java/实验五/DoubanStrategy.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 DoubanStrategy implements CrawlStrategy {
    private static final String URL = "https://movie.douban.com/top250?start=0";

    @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(".item");
            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("豆瓣抓取失败（反爬保护），已跳过");
        }
        return list;
    }

    @Override
    public Movie parseMovie(Element element) {
        try {
            String title = element.select(".hd .title").first().text();
            double rating = Double.parseDouble(element.select(".rating_num").first().text());
            return new TheatreMovie(title, 2024, rating, "电影", 49.9);
        } catch (Exception e) {
            return null;
        }
    }
}