java/W11/strategy/NewsStrategy.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 org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.ArrayList;
import java.util.List;

public class NewsStrategy implements CrawlStrategy {
    private static final Logger logger = LoggerFactory.getLogger(NewsStrategy.class);

    @Override
    public boolean supports(String url) {
        return url.contains("news.example.com");
    }

    @Override
    public List<Article> parse(String url, Document doc) throws ParseException {
        logger.debug("Parsing news content from: {}", url);
        List<Article> articles = new ArrayList<>();
        Elements items = doc.select(".article-headline");
        for (Element e : items) {
            articles.add(new Article(e.text(), url, ""));
        }
        logger.debug("Parsed {} articles from news", articles.size());
        return articles;
    }
}