java/project/strategy/SinaNewsStrategy.java

package com.example.moviecli.strategy;

import com.example.moviecli.model.Movie;
import com.example.moviecli.exception.ParseFailedException;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.util.ArrayList;
import java.util.LinkedHashSet;
import java.util.List;
import java.util.Set;

public class SinaNewsStrategy implements MovieCrawlStrategy {
    @Override
    public boolean supports(String url) {
        return url.contains("news.sina.com.cn");
    }

    @Override
    public List<Movie> parse(Document doc) throws ParseFailedException {
        try {
            List<Movie> newsList = new ArrayList<>();
            Set<String> titleSet = new LinkedHashSet<>();

            // 抓取所有 a 标签，过滤出标题较长的（通常新闻标题长度 > 8）
            Elements allLinks = doc.select("a");
            for (Element link : allLinks) {
                String title = link.text().trim();
                // 过滤短文本、纯数字、纯符号、常见非标题文字
                if (title.length() > 8 && !title.matches("^[\\d\\s]+$") 
                        && !title.contains("评论") && !title.contains("举报")) {
                    // 进一步过滤：通常新闻标题不会太短且不会包含过多标点
                    titleSet.add(title);
                }
                if (titleSet.size() >= 120) break; // 最多抓取120条
            }

            // 如果数量不够 30，再尝试抓取特定区域
            if (titleSet.size() < 30) {
                Elements newsItems = doc.select(".news-item, .blk, .main-content a");
                for (Element item : newsItems) {
                    String title = item.text().trim();
                    if (title.length() > 8 && !titleSet.contains(title)) {
                        titleSet.add(title);
                    }
                    if (titleSet.size() >= 120) break;
                }
            }

            int rank = 1;
            for (String title : titleSet) {
                newsList.add(new Movie(rank++, title, "", "新闻", "新浪", ""));
            }
            return newsList;
        } catch (Exception e) {
            throw new ParseFailedException("新浪新闻解析失败", e);
        }
    }
}