Java使用Jsoup之爬取博客数据应用实例

<!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->


    <dependency>


        <groupId>org.jsoup</groupId>


        <artifactId>jsoup</artifactId>


        <version>1.11.3</version>


    </dependency>

package cn.test;


import org.jsoup.Connection;


 org.jsoup.Jsoup;


 org.jsoup.nodes.Document;


 org.jsoup.nodes.Element;


 org.jsoup.select.Elements;


 java.io.IOException;


 java.util.ArrayList;


 java.util.List;





/**


 * A simple example,used on the jsoup website.


 */


public class BlogJsoup {


    


     * 获取博客最近十篇文章


     * @param args


     * @throws IOException


     */


    static void main(String[] args) throws IOException {


        


        Connection connection = Jsoup.connect("https://www.cnblogs.com/youcong/");


        


        connection.header("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/52.0.2743.116 Safari/537.36");





        try {


           


            Document document = connection.timeout(100000).get();





            包含所有列表的文章


            Elements elements = document.getElementsByClass("postTitle2");


     


            for (Element element : elements) {


         


                String path = element.attr("href");


                String text = element.text();


                String msg = text+" "+path;


                System.out.println(msg);





            }


            





        } catch (IOException e) {


            


            e.printStackTrace();


        }


             





   


}


    


}