mdbq 1.7.1__tar.gz → 1.7.2__tar.gz

{mdbq-1.7.1 → mdbq-1.7.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 1.7.1
+Version: 1.7.2
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-1.7.1 → mdbq-1.7.2}/mdbq/aggregation/aggregation.py

@@ -530,6 +530,17 @@ class DatabaseUpdate:
                     df.drop("'当前时间'", axis=1, inplace=True)
                     df.rename(columns={'全站ROI': '全站roi'}, inplace=True)
                     df.insert(loc=1, column='产品线', value='全站营销')
+                elif name.endswith('.csv') and '关键词点击成交报表_pbix同步_勿删改' in name:
+                    df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
+                    for col in df.columns.tolist():
+                        if '（' in col:
+                            new_col = re.sub('[（）]', '_', col)
+                            new_col = new_col.strip('_')
+                            df.rename(columns={col: new_col}, inplace=True)
+                    df['日期'] = df['日期'].apply(lambda x: f'{str(x)[:4]}-{str(x)[4:6]}-{str(x)[6:8]}')
+                    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]
 
                 # 商品素材，必须保持放在最后处理
                 elif name.endswith('xlsx'):
@@ -960,7 +971,9 @@ def upload_dir(path, db_name, collection_name, dbs={'mysql': True, 'mongodb': Tr
                         d.df_to_mongo(df=df, db_name=db_name, collection_name=collection_name)
                     if dbs['mysql']:  # drop_duplicates: 值为 True 时检查重复数据再插入
                         m.df_to_mysql(df=df, db_name=db_name, table_name=collection_name,
-                                      drop_duplicates=True, filename=name, count=f'{i}/{count}')
+                                      df_sql = True,
+                                      drop_duplicates=False,
+                                      filename=name, count=f'{i}/{count}')
                         # nas.df_to_mysql(df=df, db_name=db_name, table_name=collection_name, drop_duplicates=True,)
                 except Exception as e:
                     print(name, e)
@@ -1068,11 +1081,13 @@ if __name__ == '__main__':
     #     target_service='company',
     #     database='mysql'
     # )
-    db_name = '市场数据2'
-    table_name = '类目洞察_属性分析_商品发现'
+
+    db_name = '京东数据2'
+    table_name = '推广数据_关键词报表'
     upload_dir(
-        path='/Users/xigua/Downloads/类目洞察/属性分析/商品发现',
+        path='/Users/xigua/数据中心/原始文件2/京东报表/JD推广_关键词报表',
         db_name=db_name,
         collection_name=table_name,
-        dbs={'mysql': False, 'mongodb': False},
+        dbs={'mysql': True, 'mongodb': False},
     )
+

{mdbq-1.7.1 → mdbq-1.7.2}/mdbq/clean/data_clean.py

@@ -683,6 +683,20 @@ class DataClean:
                         m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='万相台_人群洞察')
 
                 # ----------------------- 京东数据处理分界线 -----------------------
+                elif name.endswith('.csv') and '关键词点击成交报表_pbix同步_勿删改' in name:
+                    df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
+                    for col in df.columns.tolist():
+                        if '（' in col:
+                            new_col = re.sub('[（）]', '_', col)
+                            new_col = new_col.strip('_')
+                            df.rename(columns={col: new_col}, inplace=True)
+                    df['日期'] = df['日期'].apply(lambda x: f'{str(x)[:4]}-{str(x)[4:6]}-{str(x)[6:8]}')
+                    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'京东推广关键词点击成交报表_{min_clm}_{max_clm}.csv'
+                    self.save_to_csv(df, root, new_name)
+                    os.remove(os.path.join(root, name))
                 elif name.endswith('.csv') and '营销概况_全站营销' in name:
                     df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=1, na_filter=False)
                     df = df[(df['日期'] != '日期') & (df['日期'] != '汇总') & (df['日期'] != '0') & (df['花费'] != '0') & (df['花费'] != '0.00')]
@@ -1199,6 +1213,9 @@ class DataClean:
                 elif name.endswith('.csv') and '营销概况_全站营销' in name:
                     t_path = str(pathlib.Path(self.source_path, '京东报表/JD推广_全站营销报表'))
                     bib(t_path, _as_month=True)
+                elif name.endswith('.csv') and '京东推广关键词点击成交报表' in name:
+                    t_path = str(pathlib.Path(self.source_path, '京东报表/JD推广_关键词报表'))
+                    bib(t_path, _as_month=True)
                 #  京东分界线   ------- 结束标记
 
     def attribute(self, path=None, _str='商品素材导出', ):

{mdbq-1.7.1 → mdbq-1.7.2}/mdbq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 1.7.1
+Version: 1.7.2
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-1.7.1 → mdbq-1.7.2}/setup.py

@@ -3,7 +3,7 @@
 from setuptools import setup, find_packages
 
 setup(name='mdbq',
-      version='1.7.1',
+      version='1.7.2',
       author='xigua, ',
       author_email="2587125111@qq.com",
       url='https://pypi.org/project/mdbsql',