一个简单的java提取页面源码的示例

package Main;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URLConnection;
import java.net.URL;
public class Test {
public static void main (String[] args) {
getHtml("http://www.XXXX.com/");
}
public static void save(String name,String Lname,String data) throws IOException {
File html=new File("./"+name+"."+Lname);
if (!html.exists()) {
html.createNewFile();
}
FileWriter fw=new FileWriter(html.getAbsoluteFile());
BufferedWriter bw=new BufferedWriter(fw);
bw.write(data);
bw.close();
}
public static String getHtml(String target) {
String result="";
BufferedReader in=null;
try{
URL url_address=new URL(target);
URLConnection get_url=url_address.openConnection();
//构造请求头
get_url.setRequestProperty("accept", "*/*");
get_url.setRequestProperty("connection", "Keep-Alive");
get_url.setRequestProperty("user-agent", "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
//打开请求
get_url.connect();
in =new BufferedReader(new InputStreamReader(get_url.getInputStream()));
String out;
while ((out = in.readLine()) != null) {
result += "\n"+line;
}
System.out.println(result);
}catch (Exception e) {
e.printStackTrace();
}finally {
if(in!=null){
try{
in.close();
}catch(Exception e2){
e2.printStackTrace();
}
}
}
return result;
}
}