JAVA获取网页源码

java 获取网页源码

?

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56

package cn.itcast.getcode;   import java.io.BufferedReader; import java.io.IOException; import java.io.InputStreamReader; import java.net.HttpURLConnection; import java.net.URL;   public class GetCode {        public static void main(String[] a) throws IOException {            String url = "http://www.baidu.com" ;            System.out.println(getHTML(url, "gbk" )); // 使用原网页里声明的gb2312反而会出现乱码        }        public static String getHTML(String pageURL, String encoding) {            StringBuilder pageHTML = new StringBuilder();            try {                URL url = new URL(pageURL);                HttpURLConnection connection = (HttpURLConnection) url                      .openConnection();                connection.setRequestProperty( "User-Agent" , "MSIE 7.0" );                BufferedReader br = new BufferedReader( new InputStreamReader(                      connection.getInputStream(), encoding));                String line = null ;                while ((line = br.readLine()) != null ) {                    pageHTML.append(line);                    pageHTML.append( "\r\n" );                }                connection.disconnect();            } catch (Exception e) {                e.printStackTrace();            }            return pageHTML.toString();        } }