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. */
    protected static final Logger logger = LogManager.getLogger(HtmlExtractor.class);

    /** Pattern for extracting charset from meta tags. */

    public HtmlExtractor htmlExtractor;

    @Override
    protected void setUp() throws Exception {
        super.setUp();
        StandardCrawlerContainer container = new StandardCrawlerContainer().singleton("htmlExtractor", HtmlExtractor.class);
        htmlExtractor = container.getComponent("htmlExtractor");
        htmlExtractor.addMetadata("title", "//TITLE");
    }