Jsuop实现爬取数据

Jsuop实现爬取数据

Jsuop实现爬取数据

• 首先引入依赖

  
          <dependency>
              <groupId>org.jsoupgroupId>
              <artifactId>jsoupartifactId>
              <version>1.10.2version>
          dependency>
  

• 实现

  public List<Content> parseJD(String name) throws Exception {
          String url = "https://search.jd.com/Search?keyword="+name;
          //解析网页，返回值就是网页对象,30000是响应时间，随意设置
          Document document = Jsoup.parse(new URL(url), 30000);
          //参数为需要获取内容的class
          Element goodsList = document.getElementById("J_goodsList");
          Elements elements = goodsList.getElementsByTag("li");
          ArrayList<Content> contents = new ArrayList<>();
          for (Element element : elements) {
              String img = element.getElementsByTag("img").eq(0).attr("src");
              String price = element.getElementsByClass("p-price").eq(0).text();
              String title = element.getElementsByClass("p-name").eq(0).text();
  
              Content content = new Content(title, price, img);
              contents.add(content);
          }
          return contents;
      }