html页面抓取

public class Test001 {  
    List<String> rsList = new ArrayList<String>();  
    private Test001() {  
        try {  
            loadHtml();  
        } catch (IOException e) {  
            e.printStackTrace();  
        }  
    }  
 
    private void loadHtml() throws IOException {  
        // 定义一个url类的实例。  
        URL url = new URL("http://top.baidu.com/buzz/top10.html");  
        // 以特定格式读取文件流。  
        InputStreamReader isr = new InputStreamReader(url.openStream(),  
                "gb2312");  
        BufferedReader br = new BufferedReader(isr);  
        String s;  
 
        boolean beginFind = false;  
        while (null != (s = br.readLine())) {  
            if ("<tbody id=\"listdata\">".equals(s.trim())) {  
                beginFind = true;  
            } else if ("</tbody>".equals(s.trim())) {  
                break;  
            }  
 
            if (beginFind) {  
                if(s.trim().startsWith("<td><a")){  
                    rsList.add(findContent(s.trim()));  
                }  
            }  
        }  
          
        for (int i = 0; i < rsList.size(); i++) {  
            System.out.println(rsList.get(i));  
        }  
    }  
 
    public String findContent(String html) {  
        // 配置html标记。  
        Pattern p = Pattern.compile("<(\\S*?)[^>]*>.*?| <.*? />");  
        Matcher m = p.matcher(html);  
 
        String rs = new String(html);  
        // 找出所有html标记。  
        while (m.find()) {  
            // 删除html标记。  
            rs = rs.replace(m.group(), "");  
        }  
        return rs;  
    }  
 
    public static void main(String[] args) throws IOException {  
        new Test001();  
    }  
}