爬虫学习之Java（一）

爬虫学习（一）

---

抓取网页源码

代码块：

package com.spider;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;

public class BaiduSourceCodeTest {

    public static void main(String[] args) {

        String url = "http://www.baidu.com";

        String result = "";

        BufferedReader in = null;

        try {
            URL realUrl = new URL(url);

            URLConnection con = realUrl.openConnection();

            con.connect();

            in = new BufferedReader(new InputStreamReader(con.getInputStream()));

            String line;

            while((line=in.readLine()) != null) {
                result = result + line;
            }

        } catch (MalformedURLException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } finally {
            if(in != null) {
                try {
                    in.close();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
        }

        System.out.println(result);

    }

}