jsoup爬虫简单演示

firstDemo_src_demo.java

import org.apache.http.HttpHost;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.conn.params.ConnRouteParams;
import org.apache.http.impl.client.DefaultHttpClient;
import org.apache.http.params.CoreConnectionPNames;
import org.apache.http.util.EntityUtils;


/**利用httpclient爬取相关数据
 * Created by 张巍瀚 on 2017/6/4.
 */

public class demo
{
    public static void main(String[] args) throws Exception
    {    //创建HttpClient对象
        HttpClient httpClient=new DefaultHttpClient();
        //创建爬虫所需要的Get请求地址 本案例只是一个演示流程,所以不涉及有关网络协议问题以及证书问题
        HttpGet httpGet =new HttpGet("http://www.12306.cn/mormhweb/");
        //设置响应时间 传输时间 设置代理服务器
//        httpClient.getParams().setParameter(CoreConnectionPNames.CONNECTION_TIMEOUT,10000);//连接时间
//        httpClient.getParams().setParameter(CoreConnectionPNames.SO_TIMEOUT,10000);
//        httpClient.getParams().setParameter(ConnRouteParams.DEFAULT_PROXY,new HttpHost("222.218.208.104",8998));

         //向服务器请求获取相应代码
        HttpResponse httpResponse= httpClient.execute(httpGet);
      // 利用工具将所获得的代码转换成字符串
       String content= EntityUtils.toString(httpResponse.getEntity(),"utf-8");
        System.out.println(content);
    }


}

firstDemo_src_jsoupDemo.java

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

/**利用Jsoup解析网页
 * Created by 张巍瀚 on 2017/6/5.
 */
public class jsoupDemo
{
    public static void main(String[] args)throws  Exception
    {
        Document doc=Jsoup.connect("http://www.12306.cn/mormhweb/").get();
//       Elements element= doc.getElementsByTag("a");
//        System.out.println(element.text());
       Elements element= doc.select("ul.menubg a");
       // System.out.println(element);
    for(Element elements:element){
        System.out.println(elements.text()+":"+elements.attr("href"));
    }
    }
}

对于HttpClient版本不同，写法也不同，本人刚入门，代码也是有所参考的