java/实验五/XiaohongshuStrategy.java

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.util.ArrayList;
import java.util.List;

public class XiaohongshuStrategy implements CrawlStrategy {
    private static final String URL = "https://www.xiaohongshu.com";

    @Override
    public List<Movie> crawl(int limit) {
        List<Movie> list = new ArrayList<>();
        try {
            Document doc = Jsoup.connect(URL)
                    .userAgent("Mozilla/5.0")
                    .timeout(10000)
                    .get();

            Elements items = doc.select("div");
            int count = 0;
            for (Element e : items) {
                if (count >= limit) break;
                Movie m = parseMovie(e);
                if (m != null) {
                    list.add(m);
                    count++;
                }
            }
        } catch (Exception ex) {
            System.out.println("小红书抓取失败（反爬保护），已跳过");
        }
        return list;
    }

    @Override
    public Movie parseMovie(Element element) {
        try {
            String title = element.select("h2").first().text();
            return new XiaohongshuMovie(title, 2024, 9.2, "笔记", "小红书用户");
        } catch (Exception e) {
            return null;
        }
    }
}