w11-张思渊-202401070104

w11/CrawlCommand.java

@@ -0,0 +1,81 @@
+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 <url>");
+            return;
+        }
+        String url = args[1];
+        logger.info("Crawl started for: {}", url);
+
+        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 + ")" : ""));
+                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.");
+                return;
+            } catch (ParseException e) {
+                logger.severe("Parse error for " + url + ": " + e.getMessage());
+                view.printError("Parse error: " + e.getMessage());
+                return;
+            } catch (Exception e) {
+                retryCount++;
+                if (retryCount > MAX_RETRIES) {
+                    logger.severe("Failed to crawl " + url + " after " + MAX_RETRIES + " retries: " + e.getMessage());
+                    view.printError("Failed to crawl after " + MAX_RETRIES + " retries: " + e.getMessage());
+                    return;
+                }
+                logger.warning("Network error for " + url + " (attempt " + retryCount + "/" + MAX_RETRIES + "): " + e.getMessage());
+                try {
+                    Thread.sleep(RETRY_DELAY_MS);
+                } catch (InterruptedException ie) {
+                    Thread.currentThread().interrupt();
+                    logger.severe("Retry interrupted: " + ie.getMessage());
+                    view.printError("Crawl interrupted");
+                    return;
+                }
+            }
+        }
+    }
+}