6、抓取数据

ElasticSearch - 点击查看当前系列文章

§ 6、抓取数据「当前文章」

常用的抓取数据的姿势
#

姿势1：HTMLParser
姿势2：HttpClient
姿势3：Jsoup

Jsoup
#

1、添加依赖
#

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

2、代码
#

@Test
public void test5() throws Exception {
    String url = "https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CJFD&dbname=CJFDAUTODAY&filename=SAHG202109022&uniplatform=NZKPT";
    //解析资源路径,设置超时时间30秒
    //此方法生成一个Document对象，可以按照前端方式进行操作
    Document doc = Jsoup.parse(new URL(url), 30000);
    //获取标题
    Element element = doc.getElementsByClass("wx-tit").get(0);
    String title = element.child(0).text();
    System.out.println("标题：" + title);

    //获取摘要
    Element chDivSummary = doc.getElementById("ChDivSummary");
    String digest = chDivSummary.text();
    System.out.println("摘要：" + digest);

    //获取关键字
    Element keywords = doc.getElementsByClass("keywords").get(0);
    int num = keywords.childNodeSize();
    String keyword = "";
    for (int i = 0; i < num; i++) {
        keyword += keywords.child(i).text();
    }
    System.out.println("关键字：" + keyword);
}