java/w11/CrawlCommand.java

package com.example.datacollect.command;

import com.example.datacollect.exception.CrawlerException;
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;

import java.io.IOException;

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 == null || args.length < 2) {
            logger.warn("Invalid arguments for crawl command");
            view.printError("Usage: crawl <url>");
            return;
        }
        String url = args[1];
        logger.info("Starting crawl for URL: {}", url);

        CrawlStrategy strategy = strategyFactory.getStrategy(url);
        if (strategy == null) {
            logger.warn("No strategy found for URL: {}", url);
            view.printError("No strategy found for: " + url);
            return;
        }
        logger.debug("Using strategy: {} for URL: {}", strategy.getClass().getSimpleName(), url);

        int retryCount = 0;
        while (retryCount < MAX_RETRIES) {
            try {
                view.printInfo("Crawling: " + url + (retryCount > 0 ? " (attempt " + (retryCount + 1) + ")" : ""));
                Document doc = Jsoup.connect(url).get();
                var articles = strategy.parse(url, doc);
                for (var article : articles) {
                    repository.add(article);
                }
                view.printSuccess("Crawled " + articles.size() + " articles.");
                logger.info("Successfully crawled {} articles from URL: {}", articles.size(), url);
                return;
            } catch (IOException e) {
                retryCount++;
                logger.warn("Network error on attempt {} for URL {}: {}", retryCount, url, e.getMessage());
                if (retryCount < MAX_RETRIES) {
                    view.printInfo("Network error, retrying in " + RETRY_DELAY_MS + "ms...");
                    try {
                        Thread.sleep(RETRY_DELAY_MS);
                    } catch (InterruptedException ie) {
                        logger.error("Interrupted during retry delay", ie);
                        Thread.currentThread().interrupt();
                        break;
                    }
                } else {
                    logger.error("Failed to crawl URL {} after {} attempts", url, MAX_RETRIES, e);
                    view.printError("Failed to crawl after " + MAX_RETRIES + " attempts: " + e.getMessage());
                }
            } catch (ParseException e) {
                logger.error("Parse error for URL {}: {}", url, e.getMessage(), e);
                view.printError("Parse error for " + url + ": " + e.getMessage());
                return;
            } catch (Exception e) {
                logger.error("Unexpected error crawling URL {}: {}", url, e.getMessage(), e);
                view.printError("Unexpected error: " + e.getMessage());
                return;
            }
        }
    }
}