java/project/CrawlCommand.java

package com.example.datacollect.command;

import com.example.datacollect.repository.ArticleRepository;
import com.example.datacollect.strategy.CrawlStrategy;
import com.example.datacollect.strategy.StrategyFactory;
import com.example.datacollect.view.ConsoleView;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

public class CrawlCommand implements Command {
    private final ConsoleView view;
    private final StrategyFactory strategyFactory;

    public CrawlCommand(ConsoleView view, StrategyFactory strategyFactory) {
        this.view = view;
        this.strategyFactory = strategyFactory;
    }

    @Override
    public String getName() {
        return "crawl";
    }

    @Override
    public void execute(String[] args, ArticleRepository repository) {
        if (args.length < 2) {
            view.printError("Usage: crawl <url>");
            return;
        }
        String url = args[1];

        CrawlStrategy strategy = strategyFactory.getStrategy(url);
        if (strategy == null) {
            view.printError("No strategy found for: " + url);
            return;
        }

        try {
            view.printInfo("Crawling: " + url);
            Document doc = Jsoup.connect(url)
                    .timeout(10000)
                    .userAgent("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36")
                    .get();
            var articles = strategy.parse(url, doc);
            for (var article : articles) {
                repository.add(article);
            }
            view.printSuccess("Crawled " + articles.size() + " articles.");
        } catch (Exception e) {
            view.printError("Failed to crawl: " + e.getMessage());
        }
    }
}