java/w10/DefaultStrategy.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 java.util.ArrayList;
import java.util.List;

public class DefaultStrategy implements CrawlStrategy {
    @Override
    public boolean supports(String url) {
        return true;
    }

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

    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();
        Elements headings = doc.select("h1, h2, h3, h4, h5, h6");
        for (Element h : headings) {
            String text = h.text().trim();
            if (!text.isEmpty()) {
                articles.add(new Article(text, url, ""));
            }
        }
        if (articles.isEmpty()) {
            String title = doc.title();
            if (!title.isEmpty()) {
                articles.add(new Article(title, url, ""));
            }
        }
        return articles;
    }
}