java/w10/RegexStrategy.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;
import java.util.regex.Pattern;

public class RegexStrategy implements CrawlStrategy {
    private final Pattern pattern;
    private final int priority;

    public RegexStrategy(String regex, int priority) {
        this.pattern = Pattern.compile(regex);
        this.priority = priority;
    }

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

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

    @Override
    public List<Article> parse(String url, Document doc) {
        List<Article> articles = new ArrayList<>();
        Elements items = doc.select("a[href]");
        for (Element item : items) {
            String text = item.text();
            if (!text.isEmpty()) {
                String href = item.attr("href");
                String fullUrl = href.startsWith("http") ? href : url + href;
                articles.add(new Article(text, fullUrl, ""));
            }
        }
        return articles;
    }
}