删除 'w11/CrawlCommand.java.java'

w11/CrawlCommand.java.java

@@ -1,98 +0,0 @@
-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;
-
-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.length < 2) {
-            view.printError("Usage: crawl <url>");
-            return;
-        }
-        String url = args[1];
-        logger.info("Crawl command received for URL: {}", url);
-
-        CrawlStrategy strategy = strategyFactory.getStrategy(url);
-        if (strategy == null) {
-            view.printError("No strategy found for: " + url);
-            logger.warn("No strategy found for URL: {}", url);
-            return;
-        }
-
-        for (int attempt = 1; attempt <= MAX_RETRIES; attempt++) {
-            try {
-                view.printInfo("Crawling: " + url + " (attempt " + attempt + "/" + MAX_RETRIES + ")");
-                logger.debug("Attempt {} to crawl {}", attempt, url);
-
-                Document doc = Jsoup.connect(url)
-                        .userAgent("Mozilla/5.0")
-                        .timeout(10000)
-                        .get();
-
-                var articles = strategy.parse(url, doc);
-
-                for (var article : articles) {
-                    repository.add(article);
-                    logger.debug("Added article: {}", article.getTitle());
-                }
-
-                view.printSuccess("Crawled " + articles.size() + " articles.");
-                logger.info("Successfully crawled {} articles from {}", articles.size(), url);
-                return; // 成功，退出重试循环
-
-            } catch (ParseException e) {
-                logger.error("Parse error for URL {}: {}", url, e.getMessage(), e);
-                view.printError("Failed to parse: " + e.getMessage());
-                return; // 解析错误不重试，直接退出
-
-            } catch (IOException e) {
-                logger.warn("Network error for URL {} (attempt {}/{}): {}", url, attempt, MAX_RETRIES, e.getMessage());
-
-                if (attempt == MAX_RETRIES) {
-                    view.printError("Failed to crawl after " + MAX_RETRIES + " attempts: " + e.getMessage());
-                } else {
-                    view.printWarning("Network error, retrying in " + RETRY_DELAY_MS + "ms...");
-                    try {
-                        Thread.sleep(RETRY_DELAY_MS);
-                    } catch (InterruptedException ie) {
-                        Thread.currentThread().interrupt();
-                        view.printError("Retry interrupted");
-                        return;
-                    }
-                }
-            } catch (Exception e) {
-                logger.error("Unexpected error crawling {}: {}", url, e.getMessage(), e);
-                view.printError("Unexpected error: " + e.getMessage());
-                return;
-            }
-        }
-    }
-}