java/w12/DefaultStrategy.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 DefaultStrategy implements CrawlStrategy {
    private static final Pattern URL_PATTERN = Pattern.compile("https?://[\\w\\-.]+(?:/[\\w\\-./?%&=]*)?");

    @Override
    public boolean supports(String url) {
        return true;
    }

    @Override
    public List<Article> parse(String url, Document doc) throws ParseException {
        List<Article> articles = new ArrayList<>();
        
        String title = doc.title();
        
        String content = "";
        Element contentEl = doc.selectFirst("article, .article, #content, .content, main");
        if (contentEl != null) {
            content = contentEl.text().trim();
        } else {
            content = doc.body().text().trim();
        }
        
        if (content.length() > 200) {
            content = content.substring(0, 200) + "...";
        }
        
        articles.add(new Article(title, url, content));
        
        Elements links = doc.select("a[href]");
        for (Element link : links) {
            String href = link.attr("abs:href");
            String linkText = link.text().trim();
            if (!linkText.isEmpty() && href.matches("https?://.*")) {
                articles.add(new Article(linkText, href, ""));
            }
        }
        
        return articles;
    }

    @Override
    public int getPriority() {
        return Integer.MIN_VALUE;
    }
}