java 抓取页面源码

我要抓取的页面的完整路径为：http://www.google.cn/language_tools?hl=zh-CN

String strServer="www.google.cn";//这里同样可以用ip来访问:203.208.35.100

String strPage="/language_tools?hl=zh-CN";

try {

String hostname = strServer;

int port = 80;

InetAddress addr = InetAddress.getByName(hostname);

Socket socket = new Socket(addr, port);

BufferedWriter wr = new BufferedWriter(new OutputStreamWriter(socket.getOutputStream(), "UTF8"));

wr.write("GET " + strPage + " HTTP/1.0"r"n");

wr.write("HOST:" + strServer + ""r"n");

wr.write(""r"n");

wr.flush();

BufferedReader rd = new BufferedReader(new InputStreamReader(socket.getInputStream()));

String line;

while ((line = rd.readLine()) != null) {

System.out.println(line);

}

wr.close();

rd.close();

} catch (Exception e) {

System.out.println(e.toString());

}