Crawler_study notes

Crawl data

Get the page information returned by the request and filter out the data we want.
jsoupPackage: Parse the web page

 <dependency>
     <groupId>org.jsoup</groupId>
     <artifactId>jsoup</artifactId>
     <version>1.10.2</version>
 </dependency>

tikaPackage: Climbing Movie

Code

package com.qun.util;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import java.net.URL;

public class HtmlParseUtil {
    
    
    public static void main(String[] args) throws  Exception {
    
    

        String url="https://search.jd.com/Search?keyword=java";
        //解析网页,返回的是浏览器document对象
        Document document = Jsoup.parse(new URL(url),3000);
        Element element = document.getElementById("J_goodsList");
//        System.out.println(element.html());
        Element elements = element.getElementById("li");
        System.out.println(elements);

    }
}