mdbq 2.3.5__tar.gz → 2.3.7__tar.gz

{mdbq-2.3.5 → mdbq-2.3.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.3.5
+Version: 2.3.7
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.3.5 → mdbq-2.3.7}/mdbq/aggregation/query_data.py

@@ -1,5 +1,6 @@
 # -*- coding: UTF-8 –*-
 import re
+from unittest.mock import inplace
 
 from mdbq.mongo import mongo
 from mdbq.mysql import mysql
@@ -1003,6 +1004,23 @@ class GroupBy:
             df.insert(loc=1, column='推广渠道', value='万相台无界版')  # df中插入新列
             df['是否品牌词'] = df['词名字/词包名字'].str.contains('万里马|wanlima', regex=True)
             df['是否品牌词'] = df['是否品牌词'].apply(lambda x: '品牌词' if x else '')
+            dir_file = f'\\\\192.168.1.198\\时尚事业部\\01.运营部\\0-电商周报-每周五更新\\分类配置文件.xlsx'
+            dir_file2 = '/Volumes/时尚事业部/01.运营部/0-电商周报-每周五更新/分类配置文件.xlsx'
+            if not os.path.isfile(dir_file):
+                dir_file = dir_file2
+            if os.path.isfile(dir_file):
+                df_fl = pd.read_excel(dir_file, sheet_name='关键词分类', header=0)
+                df_fl.rename(columns={'分类1': '词分类'}, inplace=True)
+                df_fl = df_fl[['关键词', '词分类']]
+                df = pd.merge(df, df_fl, left_on=['词名字/词包名字'], right_on=['关键词'], how='left')
+                df.pop('关键词')
+                df['词分类'].fillna('', inplace=True)
+            if '词分类' in df.columns.tolist():
+                df['词分类'] = df.apply(lambda x: self.ret_keyword(keyword=str(x['词名字/词包名字']), as_file=False) if x['词分类'] == '' else x['词分类'], axis=1)
+            else:
+                df['词分类'] = df['词名字/词包名字'].apply(lambda x: self.ret_keyword(keyword=str(x), as_file=False))
+            # df.to_csv('/Users/xigua/Downloads/test.csv', index=False, header=True, encoding='utf-8_sig')
+            # breakpoint()
             return df
         elif '天猫_超级直播' in table_name:
             df.rename(columns={
@@ -1389,6 +1407,153 @@ class GroupBy:
             print(f'<{table_name}>: Groupby 类尚未配置，数据为空')
             return pd.DataFrame({})
 
+    def ret_keyword(self, keyword, as_file=False):
+        datas = [
+            {
+                '类别': '品牌词',
+                '值': [
+                    '万里马',
+                    'wanlima',
+                    'fion',
+                    '菲安妮',
+                    '迪桑娜',
+                    'dissona',
+                    'hr',
+                    'vh',
+                    'songmont',
+                    'vanessahogan',
+                    'dilaks',
+                    'khdesign',
+                    'peco',
+                    'giimmii',
+                    'cassile',
+                    'grotto',
+                    'why',
+                    'roulis',
+                    'lesschic',
+                    'amazing song',
+                    'mytaste',
+                    'bagtree',
+                    '红谷',
+                    'hongu',
+                ]
+            },
+            {
+                '类别': '智选',
+                '值': [
+                    '智选',
+                ]
+            },
+            {
+                '类别': '年份',
+                '值': [
+                    '20',
+                ]
+            },
+            {
+                '类别': '材质',
+                '值': [
+                    '皮',
+                    '牛仔',
+                    '丹宁',
+                    '帆布',
+                ]
+            },
+            {
+                '类别': '季节',
+                '值': [
+                    '春',
+                    '夏',
+                    '秋',
+                    '冬',
+                ]
+            },
+            {
+                '类别': '款式',
+                '值': [
+                    '水桶',
+                    '托特',
+                    '腋下',
+                    '小方',
+                    '通用款',
+                    '手拿',
+                    '马鞍',
+                    '链条',
+                    '菜篮',
+                    'hobo',
+                    '波士顿',
+                    '凯莉',
+                    '饺子',
+                    '盒子',
+                    '牛角',
+                    '公文',
+                    '月牙',
+                    '单肩',
+                    '枕头',
+                    '斜挎',
+                    '手提',
+                    '手拎',
+                    '拎手',
+                    '斜肩',
+                    '棒球',
+                    '饺包',
+                    '保龄球',
+                    '戴妃',
+                    '半月',
+                    '弯月',
+                    '法棍',
+                    '流浪',
+                    '拎包',
+                    '中式',
+                    '手挽',
+                    '皮带',
+                    '眼镜',
+                    '斜跨',
+                    '律师',
+                    '斜背',
+                ]
+            },
+            {
+                '类别': '品类词',
+                '值': [
+                    '老花',
+                    '包包',
+                    '通勤',
+                    '高级感',
+                    '轻奢',
+                    '包',
+                    '新款',
+                    '小众',
+                    '爆款',
+                    '工作',
+                    '精致',
+                    '奢侈',
+                    '袋',
+                ],
+            },
+        ]
+        if as_file:
+            with open(os.path.join(self.output, f'分类配置.json'), 'w') as f:
+                json.dump(datas, f, ensure_ascii=False, sort_keys=False, indent=4)
+            breakpoint()
+        result = ''
+        res = []
+        is_continue = False
+        for data in datas:
+            for item in data['值']:
+                if item == '20':
+                    pattern = r'\d\d'
+                    res = re.findall(f'{item}{pattern}', str(keyword), re.IGNORECASE)
+                else:
+                    res = re.findall(item, str(keyword), re.IGNORECASE)
+                if res:
+                    result = data['类别']
+                    is_continue = True
+                    break
+            if is_continue:
+                break
+        return result
+
     # @try_except
     def performance(self, bb_tg=True):
          # print(self.data_tgyj)
@@ -1875,6 +2040,6 @@ def main():
 
 
 if __name__ == '__main__':
-    data_aggregation(service_databases=[{'company': 'mysql'}], months=1)  # 正常的聚合所有数据
+    data_aggregation(service_databases=[{'company': 'mysql'}], months=0)  # 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-2.3.5 → mdbq-2.3.7}/mdbq/company/copysh.py

@@ -265,8 +265,13 @@ class TbFiles:
             time.sleep(5)
 
         # 临时加的
-        excel_file = f'\\\\192.168.1.198\\时尚事业部\\01.运营部\\0-电商周报-每周五更新\\WLM 周报-模版V1.xlsx'
-        r.refresh_excel(file=excel_file)
+        # excel_file = f'\\\\192.168.1.198\\时尚事业部\\01.运营部\\0-电商周报-每周五更新\\0-WLM_运营周报-1012输出.xlsx'
+        dir_files = f'\\\\192.168.1.198\\时尚事业部\\01.运营部\\0-电商周报-每周五更新'
+        files = os.listdir(dir_files)
+        for file in files:
+            if file.endswith('.xlsx') and '0-WLM_运营周报' in file and '~' not in file and 'baidu' not in file:
+                excel_file = os.path.join(dir_files, file)
+                r.refresh_excel(file=excel_file)
 
         self.before_max_time = self.check_change()  # 重置值, 避免重复同步