mdbq 2.5.5__tar.gz → 2.5.6__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {mdbq-2.5.5 → mdbq-2.5.6}/PKG-INFO +1 -1
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/clean/clean_upload.py +65 -6
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq.egg-info/PKG-INFO +1 -1
- {mdbq-2.5.5 → mdbq-2.5.6}/setup.py +1 -1
- {mdbq-2.5.5 → mdbq-2.5.6}/README.txt +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/__version__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/aggregation/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/aggregation/aggregation.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/aggregation/df_types.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/aggregation/mysql_types.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/aggregation/optimize_data.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/aggregation/query_data.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/bdup/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/bdup/bdup.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/clean/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/clean/data_clean.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/company/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/company/copysh.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/company/home_sh.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/config/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/config/get_myconf.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/config/products.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/config/set_support.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/config/update_conf.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/dataframe/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/dataframe/converter.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/log/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/log/mylogger.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/mongo/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/mongo/mongo.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/mysql/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/mysql/mysql.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/mysql/s_query.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/mysql/year_month_day.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/other/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/other/porxy.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/other/pov_city.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/other/sku_picture.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/other/ua_sj.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/pbix/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/pbix/pbix_refresh.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/pbix/refresh_all.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/pbix/refresh_all_old.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/req_post/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/req_post/req_tb.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/spider/__init__.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq/spider/aikucun.py +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq.egg-info/SOURCES.txt +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq.egg-info/dependency_links.txt +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/mdbq.egg-info/top_level.txt +0 -0
- {mdbq-2.5.5 → mdbq-2.5.6}/setup.cfg +0 -0
@@ -646,6 +646,52 @@ class DataClean:
|
|
646
646
|
}
|
647
647
|
)
|
648
648
|
|
649
|
+
def sp_scene_clean(self, path=None, is_except=[]):
|
650
|
+
if not path:
|
651
|
+
path = self.path
|
652
|
+
for root, dirs, files in os.walk(path, topdown=False):
|
653
|
+
for name in files:
|
654
|
+
if '~$' in name or '.DS' in name or '.localized' in name or '.jpg' in name or '.png' in name:
|
655
|
+
continue
|
656
|
+
if 'py_xg' in name:
|
657
|
+
continue
|
658
|
+
is_continue = False
|
659
|
+
if is_except:
|
660
|
+
for item in is_except:
|
661
|
+
if item in os.path.join(root, name):
|
662
|
+
# print(name)
|
663
|
+
is_continue = True
|
664
|
+
break
|
665
|
+
if is_continue: # 需要排除不做处理的文件或文件夹
|
666
|
+
continue
|
667
|
+
|
668
|
+
if name.endswith('.xlsx') and '商品素材_' in name:
|
669
|
+
shop_name = re.findall(r'_([\u4e00-\u9fffA-Za-z]+店)_', name)[0]
|
670
|
+
df = pd.read_excel(os.path.join(root, name), header=0)
|
671
|
+
df.insert(loc=1, column='店铺名称', value=shop_name)
|
672
|
+
new_name = f'py_xg_{name}'
|
673
|
+
df.to_excel(os.path.join(upload_path, new_name),
|
674
|
+
index=False, header=True, engine='openpyxl', freeze_panes=(1, 0))
|
675
|
+
if '官方旗舰店' in name:
|
676
|
+
db_name = '属性设置3'
|
677
|
+
collection_name = '商品素材_天猫'
|
678
|
+
elif '官方企业店' in name:
|
679
|
+
db_name = '属性设置3'
|
680
|
+
collection_name = '商品素材_淘宝'
|
681
|
+
os.remove(os.path.join(root, name))
|
682
|
+
|
683
|
+
# 将数据传入 self.datas 等待更新进数据库
|
684
|
+
if not db_name or not collection_name:
|
685
|
+
print(f'db_name/collection_name 不能为空')
|
686
|
+
continue
|
687
|
+
self.datas.append(
|
688
|
+
{
|
689
|
+
'数据库名': db_name,
|
690
|
+
'集合名称': collection_name,
|
691
|
+
'数据主体': df,
|
692
|
+
'文件名': name,
|
693
|
+
}
|
694
|
+
)
|
649
695
|
"""
|
650
696
|
{文件分类}
|
651
697
|
将已处理完的文件 分类移到原始文件夹下
|
@@ -711,16 +757,16 @@ class DataClean:
|
|
711
757
|
elif '天猫' in name and name.endswith('.csv') and 'order' in name:
|
712
758
|
t_path = os.path.join(self.source_path, '天猫_生意经', '订单数据')
|
713
759
|
bib(t_path, _as_month=False)
|
714
|
-
elif '淘宝' in name and name.endswith('.csv') and 'baobei' in name:
|
760
|
+
elif '淘宝' in name or '企业店' in name and name.endswith('.csv') and 'baobei' in name:
|
715
761
|
t_path = os.path.join(self.source_path, '淘宝_生意经', '宝贝指标')
|
716
762
|
bib(t_path, _as_month=True)
|
717
|
-
elif '淘宝' in name and name.endswith('.csv') and '省份城市分析' in name:
|
763
|
+
elif '淘宝' in name or '企业店' in name and name.endswith('.csv') and '省份城市分析' in name:
|
718
764
|
t_path = os.path.join(self.source_path, '淘宝_生意经', '省份城市分析')
|
719
765
|
bib(t_path, _as_month=True)
|
720
|
-
elif '淘宝' in name and name.endswith('.csv') and '店铺销售指标' in name:
|
766
|
+
elif '淘宝' in name or '企业店' in name and name.endswith('.csv') and '店铺销售指标' in name:
|
721
767
|
t_path = os.path.join(self.source_path, '淘宝_生意经', '店铺销售指标')
|
722
768
|
bib(t_path, _as_month=False)
|
723
|
-
elif '淘宝' in name and name.endswith('.csv') and 'order' in name:
|
769
|
+
elif '淘宝' in name or '企业店' in name and name.endswith('.csv') and 'order' in name:
|
724
770
|
t_path = os.path.join(self.source_path, '淘宝_生意经', '订单数据')
|
725
771
|
bib(t_path, _as_month=False)
|
726
772
|
|
@@ -850,7 +896,12 @@ class DataClean:
|
|
850
896
|
elif '定向人群' in name:
|
851
897
|
t_path = os.path.join(self.source_path, '天猫推广报表', '品销宝', '定向人群报表')
|
852
898
|
bib(t_path, _as_month=True)
|
853
|
-
|
899
|
+
elif name.endswith('xlsx') and '商品素材_万里马官方旗舰店' in name:
|
900
|
+
t_path = os.path.join(self.source_path, '商品素材', '天猫')
|
901
|
+
bib(t_path, _as_month=True)
|
902
|
+
elif name.endswith('xlsx') and '商品素材_万里马官方企业店' in name:
|
903
|
+
t_path = os.path.join(self.source_path, '商品素材', '淘宝')
|
904
|
+
bib(t_path, _as_month=True)
|
854
905
|
|
855
906
|
# @try_except
|
856
907
|
def move_tg_tb(self, path=None, is_except=[]):
|
@@ -1110,9 +1161,10 @@ def main(service_databases=None):
|
|
1110
1161
|
)
|
1111
1162
|
c.new_unzip(is_move=True) # 解压文件, is_move 解压后是否删除原 zip 压缩文件
|
1112
1163
|
c.tg_reports(is_except=['except']) # 推广报表,天猫淘宝共同清洗
|
1113
|
-
c.syj_reports_tm(is_except=['except']) #
|
1164
|
+
c.syj_reports_tm(is_except=['except']) # 天猫生意经
|
1114
1165
|
# c.syj_reports_tb(is_except=['except']) # 淘宝生意经,不可以和天猫同时运行
|
1115
1166
|
c.jd_reports(is_except=['except']) # 清洗京东报表
|
1167
|
+
c.sp_scene_clean(is_except=['except']) # 商品素材
|
1116
1168
|
c.upload_df(service_databases=service_databases) # 上传数据库
|
1117
1169
|
|
1118
1170
|
c.move_sjy(is_except=['临时文件',]) # 生意经,移到文件到原始文件夹
|
@@ -1171,3 +1223,10 @@ if __name__ == '__main__':
|
|
1171
1223
|
]
|
1172
1224
|
)
|
1173
1225
|
|
1226
|
+
# c = DataClean(
|
1227
|
+
# path=upload_path, # 源文件目录,下载文件夹
|
1228
|
+
# source_path=source_path3, # 原始文件保存目录
|
1229
|
+
# service_databases=[{'home_lx': 'mysql'},]
|
1230
|
+
# )
|
1231
|
+
# c.sp_scene_clean(is_except=['except']) # 商品素材
|
1232
|
+
# c.move_tg_tm(is_except=['临时文件', ]) # 天猫,移到文件到原始文件夹
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|