HTMLParserを使ってみる(HTMLParser)*2

用意するもの

HTML Parser
- htmllexer.jar
- htmlparser.jar

URLを指定してHTMLを読み込みドキュメントツリーを見るテスト

package jp.seraphyware.htmlparsertest;

import java.net.URL;
import java.net.URLConnection;

import org.htmlparser.Node;
import org.htmlparser.Parser;
import org.htmlparser.Tag;
import org.htmlparser.Text;
import org.htmlparser.util.NodeList;

public class HTMLParserTest {

    public static void main(final String[] args) throws Exception {
        final URL url = new URL("http://java.sun.com/");
        final URLConnection urlConnection = url.openConnection();
        
        final Parser parser = new Parser(urlConnection);
        final NodeList lst = parser.parse(null);
        walkTree("", lst);
    }
    
    private static void walkTree(final String level,
            final NodeList lst) throws Exception {
        if (lst == null) {
            return;
        }
        final int cnt = lst.size();
        for (int idx = 0; idx < cnt; idx++) {
            final Node node = lst.elementAt(idx);
            if (node instanceof Tag) {
                final String tagName = ((Tag) node).getTagName();
                System.out.println(level + "<" + tagName + ">");
                walkTree(level + " ", node.getChildren());
            }
            else if (node instanceof Text) {
                final String txt = node.getText();
                if (txt.trim().length() > 0) {
                    System.out.println(level + txt);
                }
            }
        }
    }
    
}