Java/w11/datacollect/strategy/BlogStrategy.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;
import java.util.regex.Pattern;

public class BlogStrategy implements CrawlStrategy {
    private static final Logger logger = LoggerFactory.getLogger(BlogStrategy.class);
    private static final Pattern URL_PATTERN = Pattern.compile(".*blog\\.example\\.com.*");

    @Override
    public boolean supports(String url) {
        boolean isSupported = URL_PATTERN.matcher(url).matches();
        logger.debug("URL {} support status: {}", url, isSupported);
        return isSupported;
    }

    @Override
    public List<Article> parse(String url, Document doc) throws ParseException {
        try {
            logger.info("Start parsing blog articles from url: {}", url);
            List<Article> articles = new ArrayList<>();
            Elements titles = doc.select(".post-title");
            for (Element e : titles) {
                articles.add(new Article(e.text(), url, ""));
            }
            logger.debug("Parsed {} blog articles from url: {}", articles.size(), url);
            return articles;
        } catch (Exception e) {
            logger.error("Failed to parse blog articles from url: {}", url, e);
            throw new ParseException("Blog article parse failed for url: " + url, e);
        }
    }

    @Override
    public int getPriority() {
        return 10; // 优先级高于默认策略
    }
}