springBoot集成jsoup

最新推荐文章于 2024-06-26 08:37:40 发布

1 2 3 一起追梦

最新推荐文章于 2024-06-26 08:37:40 发布

阅读量818

点赞数 1

文章标签： spring boot java

本文链接：https://blog.csdn.net/qq_41720578/article/details/126390089

版权

1、依赖

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.13.1</version>
</dependency>

2、使用

public final class JDUtil {
	private static String keyword_url = "https://search.jd.com/Search?keyword=";

	public static List<Good> getGoodList(String keyword) throws IOException {
		List<Good> goodList = new ArrayList<>();

		Document document = null;
		try {

			 Connection con = Jsoup.connect(keyword_url + keyword).userAgent(
                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.90 Safari/537.36")
                .timeout(30000); // 设置连接超时时间

			document = con.get();

			System.out.println(document);

			Element j_goodsList = document.getElementById("J_goodsList");

			Elements elementsByClass = j_goodsList.getElementsByClass("gl-i-wrap");

			elementsByClass.stream().forEach(item -> {
				String price = item.getElementsByClass("p-price").eq(0).text();
				price = price.substring(1, price.lastIndexOf("￥") != 0 ? price.lastIndexOf("￥") : price.length());
				System.out.println(price);
				Good good = Good.builder().publish(item.getElementsByClass("p-shopnum").text())
							  .imgUrl(item.getElementsByTag("img").attr("data-lazy-img"))
							  .name(item.getElementsByClass("p-name").tagName("a").text())
							  .desc(item.getElementsByAttribute("data-tips").attr("data-tips"))
							  .price(Double.parseDouble(price))
							  .unit(item.getElementsByClass("p-price").tagName("em").text().substring(0,1)).build();
				goodList.add(good);
			});
		}catch (NullPointerException e){
			e.printStackTrace();
			System.out.println("未拿到页面数据");
		}

		return goodList;
	}
}