*/
    @Override
    public void close() {
        clientFactory.close();
    }

    /**
     * Adds an include filter for URLs.
     * Only URLs matching this regular expression will be crawled.
     * @param regexp The regular expression for the include filter.
     */
    public void addIncludeFilter(final String regexp) {
        if (StringUtil.isNotBlank(regexp)) {
            urlFilter.addInclude(regexp);

 * </p>
 * <p>
 * The encoding of the HTML document is automatically detected using a regular expression that matches the charset attribute in the meta tag.
 * </p>
 *
 */
public class HtmlXpathExtractor extends AbstractXmlExtractor {
    /**
     * Regular expression pattern to match the charset attribute in the meta tag of HTML documents.

            }
        }
        return null;
    }

    /**
     * Adds a directive to the robots.txt rules.
     * The user-agent pattern in the directive is converted to a regular expression pattern,
     * where '*' is replaced with '.*' for pattern matching, and stored case-insensitively.
     *
     * @param directive The directive to add to the robots.txt rules
     */

 *       specified in the HTML content.</li>
 *   <li><b>preloadSizeForCharset:</b> The number of bytes to read from the input
 *       stream to determine the character set encoding.</li>
 *   <li><b>invalidUrlPattern:</b> A regular expression pattern used to identify
 *       invalid URLs.</li>
 * </ul>
 *
 * <p>
 * <b>Usage:</b>
 * </p>
 * <p>
 * The {@code transform} method is the main entry point for transforming an HTML