java/w12/HnuNewsStrategy.java

package com.example.datacollect.strategy;

import com.example.datacollect.exception.ParseException;
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;
import java.util.regex.Pattern;

public class HnuNewsStrategy implements CrawlStrategy {
    private static final Pattern URL_PATTERN = Pattern.compile("https?://news\\.hnu\\.edu\\.cn/.*");

    @Override
    public boolean supports(String url) {
        return URL_PATTERN.matcher(url).matches();
    }

    @Override
    public List<Article> parse(String url, Document doc) throws ParseException {
        List<Article> articles = new ArrayList<>();
        Elements listItems = doc.select("ul.list11 li");

        for (Element li : listItems) {
            Element link = li.selectFirst("a");
            if (link == null) continue;

            String articleUrl = link.attr("href");
            if (!articleUrl.startsWith("http")) {
                articleUrl = "https://news.hnu.edu.cn" + articleUrl.replace("..", "");
            }

            String title = "";
            Element titleEl = link.selectFirst("h4.l2.h4s2");
            if (titleEl != null) {
                title = titleEl.text().trim();
            }

            String content = "";
            Element contentEl = link.selectFirst("p.l3.ps3");
            if (contentEl != null) {
                content = contentEl.text().trim();
            }

            if (!title.isEmpty()) {
                articles.add(new Article(title, articleUrl, content));
            }
        }

        return articles;
    }

    @Override
    public int getPriority() {
        return 3;
    }
}