从网络中获取网页数据时,网页有可能使用GZIP压缩技术对页面进行压缩,这样就会减小通过网络传输的数据量,提高浏览的速度。因此在获取网络数据时要对其进行判断,对GZIP格式的数据使用GZIPInputStream对其特殊处理,否则在获取数据可能出现乱码哦.
以下为网络中获取网页数据的案例代码
public class InternetTest2 { public static void main(String[] args) throws Exception{ String result = ""; //URL url = new URL("http://www.sohu.com"); URL url = new URL("http://www.ku6.com/"); HttpURLConnection conn = (HttpURLConnection) url.openConnection(); conn.setConnectTimeout(6* 1000);//设置连接超时 if (conn.getResponseCode() != 200) throw new RuntimeException("请求url失败"); InputStream is = conn.getInputStream();//得到网络返回的输入流 if("gzip".equals(conn.getContentEncoding())){ result = new InternetTest2().readDataForZgip(is, "GBK"); }else { result = new InternetTest2().readData(is, "GBK"); } conn.disconnect(); System.out.println(result); System.err.println("ContentEncoding: " + conn.getContentEncoding()); } //第一个参数为输入流,第二个参数为字符集编码 public static String readData(InputStream inStream, String charsetName) throws Exception{ ByteArrayOutputStream outStream = new ByteArrayOutputStream(); byte[] buffer = new byte[1024]; int len = -1; while( (len = inStream.read(buffer)) != -1 ){ outStream.write(buffer, 0, len); } byte[] data = outStream.toByteArray(); outStream.close(); inStream.close(); return new String(data, charsetName); } //第一个参数为输入流,第二个参数为字符集编码 public static String readDataForZgip(InputStream inStream, String charsetName) throws Exception{ GZIPInputStream gzipStream = new GZIPInputStream(inStream); ByteArrayOutputStream outStream = new ByteArrayOutputStream(); byte[] buffer =new byte[1024]; int len = -1; while ((len = gzipStream.read(buffer))!=-1) { outStream.write(buffer, 0, len); } byte[] data = outStream.toByteArray(); outStream.close(); gzipStream.close(); inStream.close(); return new String(data, charsetName); } }