In this example, you will see complete steps to extract content and metadata from the HTML file by using TIKA HtmlParser.

Sample File

Complete Example

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;

import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.html.HtmlParser;
import org.apache.tika.sax.BodyContentHandler;

import org.xml.sax.SAXException;

public class TikaHTMLParserExample {

	public static void main(final String[] args) throws IOException, SAXException, TikaException {

		// detecting the file type
		BodyContentHandler handler = new BodyContentHandler();
		Metadata metadata = new Metadata();
		FileInputStream inputstream = new FileInputStream(new File("C:\\Users\\Saurabh Gupta\\Desktop\\TIKA\\HTML-FILE.html"));
		ParseContext pcontext = new ParseContext();

		// Html parser to get content
		HtmlParser htmlparser = new HtmlParser();
		htmlparser.parse(inputstream, handler, metadata, pcontext);
		System.out.println("Contents of the HTML document:" + handler.toString());
		System.out.println("Metadata of the HTML document:");
		String[] metadataNames = metadata.names();

		for (String name : metadataNames) {
			System.out.println(name + ":   " + metadata.get(name));
		}
	}
}

Output

Contents of the HTML document:  First Name  Last Name   DOB
    Saurabh Gupta   10-Dec-2085
    Gaurav  Kumar   12-May-1986
    Rahul   Roi 12-Jun-2010
    Raghvendra  Rana    05-Jan-2095
    Tanaya  Jain    13-Mar-1985


Metadata of the HTML document:
Content-Encoding:   windows-1252
Content-Type:   text/html; charset=windows-1252