Java爬取京东商品

最新推荐文章于 2024-08-22 22:09:54 发布

依我去

最新推荐文章于 2024-08-22 22:09:54 发布

阅读量427

点赞数

分类专栏： Java爬虫入门到实战

本文链接：https://blog.csdn.net/weixin_43816119/article/details/108262461

版权

Java爬虫入门到实战专栏收录该内容

3 篇文章 0 订阅

订阅专栏

package com.yiwoqu.yiwoquesjd.utils;

import com.yiwoqu.yiwoquesjd.pojo.Content;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.springframework.stereotype.Component;


import java.net.URL;
import java.util.ArrayList;

/**
 * @ClassName: HtmlParesUtil
 * @Description: 爬取京东数据
 * @author: 易海涛
 * @date: 2020/8/24  10:34
 */
@Component
//HTME解析工具
public class HtmlParseUtil {
    public static void main(String[] args) throws Exception {
        new HtmlParseUtil().parseJD("java").forEach(System.out::println);
    }

    public ArrayList<Content> parseJD(String kewwords) throws Exception{
        //获取请求
        String url = "https://search.jd.com/Search?keyword="+kewwords;
        Document document =Jsoup.parse(new URL(url),30000);
        Element element = document.getElementById("J_goodsList");
        Elements elements= element.getElementsByTag("li");
        ArrayList<Content> goodsList = new ArrayList<>();
        for (Element el : elements){
            String img = el.getElementsByTag("img").eq(0).attr("src");
            String price = el.getElementsByClass("p-price").eq(0).text();
            String title = el.getElementsByClass("p-name").eq(0).text();

            Content content = new Content();
            content.setImg(img);
            content.setPrice(price);
            content.setTitle(title);
            goodsList.add(content);
        }
        return goodsList;
    }
}