Java/w11/datacollect/strategy/NewsStrategy.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 org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;

public class NewsStrategy implements CrawlStrategy {

    // 1. 添加 Logger 成员
    private static final Logger logger = LoggerFactory.getLogger(NewsStrategy.class);

    // 使用正则匹配
    private static final Pattern URL_PATTERN = Pattern.compile(".*news\\.example\\.com.*");

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

    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();

        // 2. 添加解析过程日志
        logger.debug("开始解析 URL: [{}]", url);

        Elements items = doc.select(".article-headline");

        if (items.isEmpty()) {
            logger.warn("在 URL [{}] 中未找到符合选择器 '.article-headline' 的文章标题元素。", url);
            return articles;
        }

        for (Element e : items) {
            String title = e.text().trim();
            if (!title.isEmpty()) {
                articles.add(new Article(title, url, ""));
                logger.trace("提取到文章标题: {}", title);
            }
        }

        logger.info("成功解析 URL [{}]，共提取 {} 篇文章。", url, articles.size());
        return articles;
    }

    @Override
    public int getPriority() {
        return 10;
    }
}