init

3_handle.py

@@ -23,7 +23,7 @@ class Handler:
                              source_type: Optional[str], 
                              source_channel: Optional[str]) -> Tuple[str, Tuple]:
         """构建查询条件和参数"""
-        conditions = ["formatted_content is not null", "multimodal_recognition is null"]
+        conditions = ["multimodal_recognition is not null", "structured_data is null"]
         params = []
         
         if query_word is not None:
@@ -50,7 +50,7 @@ class Handler:
             # 构建查询条件和参数
             where_clause, params = self.build_query_conditions(query_word, source_type, source_channel)
             sql = f"""
-                SELECT id, formatted_content 
+                SELECT id, multimodal_recognition 
                 FROM knowledge_search_content 
                 WHERE {where_clause}
             """
@@ -65,26 +65,31 @@ class Handler:
                 try:
                     # 处理内容
                     result = self.processor.process(row[1], self.system_prompt)
-                    
+
+                    print(result)
+
                     # 更新数据库
                     update_sql = """
                         UPDATE knowledge_search_content 
-                        SET multimodal_recognition = %s 
+                        SET structured_data = %s 
                         WHERE id = %s
                     """
-                    MysqlHelper.update_values(update_sql, (result, row[0]))
-                    
-                    # 添加延迟避免API限制
-                    time.sleep(1)
+
+                    affected_rows = MysqlHelper.update_values(update_sql, (result, row[0]))
+
+
                     total_success += 1
+
+                    # 添加延迟避免API限制
+                    time.sleep(5)
                     
                 except Exception as e:
                     print(f"处理记录 {row[0]} 失败: {str(e)}")
+                finally:
+                    print(f"处理完成！总数据量 {len(records)}，已处理 {total_processed} ，成功 {total_success} ")
                     
         except Exception as e:
             print(f"处理过程中发生错误: {str(e)}")
-        finally:
-            print(f"处理完成！总共处理 {total_processed} 条记录，成功 {total_success} 条")
 
 
 def main():

README.md

@@ -5,3 +5,22 @@ source myenv/bin/activate
 pip install -r requirements.txt
 
 
+
+
+# 执行命令
+
+## 1 抓取
+```
+
+```
+
+## 2 图文、视频识别
+```
+
+```
+
+## 3 文档化
+```
+python 3_handle.py
+```
+