mdbq 2.3.4__tar.gz → 2.3.5__tar.gz

{mdbq-2.3.4 → mdbq-2.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.3.4
+Version: 2.3.5
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.3.4 → mdbq-2.3.5}/mdbq/aggregation/aggregation.py

@@ -526,7 +526,7 @@ class DatabaseUpdate:
                 elif name.endswith('.csv') and '竞店分析-来源分析-入店搜索词' in name:
                     df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
                     check_remove_file = True
-                elif name.endswith('.csv') and '爱库存_商品榜单' in name:
+                elif name.endswith('.csv') and '爱库存_商品榜单_spu_' in name:
                     df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
                     check_remove_file = True
                 # ----------------------- 京东数据处理分界线 -----------------------

{mdbq-2.3.4 → mdbq-2.3.5}/mdbq/clean/data_clean.py

@@ -1147,7 +1147,7 @@ class DataClean:
             path = self.path
         for root, dirs, files in os.walk(path, topdown=False):
             for name in files:
-                print(name)
+                # print(name)
                 is_continue = False
                 if is_except:
                     for item in is_except:
@@ -1158,7 +1158,7 @@ class DataClean:
                             break
                 if is_continue:  # 需要排除不做处理的文件或文件夹
                     continue
-                print(is_except, is_continue)
+                # print(is_except, is_continue)
                 def bib(paths, _as_month=None):
                     """闭包函数"""
                     self.move_files(path=path, _name=name, target_path=paths, _as_month=_as_month)
@@ -1348,7 +1348,7 @@ class DataClean:
                 elif name.endswith('.csv') and '京东推广关键词点击成交报表' in name:
                     t_path = str(pathlib.Path(self.source_path, '京东报表/JD推广_关键词报表'))
                     bib(t_path, _as_month=True)
-                elif name.endswith('.csv') and '爱库存' in name and '商品榜单' in name:
+                elif name.endswith('.csv') and '爱库存_商品榜单_spu_' in name:
                     t_path = str(pathlib.Path(self.source_path, '爱库存/商品榜单'))
                     bib(t_path, _as_month=True)
                 #  京东分界线   ------- 结束标记

{mdbq-2.3.4 → mdbq-2.3.5}/mdbq/spider/aikucun.py

@@ -43,11 +43,12 @@ else:
     Source_Path = str(pathlib.Path(Data_Path, '原始文件2'))
 
 
-def test():
+def get_cookie_aikucun():
     """
     """
     _url = 'https://gray-merc.aikucun.com/index.html'
-    cookie_path = '/Users/xigua/Downloads'
+    cookie_path = os.path.join(set_support.SetSupport(dirname='support').dirname, 'cookies')
+    filename_aikucun = 'cookie_aikucun.txt'
     print(_url)
 
     option = webdriver.ChromeOptions()  # 浏览器启动选项
@@ -79,7 +80,6 @@ def test():
         service = Service(chromedriver_path)
     _driver = webdriver.Chrome(service=service, options=option)  # 创建Chrome驱动程序实例
 
-    print('yes')
     # 登录
     _driver.get(_url)
     time.sleep(0.1)
@@ -91,16 +91,16 @@ def test():
     time.sleep(0.1)
 
 
-    _file = os.path.join(cookie_path, f'cookie_.txt')
+    _file = os.path.join(cookie_path, filename_aikucun)
     with open(_file, 'w') as f:
         # 将cookies保存为json格式
         cookies_list = _driver.get_cookies()
-        for cookie in cookies_list:
-            # 该字段有问题所以删除就可以
-            if 'expiry' in cookie:
-                del cookie['expiry']
-            # if 'domain' in cookie:
-            #     cookie['domain'] = '.taobao.com'
+        # for cookie in cookies_list:
+        #     # 该字段有问题所以删除就可以
+        #     if 'expiry' in cookie:
+        #         del cookie['expiry']
+        #     # if 'domain' in cookie:
+        #     #     cookie['domain'] = '.taobao.com'
         cookies_list = json.dumps(cookies_list)
         f.write(cookies_list)
         print(f'cookie已保存: {_file}')
@@ -109,7 +109,8 @@ def test():
 
 class AikuCun:
     def __init__(self):
-        self.url = 'https://gray-merc.aikucun.com/index.html'
+        # self.url = 'https://gray-merc.aikucun.com/index.html'
+        self.sp_url = 'https://treasurebox.aikucun.com/dashboard/commodity/ranking/merchant?LS=true&shopId=1814114991487782914&from=menu&v=0.1936043279838604'
         self.cookie_path = os.path.join(set_support.SetSupport(dirname='support').dirname, 'cookies')
 
     def login(self, shop_name='aikucun'):
@@ -173,7 +174,7 @@ class AikuCun:
         _driver.maximize_window()  # 窗口最大化 方便后续加载数据
 
         # 登录
-        _driver.get(self.url)
+        _driver.get(self.sp_url)
         _driver.delete_all_cookies()  # 首先清除浏览器打开已有的cookies
         name_lists = os.listdir(self.cookie_path)  # cookie 放在主目录下的 cookies 文件夹
         for name in name_lists:
@@ -193,9 +194,10 @@ class AikuCun:
         """
 
         _driver = self.login(shop_name=shop_name)
-        _url = 'https://treasurebox.aikucun.com/dashboard/commodity/ranking/merchant?LS=true&shopId=1814114991487782914&from=menu&v=0.1936043279838604'
-        _driver.get(_url)
+
+        _driver.get(self.sp_url)
         time.sleep(3)
+        # breakpoint()
 
         today = datetime.date.today()
         for date_s in range(date_num):
@@ -271,7 +273,7 @@ class AikuCun:
 
 def akucun():
     akc = AikuCun()
-    akc.get_data(shop_name='aikucun', date_num=1)
+    akc.get_data(shop_name='aikucun', date_num=2)
     # akc.clean_data()
 
     # 新版 数据分类
@@ -296,5 +298,5 @@ def akucun():
 
 if __name__ == '__main__':
     pass
-    # test()
+    # get_cookie_aikucun()
     akucun()

{mdbq-2.3.4 → mdbq-2.3.5}/mdbq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.3.4
+Version: 2.3.5
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.3.4 → mdbq-2.3.5}/setup.py

@@ -3,7 +3,7 @@
 from setuptools import setup, find_packages
 
 setup(name='mdbq',
-      version='2.3.4',
+      version='2.3.5',
       author='xigua, ',
       author_email="2587125111@qq.com",
       url='https://pypi.org/project/mdbsql',