mdbq 1.9.0__py3-none-any.whl → 1.9.2__py3-none-any.whl

mdbq/clean/data_clean.py

@@ -86,943 +86,967 @@ class DataClean:
             for name in files:
                 if '~$' in name or '.DS' in name or '.localized' in name or '.jpg' in name or '.png' in name:
                     continue
-                encoding = self.get_encoding(file_path=pathlib.Path(root, name))
-                # ----------------- 推广报表 分割线 -----------------
-                tg_names = ['营销场景报表', '计划报表', '单元报表', '关键词报表', '人群报表', '主体报表',
-                            '其他主体报表',
-                            '创意报表', '地域报表', '权益报表']
-                for tg_name in tg_names:
-                    if tg_name in name and '汇总' not in name and name.endswith('.csv'):  # 人群报表排除达摩盘报表： 人群报表汇总
-                        pattern = re.findall(r'(.*_)\d{8}_\d{6}', name)
-                        if not pattern:  # 说明已经转换过
+
+                try:
+                    encoding = self.get_encoding(file_path=pathlib.Path(root, name))
+                    # ----------------- 推广报表 分割线 -----------------
+                    tg_names = ['营销场景报表', '计划报表', '单元报表', '关键词报表', '人群报表', '主体报表',
+                                '其他主体报表',
+                                '创意报表', '地域报表', '权益报表']
+                    for tg_name in tg_names:
+                        if tg_name in name and '汇总' not in name and name.endswith('.csv'):  # 人群报表排除达摩盘报表： 人群报表汇总
+                            pattern = re.findall(r'(.*_)\d{8}_\d{6}', name)
+                            if not pattern:  # 说明已经转换过
+                                continue
+                            shop_name = re.findall(r'\d{8}_\d{6}_(.*)\W', name)
+                            if shop_name:
+                                shop_name = shop_name[0]
+                            else:
+                                shop_name = ''
+                            df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
+                            if '地域' not in name:  # 除了地域报表, 检查数据的字段是否包含“场景名字”,如果没有,说明没有选“pbix” 数据模块下载
+                                ck = df.columns.tolist()
+                                if '场景名字' not in ck:
+                                    print(f'{name} 报表字段缺失, 请选择Pbix数据模板下载')
+                                    continue
+                            if len(df) == 0:
+                                print(f'{name} 报表是空的, 请重新下载, 此报表已移除')
+                                os.remove(os.path.join(root, name))
+                                continue
+
+                            df.replace(to_replace=['\\N'], value=0, regex=False, inplace=True)  # 替换掉特殊字符
+                            df.fillna(0, inplace=True)
+                            col_ids = ['场景ID', '计划ID', '单元ID', '主体ID', '宝贝ID', '词ID/词包ID', '创意ID']
+                            sb = df.columns.tolist()
+                            if '日期' not in sb:
+                                print(f'{name} 注意：该报表不包含分日数据，数据不会保存，请重新下载！')
+                                continue
+                            if '省' in sb:
+                                if '市' not in sb:
+                                    print(
+                                        f'{name} 注意：请下载市级地域报表，而不是省报表，数据不会保存，请重新下载！')
+                                    continue
+                            for col_id in col_ids:
+                                if col_id in sb:
+                                    df[col_id] = df[col_id].apply(
+                                        lambda x: f'="{x}"' if x and '=' not in str(x) else x
+                                    )
+                            date_min = f'_{df["日期"].values.min()}_'
+                            date_max = f'{df["日期"].values.max()}.csv'
+                            if '万里马' in name:
+                                tm_s_name = pattern[0] + shop_name + date_min + date_max
+                                new_root_p = pathlib.Path(self.source_path, '推广报表', tg_name)  # 文件夹，未包括文件名
+                                df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                                if '省' in df.columns.tolist() and '场景名字' in df.columns.tolist() and '完整' in name:
+                                    new_root_p = pathlib.Path(self.source_path, '推广报表', f'完整_{tg_name}')
+                                    tm_s_name = f'完整_{tm_s_name}'
+                                self.save_to_csv(df, new_root_p, tm_s_name)
+                                if self.set_up_to_mogo:
+                                    d.df_to_mongo(df=df, db_name='天猫数据1', collection_name=f'天猫_推广_{tg_name}')
+                                if self.set_up_to_mysql:
+                                    m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name=f'天猫_推广_{tg_name}')
+                                os.remove(os.path.join(root, name))
+                            else:
+                                print(f'{name} 文件名不含"万里马", 不属于爬虫下载，您可以手动进行分类，但不会上传数据库')
+
+                    if name.endswith('.csv') and '超级直播' in name:
+                        # 超级直播
+                        df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
                             continue
+                        pattern = re.findall(r'(.*_)\d{8}_\d{6}', name)
                         shop_name = re.findall(r'\d{8}_\d{6}_(.*)\W', name)
                         if shop_name:
                             shop_name = shop_name[0]
                         else:
                             shop_name = ''
-                        df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
-                        if '地域' not in name:  # 除了地域报表, 检查数据的字段是否包含“场景名字”,如果没有,说明没有选“pbix” 数据模块下载
-                            ck = df.columns.tolist()
-                            if '场景名字' not in ck:
-                                print(f'{name} 报表字段缺失, 请选择Pbix数据模板下载')
-                                continue
-                        if len(df) == 0:
-                            print(f'{name} 报表是空的, 请重新下载, 此报表已移除')
-                            os.remove(os.path.join(root, name))
-                            continue
-
+                        cols = ['场景ID', '计划ID']
+                        for col in cols:
+                            df[col] = df[col].apply(lambda x: f'="{x}"' if x and '=' not in str(x) else x)
                         df.replace(to_replace=['\\N'], value=0, regex=False, inplace=True)  # 替换掉特殊字符
-                        df.fillna(0, inplace=True)
-                        col_ids = ['场景ID', '计划ID', '单元ID', '主体ID', '宝贝ID', '词ID/词包ID', '创意ID']
-                        sb = df.columns.tolist()
-                        if '日期' not in sb:
-                            print(f'{name} 注意：该报表不包含分日数据，数据不会保存，请重新下载！')
-                            continue
-                        if '省' in sb:
-                            if '市' not in sb:
-                                print(
-                                    f'{name} 注意：请下载市级地域报表，而不是省报表，数据不会保存，请重新下载！')
-                                continue
-                        for col_id in col_ids:
-                            if col_id in sb:
-                                df[col_id] = df[col_id].apply(
-                                    lambda x: f'="{x}"' if x and '=' not in str(x) else x
-                                )
-                        date_min = f'_{df["日期"].values.min()}_'
+                        root_new = pathlib.Path(self.source_path, '推广报表', '超级直播')
+                        date_min = f'_{df["日期"].values.min()}_'  # 仅适用于日期列未转换之前, 还是整数，转换后不能用这个函数
                         date_max = f'{df["日期"].values.max()}.csv'
-                        if '万里马' in name:
-                            tm_s_name = pattern[0] + shop_name + date_min + date_max
-                            new_root_p = pathlib.Path(self.source_path, '推广报表', tg_name)  # 文件夹，未包括文件名
-                            df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                            if '省' in df.columns.tolist() and '场景名字' in df.columns.tolist() and '完整' in name:
-                                new_root_p = pathlib.Path(self.source_path, '推广报表', f'完整_{tg_name}')
-                                tm_s_name = f'完整_{tm_s_name}'
-                            self.save_to_csv(df, new_root_p, tm_s_name)
-                            if self.set_up_to_mogo:
-                                d.df_to_mongo(df=df, db_name='天猫数据1', collection_name=f'天猫_推广_{tg_name}')
-                            if self.set_up_to_mysql:
-                                m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name=f'天猫_推广_{tg_name}')
-                            os.remove(os.path.join(root, name))
-                        else:
-                            print(f'{name} 文件名不含"万里马", 不属于爬虫下载，您可以手动进行分类，但不会上传数据库')
-
-                if name.endswith('.csv') and '超级直播' in name:
-                    # 超级直播
-                    df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
-                        os.remove(os.path.join(root, name))
-                        continue
-                    pattern = re.findall(r'(.*_)\d{8}_\d{6}', name)
-                    shop_name = re.findall(r'\d{8}_\d{6}_(.*)\W', name)
-                    if shop_name:
-                        shop_name = shop_name[0]
-                    else:
-                        shop_name = ''
-                    cols = ['场景ID', '计划ID']
-                    for col in cols:
-                        df[col] = df[col].apply(lambda x: f'="{x}"' if x and '=' not in str(x) else x)
-                    df.replace(to_replace=['\\N'], value=0, regex=False, inplace=True)  # 替换掉特殊字符
-                    root_new = pathlib.Path(self.source_path, '推广报表', '超级直播')
-                    date_min = f'_{df["日期"].values.min()}_'  # 仅适用于日期列未转换之前, 还是整数，转换后不能用这个函数
-                    date_max = f'{df["日期"].values.max()}.csv'
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    new_name = pattern[0] + shop_name + date_min + date_max
-                    self.save_to_csv(df, root_new, new_name)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_超级直播')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_超级直播')
-                    os.remove(os.path.join(root, name))
-                elif name.endswith('.xls') and '短直联投' in name:
-                    # 短直联投
-                    df = pd.read_excel(os.path.join(root, name), sheet_name=None, header=0)
-                    df = pd.concat(df)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        new_name = pattern[0] + shop_name + date_min + date_max
+                        self.save_to_csv(df, root_new, new_name)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_超级直播')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_超级直播')
                         os.remove(os.path.join(root, name))
-                        continue
-                    new_name2 = os.path.splitext(name)[0] + '.csv'
-                    df['订单Id'] = df['订单Id'].apply(
-                        lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
-                    )
-                    root_new = pathlib.Path(self.source_path, '推广报表/短直联投')
-                    self.save_to_csv(df, root_new, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_短直联投')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_短直联投')
-                    os.remove(os.path.join(root, name))
-                elif name.endswith('.xls') and '视频加速推广' in name:
-                    # 超级短视频
-                    df = pd.read_excel(os.path.join(root, name), sheet_name=None, header=0)
-                    df = pd.concat(df)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '短直联投' in name:
+                        # 短直联投
+                        df = pd.read_excel(os.path.join(root, name), sheet_name=None, header=0)
+                        df = pd.concat(df)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        new_name2 = os.path.splitext(name)[0] + '.csv'
+                        df['订单Id'] = df['订单Id'].apply(
+                            lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
+                        )
+                        root_new = pathlib.Path(self.source_path, '推广报表/短直联投')
+                        self.save_to_csv(df, root_new, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_短直联投')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_短直联投')
                         os.remove(os.path.join(root, name))
-                        continue
-                    new_name2 = os.path.splitext(name)[0] + '.csv'
-                    df['计划ID'] = df['计划ID'].apply(
-                        lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
-                    )
-                    df['视频id'] = df['视频id'].apply(
-                        lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
-                    )
-                    root_new = pathlib.Path(self.source_path, '推广报表/超级短视频')
-                    self.save_to_csv(df, root_new, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_超级短视频')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_超级短视频')
-                    os.remove(os.path.join(root, name))
-                if '人群报表汇总' in name:
-                    df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=1, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '视频加速推广' in name:
+                        # 超级短视频
+                        df = pd.read_excel(os.path.join(root, name), sheet_name=None, header=0)
+                        df = pd.concat(df)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        new_name2 = os.path.splitext(name)[0] + '.csv'
+                        df['计划ID'] = df['计划ID'].apply(
+                            lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
+                        )
+                        df['视频id'] = df['视频id'].apply(
+                            lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
+                        )
+                        root_new = pathlib.Path(self.source_path, '推广报表/超级短视频')
+                        self.save_to_csv(df, root_new, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_超级短视频')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_超级短视频')
                         os.remove(os.path.join(root, name))
-                        continue
-                    min_clm = df.min()['日期']
-                    max_clm = df.max()['日期']
-                    new_name = '{}{}{}'.format(min_clm, '_', max_clm)
-                    df['点击率'] = df['点击率'].apply(lambda x: format(x, '.2%') if x > 0 else '')  # 格式化成百分比
-                    df['UV点击率'] = df['UV点击率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
-                    df['收藏加购率'] = df['收藏加购率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
-                    df['UV收藏加购率'] = df['UV收藏加购率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
-                    df['点击转化率'] = df['点击转化率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
-                    df['UV点击转化率'] = df['UV点击转化率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
-                    df.replace(to_replace=[0], value='', regex=False, inplace=True)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    df.to_csv(os.path.join(self.path, 'DMP报表_' + new_name + '.csv'), encoding='utf-8_sig',
-                              index=False, header=True)
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_达摩盘_DMP报表',)
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_达摩盘_DMP报表')
-                    os.remove(os.path.join(root, name))
-                # ----------------- 推广报表 分割线 -----------------
-                # ----------------- 推广报表 分割线 -----------------
-
-                date01 = re.findall(r'(\d{4}-\d{2}-\d{2})_\d{4}-\d{2}-\d{2}', str(name))
-                date02 = re.findall(r'\d{4}-\d{2}-\d{2}_(\d{4}-\d{2}-\d{2})', str(name))
-                if name.endswith('.xls') and '生意参谋' in name and '无线店铺流量来源' in name:
-                    # 无线店铺流量来源
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    df = pd.read_excel(os.path.join(root, name), header=5)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    if '人群报表汇总' in name:
+                        df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=1, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        min_clm = df.min()['日期']
+                        max_clm = df.max()['日期']
+                        new_name = '{}{}{}'.format(min_clm, '_', max_clm)
+                        df['点击率'] = df['点击率'].apply(lambda x: format(x, '.2%') if x > 0 else '')  # 格式化成百分比
+                        df['UV点击率'] = df['UV点击率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
+                        df['收藏加购率'] = df['收藏加购率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
+                        df['UV收藏加购率'] = df['UV收藏加购率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
+                        df['点击转化率'] = df['点击转化率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
+                        df['UV点击转化率'] = df['UV点击转化率'].apply(lambda x: format(x, '.2%') if x > 0 else '')
+                        df.replace(to_replace=[0], value='', regex=False, inplace=True)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        df.to_csv(os.path.join(self.path, 'DMP报表_' + new_name + '.csv'), encoding='utf-8_sig',
+                                  index=False, header=True)
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_达摩盘_DMP报表',)
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_达摩盘_DMP报表')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.replace(to_replace=['-'], value='', regex=False, inplace=True)
-                    if date01[0] != date02[0]:
-                        data_lis = date01[0] + '_' + date02[0]
-                        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 = df[df['访客数'] != '0']
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    for col in df.columns.tolist():
-                        df[col] = df[col].apply(lambda x: 0 if not x else 0 if x == '' else x)
-                    if '经营优势' in df['一级来源'].tolist():  # 新版流量
-                        new_name = re.sub(r'\s?\(.*\)', '', new_name)  # 删除小括号
-                        new_name = os.path.splitext(new_name)[0] + '_新版.csv'
+                    # ----------------- 推广报表 分割线 -----------------
+                    # ----------------- 推广报表 分割线 -----------------
 
-                    self.save_to_csv(df, root, new_name)  # 因为 mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
-                    if '经营优势' in df['一级来源'].tolist():  # 新版流量
-                        if '数据周期' in df.columns.tolist():
-                            if self.set_up_to_mogo:
-                                d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_月数据')
-                            if self.set_up_to_mysql:
-                                m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_月数据')
-                        else:
-                            if self.set_up_to_mogo:
-                                d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_日数据')
-                            if self.set_up_to_mysql:
-                                m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_日数据')
-                    else:  # 旧版流量
-                        if '数据周期' in df.columns.tolist():
-                            if self.set_up_to_mogo:
-                                d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_月数据_旧版')
-                            if self.set_up_to_mysql:
-                                m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_月数据_旧版')
-                        else:
-                            if self.set_up_to_mogo:
-                                d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_日数据_旧版')
-                            if self.set_up_to_mysql:
-                                m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_日数据_旧版')
-                    os.remove(os.path.join(root, name))
-
-                elif name.endswith('.xls') and '生意参谋' in name and '无线店铺三级流量来源详情' in name:
-                    # 店铺来源，手淘搜索，关键词
-                    pattern = re.findall(r'(\d{4}-\d{2}-\d{2})_(\d{4}-\d{2}-\d{2})', name)
-                    df = pd.read_excel(os.path.join(root, name), header=5)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
-                        continue
-                    df.replace(to_replace=[','], value='', regex=True, inplace=True)
-                    df.insert(loc=0, column='日期', value=pattern[0][1])
-                    df.rename(columns={
-                        '来源名称': '关键词',
-                        '收藏商品-支付买家数': '收藏商品_支付买家数',
-                        '加购商品-支付买家数': '加购商品_支付买家数',
-                    }, inplace=True)
-                    if pattern[0][0] != pattern[0][1]:
-                        data_lis = pattern[0][0] + '_' + pattern[0][1]
-                        df.insert(loc=1, column='数据周期', value=data_lis)
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    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))
+                    date01 = re.findall(r'(\d{4}-\d{2}-\d{2})_\d{4}-\d{2}-\d{2}', str(name))
+                    date02 = re.findall(r'\d{4}-\d{2}-\d{2}_(\d{4}-\d{2}-\d{2})', str(name))
+                    if name.endswith('.xls') and '生意参谋' in name and '无线店铺流量来源' in name:
+                        # 无线店铺流量来源
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        df = pd.read_excel(os.path.join(root, name), header=5)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.replace(to_replace=['-'], value='', regex=False, inplace=True)
+                        if date01[0] != date02[0]:
+                            data_lis = date01[0] + '_' + date02[0]
+                            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 = df[df['访客数'] != '0']
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        for col in df.columns.tolist():
+                            df[col] = df[col].apply(lambda x: 0 if not x else 0 if x == '' else x)
+                        if '经营优势' in df['一级来源'].tolist():  # 新版流量
+                            new_name = re.sub(r'\s?\(.*\)', '', new_name)  # 删除小括号
+                            new_name = os.path.splitext(new_name)[0] + '_新版.csv'
 
-                elif name.endswith('.xls') and '生意参谋' in name and '商品_全部' in name:
-                    # 店铺商品排行
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    df = pd.read_excel(os.path.join(root, name), header=4)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                        self.save_to_csv(df, root, new_name)  # 因为 mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                        if '经营优势' in df['一级来源'].tolist():  # 新版流量
+                            if '数据周期' in df.columns.tolist():
+                                if self.set_up_to_mogo:
+                                    d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_月数据')
+                                if self.set_up_to_mysql:
+                                    m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_月数据')
+                            else:
+                                if self.set_up_to_mogo:
+                                    d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_日数据')
+                                if self.set_up_to_mysql:
+                                    m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_日数据')
+                        else:  # 旧版流量
+                            if '数据周期' in df.columns.tolist():
+                                if self.set_up_to_mogo:
+                                    d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_月数据_旧版')
+                                if self.set_up_to_mysql:
+                                    m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_月数据_旧版')
+                            else:
+                                if self.set_up_to_mogo:
+                                    d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_店铺来源_日数据_旧版')
+                                if self.set_up_to_mysql:
+                                    m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_店铺来源_日数据_旧版')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.replace(to_replace=['-'], value='', regex=False, inplace=True)
-                    df['商品ID'] = df['商品ID'].apply(
-                        lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
-                    )
-                    df['货号'] = df['货号'].apply(
-                        lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
-                    )
-                    df.rename(columns={'统计日期': '日期', '商品ID': '商品id'}, inplace=True)
-                    if date01[0] != date02[0]:
-                        data_lis = date01[0] + '_' + date02[0]
-                        df.insert(loc=1, column='数据周期', value=data_lis)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_商品排行')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_商品排行')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xls') and '参谋店铺整体日报' in name:
-                    # 自助取数，店铺日报
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    df = pd.read_excel(os.path.join(root, name), header=7)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '生意参谋' in name and '无线店铺三级流量来源详情' in name:
+                        # 店铺来源，手淘搜索，关键词
+                        pattern = re.findall(r'(\d{4}-\d{2}-\d{2})_(\d{4}-\d{2}-\d{2})', name)
+                        df = pd.read_excel(os.path.join(root, name), header=5)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            continue
+                        df.replace(to_replace=[','], value='', regex=True, inplace=True)
+                        df.insert(loc=0, column='日期', value=pattern[0][1])
+                        df.rename(columns={
+                            '来源名称': '关键词',
+                            '收藏商品-支付买家数': '收藏商品_支付买家数',
+                            '加购商品-支付买家数': '加购商品_支付买家数',
+                        }, inplace=True)
+                        if pattern[0][0] != pattern[0][1]:
+                            data_lis = pattern[0][0] + '_' + pattern[0][1]
+                            df.insert(loc=1, column='数据周期', value=data_lis)
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        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))
-                        continue
-                    df.rename(columns={'统计日期': '日期'}, inplace=True)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df,db_name='生意参谋2', collection_name='生意参谋_自助取数_整体日报')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_整体日报')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xls') and '参谋每日流量_自助取数_新版' in name:
-                    # 自助取数，每日流量
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    df = pd.read_excel(os.path.join(root, name), header=7)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '生意参谋' in name and '商品_全部' in name:
+                        # 店铺商品排行
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        df = pd.read_excel(os.path.join(root, name), header=4)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.replace(to_replace=['-'], value='', regex=False, inplace=True)
+                        df['商品ID'] = df['商品ID'].apply(
+                            lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
+                        )
+                        df['货号'] = df['货号'].apply(
+                            lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
+                        )
+                        df.rename(columns={'统计日期': '日期', '商品ID': '商品id'}, inplace=True)
+                        if date01[0] != date02[0]:
+                            data_lis = date01[0] + '_' + date02[0]
+                            df.insert(loc=1, column='数据周期', value=data_lis)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_商品排行')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_商品排行')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.rename(columns={'统计日期': '日期'}, inplace=True)
-                    # 2024-2-19 官方更新了推广渠道来源名称，自助取数没有更新，这里强制更改
-                    df['三级来源'] = df['三级来源'].apply(
-                        lambda x: '精准人群推广' if x == '引力魔方'
-                        else '关键词推广' if x == '直通车'
-                        else '智能场景' if x == '万相台'
-                        else '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['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_自助取数_每日流量')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_每日流量')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xls') and '商品sku' in name:
-                    # 自助取数，商品sku
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    df = pd.read_excel(os.path.join(root, name), header=7)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '参谋店铺整体日报' in name:
+                        # 自助取数，店铺日报
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        df = pd.read_excel(os.path.join(root, name), header=7)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.rename(columns={'统计日期': '日期'}, inplace=True)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df,db_name='生意参谋2', collection_name='生意参谋_自助取数_整体日报')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_整体日报')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.rename(columns={
-                        '统计日期': '日期',
-                        '商品ID': '商品id',
-                        'SKU ID': 'sku id',
-                        '商品SKU': '商品sku',
-                    }, inplace=True)
-                    for _i in ['商品id', 'sku id']:
-                        df[_i] = df[_i].astype(str).apply(lambda x: f'="{x}"')
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_自助取数_商品sku')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_商品sku')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xls') and '参谋店铺流量来源（月）' in name:
-                    # 自助取数，月店铺流量来源
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    df = pd.read_excel(os.path.join(root, name), header=7)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '参谋每日流量_自助取数_新版' in name:
+                        # 自助取数，每日流量
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        df = pd.read_excel(os.path.join(root, name), header=7)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.rename(columns={'统计日期': '日期'}, inplace=True)
+                        # 2024-2-19 官方更新了推广渠道来源名称，自助取数没有更新，这里强制更改
+                        df['三级来源'] = df['三级来源'].apply(
+                            lambda x: '精准人群推广' if x == '引力魔方'
+                            else '关键词推广' if x == '直通车'
+                            else '智能场景' if x == '万相台'
+                            else '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['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_自助取数_每日流量')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_每日流量')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.rename(columns={'统计日期': '数据周期'}, inplace=True)
-                    # 2024-2-19 官方更新了推广渠道来源名称，自助取数没有更新，这里强制更改
-                    df['三级来源'] = df['三级来源'].apply(
-                        lambda x: '精准人群推广' if x == '引力魔方'
-                        else '关键词推广' if x == '直通车'
-                        else '智能场景' if x == '万相台'
-                        else '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['日期'] = df['数据周期'].apply(lambda x: re.findall('(.*) ~', x)[0])
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_自助取数_店铺流量_月数据')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_店铺流量_月数据')
-                    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)
-                    date = re.findall(r's-(\d{4})(\d{2})(\d{2})\.', str(name))
-                    if not date:  # 阻止月数据及已转换的表格
-                        print(f'{name}  不支持或是已转换的表格')
-                        os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
-                        continue
-                    df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '商品sku' in name:
+                        # 自助取数，商品sku
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        df = pd.read_excel(os.path.join(root, name), header=7)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.rename(columns={
+                            '统计日期': '日期',
+                            '商品ID': '商品id',
+                            'SKU ID': 'sku id',
+                            '商品SKU': '商品sku',
+                        }, inplace=True)
+                        for _i in ['商品id', 'sku id']:
+                            df[_i] = df[_i].astype(str).apply(lambda x: f'="{x}"')
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_自助取数_商品sku')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_商品sku')
                         os.remove(os.path.join(root, name))
-                        continue
-                    if '日期' in df.columns.tolist():
-                        df.pop('日期')
-                    new_date = '-'.join(date[0])
-                    df.insert(loc=0, column='日期', value=new_date)
-                    df.replace(to_replace=['--'], value='', regex=False, inplace=True)
-                    df['宝贝ID'] = df['宝贝ID'].apply(
-                        lambda x: f'="{x}"' if x and '=' not in str(x) else x
-                    )
-                    df['商家编码'] = df['商家编码'].apply(
-                        lambda x: f'="{x}"' if x and '=' not in str(x) else x
-                    )
-                    name_st = re.findall(r'(.*)\d{4}\d{2}\d{2}\.', str(name))  # baobeitrans-
-                    new_name = f'{name_st[0]}{new_date}.csv'
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_宝贝指标')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_宝贝指标')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.csv') and '店铺销售指标' in name:
-                    # 生意经, 店铺指标，仅限月数据，实际日指标也可以
-                    name_st = re.findall(r'(.*)\(分日', name)
-                    if not name_st:
-                        print(f'{name}  已转换的表格')
-                        continue
-                    df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '参谋店铺流量来源（月）' in name:
+                        # 自助取数，月店铺流量来源
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        df = pd.read_excel(os.path.join(root, name), header=7)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.rename(columns={'统计日期': '数据周期'}, inplace=True)
+                        # 2024-2-19 官方更新了推广渠道来源名称，自助取数没有更新，这里强制更改
+                        df['三级来源'] = df['三级来源'].apply(
+                            lambda x: '精准人群推广' if x == '引力魔方'
+                            else '关键词推广' if x == '直通车'
+                            else '智能场景' if x == '万相台'
+                            else '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['日期'] = df['数据周期'].apply(lambda x: re.findall('(.*) ~', x)[0])
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_自助取数_店铺流量_月数据')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_自助取数_店铺流量_月数据')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df['日期'] = df['日期'].astype(str).apply(
-                        lambda x: '-'.join(re.findall(r'(\d{4})(\d{2})(\d{2})', x)[0]) if x else x)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')  # 转换日期列
-                    # min_clm = str(df.min()['日期']).split(' ')[0]
-                    # max_clm = str(df.max()['日期']).split(' ')[0]
-                    min_clm = str(df['日期'].min()).split(' ')[0]
-                    max_clm = str(df['日期'].max()).split(' ')[0]
-                    new_name = f'{name_st[0]}-{min_clm}_{max_clm}.csv'  # 保存时将(分日)去掉
-                    df.replace(to_replace=['--'], value='', regex=False, inplace=True)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_店铺指标')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_店铺指标')
-                    os.remove(os.path.join(root, name))
-
-                elif name.endswith('csv') and '省份' in name:
-                    # 生意经，地域分布, 仅限日数据
-                    pattern = re.findall(r'(.*[\u4e00-\u9fa5])(\d{4})(\d{2})(\d{2})\.', name)
-                    if not pattern or '省份城市分析2' not in name:
-                        print(f'{name}  不支持或已转换的表格')
-                        os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
-                        continue
-                    date = pattern[0][1:]
-                    date = '-'.join(date)
-                    new_name = f'{pattern[0][0]}-{date}.csv'
-                    df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xlsx') and '直播分场次效果' in name:
+                        pattern = re.findall(r'(\d{4}-\d{2}-\d{2})_(\d{4}-\d{2}-\d{2})', name)
+                        if pattern:
+                            continue
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            continue
+                        df.replace(to_replace=['--'], value='0', regex=False, inplace=True)
+                        df.replace(to_replace=[','], value='', regex=True, inplace=True)
+                        df['直播开播时间'] = pd.to_datetime(df['直播开播时间'], format='%Y-%m-%d %H:%M:%S', errors='ignore')
+                        df.insert(loc=0, column='日期', value=df['直播开播时间'])
+                        df['日期'] = df['日期'].apply(lambda x: pd.to_datetime(str(x).split(' ')[0], format='%Y-%m-%d', errors='ignore') if x else x)
+                        df.insert(loc=1, column='店铺', value='万里马官方旗舰店')
+                        min_clm = str(df.min()['直播开播时间']).split(' ')[0]
+                        max_clm = str(df.max()['直播开播时间']).split(' ')[0]
+                        new_name = f'{os.path.splitext(name)[0]}_{min_clm}_{max_clm}.csv'
+                        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))
-                        continue
-                    df['省'] = df['省份'].apply(lambda x: x if ' ├─ ' not in x and ' └─ ' not in x else None)
-                    df['城市'] = df[['省份', '省']].apply(lambda x: '汇总' if x['省'] else x['省份'], axis=1)
-                    df['省'].fillna(method='ffill', inplace=True)
-                    df['城市'].replace(to_replace=[' ├─ | └─ '], value='', regex=True, inplace=True)
-                    pov = df.pop('省')
-                    city = df.pop('城市')
-                    df['省+市'] = df['省份']
-                    df['省份'] = pov
-                    df.insert(loc=1, column='城市', value=city)
-                    df.insert(loc=0, column='日期', value=date)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_地域分布_省份城市分析')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_地域分布_省份城市分析')
-                    os.remove(os.path.join(root, name))  # 移除已转换的原文件
-
-                elif name.endswith('csv') and 'order' in name:
-                    # 生意经，订单数据，仅限月数据
-                    pattern = re.findall(r'(.*)(\d{4})(\d{2})(\d{2})-(\d{4})(\d{2})(\d{2})', name)
-                    if not pattern:
-                        print(f'{name}  不支持或已转换的表格')
-                        os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
-                        continue
-                    date1 = pattern[0][1:4]
-                    date1 = '-'.join(date1)
-                    date2 = pattern[0][4:]
-                    date2 = '-'.join(date2)
-                    date = f'{date1}_{date2}'
-                    new_name = f'{pattern[0][0]}{date}.csv'
-                    df = pd.read_csv(os.path.join(root, name), encoding='gb18030', header=0, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.csv') and 'baobei' in name:
+                        # 生意经宝贝指标日数据
+                        # print(name)
+                        date = re.findall(r's-(\d{4})(\d{2})(\d{2})\.', str(name))
+                        if not date:  # 阻止月数据及已转换的表格
+                            print(f'{name}  不支持或是已转换的表格')
+                            os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
+                            continue
+                        df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        if '日期' in df.columns.tolist():
+                            df.pop('日期')
+                        new_date = '-'.join(date[0])
+                        df.insert(loc=0, column='日期', value=new_date)
+                        df.replace(to_replace=['--'], value='', regex=False, inplace=True)
+                        df['宝贝ID'] = df['宝贝ID'].apply(
+                            lambda x: f'="{x}"' if x and '=' not in str(x) else x
+                        )
+                        df['商家编码'] = df['商家编码'].apply(
+                            lambda x: f'="{x}"' if x and '=' not in str(x) else x
+                        )
+                        name_st = re.findall(r'(.*)\d{4}\d{2}\d{2}\.', str(name))  # baobeitrans-
+                        new_name = f'{name_st[0]}{new_date}.csv'
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_宝贝指标')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_宝贝指标')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.insert(loc=0, column='日期', value=date1)
-                    df.insert(loc=1, column='数据周期', value=date)
-                    df['商品id'] = df['宝贝链接'].apply(
-                        lambda x: f'=\"{"".join(re.findall("id=(.*)", str(x))[0])}\"' if x else x)
-                    df.rename(columns={'宝贝标题': '商品标题', '宝贝链接': '商品链接'}, inplace=True)
-                    df['颜色编码'] = df['商家编码'].apply(
-                        lambda x: ''.join(re.findall(r' .*(\d{4})$', str(x))) if x else x)
-                    df['商家编码'] = df['商家编码'].apply(lambda x: f'="{x}"' if x else x)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_订单数据')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_订单数据')
-                    os.remove(os.path.join(root, name))  # 移除已转换的原文件
 
-                elif name.endswith('.xlsx') and '直播间成交订单明细' in name:
-                    # 直播间成交订单明细
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.csv') and '店铺销售指标' in name:
+                        # 生意经, 店铺指标，仅限月数据，实际日指标也可以
+                        name_st = re.findall(r'(.*)\(分日', name)
+                        if not name_st:
+                            print(f'{name}  已转换的表格')
+                            continue
+                        df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df['日期'] = df['日期'].astype(str).apply(
+                            lambda x: '-'.join(re.findall(r'(\d{4})(\d{2})(\d{2})', x)[0]) if x else x)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')  # 转换日期列
+                        # min_clm = str(df.min()['日期']).split(' ')[0]
+                        # max_clm = str(df.max()['日期']).split(' ')[0]
+                        min_clm = str(df['日期'].min()).split(' ')[0]
+                        max_clm = str(df['日期'].max()).split(' ')[0]
+                        new_name = f'{name_st[0]}-{min_clm}_{max_clm}.csv'  # 保存时将(分日)去掉
+                        df.replace(to_replace=['--'], value='', regex=False, inplace=True)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_店铺指标')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_店铺指标')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.rename(columns={'场次ID': '场次id', '商品ID': '商品id'}, inplace=True)
-                    df.replace(to_replace=['-'], value='', regex=False, inplace=True)
-                    cols = ['开播时间', '下单时间', '支付时间', '确认收货时间']
-                    for col in cols:
-                        df[col] = pd.to_datetime(df[col])  # 转换日期列
-                    for col2 in ['支付金额', '确认收货金额']:
-                        df[col2] = pd.to_numeric(df[col2], errors='ignore')
-                    df['日期'] = df['支付时间'].apply(lambda x: x.strftime('%Y-%m-%d'))
-                    date_min = df['日期'].values.min() + '_'
-                    date_max = df['日期'].values.max()
-                    new_name = '直播间成交订单明细_' + date_min + date_max + '.csv'
-                    for col3 in ['场次id', '商品id', '父订单', '子订单']:
-                        df[col3] = df[col3].apply(
-                            lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
-                        )
-                    col4 = ['日期', '直播标题', '开播时间', '场次id', '支付时间', '支付金额', '商品id', '商品标题',
-                            '商品一级类目', '父订单', '子订单', '下单时间', '确认收货时间', '确认收货金额']
-                    df_lin = df[col4]
-                    # 调整列顺序
-                    df = pd.merge(df_lin, df, how='outer', on=col4)
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_直播间成交订单明细')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_直播间成交订单明细')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xlsx') and '直播间大盘数据' in name:
-                    # 直播间大盘数据
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('csv') and '省份' in name:
+                        # 生意经，地域分布, 仅限日数据
+                        pattern = re.findall(r'(.*[\u4e00-\u9fa5])(\d{4})(\d{2})(\d{2})\.', name)
+                        if not pattern or '省份城市分析2' not in name:
+                            print(f'{name}  不支持或已转换的表格')
+                            os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
+                            continue
+                        date = pattern[0][1:]
+                        date = '-'.join(date)
+                        new_name = f'{pattern[0][0]}-{date}.csv'
+                        df = pd.read_csv(os.path.join(root, name), encoding=encoding, header=0, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df['省'] = df['省份'].apply(lambda x: x if ' ├─ ' not in x and ' └─ ' not in x else None)
+                        df['城市'] = df[['省份', '省']].apply(lambda x: '汇总' if x['省'] else x['省份'], axis=1)
+                        df['省'].fillna(method='ffill', inplace=True)
+                        df['城市'].replace(to_replace=[' ├─ | └─ '], value='', regex=True, inplace=True)
+                        pov = df.pop('省')
+                        city = df.pop('城市')
+                        df['省+市'] = df['省份']
+                        df['省份'] = pov
+                        df.insert(loc=1, column='城市', value=city)
+                        df.insert(loc=0, column='日期', value=date)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_地域分布_省份城市分析')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_地域分布_省份城市分析')
+                        os.remove(os.path.join(root, name))  # 移除已转换的原文件
+
+                    elif name.endswith('csv') and 'order' in name:
+                        # 生意经，订单数据，仅限月数据
+                        pattern = re.findall(r'(.*)(\d{4})(\d{2})(\d{2})-(\d{4})(\d{2})(\d{2})', name)
+                        if not pattern:
+                            print(f'{name}  不支持或已转换的表格')
+                            os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
+                            continue
+                        date1 = pattern[0][1:4]
+                        date1 = '-'.join(date1)
+                        date2 = pattern[0][4:]
+                        date2 = '-'.join(date2)
+                        date = f'{date1}_{date2}'
+                        new_name = f'{pattern[0][0]}{date}.csv'
+                        df = pd.read_csv(os.path.join(root, name), encoding='gb18030', header=0, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.insert(loc=0, column='日期', value=date1)
+                        df.insert(loc=1, column='数据周期', value=date)
+                        df['商品id'] = df['宝贝链接'].apply(
+                            lambda x: f'=\"{"".join(re.findall("id=(.*)", str(x))[0])}\"' if x else x)
+                        df.rename(columns={'宝贝标题': '商品标题', '宝贝链接': '商品链接'}, inplace=True)
+                        df['颜色编码'] = df['商家编码'].apply(
+                            lambda x: ''.join(re.findall(r' .*(\d{4})$', str(x))) if x else x)
+                        df['商家编码'] = df['商家编码'].apply(lambda x: f'="{x}"' if x else x)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意经1', collection_name='生意经_订单数据')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意经1', tabel_name='生意经_订单数据')
+                        os.remove(os.path.join(root, name))  # 移除已转换的原文件
+
+                    elif name.endswith('.xlsx') and '直播间成交订单明细' in name:
+                        # 直播间成交订单明细
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.rename(columns={'场次ID': '场次id', '商品ID': '商品id'}, inplace=True)
+                        df.replace(to_replace=['-'], value='', regex=False, inplace=True)
+                        cols = ['开播时间', '下单时间', '支付时间', '确认收货时间']
+                        for col in cols:
+                            df[col] = pd.to_datetime(df[col])  # 转换日期列
+                        for col2 in ['支付金额', '确认收货金额']:
+                            df[col2] = pd.to_numeric(df[col2], errors='ignore')
+                        df['日期'] = df['支付时间'].apply(lambda x: x.strftime('%Y-%m-%d'))
+                        date_min = df['日期'].values.min() + '_'
+                        date_max = df['日期'].values.max()
+                        new_name = '直播间成交订单明细_' + date_min + date_max + '.csv'
+                        for col3 in ['场次id', '商品id', '父订单', '子订单']:
+                            df[col3] = df[col3].apply(
+                                lambda x: "{0}{1}{2}".format('="', x, '"') if x and '=' not in str(x) else x
+                            )
+                        col4 = ['日期', '直播标题', '开播时间', '场次id', '支付时间', '支付金额', '商品id', '商品标题',
+                                '商品一级类目', '父订单', '子订单', '下单时间', '确认收货时间', '确认收货金额']
+                        df_lin = df[col4]
+                        # 调整列顺序
+                        df = pd.merge(df_lin, df, how='outer', on=col4)
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_直播间成交订单明细')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_直播间成交订单明细')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.replace(to_replace=['-'], value='', regex=False, inplace=True)
-                    df.rename(columns={'统计日期': '日期'}, inplace=True)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    df['日期'] = df['日期'].apply(lambda x: x.strftime('%Y-%m-%d'))
-                    date_min = df['日期'].values.min() + '_'
-                    date_max = df['日期'].values.max()
-                    new_name = '直播间大盘数据_' + date_min + date_max + '.csv'
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_直播间大盘数据')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_直播间大盘数据')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xls') and '直播业绩-成交拆解' in name:
-                    # 直播业绩-成交拆解
-                    df = pd.read_excel(os.path.join(root, name), header=5)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xlsx') and '直播间大盘数据' in name:
+                        # 直播间大盘数据
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.replace(to_replace=['-'], value='', regex=False, inplace=True)
+                        df.rename(columns={'统计日期': '日期'}, inplace=True)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        df['日期'] = df['日期'].apply(lambda x: x.strftime('%Y-%m-%d'))
+                        date_min = df['日期'].values.min() + '_'
+                        date_max = df['日期'].values.max()
+                        new_name = '直播间大盘数据_' + date_min + date_max + '.csv'
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_直播间大盘数据')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_直播间大盘数据')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.replace(to_replace=['-'], value='', regex=False, inplace=True)
-                    df.replace(to_replace=[','], value='', regex=True, inplace=True)
-                    df.rename(columns={'统计日期': '日期'}, inplace=True)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    df['日期'] = df['日期'].apply(lambda x: x.strftime('%Y-%m-%d'))
-                    date_min = df['日期'].values.min() + '_'
-                    date_max = df['日期'].values.max()
-                    new_name = '直播业绩_成交拆解_' + date_min + date_max + '.csv'
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_直播业绩')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_直播业绩')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xlsx') and '明星店铺' in name:
-                    # 品销宝
-                    pattern = re.findall(r'_(\d{4}-\d{2}-\d{2})_', name)
-                    if pattern:
-                        continue
-                    sheets4 = ['账户', '推广计划', '推广单元', '创意', '品牌流量包', '定向人群']  # 品销宝
-                    file_name4 = os.path.splitext(name)[0]  # 明星店铺报表
-                    for sheet4 in sheets4:
-                        df = pd.read_excel(os.path.join(root, name), sheet_name=sheet4, header=0, engine='openpyxl')
-                        # print(sheet4)
+                    elif name.endswith('.xls') and '直播业绩-成交拆解' in name:
+                        # 直播业绩-成交拆解
+                        df = pd.read_excel(os.path.join(root, name), header=5)
                         if len(df) == 0:
                             print(f'{name} 报表数据为空')
                             os.remove(os.path.join(root, name))
                             continue
-                        if len(df) < 1:
-                            print(f'{name} 跳过')
+                        df.replace(to_replace=['-'], value='', regex=False, inplace=True)
+                        df.replace(to_replace=[','], value='', regex=True, inplace=True)
+                        df.rename(columns={'统计日期': '日期'}, inplace=True)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        df['日期'] = df['日期'].apply(lambda x: x.strftime('%Y-%m-%d'))
+                        date_min = df['日期'].values.min() + '_'
+                        date_max = df['日期'].values.max()
+                        new_name = '直播业绩_成交拆解_' + date_min + date_max + '.csv'
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意参谋2', collection_name='生意参谋_直播业绩')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意参谋2', tabel_name='生意参谋_直播业绩')
+                        os.remove(os.path.join(root, name))
+
+                    elif name.endswith('.xlsx') and '明星店铺' in name:
+                        # 品销宝
+                        pattern = re.findall(r'_(\d{4}-\d{2}-\d{2})_', name)
+                        if pattern:
                             continue
-                        else:
-                            df.insert(loc=1, column='报表类型', value=sheet4)
-                            df.fillna(0, inplace=True)
-                            df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')  # 转换日期列
-                            min_clm = str(df['日期'].min()).split(' ')[0]
-                            max_clm = str(df['日期'].max()).split(' ')[0]
-                            new_file_name4 = f'{sheet4}_{file_name4}_{min_clm}_{max_clm}.csv'
-                            # 以sheet名进一步创建子文件夹
-                            root_new = str(pathlib.Path(self.source_path, '推广报表/品销宝', sheet4))
-                            self.save_to_csv(df, root_new, new_file_name4)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
-                            if self.set_up_to_mogo:
-                                d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_品销宝')
-                            if self.set_up_to_mysql:
-                                m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_品销宝')
-                    os.remove(os.path.join(root, name))
+                        sheets4 = ['账户', '推广计划', '推广单元', '创意', '品牌流量包', '定向人群']  # 品销宝
+                        file_name4 = os.path.splitext(name)[0]  # 明星店铺报表
+                        for sheet4 in sheets4:
+                            df = pd.read_excel(os.path.join(root, name), sheet_name=sheet4, header=0, engine='openpyxl')
+                            # print(sheet4)
+                            if len(df) == 0:
+                                print(f'{name} 报表数据为空')
+                                os.remove(os.path.join(root, name))
+                                continue
+                            if len(df) < 1:
+                                print(f'{name} 跳过')
+                                continue
+                            else:
+                                df.insert(loc=1, column='报表类型', value=sheet4)
+                                df.fillna(0, inplace=True)
+                                df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')  # 转换日期列
+                                min_clm = str(df['日期'].min()).split(' ')[0]
+                                max_clm = str(df['日期'].max()).split(' ')[0]
+                                new_file_name4 = f'{sheet4}_{file_name4}_{min_clm}_{max_clm}.csv'
+                                # 以sheet名进一步创建子文件夹
+                                root_new = str(pathlib.Path(self.source_path, '推广报表/品销宝', sheet4))
+                                self.save_to_csv(df, root_new, new_file_name4)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                                if self.set_up_to_mogo:
+                                    d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='天猫_推广_品销宝')
+                                if self.set_up_to_mysql:
+                                    m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='天猫_推广_品销宝')
+                        os.remove(os.path.join(root, name))
 
-                elif name.endswith('.csv') and '淘宝店铺数据' in name:
-                    df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='市场数据1', collection_name='淘宝店铺数据')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='市场数据1', tabel_name='淘宝店铺数据')
+                    elif name.endswith('.csv') and '淘宝店铺数据' in name:
+                        df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='市场数据1', collection_name='淘宝店铺数据')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='市场数据1', tabel_name='淘宝店铺数据')
 
-                elif name.endswith('.csv') and '人群洞察' in name:
-                    df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
-                    df.replace(to_replace=['--'], value='', regex=False, inplace=True)
-                    df = df[df['人群规模'] != '']
-                    if len(df) == 0:
+                    elif name.endswith('.csv') and '人群洞察' in name:
+                        df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
+                        df.replace(to_replace=['--'], value='', regex=False, inplace=True)
+                        df = df[df['人群规模'] != '']
+                        if len(df) == 0:
+                            os.remove(os.path.join(root, name))
+                            print(f'{name}: 数据为空, 已移除: {os.path.join(root, name)}')
+                            continue
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='万相台_人群洞察')
+                        if self.set_up_to_mysql:
+                            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))
-                        print(f'{name}: 数据为空, 已移除: {os.path.join(root, name)}')
-                        continue
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='天猫数据1', collection_name='万相台_人群洞察')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='天猫数据1', tabel_name='万相台_人群洞察')
+                    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')]
+                        df['日期'] = df['日期'].apply(lambda x: f'{str(x)[:4]}-{str(x)[4:6]}-{str(x)[6:8]}')
+                        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')
+                        new_name = re.sub('至', '_', name)
+                        self.save_to_csv(df, root, new_name)
+                        os.remove(os.path.join(root, name))
+                    elif name.endswith('.xlsx') and '店铺来源_流量来源' in name:
+                        # 京东店铺来源
+                        if '按天' not in name:
+                            print(f'{name} 京东流量请按天下载')
+                            continue
+                        new_name = name.split(r'__20')[0]
+                        date01 = re.findall(r'(\d{4})(\d{2})(\d{2})_(\d{4})(\d{2})(\d{2})', str(name))
+                        new_date01 = f'{date01[0][0]}-{date01[0][1]}-{date01[0][2]}'
+                        new_date02 = f'{date01[0][3]}-{date01[0][4]}-{date01[0][5]}'
+                        new_date03 = f'{new_date01}_{new_date02}'
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.replace(to_replace=['-'], value='', regex=False, inplace=True)
+                        df.insert(loc=0, column='日期', value=new_date01)
+                        if new_date01 != new_date02:
+                            df.insert(loc=1, column='数据周期', value=new_date03)
+                        cols = df.columns.tolist()
+                        if '三级来源' in cols:
+                            source = '三级来源'
+                        elif '二级来源' in cols:
+                            source = '二级来源'
+                        else:
+                            source = '一级来源'
 
-                # ----------------------- 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')]
-                    df['日期'] = df['日期'].apply(lambda x: f'{str(x)[:4]}-{str(x)[4:6]}-{str(x)[6:8]}')
-                    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')
-                    new_name = re.sub('至', '_', name)
-                    self.save_to_csv(df, root, new_name)
-                    os.remove(os.path.join(root, name))
-                elif name.endswith('.xlsx') and '店铺来源_流量来源' in name:
-                    # 京东店铺来源
-                    if '按天' not in name:
-                        print(f'{name} 京东流量请按天下载')
-                        continue
-                    new_name = name.split(r'__20')[0]
-                    date01 = re.findall(r'(\d{4})(\d{2})(\d{2})_(\d{4})(\d{2})(\d{2})', str(name))
-                    new_date01 = f'{date01[0][0]}-{date01[0][1]}-{date01[0][2]}'
-                    new_date02 = f'{date01[0][3]}-{date01[0][4]}-{date01[0][5]}'
-                    new_date03 = f'{new_date01}_{new_date02}'
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                        new_name = f'{new_name}_{source}_{new_date03}.csv'
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        self.save_to_csv(df, root, new_name)  # csv 文件仍然保留这些列
+                        for col_2024 in cols:  # 京东这个表有字段加了去年日期，删除这些同比数据字段，不然列数量爆炸
+                            if '20' in col_2024 and '流量来源' in name:
+                                df.drop(col_2024, axis=1, inplace=True)
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_流量来源_日数据')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_流量来源_日数据')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.replace(to_replace=['-'], value='', regex=False, inplace=True)
-                    df.insert(loc=0, column='日期', value=new_date01)
-                    if new_date01 != new_date02:
-                        df.insert(loc=1, column='数据周期', value=new_date03)
-                    cols = df.columns.tolist()
-                    if '三级来源' in cols:
-                        source = '三级来源'
-                    elif '二级来源' in cols:
-                        source = '二级来源'
-                    else:
-                        source = '一级来源'
 
-                    new_name = f'{new_name}_{source}_{new_date03}.csv'
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    self.save_to_csv(df, root, new_name)  # csv 文件仍然保留这些列
-                    for col_2024 in cols:  # 京东这个表有字段加了去年日期，删除这些同比数据字段，不然列数量爆炸
-                        if '20' in col_2024 and '流量来源' in name:
-                            df.drop(col_2024, axis=1, inplace=True)
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_流量来源_日数据')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_流量来源_日数据')
-                    os.remove(os.path.join(root, name))
+                    elif name.endswith('.xlsx') and '全部渠道_商品明细' in name:
+                        # 京东商品明细 文件转换
+                        date1 = re.findall(r'_(\d{4})(\d{2})(\d{2})_全部', str(name))
+                        if not date1[0]:
+                            print(f'{name}: 仅支持日数据')
+                            continue
+                        if date1:
+                            date1 = f'{date1[0][0]}-{date1[0][1]}-{date1[0][2]}'
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        if '10035975359247' in df['商品ID'].values or '10056642622343' in df['商品ID'].values:
+                            new_name = f'sku_{date1}_全部渠道_商品明细.csv'
+                        elif '10021440233518' in df['商品ID'].values or '10022867813485' in df['商品ID'].values:
+                            new_name = f'spu_{date1}_全部渠道_商品明细.csv'
+                        else:
+                            new_name = f'未分类_{date1}_全部渠道_商品明细.csv'
+                        df.replace(to_replace=['-'], value='', regex=False, inplace=True)
+                        df.rename(columns={'商品ID': '商品id'}, inplace=True)
+                        df['商品id'] = df['商品id'].apply(lambda x: f'="{x}"' if x else x)
+                        df['货号'] = df['货号'].apply(lambda x: f'="{x}"' if x else x)
+                        df.insert(loc=0, column='日期', value=date1)
 
-                elif name.endswith('.xlsx') and '全部渠道_商品明细' in name:
-                    # 京东商品明细 文件转换
-                    date1 = re.findall(r'_(\d{4})(\d{2})(\d{2})_全部', str(name))
-                    if not date1[0]:
-                        print(f'{name}: 仅支持日数据')
-                        continue
-                    if date1:
-                        date1 = f'{date1[0][0]}-{date1[0][1]}-{date1[0][2]}'
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                        self.save_to_csv(df, root, new_name)
+                        if self.set_up_to_mogo:
+                            if 'sku' in new_name:
+                                d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_sku_商品明细')
+                            elif 'spu' in new_name:
+                                d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_spu_商品明细')
+                        if self.set_up_to_mysql:
+                            if 'sku' in new_name:
+                                m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_sku_商品明细')
+                            elif 'spu' in new_name:
+                                m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_spu_商品明细')
                         os.remove(os.path.join(root, name))
-                        continue
-                    if '10035975359247' in df['商品ID'].values or '10056642622343' in df['商品ID'].values:
-                        new_name = f'sku_{date1}_全部渠道_商品明细.csv'
-                    elif '10021440233518' in df['商品ID'].values or '10022867813485' in df['商品ID'].values:
-                        new_name = f'spu_{date1}_全部渠道_商品明细.csv'
-                    else:
-                        new_name = f'未分类_{date1}_全部渠道_商品明细.csv'
-                    df.replace(to_replace=['-'], value='', regex=False, inplace=True)
-                    df.rename(columns={'商品ID': '商品id'}, inplace=True)
-                    df['商品id'] = df['商品id'].apply(lambda x: f'="{x}"' if x else x)
-                    df['货号'] = df['货号'].apply(lambda x: f'="{x}"' if x else x)
-                    df.insert(loc=0, column='日期', value=date1)
+                    elif name.endswith('.xlsx') and '搜索分析-排名定位-商品词下排名' in name:
+                        # 京东商品词下排名
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        # print(name)
+                        df = pd.read_excel(os.path.join(root, name), header=0, engine='openpyxl')
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.rename(columns={'商品的ID': 'skuid'}, inplace=True)
+                        df['skuid'] = df['skuid'].apply(lambda x: f'="{x}"' if x and '=' not in str(x) else x)
+                        self.save_to_csv(df, root, new_name)
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_商品词下排名')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_商品词下排名')
+                        os.remove(os.path.join(root, name))  # 移除已转换的原文件
 
-                    self.save_to_csv(df, root, new_name)
-                    if self.set_up_to_mogo:
-                        if 'sku' in new_name:
-                            d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_sku_商品明细')
-                        elif 'spu' in new_name:
-                            d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_spu_商品明细')
-                    if self.set_up_to_mysql:
-                        if 'sku' in new_name:
-                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_sku_商品明细')
-                        elif 'spu' in new_name:
-                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_spu_商品明细')
-                    os.remove(os.path.join(root, name))
-                elif name.endswith('.xlsx') and '搜索分析-排名定位-商品词下排名' in name:
-                    # 京东商品词下排名
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    # print(name)
-                    df = pd.read_excel(os.path.join(root, name), header=0, engine='openpyxl')
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
-                        os.remove(os.path.join(root, name))
-                        continue
-                    df.rename(columns={'商品的ID': 'skuid'}, inplace=True)
-                    df['skuid'] = df['skuid'].apply(lambda x: f'="{x}"' if x and '=' not in str(x) else x)
-                    self.save_to_csv(df, root, new_name)
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_商品词下排名')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_商品词下排名')
-                    os.remove(os.path.join(root, name))  # 移除已转换的原文件
+                    elif name.endswith('.xlsx') and '搜索分析-排名定位-商品排名' in name:
+                        # 京东商品排名
+                        new_name = os.path.splitext(name)[0] + '.csv'
+                        date_in = re.findall(r'(\d{4}-\d{2}-\d{2})-搜索', str(name))[0]
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.insert(0, '日期', date_in)  # 插入新列
+                        df.rename(columns={'SKU': 'skuid'}, inplace=True)
+                        df['skuid'] = df['skuid'].apply(lambda x: f'="{x}"' if x and '=' not in str(x) else x)
+                        self.save_to_csv(df, root, new_name, encoding='utf-8_sig')
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_商品排名')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_商品排名')
+                        os.remove(os.path.join(root, name))  # 移除已转换的原文件
 
-                elif name.endswith('.xlsx') and '搜索分析-排名定位-商品排名' in name:
-                    # 京东商品排名
-                    new_name = os.path.splitext(name)[0] + '.csv'
-                    date_in = re.findall(r'(\d{4}-\d{2}-\d{2})-搜索', str(name))[0]
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '竞店概况_竞店详情' in name:
+                        # 京东，竞争-竞店概况-竞店详情-全部渠道
+                        date01 = re.findall(r'全部渠道_(\d{4})(\d{2})(\d{2})_(\d{4})(\d{2})(\d{2})', str(name))
+                        start_date = f'{date01[0][0]}-{date01[0][1]}-{date01[0][2]}'
+                        end_date = f'{date01[0][3]}-{date01[0][4]}-{date01[0][5]}'
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df.replace(to_replace=[','], value='', regex=True, inplace=True)
+                        df.insert(loc=0, column='日期', value=start_date)
+                        new_name = f'{os.path.splitext(name)[0]}'
+                        new_name = re.sub(r'\d{8}_\d{8}', f'{start_date}_{end_date}', new_name)
+                        self.save_to_csv(df, root, new_name)
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_竞店监控_日数据')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_竞店监控_日数据')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.insert(0, '日期', date_in)  # 插入新列
-                    df.rename(columns={'SKU': 'skuid'}, inplace=True)
-                    df['skuid'] = df['skuid'].apply(lambda x: f'="{x}"' if x and '=' not in str(x) else x)
-                    self.save_to_csv(df, root, new_name, encoding='utf-8_sig')
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_商品排名')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_商品排名')
-                    os.remove(os.path.join(root, name))  # 移除已转换的原文件
 
-                elif name.endswith('.xls') and '竞店概况_竞店详情' in name:
-                    # 京东，竞争-竞店概况-竞店详情-全部渠道
-                    date01 = re.findall(r'全部渠道_(\d{4})(\d{2})(\d{2})_(\d{4})(\d{2})(\d{2})', str(name))
-                    start_date = f'{date01[0][0]}-{date01[0][1]}-{date01[0][2]}'
-                    end_date = f'{date01[0][3]}-{date01[0][4]}-{date01[0][5]}'
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '店铺' in name:
+                        # 京东 自助报表  店铺日报
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df['日期'] = df['日期'].apply(
+                            lambda x: '-'.join(re.findall(r'(\d{4})(\d{2})(\d{2})', str(x))[0])
+                        )
+                        date_min = df['日期'].values.min()
+                        date_max = df['日期'].values.max()
+                        # df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        new_name = f'JD店铺日报_' + re.findall(r"(.*)\d{8}_\d{8}", name)[0] + f'_{date_min}_{date_max}.csv'
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='京东数据1', collection_name='京东_自助取数_店铺日报')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_自助取数_店铺日报')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df.replace(to_replace=[','], value='', regex=True, inplace=True)
-                    df.insert(loc=0, column='日期', value=start_date)
-                    new_name = f'{os.path.splitext(name)[0]}'
-                    new_name = re.sub(r'\d{8}_\d{8}', f'{start_date}_{end_date}', new_name)
-                    self.save_to_csv(df, root, new_name)
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_竞店监控_日数据')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_竞店监控_日数据')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xls') and '店铺' in name:
-                    # 京东 自助报表  店铺日报
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xls') and '商家榜单_女包_整体' in name:
+                        # 京东 行业 商家榜单
+                        date2 = re.findall(r'_\d{8}-\d+', name)
+                        if date2:
+                            print(f'{name}: 请下载日数据，不支持其他周期')
+                            os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
+                            continue
+                        date1 = re.findall(r'_(\d{4})(\d{2})(\d{2})', name)
+                        date1 = f'{date1[0][0]}-{date1[0][1]}-{date1[0][2]}'
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df['日期'] = df['日期'].astype(str).apply(lambda x: f'{x[:4]}-{x[4:6]}-{x[6:8]}')
+                        df.insert(loc=0, column='类型', value='商家榜单')
+                        new_name = f'{os.path.splitext(name)[0]}_{date1}.csv'
+                        self.save_to_csv(df, root, new_name)
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_商家榜单')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_商家榜单')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df['日期'] = df['日期'].apply(
-                        lambda x: '-'.join(re.findall(r'(\d{4})(\d{2})(\d{2})', str(x))[0])
-                    )
-                    date_min = df['日期'].values.min()
-                    date_max = df['日期'].values.max()
-                    # df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    new_name = f'JD店铺日报_' + re.findall(r"(.*)\d{8}_\d{8}", name)[0] + f'_{date_min}_{date_max}.csv'
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='京东数据1', collection_name='京东_自助取数_店铺日报')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_自助取数_店铺日报')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xls') and '商家榜单_女包_整体' in name:
-                    # 京东 行业 商家榜单
-                    date2 = re.findall(r'_\d{8}-\d+', name)
-                    if date2:
-                        print(f'{name}: 请下载日数据，不支持其他周期')
-                        os.remove(os.path.join(root, name))  # 直接删掉，避免被分到原始文件, encoding 不同会引发错误
-                        continue
-                    date1 = re.findall(r'_(\d{4})(\d{2})(\d{2})', name)
-                    date1 = f'{date1[0][0]}-{date1[0][1]}-{date1[0][2]}'
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xlsx') and '批量SKU导出-批量任务' in name:
+                        # 京东 sku 导出
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        d_time = datetime.datetime.today().strftime('%Y-%m-%d')
+                        df.insert(loc=0, column='日期', value=d_time)
+                        for col in ['SKUID', '商品编码', '商家SKU', '货号']:
+                            df[col] = df[col].apply(lambda x: f'="{x}"' if x else x)
+                        df['商品链接'] = df['商品链接'].apply(lambda x: f'https://{x}' if x else x)
+                        new_name = f'京东商品信息_{os.path.splitext(name)[0]}_{d_time}.csv'
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='属性设置1', collection_name='京东商品信息')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='属性设置1', tabel_name='京东商品信息')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df['日期'] = df['日期'].astype(str).apply(lambda x: f'{x[:4]}-{x[4:6]}-{x[6:8]}')
-                    df.insert(loc=0, column='类型', value='商家榜单')
-                    new_name = f'{os.path.splitext(name)[0]}_{date1}.csv'
-                    self.save_to_csv(df, root, new_name)
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df,db_name='京东数据1', collection_name='京东_商家榜单')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_商家榜单')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xlsx') and '批量SKU导出-批量任务' in name:
-                    # 京东 sku 导出
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
-                        os.remove(os.path.join(root, name))
-                        continue
-                    d_time = datetime.datetime.today().strftime('%Y-%m-%d')
-                    df.insert(loc=0, column='日期', value=d_time)
-                    for col in ['SKUID', '商品编码', '商家SKU', '货号']:
-                        df[col] = df[col].apply(lambda x: f'="{x}"' if x else x)
-                    df['商品链接'] = df['商品链接'].apply(lambda x: f'https://{x}' if x else x)
-                    new_name = f'京东商品信息_{os.path.splitext(name)[0]}_{d_time}.csv'
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='属性设置1', collection_name='京东商品信息')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='属性设置1', tabel_name='京东商品信息')
-                    os.remove(os.path.join(root, name))
+                    elif name.endswith('.xlsx') and '批量SPU导出-批量任务' in name:
+                        # 京东 spu 导出
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        d_time = datetime.datetime.today().strftime('%Y-%m-%d')
+                        df.insert(loc=0, column='日期', value=d_time)
+                        for col in ['商品编码', '货号']:
+                            df[col] = df[col].apply(lambda x: f'="{x}"' if x else x)
+                        new_name = f'京东商品信息_{os.path.splitext(name)[0]}_{d_time}.csv'
 
-                elif name.endswith('.xlsx') and '批量SPU导出-批量任务' in name:
-                    # 京东 spu 导出
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                        self.save_to_csv(df, root, new_name)
                         os.remove(os.path.join(root, name))
-                        continue
-                    d_time = datetime.datetime.today().strftime('%Y-%m-%d')
-                    df.insert(loc=0, column='日期', value=d_time)
-                    for col in ['商品编码', '货号']:
-                        df[col] = df[col].apply(lambda x: f'="{x}"' if x else x)
-                    new_name = f'京东商品信息_{os.path.splitext(name)[0]}_{d_time}.csv'
 
-                    self.save_to_csv(df, root, new_name)
-                    os.remove(os.path.join(root, name))
-
-                elif name.endswith('.csv') and '万里马箱包推广1_完整点击成交' in name:
-                    # 京东推广数据
-                    df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.csv') and '万里马箱包推广1_完整点击成交' in name:
+                        # 京东推广数据
+                        df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        pic_list = df['日期'].tolist()
+                        pic = []
+                        for i in pic_list:
+                            pics = re.findall(pattern=r'(\d{4})(\d{2})(\d{2})', string=str(i))
+                            if pics:
+                                pics = '-'.join(pics[0])
+                                pic.append(pics)
+                            else:
+                                pic.append(i)
+                        df['日期'] = pd.Series(pic)
+                        date_min = df['日期'].values.min() + '_'
+                        date_max = df['日期'].values.max()
+                        new_name2 = '京东点击成交报表_' + date_min + date_max + '.csv'
+                        for col in ['计划ID', '触发SKU ID', '跟单SKU ID',  'SPU ID']:
+                            df[col] = df[col].astype(str).apply(lambda x: f'="{x}"' if x and '=' not in x else x)
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        self.save_to_csv(df, root, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='京东数据1', collection_name='京东_推广_京准通')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_推广_京准通')
                         os.remove(os.path.join(root, name))
-                        continue
-                    pic_list = df['日期'].tolist()
-                    pic = []
-                    for i in pic_list:
-                        pics = re.findall(pattern=r'(\d{4})(\d{2})(\d{2})', string=str(i))
-                        if pics:
-                            pics = '-'.join(pics[0])
-                            pic.append(pics)
-                        else:
-                            pic.append(i)
-                    df['日期'] = pd.Series(pic)
-                    date_min = df['日期'].values.min() + '_'
-                    date_max = df['日期'].values.max()
-                    new_name2 = '京东点击成交报表_' + date_min + date_max + '.csv'
-                    for col in ['计划ID', '触发SKU ID', '跟单SKU ID',  'SPU ID']:
-                        df[col] = df[col].astype(str).apply(lambda x: f'="{x}"' if x and '=' not in x else x)
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    self.save_to_csv(df, root, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='京东数据1', collection_name='京东_推广_京准通')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_推广_京准通')
-                    os.remove(os.path.join(root, name))
-                elif name.endswith('.csv') and '万里马箱包推广1_京东推广搜索词_pbix同步不要' in name:
-                    df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.csv') and '万里马箱包推广1_京东推广搜索词_pbix同步不要' in name:
+                        df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        pic_list = df['日期'].tolist()
+                        pic = []
+                        for i in pic_list:
+                            pics = re.findall(pattern=r'(\d{4})(\d{2})(\d{2})', string=str(i))
+                            if pics:
+                                pics = '-'.join(pics[0])
+                                pic.append(pics)
+                            else:
+                                pic.append(i)
+                        df['日期'] = pd.Series(pic)
+                        date_min = df['日期'].values.min() + '_'
+                        date_max = df['日期'].values.max()
+                        new_name2 = '京东推广搜索词_' + date_min + date_max + '.csv'
+                        df.replace(to_replace=[0], value='', regex=False, inplace=True)
+                        df['是否品牌词'] = df['搜索词'].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 '')
+                        self.save_to_csv(df, root, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='京东数据1', collection_name='京东_推广_搜索词报表')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_推广_搜索词报表')
                         os.remove(os.path.join(root, name))
-                        continue
-                    pic_list = df['日期'].tolist()
-                    pic = []
-                    for i in pic_list:
-                        pics = re.findall(pattern=r'(\d{4})(\d{2})(\d{2})', string=str(i))
-                        if pics:
-                            pics = '-'.join(pics[0])
-                            pic.append(pics)
-                        else:
-                            pic.append(i)
-                    df['日期'] = pd.Series(pic)
-                    date_min = df['日期'].values.min() + '_'
-                    date_max = df['日期'].values.max()
-                    new_name2 = '京东推广搜索词_' + date_min + date_max + '.csv'
-                    df.replace(to_replace=[0], value='', regex=False, inplace=True)
-                    df['是否品牌词'] = df['搜索词'].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 '')
-                    self.save_to_csv(df, root, new_name2)  # mysql 可能改变 df 列名，所以在上传 mysql 前保存 csv
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='京东数据1', collection_name='京东_推广_搜索词报表')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='京东数据1', tabel_name='京东_推广_搜索词报表')
-                    os.remove(os.path.join(root, name))
 
-                elif name.endswith('.xlsx') and '零售明细统计' in name:
-                    #
-                    df = pd.read_excel(os.path.join(root, name), header=0)
-                    if len(df) == 0:
-                        print(f'{name} 报表数据为空')
+                    elif name.endswith('.xlsx') and '零售明细统计' in name:
+                        #
+                        df = pd.read_excel(os.path.join(root, name), header=0)
+                        if len(df) == 0:
+                            print(f'{name} 报表数据为空')
+                            os.remove(os.path.join(root, name))
+                            continue
+                        df['摘要'] = df['摘要'].apply(lambda x: re.sub('\'', '', str(x)) if x else x)
+                        for col in ['原单号', '商品代码', '摘要']:
+                            df[col] = df[col].apply(lambda x: f'="{re.sub(".0", "", str(x))}"' if x else x)
+                        df = df[df['缩略图'] != '合计']
+                        df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
+                        date_min = f'_{re.sub("T.*", "", str(df["日期"].values.min()))}_'
+                        date_max = f'{re.sub("T.*", "", str(df["日期"].values.max()))}.csv'
+                        new_name = re.findall(r'(.*)_\d{4}-\d{2}-\d{2}', name)[0]
+                        new_name = f'{new_name}{date_min}{date_max}'
+                        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
+                        if self.set_up_to_mogo:
+                            d.df_to_mongo(df=df, db_name='生意经1', collection_name='E3_零售明细统计')
+                        if self.set_up_to_mysql:
+                            m.df_to_mysql(df=df, db_name='生意经1', tabel_name='E3_零售明细统计')
                         os.remove(os.path.join(root, name))
-                        continue
-                    df['摘要'] = df['摘要'].apply(lambda x: re.sub('\'', '', str(x)) if x else x)
-                    for col in ['原单号', '商品代码', '摘要']:
-                        df[col] = df[col].apply(lambda x: f'="{re.sub(".0", "", str(x))}"' if x else x)
-                    df = df[df['缩略图'] != '合计']
-                    df['日期'] = pd.to_datetime(df['日期'], format='%Y-%m-%d', errors='ignore')
-                    date_min = f'_{re.sub("T.*", "", str(df["日期"].values.min()))}_'
-                    date_max = f'{re.sub("T.*", "", str(df["日期"].values.max()))}.csv'
-                    new_name = re.findall(r'(.*)_\d{4}-\d{2}-\d{2}', name)[0]
-                    new_name = f'{new_name}{date_min}{date_max}'
-                    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
-                    if self.set_up_to_mogo:
-                        d.df_to_mongo(df=df, db_name='生意经1', collection_name='E3_零售明细统计')
-                    if self.set_up_to_mysql:
-                        m.df_to_mysql(df=df, db_name='生意经1', tabel_name='E3_零售明细统计')
-                    os.remove(os.path.join(root, name))
+                except Exception as e:
+                    now = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S ')
+                    print(f'{now}{name}: 报错: {e}')
         if self.set_up_to_mogo:
             if d.client:
                 d.client.close()  # 必须手动关闭数据库连接
@@ -1187,6 +1211,12 @@ class DataClean:
                 elif name.endswith('.csv') and '客户运营平台_客户列表' in name:
                     t_path = str(pathlib.Path(self.source_path, '生意参谋/客户运营平台'))
                     bib(t_path, _as_month=True)
+                elif name.endswith('.csv') and '直播分场次效果' in name:
+                    pattern = re.findall(r'(\d{4}-\d{2}-\d{2})_(\d{4}-\d{2}-\d{2})', name)
+                    if not pattern:
+                        continue
+                    t_path = str(pathlib.Path(self.source_path, '生意参谋/直播场次分析'))
+                    bib(t_path, _as_month=True)
                 #  京东分界线   ------- 开始标记
                 #  京东分界线
                 elif name.endswith('.csv') and '全部渠道_商品明细' in name:
@@ -1430,11 +1460,11 @@ def main():
     c.set_up_to_mysql = False
     c.new_unzip(is_move=True)  # 解压文件
     c.change_and_sort()
-    # c.move_all()  # 移到文件到原始文件夹
+    c.move_all()  # 移到文件到原始文件夹
     # c.attribute()  # 商品素材重命名和分类
 
 
 if __name__ == '__main__':
-    # main()
+    main()
     username, password, host, port = get_myconf.select_config_values(target_service='aliyun', database='mongodb')
     print(username, password, host, port)