জাভা দিয়ে ওয়েবপেজ কোড এবং কনটেন্ট Read করার পদ্ধতি

package read.webpage;

import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.Scanner;
import java.util.logging.Level;
import java.util.logging.Logger;

/**
 *
 * @author Aditta Chakraborty
 */
public class ReadWebpage {

    public static void main(String[] args) throws IOException {
        
        try {
            URL url = new URL("https://www.google.com");
            //Retrieving the contents of the specified page
            Scanner sc = new Scanner(url.openStream());
            //Instantiating the StringBuffer class to hold the result
            StringBuilder sb = new StringBuilder();
            while(sc.hasNext()) {
                sb.append(sc.next());
                //System.out.println(sc.next());
            }
            //Retrieving the String from the String Buffer object
            String result = sb.toString();
            System.out.println(result);
            //Removing the HTML tags
            result = result.replaceAll("<[^>]*>", "");
            System.out.println("Contents of the web page: "+result);
        } catch (MalformedURLException ex) {
            Logger.getLogger(ReadWebpage.class.getName()).log(Level.SEVERE, null, ex);
        }
    }
    
}