更新今日的数据内容以及更新readme的内容

product/integrated_product_system.py

@@ -732,7 +732,7 @@ class IntegratedProductSystem:
                 logger.info("数据库连接已关闭")
     
     def analyze_follower_counts(self):
-        """分析并更新产品的关注数"""
+        """分析并更新产品的关注数，仅当follows字段为空或不存在时更新"""
         logger.info("=== 开始分析产品关注数 ===")
         
         conn = None
@@ -741,12 +741,14 @@ class IntegratedProductSystem:
             conn = self.connect_to_database()
             cursor = conn.cursor()
             
-            # 查询所有产品及其对应的分析记录
+            # 查询所有产品及其对应的分析记录，仅包括follows字段为空或不存在的记录
             cursor.execute("""
-                SELECT p.id, p.name, p.user_count, pa.id as analysis_id
+                SELECT p.id, p.name, p.user_count, pa.id as analysis_id, pa.follows
                 FROM products p
                 LEFT JOIN product_analysis pa ON p.name = pa.original_name
                 WHERE p.user_count IS NOT NULL AND p.user_count != ''
+                AND pa.id IS NOT NULL
+                AND (pa.follows IS NULL OR pa.follows = '')
             """)
             
             products = cursor.fetchall()
@@ -758,7 +760,7 @@ class IntegratedProductSystem:
             
             # 为每个产品转换user_count并更新到product_analysis.follows
             updated_count = 0
-            for i, (product_id, name, user_count, analysis_id) in enumerate(products, 1):
+            for i, (product_id, name, user_count, analysis_id, current_follows) in enumerate(products, 1):
                 logger.info(f"处理产品关注数 {i}/{len(products)}: {name}, 用户数: {user_count}")
                 
                 if not analysis_id:
@@ -893,8 +895,90 @@ class IntegratedProductSystem:
                 conn.close()
                 logger.info("数据库连接已关闭")
     
+    def fill_missing_product_links(self):
+        """检查product_analysis表中的product_link字段是否为空，如果为空则从tophub_data.db补全"""
+        logger.info("=== 开始补全缺失的product_link字段 ===")
+        
+        # 检查tophub_data.db是否存在
+        tophub_db_path = os.path.join(os.path.dirname(os.path.dirname(__file__)), "tophub_data.db")
+        if not os.path.exists(tophub_db_path):
+            logger.error(f"tophub_data.db不存在: {tophub_db_path}")
+            return
+        
+        conn_product = None
+        conn_tophub = None
+        try:
+            # 连接两个数据库
+            conn_product = self.connect_to_database()
+            cursor_product = conn_product.cursor()
+            
+            conn_tophub = sqlite3.connect(tophub_db_path)
+            cursor_tophub = conn_tophub.cursor()
+            logger.success(f"成功连接到tophub_data.db: {tophub_db_path}")
+            
+            # 查询product_link为空的记录
+            cursor_product.execute("""
+                SELECT id, original_name
+                FROM product_analysis
+                WHERE product_link IS NULL OR product_link = ''
+            """)
+            
+            missing_link_records = cursor_product.fetchall()
+            logger.info(f"找到 {len(missing_link_records)} 条product_link为空的记录需要补全")
+            
+            if not missing_link_records:
+                logger.info("没有发现需要补全product_link的记录")
+                return
+            
+            # 获取tophub_data.db中的所有producthunt链接
+            cursor_tophub.execute("SELECT url FROM articles WHERE url LIKE '%producthunt.com%'")
+            tophub_urls = [row[0] for row in cursor_tophub.fetchall()]
+            logger.info(f"从tophub_data.db获取到 {len(tophub_urls)} 个producthunt链接")
+            
+            if not tophub_urls:
+                logger.error("从tophub_data.db中没有找到producthunt链接")
+                return
+            
+            # 为每个缺失product_link的记录查找匹配的URL
+            updated_count = 0
+            for i, (analysis_id, original_name) in enumerate(missing_link_records, 1):
+                logger.info(f"处理记录 {i}/{len(missing_link_records)}: {original_name}")
+                
+                # 查找匹配的URL
+                matched_url = None
+                for url in tophub_urls:
+                    # 简单的匹配逻辑：如果产品名称在URL中出现
+                    if original_name.lower() in url.lower():
+                        matched_url = url
+                        break
+                
+                if matched_url:
+                    # 更新product_link字段
+                    cursor_product.execute("""
+                        UPDATE product_analysis 
+                        SET product_link = ? 
+                        WHERE id = ?
+                    """, (matched_url, analysis_id))
+                    conn_product.commit()
+                    updated_count += 1
+                    logger.success(f"成功为产品 '{original_name}' 补全链接: {matched_url}")
+                else:
+                    logger.warning(f"无法为产品 '{original_name}' 找到匹配的链接")
+            
+            logger.success(f"product_link补全完成! 成功更新 {updated_count} 条记录")
+            
+        except Exception as e:
+            logger.error(f"补全product_link过程中出错: {e}")
+        finally:
+            # 关闭数据库连接
+            if conn_product:
+                conn_product.close()
+            if conn_tophub:
+                conn_tophub.close()
+            logger.info("数据库连接已关闭")
+    
     async def run_full_workflow_async(self, max_products=None, analyze_only=False):
-        """异步运行完整工作流程：抓取+分析+补充缺失分数+更新关注数+重新分析无效难度评分"""
+        """异步运行完整工作流程：抓取+分析+补充缺失分数+更新关注数+重新分析无效难度评分+补全product_link"""
         logger.info("=== 开始全功能产品系统工作流程 ===")
         
         # 初始化数据库
@@ -923,6 +1007,10 @@ class IntegratedProductSystem:
         logger.info("步骤5: 开始重新分析invalid难度评分...")
         self.reanalyze_invalid_difficulty_scores()
         
+        # 步骤6: 补全缺失的product_link字段
+        logger.info("步骤6: 开始补全缺失的product_link字段...")
+        self.fill_missing_product_links()
+        
         logger.success("=== 全功能产品系统工作流程完成 ===")
     
     def run_full_workflow(self, max_products=None, analyze_only=False):