今日更新数据

product/integrated_product_system.py

@@ -794,8 +794,107 @@ class IntegratedProductSystem:
                 conn.close()
                 logger.info("数据库连接已关闭")
     
+    def reanalyze_invalid_difficulty_scores(self):
+        """重新分析difficulty_score为1的行，确保难度评分准确"""
+        logger.info("=== 开始重新分析无效难度评分 ===")
+        
+        conn = None
+        try:
+            # 连接数据库
+            conn = self.connect_to_database()
+            cursor = conn.cursor()
+            
+            # 查询difficulty_score为1的记录
+            cursor.execute("""
+                SELECT id, original_name, product_intro, development_difficulty, ai_response
+                FROM product_analysis
+                WHERE difficulty_score = 1
+            """)
+            
+            invalid_records = cursor.fetchall()
+            logger.info(f"找到 {len(invalid_records)} 条difficulty_score为1的记录需要重新分析")
+            
+            if not invalid_records:
+                logger.info("没有发现需要重新分析的无效难度评分记录")
+                return
+            
+            # 为每个无效记录重新分析难度
+            updated_count = 0
+            for i, (analysis_id, name, introduction, development_difficulty, ai_response) in enumerate(invalid_records, 1):
+                logger.info(f"重新分析记录 {i}/{len(invalid_records)}: {name}")
+                
+                # 调用AI API重新分析产品难度
+                logger.info(f"重新调用Ollama API分析产品难度: {name}")
+                
+                # 构建请求数据 - 使用Ollama API格式，专门用于难度分析
+                prompt = f"这个是【{name}】，简介内容是【{introduction}】。请重新分析这个产品的开发难度，特别是对于一个人加上AI辅助能否开发这个产品，请详细回答。返回的内容是产品名称/产品简介/开发难度。返回的例子一：notion/这个是笔记产品等等/一个人开发难度较高"
+                
+                data = {
+                    "model": "qwen3:8b",
+                    "prompt": prompt,
+                    "stream": False
+                }
+                
+                headers = {
+                    "Content-Type": "application/json"
+                }
+                
+                try:
+                    # 调用Ollama API
+                    response = requests.post(
+                        self.api_url,
+                        headers=headers,
+                        data=json.dumps(data, ensure_ascii=False),
+                        timeout=60
+                    )
+                    
+                    if response.status_code == 200:
+                        result = response.json()
+                        new_ai_response = result.get("response", "").strip()
+                        logger.success(f"成功重新分析产品 '{name}'")
+                        
+                        # 解析新的响应，获取难度分数
+                        _, new_difficulty, new_difficulty_score = self.parse_ai_response(new_ai_response)
+                        
+                        # 特别处理很难的情况，确保分数在70-90之间
+                        difficulty_lower = new_difficulty.lower()
+                        if any(keyword in difficulty_lower for keyword in ['高', '很难', '非常难', '复杂', '困难']):
+                            if new_difficulty_score < 70:
+                                new_difficulty_score = max(70, min(90, new_difficulty_score + 60))
+                                logger.info(f"调整很难产品的难度分数为: {new_difficulty_score} (70-90区间)")
+                        
+                        # 更新数据库记录
+                        cursor.execute("""
+                            UPDATE product_analysis 
+                            SET development_difficulty = ?, 
+                                difficulty_score = ?, 
+                                ai_response = ?
+                            WHERE id = ?
+                        """, (new_difficulty, new_difficulty_score, new_ai_response, analysis_id))
+                        
+                        conn.commit()
+                        updated_count += 1
+                        logger.success(f"成功更新产品 '{name}' 的难度分数为 {new_difficulty_score}")
+                    else:
+                        logger.error(f"API调用失败: {response.status_code}, {response.text}")
+                except Exception as e:
+                    logger.error(f"重新分析产品 '{name}' 失败: {e}")
+                
+                # 避免API调用过于频繁
+                if i < len(invalid_records):
+                    time.sleep(2)
+            
+            logger.success(f"无效难度评分重新分析完成! 成功更新 {updated_count} 条记录")
+            
+        except Exception as e:
+            logger.error(f"重新分析无效难度评分过程中出错: {e}")
+        finally:
+            if conn:
+                conn.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"""
+        """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"""
         logger.info("=== 开始全功能产品系统工作流程 ===")
         
         # 初始化数据库
@@ -820,6 +919,10 @@ class IntegratedProductSystem:
         logger.info("步骤4: 开始分析并更新产品关注数...")
         self.analyze_follower_counts()
         
+        # 步骤5: 重新分析invalid难度评分
+        logger.info("步骤5: 开始重新分析invalid难度评分...")
+        self.reanalyze_invalid_difficulty_scores()
+        
         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):