jsoup爬虫-解析京东商品页面

 pom:

    <dependencies>
        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.11.3</version>
        </dependency>
    </dependencies>

Test.java:

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

import java.net.URL;

public class Test {
    public static void main(String[] args) throws Exception {
        String keywords = "java";
        //获取请求https://search.jd.com/Search?keyword=java
        String url = "https://search.jd.com/Search?keyword=" + keywords + "&enc=utf-8";
        //解析网页(就是js页面对象)
        Document document = Jsoup.parse(new URL(url), 30000);
        Element element = document.getElementById("J_goodsList");
        System.out.println(element.html());
        Elements elements = element.getElementsByTag("li");

        for (Element el : elements) {
            //图片地址
            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();
            System.out.println("======================");
            System.out.println(img);
            System.out.println(price);
            System.out.println(title);
        }
    }
}