一个简单的JAVA网页爬虫

public class Access implements Runnable{

HttpURLConnection huc;
InputStream is;
BufferedReader reader;
String url;

public Access(){
try {
url="http://www.yahoo.com.cn";
} catch (Exception e) {
e.printStackTrace();
}
try {
huc=(HttpURLConnection)new URL(url).openConnection();
} catch (MalformedURLException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}

new Thread(this).start();
}

public void run() {
try {
huc.setRequestMethod("GET");
} catch (ProtocolException e) {
e.printStackTrace();
}
try {
huc.setUseCaches(true);
huc.connect();

} catch (IOException e) {
e.printStackTrace();
}
try {
is=huc.getInputStream();
reader=new BufferedReader(new InputStreamReader(is,huc.getContentType().equals("text-html; charset=gb2312")?"gb2312":"UTF-8"));
StringBuffer temp=new StringBuffer();
String str;
while((str=reader.readLine())!=null){
temp.append(str+"\n");
}
System.out.println(new String(temp));
} catch (IOException e) {
e.printStackTrace();
}finally{
try {
reader.close();
is.close();
huc.disconnect();
} catch (IOException e) {
e.printStackTrace();
}
}
}


}