java扒页面代码

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileWriter;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.FileOutputStream;
import java.net.URL;

public class Test2{
public static void main(String[] args)throws Exception{
URL url = new URL("https://www.baidu.com");
BufferedReader reader = new BufferedReader(new InputStreamReader(url.openStream(),"utf-8"));
BufferedWriter writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream("d:/code/data.html"),"utf-8"));
String line;
while((line = reader.readLine()) != null){
System.out.println(line);
writer.write(line);
writer.newLine();
}
reader.close();
writer.close();
}
}

转载于:https://blog.51cto.com/3945465/2140484