java/w11/strategy/BlogStrategy.java.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 BlogStrategy implements CrawlStrategy {
    private static final Logger logger = LoggerFactory.getLogger(BlogStrategy.class);

    @Override
    public boolean supports(String url) {
        boolean supported = url.contains("blog.example.com");
        logger.debug("BlogStrategy supports {}: {}", url, supported);
        return supported;
    }

    @Override
    public List<Article> parse(String url, Document doc) throws ParseException {
        List<Article> articles = new ArrayList<>();
        try {
            Elements titles = doc.select(".post-title");
            if (titles.isEmpty()) {
                logger.warn("No .post-title elements found for URL: {}", url);
                throw new ParseException("No .post-title elements found on page: " + url);
            }

            for (Element e : titles) {
                String title = e.text();
                if (title == null || title.isBlank()) {
                    logger.warn("Found empty title at URL: {}", url);
                    continue;
                }
                articles.add(new Article(title, url, ""));
                logger.debug("Parsed article: {}", title);
            }
        } catch (Exception e) {
            logger.error("Parse error for URL {}: {}", url, e.getMessage(), e);
            throw new ParseException("Failed to parse blog page: " + url, e);
        }
        return articles;
    }
}