使用Jsoup 简单抓取页面的数据

深碍√TFBOYSˉ_ 2022-06-12 09:37 229阅读 0赞

代码：

package cn.test.webcap;
    
    import java.io.IOException;
    import java.security.KeyManagementException;
    import java.security.NoSuchAlgorithmException;
    import java.sql.SQLException;
    import java.text.ParseException;
    
    import org.jsoup.Connection.Method;
    import org.jsoup.Connection.Response;
    import org.jsoup.nodes.Document;
    import org.jsoup.nodes.Element;
    import org.jsoup.select.Elements;
    import org.jsoup.Jsoup;
    
    public class MainTestCapDemo {
    
    	static int time_out = 300000;	
    	public static void main(String[] args) throws SQLException,KeyManagementException, NoSuchAlgorithmException,
    			InterruptedException, ParseException,IOException {
    		System.out.println("Start!");	
    		String url_main = "http://wx.vjiankang.org/wsite/list/index/pid/796/cid/20527/sx/3222";	
    		Response res_main = Jsoup
    				.connect(url_main)
    				.method(Method.GET)				
    				.header("User-Agent",
    					  "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.75 Safari/537.36")
    				.header("Connection","keep-alive")			
    				.ignoreContentType(true)
    				.timeout(time_out).execute();	
    		Document doc = res_main.parse();
    		Elements e = doc.select("div > ul.article_list > li").select("a");
    		for (Element ec : e) {
    			String url = ec.attr("href");
    			Element eci = ec.select("h3").first();
    			Element s = doc.select("div > p").first();
    			String title = eci.text();
    			String content = s.text();
    			System.out.println(url + "----" + title + "----" +content);
    		}
    		
    		System.out.println("End!");
    	}
    }

截取对应类选择器的数据：

![Center][]

获得的数据截图：

![Center 1][]

[Center]: /images/20220612/033a31654e7f491b9905903c7d1b42fa.png
[Center 1]: /images/20220612/da22737f75014350bd8e38997ec535bc.png