import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

import com.google.common.cache.CacheBuilder;
import com.google.common.cache.CacheLoader;
import com.google.common.cache.LoadingCache;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.util.XPathAPI;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * Extracts text content from HTML documents.
 */
public class HtmlExtractor extends AbstractXmlExtractor {
    /** Logger for this class. */

import org.codelibs.fess.Constants;
import org.codelibs.fess.helper.PluginHelper;
import org.codelibs.fess.util.ComponentUtil;
import org.codelibs.fess.util.ResourceUtil;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

/**
 * Factory class responsible for managing and providing access to data store instances.

 * underlying DOM parser, as well as defining rules for extracting child URLs
 * from specific HTML tags and attributes.
 * </p>
 *
 * <p>
 * <b>Configuration:</b>
 * </p>
 * <ul>
 *   <li><b>featureMap:</b> A map of features to be set on the DOM parser.</li>
 *   <li><b>propertyMap:</b> A map of properties to be set on the DOM parser.</li>

    public PrunedTag(final String tag) {
        this.tag = tag;
    }

    /**
     * Checks if this pruned tag configuration matches the given DOM node.
     * The matching is based on tag name, and optionally ID, CSS class, or custom attributes.
     *
     * @param node the DOM node to check against this pruned tag configuration
     * @return true if the node matches this pruned tag configuration, false otherwise
     */

import org.codelibs.fess.util.ComponentUtil;
import org.codelibs.fess.util.PrunedTag;
import org.codelibs.nekohtml.parsers.DOMParser;
import org.w3c.dom.Document;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;

import jakarta.annotation.PostConstruct;

/**

import org.codelibs.fess.util.ComponentUtil;
import org.codelibs.fess.util.ResourceUtil;
import org.lastaflute.di.exception.IORuntimeException;
import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;

import com.fasterxml.jackson.databind.ObjectMapper;
import com.fasterxml.jackson.dataformat.yaml.YAMLMapper;