extract web content html : java

/**
* redcrow
* na5cent.blogspot.com 
* 04/01/2013
*/
package com.blogspot.na5cent.jsflearning;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 *
 * @author Redcrow
 */
public class HTMLParser {

    public static final String TITLE_PATTERN = "<title>(.*?)</title>";
    public static final String YOUTUBE_SCREEN_SHORT_PATTERN = "<link itemprop=\"thumbnailUrl\" href=\"(.*?)\">";
    public static final String IMAGE_PATTERN = "<img[^>]+src\\s*=\\s*['\"]([^'\"]+)['\"][^>]*>";
    public static final String WEBCONTENT_PATTERN = "<p.*?>(.*?)</p>";
    public static final String URL_PATTERN = "^(https?|ftp|file|//)(://)?[-a-zA-Z0-9+&@#/%?=~_|!:,.;]*[-a-zA-Z0-9+&@#/%=~_|]";
    private String html = "";
    private String host;
    private String protocol;

    public HTMLParser(String urlText) throws MalformedURLException, IOException {
        URL url = new URL(urlText);
        InputStream inputStream = url.openStream();
        BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8"));
        StringBuilder builder = new StringBuilder();
        String line;
        while ((line = reader.readLine()) != null) {
            builder.append(line);
        }
        html = builder.toString();
        host = url.getHost();
        protocol = url.getProtocol();
    }

    public List<String> get(String pattern, int numberOfResult) {
        List<String> result = new ArrayList<String>();
        Pattern patternCompile = Pattern.compile(pattern);
        Matcher matcher = patternCompile.matcher(html);
        int count = 0;
        while (matcher.find() && (count++ < numberOfResult)) {
            String text = matcher.group(1);
            if (IMAGE_PATTERN.equals(pattern)) {
                if (!isMatch(text, URL_PATTERN)) {
                    text = protocol + "://" + host + text;
                }
            }
            result.add(text.replaceAll("\\<script.*?\\>.*?\\</script\\>", "")
                           .replaceAll("\\<.*?\\>", " ")
                           .replaceAll("&lt;", "")
                           .replaceAll("&gt;", ""));
        }

        if (IMAGE_PATTERN.equals(pattern) && "www.youtube.com".equals(host)) {
            Pattern pc = Pattern.compile(YOUTUBE_SCREEN_SHORT_PATTERN);
            Matcher mc = pc.matcher(html);
            while (mc.find()) {
                result.add(0, mc.group(1));
            }
        }

        return result;
    }

    private boolean isMatch(String s, String pattern) {
        try {
            Pattern patt = Pattern.compile(pattern);
            Matcher matcher = patt.matcher(s);
            return matcher.matches();
        } catch (RuntimeException e) {
            return false;
        }
    }
}

/*
example to use

try {
    HTMLParser parser = new HTMLParser(url);
    title = parser.get(HTMLParser.TITLE_PATTERN, 1);
    image = parser.get(HTMLParser.IMAGE_PATTERN, 10);
    content = parser.get(HTMLParser.WEBCONTENT_PATTERN, 2);
} catch (MalformedURLException ex) {
    Logger.getLogger(HtmlPerserMB.class.getName()).log(Level.SEVERE, null, ex);
} catch (IOException ex) {
    Logger.getLogger(HtmlPerserMB.class.getName()).log(Level.SEVERE, null, ex);
}
*/