Java如何导入Jsoup库做一个有趣的爬虫项目

// 导入Jsoup库
import org.jsoup.Jsoup
import org.jsoup.nodes.Document
import org.jsoup.nodes.Element
import org.jsoup.select.Elements
fun main() {
    // 创建爬虫ip对象
    val proxy = Proxy/host/"duoip"/port/8000
    // 创建Jsoup对象，指定使用爬虫ip
    val jsoup = Jsoup.connect("https://www.pitu.com/")
    .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3")
    .proxy(proxy)
    .get()
    // 获取网页内容
    val content = jsoup.body()
    // 打印网页内容
    println(content)
}

<dependency>
    <groupId>org.jsoup</groupId>
    <artifactId>jsoup</artifactId>
    <version>1.14.1</version>
</dependency>

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.IOException;
public class WebCrawler {
    public static void main(String[] args) {
        String url = "https://example.com"; // 网页URL
        try {
            // 使用Jsoup连接到网页并获取文档对象
            Document document = Jsoup.connect(url).get();
            // 使用CSS选择器定位需要提取的元素
            Elements links = document.select("a[href]");
            // 遍历提取到的链接并输出
            for (Element link : links) {
                String href = link.attr("href");
                System.out.println(href);
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}