protected CrawlerContainer crawlerContainer;

    /**
     * The name of the component to be retrieved from the CrawlerContainer.
     */
    protected String componentName;

    /**
     * The listener that is called when a pooled object is destroyed.
     */
    protected OnDestroyListener<T> onDestroyListener;

    /**
     * Creates a new object instance from the crawler container.

 * It also uses an AtomicBoolean to track whether the thread is running.
 * </p>
 *
 * <p>
 * The expired method is called when a timeout occurs.
 * It interrupts the running thread up to a maximum number of times.
 * The stop method is called to stop the timeout target.
 * </p>
 */
public class AccessTimeoutTarget implements TimeoutTarget {

     */
    public interface RequestListener {

        /**
         * Called when a request starts.
         *
         * @param client the fault-tolerant client
         * @param request the request data
         */
        void onRequestStart(FaultTolerantClient client, RequestData request);

        /**
         * Called before each request attempt.
         *
         * @param client the fault-tolerant client

     */
    @Override
    public boolean markSupported() {
        return fileInputStream.markSupported();
    }

    /**
     * Repositions this stream to the position at the time the mark method was last called on this input stream.
     * This method delegates to {@link FileInputStream#reset()}.
     *
     * @throws IOException if an I/O error occurs.
     */
    @Override

     *  Evaluate XPath string to an XObject.
     *  XPath namespace prefixes are resolved from the namespaceNode.
     *  The implementation of this is a little slow, since it creates
     *  a number of objects each time it is called.  This could be optimized
     *  to keep the same objects around, but then thread-safety issues would arise.
     *
     *  @param contextNode The node to start searching from.
     *  @param expression A valid XPath string.

    @Override
    public int read(final byte[] b) throws IOException {
        return inputStream.read(b);
    }

    /**
     * Repositions this stream to the position at the time the mark method was last called.
     *
     * @throws IOException if this stream has not been marked or if the mark has been invalidated
     */
    @Override
    public synchronized void reset() throws IOException {
        inputStream.reset();

    protected static class ComponentHolder<T> {
        /**
         * The component instance being held.
         */
        protected T instance;

        /**
         * The destroyer function to be called when the component is destroyed.
         */
        protected Consumer<T> destroyer;

        /**
         * Creates a new ComponentHolder with the specified instance and destroyer.

## Overview

**Fess Crawler** is a powerful, flexible Java-based web crawling framework designed for enterprise-scale content extraction and processing. Built with a modular architecture, it supports multiple protocols (HTTP/HTTPS, File System, FTP, SMB, Cloud Storage) and provides extensive content extraction capabilities from various document formats.

     */
    public HtmlXpathExtractor() {
        super();
    }

    /**
     * Initializes the XPathAPI cache with a specified cache duration.
     * This method is called to set up the cache for XPathAPI instances.
     */
    @Resource
    public void init() {
        xpathAPICache =

     */
    public ApiExtractor() {
        // NOP
    }

    /**
     * Initializes the API extractor, setting up the HTTP client and configuration.
     * This method is called after construction to initialize the HTTP client with
     * configured timeouts, authentication, and request headers.
     */
    @PostConstruct
    public void init() {
        if (logger.isDebugEnabled()) {