Extract paragraph from html

import java.io.*;

import java.net.*;

import javax.swing.text.*;

import javax.swing.text.html.*;

class GetHTMLText

{

public static void main(String[] args)

throws Exception

{

EditorKit kit = new HTMLEditorKit();

Document doc = kit.createDefaultDocument();

// The Document class does not yet handle charset's properly.

doc.putProperty("IgnoreCharsetDirective", Boolean.TRUE);

// Create a reader on the HTML content.

Reader rd = getReader(args[0]);

// Parse the HTML.

kit.read(rd, doc, 0);

// The HTML text is now stored in the document

System.out.println( doc.getText(0, doc.getLength()) );

}

// Returns a reader on the HTML data. If 'uri' begins

// with "http:", it's treated as a URL; otherwise,

// it's assumed to be a local filename.

static Reader getReader(String uri)

throws IOException

{

// Retrieve from Internet.

if (uri.startsWith("http:"))

{

URLConnection conn = new URL(uri).openConnection();

return new InputStreamReader(conn.getInputStream());

}

// Retrieve from file.

else

{

return new FileReader(uri);

}

}

}

sorry here is the codes again

this one actually returns all the text in a webpage

i need one which return only those texts in a paragraph

Rakesh_222a at 2007-7-8 23:20:56 >