Merge pull request #784 from NanmiCoder/feature/excel-export-and-tests

feat: excel store with other platform

Author: NanmiCoder

.DS_Store

@@ -228,14 +228,15 @@ python main.py --help
 
 ### 使用示例：
 ```shell
-# 使用 Excel 存储数据（推荐用于数据分析）✨ 新功能
-uv run main.py --platform xhs --lt qrcode --type search --save_data_option excel
-
-# 初始化 SQLite 数据库（使用'--init_db'时不需要携带其他optional）
+# 初始化 SQLite 数据库
 uv run main.py --init_db sqlite
-# 使用 SQLite 存储数据（推荐个人用户使用）
+# 使用 SQLite 存储数据
 uv run main.py --platform xhs --lt qrcode --type search --save_data_option sqlite
+
+# 使用 Excel 存储数据（推荐用于数据分析）
+uv run main.py --platform xhs --lt qrcode --type search --save_data_option excel
 ```
+
 ```shell
 # 初始化 MySQL 数据库
 uv run main.py --init_db mysql

README.md

@@ -71,6 +71,8 @@ class SaveDataOptionEnum(str, Enum):
     DB = "db"
     JSON = "json"
     SQLITE = "sqlite"
+    MONGODB = "mongodb"
+    EXCEL = "excel"
 
 
 class InitDbOptionEnum(str, Enum):
@@ -199,7 +201,7 @@ def main(
             SaveDataOptionEnum,
             typer.Option(
                 "--save_data_option",
-                help="数据保存方式 (csv=CSV文件 | db=MySQL数据库 | json=JSON文件 | sqlite=SQLite数据库)",
+                help="数据保存方式 (csv=CSV文件 | db=MySQL数据库 | json=JSON文件 | sqlite=SQLite数据库 | mongodb=MongoDB数据库 | excel=Excel文件)",
                 rich_help_panel="存储配置",
             ),
         ] = _coerce_enum(

cmd_arg/arg.py

@@ -87,14 +87,11 @@ async def main():
     # Flush Excel data if using Excel export
     if config.SAVE_DATA_OPTION == "excel":
         try:
-            # Get the store instance and flush data
-            from store.xhs import XhsStoreFactory
-            store = XhsStoreFactory.create_store()
-            if hasattr(store, 'flush'):
-                store.flush()
-                print(f"[Main] Excel file saved successfully")
+            from store.excel_store_base import ExcelStoreBase
+            ExcelStoreBase.flush_all()
+            print("[Main] Excel files saved successfully")
         except Exception as e:
-            print(f"Error flushing Excel data: {e}")
+            print(f"[Main] Error flushing Excel data: {e}")
 
     # Generate wordcloud after crawling is complete
     # Only for JSON save mode

main.py

@@ -38,13 +38,14 @@ class BiliStoreFactory:
         "json": BiliJsonStoreImplement,
         "sqlite": BiliSqliteStoreImplement,
         "mongodb": BiliMongoStoreImplement,
+        "excel": BiliExcelStoreImplement,
     }
 
     @staticmethod
     def create_store() -> AbstractStore:
         store_class = BiliStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
         if not store_class:
-            raise ValueError("[BiliStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or mongodb ...")
+            raise ValueError("[BiliStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or mongodb or excel ...")
         return store_class()
 
 

store/bilibili/__init__.py

@@ -365,3 +365,14 @@ async def store_creator(self, creator_item: Dict):
             data=creator_item
         )
         utils.logger.info(f"[BiliMongoStoreImplement.store_creator] Saved creator {user_id} to MongoDB")
+
+
+class BiliExcelStoreImplement:
+    """B站Excel存储实现 - 全局单例"""
+
+    def __new__(cls, *args, **kwargs):
+        from store.excel_store_base import ExcelStoreBase
+        return ExcelStoreBase.get_instance(
+            platform="bilibili",
+            crawler_type=crawler_type_var.get()
+        )

store/bilibili/_store_impl.py

@@ -37,13 +37,14 @@ class DouyinStoreFactory:
         "json": DouyinJsonStoreImplement,
         "sqlite": DouyinSqliteStoreImplement,
         "mongodb": DouyinMongoStoreImplement,
+        "excel": DouyinExcelStoreImplement,
     }
 
     @staticmethod
     def create_store() -> AbstractStore:
         store_class = DouyinStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
         if not store_class:
-            raise ValueError("[DouyinStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or mongodb ...")
+            raise ValueError("[DouyinStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or mongodb or excel ...")
         return store_class()
 
 

store/douyin/__init__.py

@@ -264,3 +264,14 @@ async def store_creator(self, creator_item: Dict):
             data=creator_item
         )
         utils.logger.info(f"[DouyinMongoStoreImplement.store_creator] Saved creator {user_id} to MongoDB")
+
+
+class DouyinExcelStoreImplement:
+    """抖音Excel存储实现 - 全局单例"""
+
+    def __new__(cls, *args, **kwargs):
+        from store.excel_store_base import ExcelStoreBase
+        return ExcelStoreBase.get_instance(
+            platform="douyin",
+            crawler_type=crawler_type_var.get()
+        )