<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.13.1</version>
</dependency>
@Component
public class HtmlParseUtil {
public ArrayList<Content> parseJD(String keyword) throws IOException {
String url = "https://search.jd.com/Search?keyword="+keyword;
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("data-lazy-img");
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;
}
}