/** Whether to extract link URLs as metadata. */
    protected boolean extractLinks = false;

    /** Markdown parser with extensions. */
    protected Parser parser;

    /** Text content renderer. */
    protected TextContentRenderer textRenderer;

    /**
     * Constructs a new MarkdownExtractor and initializes the parser.
     */
    public MarkdownExtractor() {
        super();
        initializeParser();
    }

        }
    }

    /**
     * Creates and configures a DOM parser with the specified features and properties.
     *
     * @return a configured DOM parser instance
     * @throws CrawlerSystemException if the parser configuration is invalid
     */
    protected DOMParser getDomParser() {
        try {
            final DOMParser parser = new DOMParser();
            // feature

        final DOMParser parser = getDomParser();
        try (final Reader reader = new StringReader(content)) {
            parser.parse(new InputSource(reader));
        } catch (final Exception e) {
            logger.warn("Failed to parse the content.", e);
            return new ExtractData(extractString(content));
        }

        final Document document = parser.getDocument();
        try {

			<artifactId>tika-parser-apple-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-audiovideo-module</artifactId>
			<version>${tika.version}</version>
		</dependency>
		<dependency>
			<groupId>org.apache.tika</groupId>
			<artifactId>tika-parser-cad-module</artifactId>

import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.CompositeParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.parser.PasswordProvider;
import org.apache.tika.parser.ocr.TesseractOCRConfig;
import org.apache.tika.parser.pdf.PDFParserConfig;
import org.apache.tika.sax.BodyContentHandler;

    @Resource
    protected CrawlerContainer crawlerContainer;

    /** Map of parser features to configure the DOM parser. */
    protected Map<String, String> featureMap = new HashMap<>();

    /** Map of parser properties to configure the DOM parser. */
    protected Map<String, String> propertyMap = new HashMap<>();

        }
    }

    /**
     * Gets the content of the response using the provided parser function.
     *
     * @param <T> the type of the parsed content.
     * @param parser the function to parse the content.
     * @return the parsed content.
     */
    public <T> T getContent(final Function<CurlResponse, T> parser) {
        return parser.apply(this);
    }

    /**
     * Gets the content of the response as a string.

    }

    /**
     * Disables external resources for the SAX parser to prevent XXE attacks.
     * @param parser the SAX parser to configure
     * @throws SAXNotRecognizedException if the parser doesn't recognize the feature
     * @throws SAXNotSupportedException if the parser doesn't support the feature
     */
    protected void disableExternalResources(final SAXParser parser) throws SAXNotRecognizedException, SAXNotSupportedException {

     */
    public boolean isUpdated() {
        return newInput != null;
    }

    /**
     * Checks if the item has been marked for deletion.
     *
     * @return true if the item is marked for deletion, false otherwise.
     */
    public boolean isDeleted() {
        return isUpdated() && newInput.length() == 0;
    }

    @Override
    public int hashCode() {

            spfactory.setFeature(Constants.FEATURE_EXTERNAL_PARAMETER_ENTITIES, false);
            // create a sax parser
            final SAXParser parser = spfactory.newSAXParser();
            try {
                parser.setProperty(XMLConstants.ACCESS_EXTERNAL_DTD, StringUtil.EMPTY);
                parser.setProperty(XMLConstants.ACCESS_EXTERNAL_SCHEMA, StringUtil.EMPTY);
            } catch (final Exception e) {