java/w11/CrawlCommand.java

package com.example.datacollect.command;

import com.example.datacollect.exception.CrawlerException;
import com.example.datacollect.model.Article;
import com.example.datacollect.repository.ArticleRepository;
import com.example.datacollect.service.ScraperService;
import com.example.datacollect.strategy.ArticleCrawlStrategy;
import com.example.datacollect.view.ConsoleView;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.List;

public class CrawlCommand implements Command {
    private static final Logger logger = LoggerFactory.getLogger(CrawlCommand.class);
    private final ConsoleView view;
    private final ArticleRepository repository;
    private final ScraperService scraperService;
    private static final int MAX_RETRIES = 3;
    private static final long RETRY_DELAY_MS = 1000;

    public CrawlCommand(ConsoleView view, ArticleRepository repository) {
        this.view = view;
        this.repository = repository;
        this.scraperService = new ScraperService(new ArticleCrawlStrategy(), MAX_RETRIES, RETRY_DELAY_MS);
    }

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

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

        String url = args[1];
        logger.info("Starting crawl for URL: {}", url);
        view.printInfo("Starting to crawl: " + url);

        int attempts = 0;
        boolean success = false;
        CrawlerException lastException = null;

        while (attempts < MAX_RETRIES && !success) {
            attempts++;
            try {
                Article article = scraperService.scrape(url);
                repository.save(article);
                articles.add(article);
                logger.info("Successfully crawled article: {}", article.getTitle());
                view.printSuccess("Successfully crawled: " + article.getTitle());
                success = true;
            } catch (CrawlerException e) {
                lastException = e;
                logger.warn("Attempt {}/{} failed for URL: {}", attempts, MAX_RETRIES, url);
                view.printError("Attempt " + attempts + " failed: " + e.getMessage());
                if (attempts < MAX_RETRIES) {
                    try {
                        Thread.sleep(RETRY_DELAY_MS);
                    } catch (InterruptedException ie) {
                        Thread.currentThread().interrupt();
                        logger.error("Crawl interrupted for URL: {}", url);
                        view.printError("Crawl interrupted");
                        return;
                    }
                }
            }
        }

        if (!success) {
            logger.error("Failed to crawl URL after {} attempts: {}", MAX_RETRIES, url);
            view.printError("Failed to crawl after " + MAX_RETRIES + " attempts");
            if (lastException != null) {
                view.printError("Last error: " + lastException.getMessage());
            }
        }
    }
}