1.导入maven依赖(Jsoup)
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.11.3</version>
</dependency>
2.开整
public class HtmlParseUtil {
public static void main(String[] args) throws Exception {
new HtmlParseUtil().parseJD("python").forEach(System.out::println);
}
/**
* 封装爬取京东方法
* @param keywords
* @return
* @throws Exception
*/
public List<Content> parseJD(String keywords) throws Exception{
//网站链接
String url="https://search.jd.com/Search?keyword="+keywords;
//解析网页
Document document = Jsoup.parse(new URL(url), 30000);
//找到你想要元素 div
Element element=document.getElementById("J_goodsList");
System.out.println(element.html());
//获取所有的li元素
Elements elements = element.getElementsByTag("li");
//创建list集合
ArrayList<Content> goodsList = new ArrayList<>();
//获取元素中的内容
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();
//创建对象并赋值
Content content = new Content();
content.setImg(img);
content.setPrice(price);
content.setTitle(title);
goodsList.add(content);
}
return goodsList;
}
}