Jsoup爬虫随笔

导入依赖：

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

代码：

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;

/**
 * @author len
 * @describe 爬虫
 * @createTime 2021/5/31
 */
public class PcTest {

    public static void main(String[] args) throws IOException {
        String url = "http://www.360doc.com/content/20/1206/10/9113704_949755169.shtml";
        Document document = Jsoup.parse(new URL(url), 30000);
        Element element = document.getElementById("artContent");
        System.out.println(element.html());
        Elements elements = document.getElementsByTag("p");
        for (Element el:elements){
            Elements els = el.getElementsByTag("p");
            els.stream().forEach(e -> System.out.println(e.text()));
        }
    }
}