mdbq 2.0.2__tar.gz → 2.0.4__tar.gz

{mdbq-2.0.2 → mdbq-2.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.0.2
+Version: 2.0.4
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.0.2 → mdbq-2.0.4}/mdbq/aggregation/aggregation.py

@@ -320,6 +320,14 @@ class DatabaseUpdate:
                     )
                     df['日期'] = df['数据周期'].apply(lambda x: re.findall('(.*) ~', x)[0])
                     check_remove_file = True
+                elif name.endswith('.csv') and '分天数据-计划_活动类型-推广概览-数据汇总' in name:
+                    df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
+                    df['日期'].replace(to_replace=['\\t'], value='', regex=True, inplace=True)
+                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                    # min_clm = str(df['日期'].min()).split(' ')[0]
+                    # max_clm = str(df['日期'].max()).split(' ')[0]
+                    # new_name = f'淘宝联盟_分天数据_计划_活动类型_推广概览_数据汇总_{min_clm}_{max_clm}'
+                    check_remove_file = True
                 elif name.endswith('.csv') and 'baobei' in name:
                     # 生意经宝贝指标日数据
                     date = re.findall(r's-(\d{4})(\d{2})(\d{2})\.', str(name))
@@ -1244,7 +1252,7 @@ def test2():
 if __name__ == '__main__':
     username, password, host, port = get_myconf.select_config_values(target_service='nas', database='mysql')
     print(username, password, host, port)
-    file_dir(one_file=False, target_service='home_lx')
+    file_dir(one_file=False, target_service='company')
     # one_file_to_mysql(
     #     file='/Users/xigua/数据中心/原始文件2/京东报表/JD推广_全站营销报表/2024-08/万里马箱包推广1_营销概况_全站营销_2024-08-19_2024-09-02.csv',
     #     db_name='京东数据2',
@@ -1269,8 +1277,8 @@ if __name__ == '__main__':
     # dp.new_unzip(is_move=True)
     # dp.cleaning(is_move=False)  # 清洗数据, 存入 self.datas, 不需要立即移除文件，仍保留文件到原始文件中
     # # 将 self.datas 更新至数据库
-    # dp.upload_df(service_databases=[
-    #     # {'home_lx': 'mongodb'},
-    #     {'company': 'mysql'},
-    #     # {'nas': 'mysql'},
-    # ])
+    # # dp.upload_df(service_databases=[
+    # #     # {'home_lx': 'mongodb'},
+    # #     {'company': 'mysql'},
+    # #     # {'nas': 'mysql'},
+    # # ])

{mdbq-2.0.2 → mdbq-2.0.4}/mdbq/aggregation/query_data.py

@@ -1535,7 +1535,7 @@ def main():
 
 
 if __name__ == '__main__':
-    data_aggregation(service_databases=[{'home_lx': 'mysql'}], months=24)  # 正常的聚合所有数据
+    data_aggregation(service_databases=[{'company': 'mysql'}], months=7)  # 正常的聚合所有数据
     # data_aggregation_one(service_databases=[{'company': 'mysql'}], months=1)  # 单独聚合某一个数据库，具体库进函数编辑
     # optimize_data.op_data(service_databases=[{'company': 'mysql'}], days=3650)  # 立即启动对聚合数据的清理工作
 

{mdbq-2.0.2 → mdbq-2.0.4}/mdbq/clean/data_clean.py

@@ -272,11 +272,14 @@ class DataClean:
                             df.insert(loc=0, column='数据周期', value=data_lis)
                         df.insert(loc=0, column='日期', value=date01[0])
                         # 2024-2-19 官方更新了推广渠道来源名称
+                        # df['三级来源'] = df['三级来源'].apply(
+                        #     lambda x: '精准人群推广' if x == '精准人群推广(原引力魔方)'
+                        #     else '关键词推广' if x == '关键词推广(原直通车)'
+                        #     else '智能场景' if x == '智能场景(原万相台)'
+                        #     else x
+                        # )
                         df['三级来源'] = df['三级来源'].apply(
-                            lambda x: '精准人群推广' if x == '精准人群推广(原引力魔方)'
-                            else '关键词推广' if x == '关键词推广(原直通车)'
-                            else '智能场景' if x == '智能场景(原万相台)'
-                            else x
+                            lambda x: re.sub('(.*)', '', str(x) if x else x)
                         )
                         # df = df[df['访客数'] != '0']
                         df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
@@ -474,6 +477,15 @@ class DataClean:
                         new_name = re.sub(r' ?(\(\d+\))', '',new_name)
                         self.save_to_csv(df, root, new_name)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
                         os.remove(os.path.join(root, name))
+                    elif name.endswith('.csv') and '分天数据-计划_活动类型-推广概览-数据汇总' in name:
+                        df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
+                        df['日期'].replace(to_replace=['\\t'], value='', regex=True, inplace=True)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        min_clm = str(df['日期'].min()).split(' ')[0]
+                        max_clm = str(df['日期'].max()).split(' ')[0]
+                        new_name = f'淘宝联盟_分天数据_计划_活动类型_推广概览_数据汇总_{min_clm}_{max_clm}'
+                        self.save_to_csv(df, root, new_name)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                        os.remove(os.path.join(root, name))
                     elif name.endswith('.csv') and 'baobei' in name:
                         # 生意经宝贝指标日数据
                         # print(name)
@@ -1121,7 +1133,7 @@ class DataClean:
                         bib(t_path)
                     elif '_新版' in name:
                         t_path = str(pathlib.Path(self.source_path, '生意参谋/流量来源'))
-                        bib(t_path)
+                        bib(t_path, _as_month=True)
                     else:
                         t_path = str(pathlib.Path(self.source_path, '生意参谋/流量来源_旧版'))
                         bib(t_path, _as_month=True)
@@ -1143,6 +1155,9 @@ class DataClean:
                 elif name.endswith('.csv') and '参谋店铺流量来源（月）' in name:
                     t_path = str(pathlib.Path(self.source_path, '月数据/流量来源-自助取数-月数据'))
                     bib(t_path, _as_month=True)
+                elif name.endswith('.csv') and '淘宝联盟_分天数据_计划_活动类型_推广概览_数据汇总' in name:
+                    t_path = str(pathlib.Path(self.source_path, '月数据/淘宝联盟'))
+                    bib(t_path, _as_month=False)
                 elif name.endswith('.csv') and '竞店分析' in name and '来源分析-入店来源' in name:
                     t_path = str(pathlib.Path(self.source_path, '市场数据/竞店分析/来源分析/入店来源'))
                     bib(t_path, _as_month=False)

{mdbq-2.0.2 → mdbq-2.0.4}/mdbq/config/products.py

@@ -20,6 +20,9 @@ class Products:
 
     def update_my_datas(self):
         my_datas = [
+            {
+                '平台': '天猫', '商品id': '840499705810', '上市年份': '2024年10月'
+            },
             {
                 '平台': '天猫', '商品id': '830789689032', '上市年份': '2024年9月'
             },

{mdbq-2.0.2 → mdbq-2.0.4}/mdbq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.0.2
+Version: 2.0.4
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.0.2 → mdbq-2.0.4}/setup.py

@@ -3,7 +3,7 @@
 from setuptools import setup, find_packages
 
 setup(name='mdbq',
-      version='2.0.2',
+      version='2.0.4',
       author='xigua, ',
       author_email="2587125111@qq.com",
       url='https://pypi.org/project/mdbsql',