java之Jsoup爬取网页内容

所需引入jar包：https://jsoup.org/packages/jsoup-1.13.1.jar

<!--java爬取文章jar-->
<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.13.1</version>
</dependency>

java代码

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

 // 解析html并设值content
Document document = Jsoup.connect(article.getAudioUrl()).get();
String content = document.select("body")+"";

(详情参考API：https://www.open-open.com/jsoup/)