public class RealHtml{
       public static void main(String[] args) throws Exception {
        // TODO Auto-generated method stub
        RealHtml rh=new RealHtml();
                rh.getwh();
    }
    
    public void getwh(){
        DataInputStream dis=null;
        StringBuffer strBuff=new StringBuffer();
        InputStream is=null;
        try{
            String url="web地址";
            URL rss=new URL(url);
            URLConnection con=(URLConnection)rss.openConnection();
            String ucd="";
            dis=new DataInputStream(con.getInputStream());
            String line,line2;
            while((line=dis.readLine())!=null){
                line=new String(line.trim().getBytes("iso8859-1"),"GB2312");
                    strBuff.append(line+"\n");                
            }
//            System.out.println(strBuff.toString());
            String str=readTable(strBuff.toString(), 17);            
            System.out.println(filterHtml(str));    
        dis.close();
        }catch(Exception e){}   
    }
   public static String readTable(String resource,int t) throws Exception {
        Parser myParser = new Parser(resource);            
        String filterStr = "table";            
        NodeFilter filter = new TagNameFilter(filterStr);         
        org.htmlparser.util.NodeList nodeList = myParser.extractAllNodesThatMatch(filter);
     
        TableTag tabletag = (TableTag) nodeList.elementAt(t);
//        System.out.println(tabletag.toHtml());      
        return tabletag.toHtml();
    }
    /** 过滤html标签
     * @param htmlStr  //含html标签的字符串
     * @return String
     */
    public static  String filterHtml(String htmlStr) {    
        String textStr ="";
        java.util.regex.Pattern p_script;
        java.util.regex.Matcher m_script;
        java.util.regex.Pattern p_style;
        java.util.regex.Matcher m_style;
        java.util.regex.Pattern p_html;
        java.util.regex.Matcher m_html;
        try {
         String regEx_script = "<[\\s]*?script[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?script[\\s]*?>"; //定义script的正则表达式{或<script[^>]*?>[\\s\\S]*?<\\/script> }
         String regEx_style = "<[\\s]*?style[^>]*?>[\\s\\S]*?<[\\s]*?\\/[\\s]*?style[\\s]*?>"; //定义style的正则表达式{或<style[^>]*?>[\\s\\S]*?<\\/style> }
         String regEx_html = "<[^>]+>"; //定义HTML标签的正则表达式
         
            p_script = Pattern.compile(regEx_script,Pattern.CASE_INSENSITIVE);
            m_script = p_script.matcher(htmlStr);
            htmlStr = m_script.replaceAll(""); //过滤script标签

            p_style = Pattern.compile(regEx_style,Pattern.CASE_INSENSITIVE);
            m_style = p_style.matcher(htmlStr);
            htmlStr = m_style.replaceAll(""); //过滤style标签
         
            p_html = Pattern.compile(regEx_html,Pattern.CASE_INSENSITIVE);
            m_html = p_html.matcher(htmlStr);
            htmlStr = m_html.replaceAll(" "); //过滤html标签
         
         textStr = htmlStr.replaceAll("&nbsp;"," ");
         
        }catch(Exception e) {
            e.printStackTrace();
        }
        
        return textStr;//返回文本字符串
         }
    
}