package com.example.datacollect.command; import com.example.datacollect.exception.NetworkException; import com.example.datacollect.exception.ParseException; 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; import org.slf4j.Logger; import org.slf4j.LoggerFactory; public class CrawlCommand implements Command { private static final Logger logger = LoggerFactory.getLogger(CrawlCommand.class); private static final int MAX_RETRIES = 3; private static final long RETRY_DELAY_MS = 1000; 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 "); return; } String url = args[1]; CrawlStrategy strategy = strategyFactory.getStrategy(url); if (strategy == null) { view.printError("No strategy found for: " + url); return; } int retryCount = 0; while (retryCount < MAX_RETRIES) { try { view.printInfo("Crawling: " + url + (retryCount > 0 ? " (retry " + retryCount + ")" : "")); logger.info("Crawling URL: {} (attempt {})", url, retryCount + 1); Document doc = Jsoup.connect(url) .timeout(10000) .get(); var articles = strategy.parse(url, doc); for (var article : articles) { repository.add(article); } logger.info("Successfully crawled {} articles from {}", articles.size(), url); view.printSuccess("Crawled " + articles.size() + " articles."); return; } catch (NetworkException e) { retryCount++; logger.warn("Network error on attempt {} for {}: {}", retryCount, url, e.getMessage()); if (retryCount >= MAX_RETRIES) { view.printError("Failed to crawl after " + MAX_RETRIES + " retries: " + e.getMessage()); return; } try { Thread.sleep(RETRY_DELAY_MS); } catch (InterruptedException ie) { Thread.currentThread().interrupt(); view.printError("Retry interrupted: " + ie.getMessage()); return; } } catch (ParseException e) { logger.error("Parse error for {}: {}", url, e.getMessage()); view.printError("Parse error: " + e.getMessage()); return; } catch (Exception e) { if (e.getMessage() != null && e.getMessage().contains("timeout")) { retryCount++; logger.warn("Timeout on attempt {} for {}: {}", retryCount, url, e.getMessage()); if (retryCount >= MAX_RETRIES) { view.printError("Failed to crawl after " + MAX_RETRIES + " retries: " + e.getMessage()); return; } try { Thread.sleep(RETRY_DELAY_MS); } catch (InterruptedException ie) { Thread.currentThread().interrupt(); view.printError("Retry interrupted: " + ie.getMessage()); return; } } else { logger.error("Unexpected error crawling {}: {}", url, e.getMessage()); view.printError("Failed to crawl: " + e.getMessage()); return; } } } } }