* It uses XPath expressions to extract text content from HTML documents.
 * <p>
 * This class provides methods to configure the XPath expressions, parser features, and properties.
 * It also includes caching mechanism for XPathAPI instances to improve performance.
 * </p>
 * <p>
 * The extracted text is obtained from the nodes selected by the {@code targetNodePath} XPath expression.

    @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);
        }

    private static final Pattern SPACE_PATTERN = Pattern.compile("\\s+", Pattern.MULTILINE);

    /**
     * A map of field rules, where the key is the field name and the value is the XPath expression.
     */
    protected Map<String, String> fieldRuleMap = new LinkedHashMap<>();

    /** Flag to enable or disable trimming of whitespace characters. */
    protected boolean trimSpaceEnabled = true;

    }

    /**
     * Retrieves a list of XPath nodes from the document.
     *
     * @param doc The XML document.
     * @param xpath The XPath expression.
     * @return A list of XPath nodes.
     * @throws XPathExpressionException if an XPath expression error occurs.
     */
    protected XPathNodes getNodeList(final Document doc, final String xpath) throws XPathExpressionException {

 *   <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

            }
        }
        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
     */