java读取网页内容

Posted 2020-11-25 404

package com.linxinxin.tools;


import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;

public class CrawlerUtil {
    public static void main(String[] a){
        try {
            URL url=new URL("http://www.baidu.com");
            BufferedReader reader=new BufferedReader(new InputStreamReader(url.openStream()));
            BufferedWriter writer=new BufferedWriter(new FileWriter("index.html"));
            String line;
            while((line=reader.readLine())!=null){
                System.out.println(line);
                writer.write(line);
                writer.newLine();
            }
            reader.close();
            writer.close();
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }

    }
}