Java LinkTag 获得网页中的所有链接

package IBMSpider;

import java.util.ArrayList;

import org.htmlparser.*;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;

public class testHtmlParser {
	/*此类是为了获得网页中的所有链接
	 * 
	 * */
	public static void main(String[] args) {

		ArrayList<String> links= new ArrayList<String>();
		try {

			NodeFilter filter = new NodeClassFilter(LinkTag.class);
			Parser parser = new Parser();
			parser.setURL("http://www.cb.cityu.edu.hk/is/people/academic/");
			parser.setEncoding(parser.getEncoding());
			NodeList list = parser.extractAllNodesThatMatch(filter);
			for (int i = 0; i < list.size(); i++) {
			LinkTag node = (LinkTag) list.elementAt(i);
			links.add(node.extractLink());
			}
			} catch (Exception e) {
			e.printStackTrace();
			}

	}

}