java/w12/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 java.util.ArrayList;
import java.util.List;
import java.util.regex.Pattern;

public class BlogStrategy implements CrawlStrategy {
    private static final Pattern URL_PATTERN = Pattern.compile("https?://blog\\.example\\.com/.*");

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

    @Override
    public List<Article> parse(String url, Document doc) throws ParseException {
        List<Article> articles = new ArrayList<>();
        Elements titles = doc.select(".post-title");
        for (Element e : titles) {
            articles.add(new Article(e.text(), url, ""));
        }
        return articles;
    }

    @Override
    public int getPriority() {
        return 2;
    }
}