import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.xml.sax.InputSource;

/**
 * @author shinsuke
 *
 */
public class HtmlExtractor extends AbstractXmlExtractor {
    protected static final Logger logger = LoggerFactory.getLogger(HtmlExtractor.class);

    protected Pattern metaCharsetPattern = Pattern.compile("<meta.*content\\s*=\\s*['\"].*;\\s*charset=([\\w\\d\\-_]*)['\"]\\s*/?>",

    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");
    }