how to retrieve TITLE of a HTML with the help of HTMLEditorKit

问题

I want to retrieve TITLE attribute with the help of java's HTMLEditorKit ? this what I've written but it will return "null" all the time and inspector in eclipse doesn't help that much !

import java.io.FileReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.net.URL;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;
public class testHTML

{
  public static void main(String args[]) throws Exception 
  {

    Reader reader = new FileReader("C:\\wamp\\www\\t\\index.html");

    new ParserDelegator().parse(reader, new LinkPage(), true);

  }
}
class LinkPage extends HTMLEditorKit.ParserCallback 
{
    public void handleSimpleTag(HTML.Tag tag,
            MutableAttributeSet attributes, int pos) {

        if (tag == HTML.Tag.TITLE)
        {
            System.out.println(attributes.getAttribute(HTML.Attribute.TITLE));
        }
    }
  public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos) 
  {
//    if (t == HTML.Tag.A) 
//    {
//      //System.out.println("<BR>");
//      
//    }
//    if(t == HTML.Tag.TITLE)
//    {
//      System.out.println(t.toString());
//      System.out.println(t.TITLE);
//      System.out.println();
//      String text = (String)a.getAttribute(HTML.Attribute.TITLE);
//      Object o = a.getAttribute(HTML.Attribute.TITLE);
//      System.out.println(a);
//      System.out.println(o);
//      System.out.println(text);
//    }
// 
      handleSimpleTag(t, a, pos);
  }
}

and the content of HTML is :

<html>
<head>
<title>test</title>
</head>
<body>
test
<a href="http://localhost/t/1.html">link1</a>
sdf
<a href="http://localhost/t/2.html">link2</a>
sdf
<a href="http://localhost/t/1.html">link3</a>
sdf
<a href="http://localhost/t/2.html">link3</a>
</body>
</html>

p.s : I am aware of XPATH , REGEX and any other 3rd party component to retrieve HTML attrinutes in an easy way but I want to learn the hard way too.

回答1:

import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
import javax.swing.text.html.HTMLEditorKit;
import javax.swing.text.html.parser.ParserDelegator;
import java.io.Reader;
import java.io.StringReader;

public class Test2 {
    public static final String content = "<html> \n" +
            "<head> \n" +
            "<title>test</title> \n" +
            "</head> \n" +
            "<body> \n" +
            "test \n" +
            "<a href=\"http://localhost/t/1.html\">link1</a> \n" +
            "sdf \n" +
            "<a href=\"http://localhost/t/2.html\">link2</a> \n" +
            "sdf \n" +
            "<a href=\"http://localhost/t/1.html\">link3</a> \n" +
            "sdf \n" +
            "<a href=\"http://localhost/t/2.html\">link3</a> \n" +
            "</body> \n" +
            "</html> ";

    public static void main(String args[]) throws Exception {
        Reader reader = new StringReader(content);
        new ParserDelegator().parse(reader, new LinkPage(), true);
    }
}

class LinkPage extends HTMLEditorKit.ParserCallback {
    int startPos = -1;

    public void handleText(char[] data, int pos) {
        if (startPos >= 0) {
            startPos = pos;
        }
    }

    public void handleEndTag(HTML.Tag t, int pos) {
        super.handleEndTag(t, pos);
        if (t == HTML.Tag.TITLE) {
            System.out.println(Test2.content.substring(startPos, pos));
            startPos = -1;
        }
    }

    public void handleStartTag(HTML.Tag t, MutableAttributeSet a, int pos) {
        super.handleStartTag(t, a, pos);
        if (t == HTML.Tag.TITLE) {
            startPos = pos;
        }
    }
}

来源：https://stackoverflow.com/questions/9580684/how-to-retrieve-title-of-a-html-with-the-help-of-htmleditorkit

标签

java

swing

html-parsing

htmleditorkit