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");
    }

### Key Extractors

`TikaExtractor` (1000+ formats), `PdfExtractor`, `MsWordExtractor`, `MsExcelExtractor`, `MsPowerPointExtractor`, `ZipExtractor`, `HtmlExtractor`, etc.

**Registration**:
```java
extractorFactory.addExtractor("text/html", htmlExtractor, 2);  // Weight 2
extractorFactory.addExtractor("text/html", tikaExtractor, 1);  // Fallback
```

### Helpers

		class="org.codelibs.fess.crawler.extractor.impl.LhaExtractor" />
	<component name="textExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.TextExtractor" />
	<component name="htmlExtractor"
		class="org.codelibs.fess.crawler.extractor.impl.HtmlExtractor">
		<property name="featureMap">
			<component class="java.util.LinkedHashMap">
				<postConstruct name="put">
					<arg>"http://xml.org/sax/features/namespaces"</arg>