Java HTML页面抓取实例

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.UnsupportedEncodingException;
import java.net.HttpURLConnection;
import java.net.MalformedURLException;
import java.net.URL;

public class Url {

public static void main(String[] args) throws Exception{
String html = getURLContent();
System.out.println(html);
}

/**
* 获取网页内容
*/
private static String getURLContent() throws MalformedURLException, IOException, UnsupportedEncodingException {
URL urlmy = new URL("http://www.baidu.com");

HttpURLConnection con = (HttpURLConnection) urlmy.openConnection();
HttpURLConnection.setFollowRedirects(true);
con.setInstanceFollowRedirects(false);
con.connect();

BufferedReader br = new BufferedReader(new InputStreamReader(con.getInputStream(),"UTF-8"));

String s = "";

StringBuffer sb = new StringBuffer();

while ((s = br.readLine()) != null) {
sb.append(s+"\r\n");
}

return sb.toString();
}

}