上传文件至 'project/src/main/java/com/example'

3 weeks ago · adca923eef
1 changed files with 375 additions and 0 deletions
--- a/project/src/main/java/com/example/App.java
+++ b/project/src/main/java/com/example/App.java
@ -0,0 +1,375 @@
+package com.example;
+
+import java.util.ArrayList;
+import java.util.List;
+
+/**
+ * 多网站爬虫系统 - 主程序入口
+ * 采用MVC架构，支持命令行参数控制
+ * 课堂知识点：继承、多态、封装、枚举类、命令行参数、命令模式、策略模式、异常体系
+ */
+public class App {
+
+    /**
+     * 爬虫类型枚举 - 课堂知识点：枚举类
+     */
+    public enum CrawlerType {
+        STEAM("Steam游戏爬虫"),
+        MOVIE("豆瓣电影爬虫"),
+        BOOK("豆瓣读书爬虫"),
+        ALL("全部爬虫");
+
+        private final String description;
+
+        CrawlerType(String description) {
+            this.description = description;
+        }
+
+        public String getDescription() {
+            return description;
+        }
+    }
+    
+    /**
+     * 保存策略枚举 - 课堂知识点：枚举类、策略模式
+     */
+    public enum SaveStrategyType {
+        TEXT("文本格式", new TextSaveStrategy()),
+        JSON("JSON格式", new JsonSaveStrategy()),
+        CSV("CSV格式", new CsvSaveStrategy());
+        
+        private final String description;
+        private final SaveStrategy strategy;
+        
+        SaveStrategyType(String description, SaveStrategy strategy) {
+            this.description = description;
+            this.strategy = strategy;
+        }
+        
+        public String getDescription() {
+            return description;
+        }
+        
+        public SaveStrategy getStrategy() {
+            return strategy;
+        }
+    }
+
+    public static void main(String[] args) {
+        System.out.println("========== 多网站爬虫系统启动 ==========\n");
+
+        // 解析命令行参数 - 课堂知识点：命令行参数
+        CrawlerType crawlerType = parseCrawlerType(args);
+        SaveStrategyType strategyType = parseSaveStrategy(args);
+        boolean saveToDb = shouldSaveToDatabase(args);
+        boolean mergeOutput = shouldMergeOutput(args);
+        
+        // 启动时检查网络状态
+        System.out.println("🔍 正在检查网络连接状态...");
+        if (!HttpCrawler.isNetworkAvailable()) {
+            System.err.println("⚠️ 警告：当前网络不可用！");
+            System.err.println("⚠️ 将使用默认数据运行，部分功能可能受限");
+            System.err.println("⚠️ 建议检查网络连接后重新运行");
+            System.out.println();
+        } else {
+            System.out.println("✅ 网络连接正常！");
+            System.out.println();
+        }
+
+        // 如果需要保存到数据库，先初始化数据库
+        if (saveToDb) {
+            System.out.println("📦 正在初始化数据库...");
+            DatabaseManager.getInstance(); // 初始化数据库
+        }
+
+        // 使用命令模式执行爬虫
+        executeWithCommandPattern(crawlerType, strategyType, saveToDb, mergeOutput);
+
+        // 如果使用了数据库，关闭连接
+        if (saveToDb) {
+            DatabaseManager.getInstance().close();
+        }
+
+        // 打印精美分隔线
+        printDivider();
+        System.out.println("🎉 所有爬虫执行完毕！");
+        printDivider();
+        
+        System.out.println("\n� 执行报告");
+        System.out.println("─────────────────────────────────────────────────────");
+        System.out.printf("  %-12s %s%n", "网络状态:", HttpCrawler.isNetworkAvailable() ? "✅ 正常" : "❌ 不可用");
+        System.out.printf("  %-12s %s%n", "爬虫类型:", crawlerType.getDescription());
+        System.out.printf("  %-12s %s%n", "保存策略:", strategyType.getDescription());
+        System.out.printf("  %-12s %s%n", "数据来源:", HttpCrawler.isNetworkAvailable() ? "实时爬取" : "默认缓存");
+        System.out.printf("  %-12s %s%n", "数据库:", saveToDb ? "✅ 已保存" : "❌ 未启用");
+        System.out.printf("  %-12s %s%n", "合并输出:", mergeOutput ? "✅ 已启用" : "❌ 未启用");
+        System.out.println("─────────────────────────────────────────────────────");
+        System.out.println("\n💡 提示：如需获取最新数据，请确保网络连接后重新运行");
+        printDivider();
+    }
+    
+    /**
+     * 打印精美分隔线
+     */
+    private static void printDivider() {
+        System.out.println("\n╔═══════════════════════════════════════════════════╗");
+    }
+
+    /**
+     * 解析爬虫类型参数
+     * @param args 命令行参数数组
+     * @return 爬虫类型枚举
+     */
+    private static CrawlerType parseCrawlerType(String[] args) {
+        if (args.length == 0) {
+            return CrawlerType.ALL;
+        }
+
+        String arg = args[0].toLowerCase();
+        switch (arg) {
+            case "-steam":
+            case "-s":
+                return CrawlerType.STEAM;
+            case "-movie":
+            case "-m":
+                return CrawlerType.MOVIE;
+            case "-book":
+            case "-b":
+                return CrawlerType.BOOK;
+            case "-all":
+            case "-a":
+                return CrawlerType.ALL;
+            case "-h":
+            case "--help":
+                printUsage();
+                System.exit(0);
+                return CrawlerType.ALL;
+            default:
+                System.out.println("❌ 未知参数: " + arg);
+                printUsage();
+                System.exit(1);
+                return CrawlerType.ALL;
+        }
+    }
+    
+    /**
+     * 解析保存策略参数
+     * @param args 命令行参数数组
+     * @return 保存策略枚举
+     */
+    private static SaveStrategyType parseSaveStrategy(String[] args) {
+        for (String arg : args) {
+            switch (arg.toLowerCase()) {
+                case "-text":
+                case "-t":
+                    return SaveStrategyType.TEXT;
+                case "-json":
+                case "-j":
+                    return SaveStrategyType.JSON;
+                case "-csv":
+                case "-c":
+                    return SaveStrategyType.CSV;
+            }
+        }
+        return SaveStrategyType.TEXT; // 默认文本格式
+    }
+
+    /**
+     * 判断是否需要保存到数据库
+     * @param args 命令行参数数组
+     * @return 是否保存到数据库
+     */
+    private static boolean shouldSaveToDatabase(String[] args) {
+        for (String arg : args) {
+            if ("-db".equalsIgnoreCase(arg) || "--database".equalsIgnoreCase(arg)) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    /**
+     * 打印使用说明
+     */
+    private static void printUsage() {
+        System.out.println("\n📖 使用方法:");
+        System.out.println("  java App [爬虫类型] [保存策略] [可选参数]");
+        System.out.println("\n爬虫类型:");
+        System.out.println("  -steam, -s    Steam游戏爬虫");
+        System.out.println("  -movie, -m    豆瓣电影爬虫");
+        System.out.println("  -book, -b     豆瓣读书爬虫");
+        System.out.println("  -all, -a      所有爬虫（默认）");
+        System.out.println("\n保存策略:");
+        System.out.println("  -text, -t     文本格式（默认）");
+        System.out.println("  -json, -j     JSON格式");
+        System.out.println("  -csv, -c      CSV格式");
+        System.out.println("\n可选参数:");
+        System.out.println("  -db, --database     保存数据到SQLite数据库");
+        System.out.println("  -merge              将所有数据合并保存到一个文件");
+        System.out.println("\n示例:");
+        System.out.println("  java App -movie -json    # 爬取电影并保存为JSON格式");
+        System.out.println("  java App -book -csv      # 爬取书籍并保存为CSV格式");
+        System.out.println("  java App -all -db        # 爬取所有数据并保存到数据库");
+        System.out.println("  java App -all -merge     # 爬取所有数据合并保存到一个文件");
+        System.out.println("  java App -all -json -merge # 合并保存为JSON格式");
+    }
+
+    /**
+     * 判断是否需要合并输出到一个文件
+     * @param args 命令行参数数组
+     * @return 是否合并输出
+     */
+    private static boolean shouldMergeOutput(String[] args) {
+        for (String arg : args) {
+            if ("-merge".equalsIgnoreCase(arg) || "--merge-output".equalsIgnoreCase(arg)) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    /**
+     * 使用命令模式执行爬虫 - 课堂知识点：命令模式、策略模式、异常体系、数据库持久化
+     */
+    private static void executeWithCommandPattern(CrawlerType crawlerType, SaveStrategyType strategyType, boolean saveToDb, boolean mergeOutput) {
+        // 创建命令调用器
+        CommandInvoker invoker = new CommandInvoker();
+        
+        // 创建爬虫列表
+        List<Crawler> crawlers = new ArrayList<>();
+        switch (crawlerType) {
+            case STEAM:
+                crawlers.add(new SteamCrawler());
+                break;
+            case MOVIE:
+                crawlers.add(new DoubanMovieCrawler());
+                break;
+            case BOOK:
+                crawlers.add(new DoubanBookCrawler());
+                break;
+            case ALL:
+                crawlers.add(new SteamCrawler());
+                crawlers.add(new DoubanMovieCrawler());
+                crawlers.add(new DoubanBookCrawler());
+                break;
+        }
+        
+        // 如果合并输出，收集所有数据
+        List<Object> allData = new ArrayList<>();
+        
+        // 为每个爬虫创建命令并执行
+        int index = 1;
+        for (Crawler crawler : crawlers) {
+            String filename = mergeOutput ? "merged_output" : getFilename(crawler, strategyType);
+            
+            // 创建命令（命令模式）
+            Command command = new CrawlerCommand(crawler, filename);
+            
+            try {
+                // 执行命令
+                invoker.execute(command);
+                
+                // 收集数据用于合并
+                if (mergeOutput) {
+                    if (crawler instanceof SteamCrawler) {
+                        SteamCrawler sc = (SteamCrawler) crawler;
+                        allData.add("=== Steam游戏 ===");
+                        allData.add(sc);
+                    } else if (crawler instanceof DoubanMovieCrawler) {
+                        DoubanMovieCrawler mc = (DoubanMovieCrawler) crawler;
+                        allData.add("=== 豆瓣电影 ===");
+                        allData.addAll(mc.getMovies());
+                    } else if (crawler instanceof DoubanBookCrawler) {
+                        DoubanBookCrawler bc = (DoubanBookCrawler) crawler;
+                        allData.add("=== 豆瓣书籍 ===");
+                        allData.addAll(bc.getBooks());
+                    }
+                }
+                
+                // 如果需要保存到数据库
+                if (saveToDb) {
+                    crawler.saveToDatabase();
+                }
+                
+                if (index < crawlers.size()) {
+                    System.out.println();
+                }
+            } catch (CrawlerException e) {
+                System.err.println("❌ 命令执行失败: " + e.getMessage());
+                if (e.getCause() != null) {
+                    e.getCause().printStackTrace();
+                }
+            }
+            index++;
+        }
+        
+        // 如果合并输出，保存到一个文件
+        if (mergeOutput && !allData.isEmpty()) {
+            saveMergedData(allData, strategyType);
+        }
+        
+        // 显示命令历史
+        invoker.showHistory();
+    }
+    
+    /**
+     * 将所有数据合并保存到一个文件（保存到桌面）
+     * @param data 所有爬虫数据
+     * @param strategyType 保存策略
+     */
+    private static void saveMergedData(List<Object> data, SaveStrategyType strategyType) {
+        // 获取桌面路径
+        String desktopPath = System.getProperty("user.home") + "\\Desktop";
+        String extension = strategyType == SaveStrategyType.JSON ? "json" : 
+                          strategyType == SaveStrategyType.CSV ? "csv" : "txt";
+        String filename = desktopPath + "\\crawler_merged_" + System.currentTimeMillis() + "." + extension;
+        
+        try {
+            SaveStrategy strategy = strategyType.getStrategy();
+            strategy.save(data, filename);
+            System.out.println("\n📥 已将所有数据合并保存到桌面文件:");
+            System.out.println("   " + filename);
+        } catch (Exception e) {
+            System.err.println("❌ 合并保存失败: " + e.getMessage());
+        }
+    }
+    
+    /**
+     * 根据爬虫类型和策略获取文件名
+     */
+    private static String getFilename(Crawler crawler, SaveStrategyType strategyType) {
+        String baseName;
+        if (crawler instanceof SteamCrawler) {
+            baseName = "steam_game_info";
+        } else if (crawler instanceof DoubanMovieCrawler) {
+            baseName = "douban_movies";
+        } else if (crawler instanceof DoubanBookCrawler) {
+            baseName = "douban_books";
+        } else {
+            baseName = "crawler_output";
+        }
+        
+        String extension;
+        switch (strategyType) {
+            case JSON:
+                extension = ".json";
+                break;
+            case CSV:
+                extension = ".csv";
+                break;
+            case TEXT:
+            default:
+                extension = ".txt";
+                break;
+        }
+        
+        return baseName + extension;
+    }
+    
+    /**
+     * 简单加法方法 - 演示方法定义
+     */
+    public int add(int a, int b) {
+        return a + b;
+    }
+}