HtmlParser--TextExtractingVisitor

import org.htmlparser.Parser;

import org.htmlparser.util.ParserException;

import org.htmlparser.visitors.HtmlPage;

import org.htmlparser.visitors.TextExtractingVisitor;

 

public class HTMLTest

{

    public static void main(String[] args) throws ParserException

    {

       Parser parser=new Parser("http://baidu.com");

      

       parser.setEncoding("gb2312");

      

       TextExtractingVisitor visitor=new TextExtractingVisitor();

      

       parser.visitAllNodesWith(visitor);

      

       String s=visitor.getExtractedText();

      

//     String ss=s.replaceAll("", "");

       System.out.println(s);

      

 

    }

 

}