Read and parse a web page

HttpUrlReadAndParseApp

package reader;

import bilgiturk.commons.ParserFactory;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
import org.htmlparser.Parser;
import org.htmlparser.filters.CssSelectorNodeFilter;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

import java.io.File;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;

/**
 * Hello world!
 */
public class ReadAndParseApp {
    public static void main(String[] args) throws IOException, ParserException {
        System.setProperty("sun.net.client.defaultReadTimeout", "10000");
        System.setProperty("sun.net.client.defaultConnectTimeout", "10000");

        URL url = new URL("http://www.javacodegeeks.com/2013/10/how-to-network-less-for-geeks.html");
        InputStream htmlInputStream = (InputStream) url.getContent();
        String html = new IOUtils().toString(htmlInputStream);

        Parser parser = ParserFactory.newParser();
        parser.setInputHTML(html);

        NodeList parsed = parser.parse(new CssSelectorNodeFilter("div[class='entry entry-content']"));

        FileUtils.writeStringToFile(new File("output.html"), parsed.toHtml(), "UTF-8");
    }
}