param url URL
     * @return true if url is matched
     */
    boolean match(String url);

    /**
     * Add an url pattern as a target.
     *
     * @param urlPattern Regular expression that is crawled
     */
    void addInclude(String urlPattern);

    /**
     * Add an url pattern as a non-target.
     *
     * @param urlPattern Regular expression that is not crawled
     */

 * including its location, last modification date, change frequency, and priority.
 * It implements the {@link Sitemap} interface.
 * </p>
 *
 * <p>
 * The {@code SitemapUrl} class provides getter and setter methods for each of these properties,
 * as well as implementations for {@code equals()}, {@code hashCode()}, and {@code toString()} methods.
 * </p>
 *
 */
public class SitemapUrl implements Sitemap {

    /**
     * Constructs a new {@code CrawlerSystemException} with the specified detail message and cause.
     *
     * @param message the detail message (which is saved for later retrieval by the {@link #getMessage()} method).
     * @param cause the cause (which is saved for later retrieval by the {@link #getCause()} method).
     *              (A {@code null} value is permitted, and indicates that the cause is nonexistent or unknown.)
     */

 * It allows setting delays before processing, after processing, when no URLs are in the queue,
 * and when waiting for new URLs.
 * The delays are configurable via constructor parameters.
 *
 */
public class DefaultIntervalController extends AbstractIntervalController {

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

        sitemapsRule.addRule("url", Pattern.compile(".*sitemap.*"));
        assertTrue(sitemapsRule.match(responseData));
        InputStream is = responseData.getResponseBody();
        assertTrue(is instanceof InputStream);
        CloseableUtil.closeQuietly(responseData);
    }

    private void assertMatchFalse(ResponseData responseData) {
        sitemapsRule.addRule("url", Pattern.compile(".*sitemap.*"));

    /**
     * Constructs a new exception with the specified detail message and cause.
     *
     * @param message the detail message
     * @param cause the cause (which is saved for later retrieval by the {@link Throwable#getCause()} method)
     */
    public ExecutionTimeoutException(final String message, final Throwable cause) {
        super(message, cause);
    }

    /**

    /** Pattern for extracting charset from meta tags. */
    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",
            Pattern.MULTILINE | Pattern.CASE_INSENSITIVE);

    /**
     * Pattern for HTML tags.
     */
    protected Pattern htmlTagPattern = Pattern.compile("<[^>]+>");

    /** Map of parser features. */

        final RegexRule regexRule = new RegexRule();
        regexRule.defaultRule = true;
        regexRule.allRequired = true;
        regexRule.addRule("url", Pattern.compile("http:.*"));
        regexRule.addRule("mimeType", Pattern.compile("text/html"));

        assertTrue(regexRule.match(getTestData1()));
        assertTrue(regexRule.match(getTestData2()));
        assertTrue(regexRule.match(getTestData3()));

    }

    /**
     * Extracts the token value from the content using the given pattern.
     * @param tokenPattern The regex pattern.
     * @param content The content to search.
     * @return The extracted token value.
     */
    protected String getTokenValue(final String tokenPattern, final String content) {
        final Matcher matcher = Pattern.compile(tokenPattern).matcher(content);
        if (matcher.find()) {