java/w10/strategy/GenericNewsStrategy.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;
import java.util.regex.Pattern;

public class GenericNewsStrategy implements CrawlStrategy {
    private static final Pattern PATTERN = Pattern.compile(".*\\.(news|press|article)s?\\..*");
    private static final int PRIORITY = 5;

    @Override
    public boolean supports(String url) {
        return PATTERN.matcher(url).find();
    }

    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();
        
        Elements items = doc.select("article, .news-item, .article-item, [class*='news'], [class*='article']");
        
        for (Element item : items) {
            String title = item.selectFirst("h1, h2, h3, .title, [class*='title']") != null 
                ? item.selectFirst("h1, h2, h3, .title, [class*='title']").text().trim() 
                : "";
            
            String articleUrl = item.selectFirst("a[href]") != null 
                ? item.selectFirst("a[href]").attr("abs:href") 
                : url;
            
            String content = item.selectFirst("p, .content, [class*='content']") != null 
                ? item.selectFirst("p, .content, [class*='content']").text().trim() 
                : "";

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

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

    @Override
    public Pattern getPattern() {
        return PATTERN;
    }
}