java/project/HnuNewsStrategy.java

package com.example.datacollect.strategy;

import com.example.datacollect.model.Article;
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 HnuNewsStrategy implements CrawlStrategy {
    @Override
    public boolean supports(String url) {
        return url.contains("news.hnu.edu.cn");
    }

    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();
        
        Elements links = doc.select("a[href*='/info/']");
        
        for (Element link : links) {
            String articleUrl = link.attr("abs:href");
            
            if (!articleUrl.startsWith("http")) {
                articleUrl = "https://news.hnu.edu.cn" + link.attr("href").replace("..", "");
            }
            
            String title = link.text().trim();
            
            if (title.isEmpty()) {
                Element titleEl = link.selectFirst("h2, h3, h4, .title");
                if (titleEl != null) {
                    title = titleEl.text().trim();
                }
            }
            
            String content = "";
            Element parent = link.parent();
            if (parent != null) {
                Element contentEl = parent.selectFirst("p, .summary, .description");
                if (contentEl != null) {
                    content = contentEl.text().trim();
                }
            }
            
            if (!title.isEmpty() && articleUrl.contains("/info/")) {
                articles.add(new Article(title, articleUrl, content));
            }
        }
        
        return articles;
    }
}