Java解析网页内容

Java解析网页内容

• IO 流读取网页内容

try {
            //创建一个URL实例
            URL url = new URL("http://www.baidu.com");
            StringBuffer result = new StringBuffer();
            try {
                //通过URL的openStrean方法获取URL对象所表示的自愿字节输入流
                InputStream is = url.openStream();
                InputStreamReader isr = new InputStreamReader(is,"utf-8");

                //为字符输入流添加缓冲
                BufferedReader br = new BufferedReader(isr);
                //读取数据
                String data = br.readLine();

                //循环读取数据
                while (data!=null){
                    //输出数据
                    result.append(data).append("\n");
                    System.out.println(data);
                    data = br.readLine();
                }

                br.close();
                isr.close();
                is.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
            System.out.println(result.toString());



        } catch (MalformedURLException e) {
            e.printStackTrace();
        }